NVIDIA Fortran CUDA Interfaces

Preface

This document describes the NVIDIA Fortran interfaces to cuBLAS, cuFFT, cuRAND, cuSPARSE, and other CUDA Libraries used in scientific and engineering applications built upon the CUDA computing architecture.

Intended Audience

This guide is intended for application programmers, scientists and engineers proficient in programming with the Fortran language. This guide assumes some familiarity with either CUDA Fortran or OpenACC.

Organization

The organization of this document is as follows:

Introduction

contains a general introduction to Fortran interfaces, OpenACC, CUDA Fortran, and CUDA Library functions

BLAS Runtime Library

describes the Fortran interfaces to the various cuBLAS libraries

FFT Runtime Library APIs

describes the module types, definitions and Fortran interfaces to the cuFFT library

Random Number Runtime APIs

describes the Fortran interfaces to the host and device cuRAND libraries

Sparse Matrix Runtime APIs

describes the module types, definitions and Fortran interfaces to the cuSPARSE Library

Matrix Solver Runtime APIs

describes the module types, definitions and Fortran interfaces to the cuSOLVER Library

Tensor Primitives Runtime APIs

describes the module types, definitions and Fortran interfaces to the cuTENSOR Library

NVIDIA Collective Communications Library APIs

describes the module types, definitions and Fortran interfaces to the NCCL Library

NVSHMEM Communication Library APIs

describes the module types, definitions and Fortran interfaces to the NVSHMEM Library

NVTX Profiling Library APIs

describes the module types, definitions and Fortran interfaces to the NVTX API and Library

Examples

provides sample code and an explanation of each of the simple examples.

Conventions

This guide uses the following conventions:

italic

is used for emphasis.

Constant Width

is used for filenames, directories, arguments, options, examples, and for language statements in the text, including assembly language statements.

Bold

is used for commands.

[ item1 ]

in general, square brackets indicate optional items. In this case item1 is optional. In the context of p/t-sets, square brackets are required to specify a p/t-set.

{ item2 | item 3 }

braces indicate that a selection is required. In this case, you must select either item2 or item3.

filename …

ellipsis indicate a repetition. Zero or more of the preceding item may occur. In this example, multiple filenames are allowed.

FORTRAN

Fortran language statements are shown in the text of this guide using a reduced fixed point size.

C++ and C

C++ and C language statements are shown in the test of this guide using a reduced fixed point size.

Terminology

If there are terms in this guide with which you are unfamiliar, see the NVIDIA HPC glossary.

Related Publications

The following documents contain additional information related to OpenACC and CUDA Fortran programming, CUDA, and the CUDA Libraries.

• ISO/IEC 1539-1:1997, Information Technology – Programming Languages – FORTRAN, Geneva, 1997 (Fortran 95).

• NVIDIA CUDA Programming Guides, NVIDIA. Available online at docs.nvidia.com/cuda.

• NVIDIA HPC Compiler User’s Guide, Release 2024. Available online at docs.nvidia.com/hpc-sdk.

1. Introduction

This document provides a reference for calling CUDA Library functions from NVIDIA Fortran. It can be used from Fortran code using the OpenACC or OpenMP programming models, or from NVIDIA CUDA Fortran. Currently, the CUDA libraries which NVIDIA provides pre-built interface modules for, and which are documented here, are:

• cuBLAS, an implementation of the BLAS.

• cuFFT, a library of Fast Fourier Transform (FFT) routines.

• cuRAND, a library for random number generation.

• cuSPARSE, a library of linear algebra routines used with sparse matrices.

• cuSOLVER, a library of equation solvers used with dense or other matrices.

• cuTENSOR, a library for tensor primitive operations.

• NCCL, a collective communications librarys.

• NVSHMEM, a library implementation of OpenSHMEM on GPUs.

• NVTX, an API for annotating application events, code ranges, and resources.

The OpenACC Application Program Interface is a collection of compiler directives and runtime routines that allows the programmer to specify loops and regions of code for offloading from a host CPU to an attached accelerator, such as a GPU. The OpenACC API was designed and is maintained by an industry consortium. See the OpenACC website for more information about the OpenACC API.

OpenMP is a specification for a set of compiler directives, an applications programming interface (API), and a set of environment variables that can be used to specify parallel execution from Fortran (and other languages). The OpenMP target offload capabilities are similar in many respects to OpenACC. The methods for passing device arrays to library functions from host code differ only in syntax compared to those used in OpenACC. For general information about using OpenMP and to obtain a copy of the OpenMP specification, refer to the OpenMP organization’s website.

CUDA Fortran is a small set of extensions to Fortran that supports and is built upon the CUDA computing architecture. CUDA Fortran includes a Fortran 2003 compiler and tool chain for programming NVIDIA GPUs using Fortran, and is an analog to NVIDIA’s CUDA C compiler. Compared to the NVIDIA Accelerator and OpenACC directives-based model and compilers, CUDA Fortran is a lower-level explicit programming model with substantial runtime library components that give expert programmers direct control of all aspects of GPGPU programming.

This document does not contain explanations or purposes of the library functions, nor does it contain details of the approach used in the CUDA implementation to target GPUs. For that information, please see the appropriate library document that comes with the NVIDIA CUDA Toolkit. This document does provide the Fortran module contents: derived types, enumerations, and interfaces, to make use of the libraries from Fortran rather than from C or C++.

Many of the examples used in this document are provided in the HPC compiler and tools distribution, along with Makefiles, and are stored in the yearly directory, such as 2020/examples/CUDA-Libraries.

1.1. Fortran Interfaces and Wrappers

Almost all of the function interfaces shown in this document make use of features from the Fortran 2003 iso_c_binding intrinsic module. This module provides a standard way for dealing with isues such as inter-language data types, capitalization, adding underscores to symbol names, or passing arguments by value.

Often, the iso_c_binding module enables Fortran programs containing properly written interfaces to call directly into the C library functions. In some cases, NVIDIA has written small wrappers around the C library function, to make the Fortran call site more “Fortran-like”, hiding some issues exposed in the C interfaces like handle management, host vs. device pointer management, or character and complex data type issues.

In a small number of cases, the C Library may contain multiple entry points to handle different data types, perhaps an int in one function and a size_t in another, otherwise the functions are identical. In these cases, NVIDIA may provide just one generic Fortran interface, and will call the appropriate C function under the hood.

1.2. Using CUDA Libraries from OpenACC Host Code

All of the libraries covered in this document contain functions which are callable from OpenACC host code. Most functions take some arguments which are expected to be device pointers (the address of a variable in device global memory). There are several ways to do that in OpenACC.

If the call is lexically nested within an OpenACC data directive, the NVIDIA Fortran compiler, in the presence of an explicit interface such as those provided by the NVIDIA library modules, will default to passing the device pointer when required.

subroutine hostcall(a, b, n)
use cublas
real a(n), b(n)
!$acc data copy(a, b)
call cublasSswap(n, a, 1, b, 1)
!$acc end data

return
end

A Fortran interface is made explicit when you use the module that contains it, as in the line use cublas in the example above. If you look ahead to the actual interface for cublasSswap, you will see that the arrays a and b are declared with the CUDA Fortran device attribute, so they take only device addresses as arguments.

It is more acceptable and general when using OpenACC to pass device pointers to subprograms by using the host_data clause as most implementations don’t have a way to mark arguments as device pointers. The host_data construct with the use_device clause makes the device addresses available in host code for passing to the subprogram.

use cufft
use openacc
. . .
!$acc data copyin(a), copyout(b,c)
ierr = cufftPlan2D(iplan1,m,n,CUFFT_C2C)
ierr = ierr + cufftSetStream(iplan1,acc_get_cuda_stream(acc_async_sync))
!$acc host_data use_device(a,b,c)
ierr = ierr + cufftExecC2C(iplan1,a,b,CUFFT_FORWARD)
ierr = ierr + cufftExecC2C(iplan1,b,c,CUFFT_INVERSE)
!$acc end host_data

! scale c
!$acc kernels
c = c / (m*n)
!$acc end kernels
!$acc end data

This code snippet also shows an example of sharing the stream that OpenACC and the cuFFT library use. Every library in this document has a function for setting the CUDA stream which the library runs on. Usually, when using OpenACC, you want the OpenACC kernels to run on the same stream as the library functions. In the case above, this guarantees that the kernel c = c / (m*n) does not start until the FFT operations complete. The function acc_get_cuda_stream and the definition for acc_async_sync are in the openacc module.

1.3. Using CUDA Libraries from OpenACC Device Code

Two libraries are currently available from within OpenACC compute regions. Certain functions in both the openacc_curand module and the nvshmem module are marked acc routine seq.

The cuRAND device library is all contained within CUDA header files. In device code, it is designed to return one or a small number of random numbers per thread. The thread’s random generators run independently of each other, and it is usually advised for performance reasons to give each thread a different seed, rather than a different offset.

program t
use openacc_curand
integer, parameter :: n = 500
real a(n,n,4)
type(curandStateXORWOW) :: h
integer(8) :: seed, seq, offset
a = 0.0
!$acc parallel num_gangs(n) vector_length(n) copy(a)
!$acc loop gang
do j = 1, n
!$acc loop vector private(h)
  do i = 1, n
    seed = 12345_8 + j*n*n + i*2
    seq = 0_8
    offset = 0_8
    call curand_init(seed, seq, offset, h)
!$acc loop seq
    do k = 1, 4
      a(i,j,k) = curand_uniform(h)
    end do
  end do
end do
!$acc end parallel
print *,maxval(a),minval(a),sum(a)/(n*n*4)
end

When using the openacc_curand module, since all the code is contained in CUDA header files, you do not need any additional libraries on the link line.

1.4. Using CUDA Libraries from CUDA Fortran Host Code

The predominant usage model for the library functions listed in this document is to call them from CUDA Host code. CUDA Fortran allows some special capabilities in that the compiler is able to recognize the device and managed attribute in resolving generic interfaces. Device actual arguments can only match the interface’s device dummy arguments; managed actual arguments, by precedence, match managed dummy arguments first, then device dummies, then host.

program testisamax  ! link with -cudalib=cublas -lblas
use cublas
real*4              x(1000)
real*4, device  :: xd(1000)
real*4, managed :: xm(1000)

call random_number(x)

! Call host BLAS
j = isamax(1000,x,1)

xd = x
! Call cuBLAS
k = isamax(1000,xd,1)
print *,j.eq.k

xm = x
! Also calls cuBLAS
k = isamax(1000,xm,1)
print *,j.eq.k
end

Using the cudafor module, the full set of CUDA functionality is available to programmers for managing CUDA events, streams, synchronization, and asynchronous behaviors. CUDA Fortran can be used in OpenMP programs, and the CUDA Libraries in this document are thread safe with respect to host CPU threads. Further examples are included in chapter Examples.

1.5. Using CUDA Libraries from CUDA Fortran Device Code

The cuRAND and NVSHMEM libraries have functions callable from CUDA Fortran device code, and their interfaces are accessed via the curand_device and nvshmem modules, respectively. The module interfaces are very similar to the modules used in OpenACC device code, but for CUDA Fortran, each subroutine and function is declared attributes([host,]device), and the subroutines and functions do not need to be marked as acc routine seq.

module mrand
    use curand_device
    integer, parameter :: n = 500
    contains
    attributes(global) subroutine randsub(a)
    real, device :: a(n,n,4)
    type(curandStateXORWOW) :: h
    integer(8) :: seed, seq, offset
    j = blockIdx%x; i = threadIdx%x
    seed = 12345_8 + j*n*n + i*2
    seq = 0_8
    offset = 0_8
    call curand_init(seed, seq, offset, h)
    do k = 1, 4
        a(i,j,k) = curand_uniform(h)
    end do
    end subroutine
end module

program t   ! nvfortran t.cuf
use mrand
use cudafor ! recognize maxval, minval, sum w/managed
real, managed :: a(n,n,4)
a = 0.0
call randsub<<<n,n>>>(a)
print *,maxval(a),minval(a),sum(a)/(n*n*4)
end program

1.6. Pointer Modes in cuBLAS and cuSPARSE

Because the NVIDIA Fortran compiler can distinguish between host and device arguments, the NVIDIA modules for interfacing to cuBLAS and cuSPARSE handle pointer modes differently than CUDA C, which requires setting the mode explicitly for scalar arguments. Examples of scalar arguments which can reside either on the host or device are the alpha and beta scale factors to the *gemm functions.

Typically, when using the normal “non-_v2” interfaces in the cuBLAS and cuSPARSE modules, the runtime wrappers will implicitly add the setting and restoring of the library pointer modes behind the scenes. This adds some negligible but non-zero overhead to the calls.

To avoid the implicit getting and setting of the pointer mode with every invocation of a library function do the following:

• For the BLAS, use the cublas_v2 module, and the v2 entry points, such as cublasIsamax_v2. It is the programmer’s responsibility to properly set the pointer mode when needed. Examples of scalar arguments which do require setting the pointer mode are the alpha and beta scale factors passed to the *gemm routines, and the scalar results returned from the v2 versions of the *amax(), *amin(), *asum(), *rotg(), *rotmg(), *nrm2(), and *dot() functions. In the v2 interfaces shown in the chapter 2, these scalar arguments will have the comment ! device or host variable. Examples of scalar arguments which do not require setting the pointer mode are increments, extents, and lengths such as incx, incy, n, lda, ldb, and ldc.

• For the cuSPARSE library, each function listed in chapter 5 which contains scalar arguments with the comment ! device or host variable has a corresponding v2 interface, though it is not documented here. For instance, in addition to the interface named cusparseSaxpyi, there is another interface named cusparseSaxpyi_v2 with the exact same argument list which calls into the cuSPARSE library directly and will not implicitly get or set the library pointer mode.

The CUDA default pointer mode is that the scalar arguments reside on the host. The NVIDIA runtime does not change that setting.

1.7. Writing Your Own CUDA Interfaces

Despite the large number of interfaces included in the modules described in this document, users will have the need from time-to-time to write their own interfaces to new libraries or their own tuned CUDA, perhaps written in C/C++. There are some standard techniques to use, and some non-standard NVIDIA extensions which can make creating working interfaces easier.

! cufftExecC2C
interface cufftExecC2C
    integer function cufftExecC2C( plan, idata, odata, direction ) &
        bind(C,name='cufftExecC2C')
        integer, value :: plan
        complex, device, dimension(*) :: idata, odata
        integer, value :: direction
    end function cufftExecC2C
end interface cufftExecC2C

This interface calls the C library function directly. You can deal with Fortran’s capitalization issues by putting the properly capitalized C function in the bind(C) attribute. If the C function expects input arguments passed by value, you can add the value attribute to the dummy declaration as well. A nice feature of Fortran is that the interface can change, but the code at the call site may not have to. The compiler changes the details of the call to fit the interface.

Now suppose a user of this interface would like to call this function with REAL data (F77 code is notorious for mixing REAL and COMPLEX declarations). There are two ways to do this:

! cufftExecC2C
interface cufftExecC2C
    integer function cufftExecC2C( plan, idata, odata, direction ) &
        bind(C,name='cufftExecC2C')
        integer, value :: plan
        complex, device, dimension(*) :: idata, odata
        integer, value :: direction
    end function cufftExecC2C
    integer function cufftExecR2R( plan, idata, odata, direction ) &
        bind(C,name='cufftExecC2C')
        integer, value :: plan
        real, device, dimension(*) :: idata, odata
        integer, value :: direction
    end function cufftExecR2R
end interface cufftExecC2C

Here the C name hasn’t changed. The compiler will now accept actual arguments corresponding to idata and odata that are declared REAL. A generic interface is created named cufftExecC2C. If you have problems debugging your generic interface, as a debugging aid you can try calling the specific name, cufftExecR2R in this case, to help diagnose the problem.

A commonly used extension which is supported by NVIDIA is ignore_tkr. A programmer can use it in an interface to instruct the compiler to ignore any combination of the type, kind, and rank during the interface matching process. The previous example using ignore_tkr looks like this:

! cufftExecC2C
interface cufftExecC2C
    integer function cufftExecC2C( plan, idata, odata, direction ) &
        bind(C,name='cufftExecC2C')
        integer, value :: plan
        !dir$ ignore_tkr(tr) idata, (tr) odata
        complex, device, dimension(*) :: idata, odata
        integer, value :: direction
    end function cufftExecC2C
end interface cufftExecC2C

Now the compiler will ignore both the type and rank (F77 could also be sloppy in its handling of array dimensions) of idata and odata when matching the call site to the interface. An unfortunate side-effect is that the interface will now allow integer, logical, and character data for idata and odata. It is up to the implementor to determine if that is acceptable.

A final aid, specific to NVIDIA, worth mentioning here is ignore_tkr (d), which ignores the device attribute of an actual argument during interface matching.

Of course, if you write a wrapper, a narrow strip of code between the Fortran call and your library function, you are not limited by the simple transormations that a compiler can do, such as those listed here. As mentioned earlier, many of the interfaces provided in the cuBLAS and cuSPARSE modules use wrappers.

A common request is a way for Fortran programmers to take advantage of the thrust library. Explaining thrust and C++ programming is outside of the scope of this document, but this simple example can show how to take advantage of the excellent sort capabilities in thrust:

// Filename: csort.cu
// nvcc -c -arch sm_35 csort.cu
#include <thrust/device_vector.h>
#include <thrust/copy.h>
#include <thrust/sort.h>

extern "C" {

    //Sort for integer arrays
    void thrust_int_sort_wrapper( int *data, int N)
    {
    thrust::device_ptr <int> dev_ptr(data);
    thrust::sort(dev_ptr, dev_ptr+N);
    }

    //Sort for float arrays
    void thrust_float_sort_wrapper( float *data, int N)
    {
    thrust::device_ptr <float> dev_ptr(data);
    thrust::sort(dev_ptr, dev_ptr+N);
    }

    //Sort for double arrays
    void thrust_double_sort_wrapper( double *data, int N)
    {
    thrust::device_ptr <double> dev_ptr(data);
    thrust::sort(dev_ptr, dev_ptr+N);
    }
}

Set up interface to the sort subroutine in Fortran and calls are simple:

program t
interface sort
   subroutine sort_int(array, n) &
        bind(C,name='thrust_int_sort_wrapper')
        integer(4), device, dimension(*) :: array
        integer(4), value :: n
    end subroutine
end interface
integer(4), parameter :: n = 100
integer(4), device :: a_d(n)
integer(4) :: a_h(n)
!$cuf kernel do
do i = 1, n
    a_d(i) = 1 + mod(47*i,n)
end do
call sort(a_d, n)
a_h = a_d
nres  = count(a_h .eq. (/(i,i=1,n)/))
if (nres.eq.n) then
    print *,"test PASSED"
else
    print *,"test FAILED"
endif
end

1.8. NVIDIA Fortran Compiler Options

The NVIDIA Fortran compiler driver is called nvfortran. General information on the compiler options which can be passed to nvfortran can be obtained by typing nvfortran -help. To enable targeting NVIDIA GPUs using OpenACC, use nvfortran -acc=gpu. To enable targeting NVIDIA GPUs using CUDA Fortran, use nvfortran -cuda. CUDA Fortran is also supported by the NVIDIA Fortran compilers when the filename uses the .cuf extension. Uppercase file extensions, .F90 or .CUF, for example, may also be used, in which case the program is processed by the preprocessor before being compiled.

Other options which are pertinent to the examples in this document are:

• -⁠cudalib[=cublas|cufft|cufftw|curand|cusolver|cusparse|cutensor|nvblas|nccl|nvshmem|nvlamath|nvtx]: this option adds the appropriate versions of the CUDA-optimized libraries to the link line. It handles static and dynamic linking, and platform (Linux, Windows) differences unobtrusively.

• -⁠gpu=cc70: this option compiles for compute capability 7.0. Certain library functionality may require minimum compute capability of 6.0, 7.0, or higher.

• -⁠gpu=cudaX.Y: this option compiles and links with a particular CUDA Toolkit version. Certain library functionality may require a newer (or older, for deprecated functions) CUDA runtime version.

2. BLAS Runtime APIs

This section describes the Fortran interfaces to the CUDA BLAS libraries. There are currently four separate collections of function entry points which are commonly referred to as the cuBLAS:

• The original CUDA implementation of the BLAS routines, referred to as the legacy API, which are callable from the host and expect and operate on device data.

• The newer “v2” CUDA implementation of the BLAS routines, plus some extensions for batched operations. These are also callable from the host and operate on device data. In Fortran terms, these entry points have been changed from subroutines to functions which return status.

• The cuBLAS XT library which can target multiple GPUs using only host-resident data.

• The cuBLAS MP library which can target multiple GPUs using distributed device data, similar to the ScaLAPACK PBLAS functions. The cublasMp and cusolverMp libraries are built, in part, upon a communications library named CAL, which is documented in another section of this document.

NVIDIA currently ships with four Fortran modules which programmers can use to call into this cuBLAS functionality:

• cublas, which provides interfaces to into the main cublas library. Both the legacy and v2 names are supported. In this module, the cublas names (such as cublasSaxpy) use the legacy calling conventions. Interfaces to a host BLAS library (for instance libblas.a in the NVIDIA distribution) are also included in the cublas module. These interfaces are exposed by adding the line

  use cublas
  

  to your program unit.

• cublas_v2, which is similar to the cublas module in most ways except the cublas names (such as cublasSaxpy) use the v2 calling conventions. For instance, instead of a subroutine, cublasSaxpy is a function which takes a handle as the first argument and returns an integer containing the status of the call. These interfaces are exposed by adding the line

  use cublas_v2
  

  to your program unit.

• cublasxt, which interfaces directly to the cublasXT API. These interfaces are exposed by adding the line

  use cublasxt
  

  to your program unit.

• cublasmp, which provides interfaces into the cublasMp API. These interfaces are exposed by adding the line

  use cublasMp
  

  to your program unit.

The v2 routines are integer functions that return an error status code; they return a value of CUBLAS_STATUS_SUCCESS if the call was successful, or other cuBLAS status return value if there was an error.

Documented interfaces to the traditional BLAS names in the subsequent sections, which contain the comment ! device or host variable should not be confused with the pointer mode issue from section 1.6. The traditional BLAS names are overloaded generic names in the cublas module. For instance, in this interface

subroutine scopy(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

The arrays x and y can either both be device arrays, in which case cublasScopy is called via the generic interface, or they can both be host arrays, in which case scopy from the host BLAS library is called. Using CUDA Fortran managed data as actual arguments to scopy poses an interesting case, and calling cublasScopy is chosen by default. If you wish to call the host library version of scopy with managed data, don’t expose the generic scopy interface at the call site.

Unless a specific kind is provided, in the following interfaces the plain integer type implies integer(4) and the plain real type implies real(4).

2.1. CUBLAS Definitions and Helper Functions

This section contains definitions and data types used in the cuBLAS library and interfaces to the cuBLAS Helper Functions.

The cublas module contains the following derived type definitions:

TYPE cublasHandle
  TYPE(C_PTR)  :: handle
END TYPE

The cuBLAS module contains the following enumerations:

enum, bind(c)
    enumerator :: CUBLAS_STATUS_SUCCESS         =0
    enumerator :: CUBLAS_STATUS_NOT_INITIALIZED =1
    enumerator :: CUBLAS_STATUS_ALLOC_FAILED    =3
    enumerator :: CUBLAS_STATUS_INVALID_VALUE   =7
    enumerator :: CUBLAS_STATUS_ARCH_MISMATCH   =8
    enumerator :: CUBLAS_STATUS_MAPPING_ERROR   =11
    enumerator :: CUBLAS_STATUS_EXECUTION_FAILED=13
    enumerator :: CUBLAS_STATUS_INTERNAL_ERROR  =14
end enum

enum, bind(c)
    enumerator :: CUBLAS_FILL_MODE_LOWER=0
    enumerator :: CUBLAS_FILL_MODE_UPPER=1
end enum

enum, bind(c)
    enumerator :: CUBLAS_DIAG_NON_UNIT=0
    enumerator :: CUBLAS_DIAG_UNIT=1
end enum

enum, bind(c)
    enumerator :: CUBLAS_SIDE_LEFT =0
    enumerator :: CUBLAS_SIDE_RIGHT=1
end enum

enum, bind(c)
    enumerator :: CUBLAS_OP_N=0
    enumerator :: CUBLAS_OP_T=1
    enumerator :: CUBLAS_OP_C=2
end enum

enum, bind(c)
    enumerator :: CUBLAS_POINTER_MODE_HOST   = 0
    enumerator :: CUBLAS_POINTER_MODE_DEVICE = 1
end enum

2.1.1. cublasCreate

This function initializes the CUBLAS library and creates a handle to an opaque structure holding the CUBLAS library context. It allocates hardware resources on the host and device and must be called prior to making any other CUBLAS library calls. The CUBLAS library context is tied to the current CUDA device. To use the library on multiple devices, one CUBLAS handle needs to be created for each device. Furthermore, for a given device, multiple CUBLAS handles with different configuration can be created. Because cublasCreate allocates some internal resources and the release of those resources by calling cublasDestroy will implicitly call cublasDeviceSynchronize, it is recommended to minimize the number of cublasCreate/cublasDestroy occurences. For multi-threaded applications that use the same device from different threads, the recommended programming model is to create one CUBLAS handle per thread and use that CUBLAS handle for the entire life of the thread.

integer(4) function cublasCreate(handle)
  type(cublasHandle) :: handle

2.1.2. cublasDestroy

This function releases hardware resources used by the CUBLAS library. This function is usually the last call with a particular handle to the CUBLAS library. Because cublasCreate allocates some internal resources and the release of those resources by calling cublasDestroy will implicitly call cublasDeviceSynchronize, it is recommended to minimize the number of cublasCreate/cublasDestroy occurences.

integer(4) function cublasDestroy(handle)
  type(cublasHandle) :: handle

2.1.3. cublasGetVersion

This function returns the version number of the cuBLAS library.

integer(4) function cublasGetVersion(handle, version)
  type(cublasHandle) :: handle
  integer(4) :: version

2.1.4. cublasSetStream

This function sets the cuBLAS library stream, which will be used to execute all subsequent calls to the cuBLAS library functions. If the cuBLAS library stream is not set, all kernels use the default NULL stream. In particular, this routine can be used to change the stream between kernel launches and then to reset the cuBLAS library stream back to NULL.

integer(4) function cublasSetStream(handle, stream)
  type(cublasHandle) :: handle
  integer(kind=cuda_stream_kind()) :: stream

2.1.5. cublasGetStream

This function gets the cuBLAS library stream, which is being used to execute all calls to the cuBLAS library functions. If the cuBLAS library stream is not set, all kernels use the default NULL stream.

integer(4) function cublasGetStream(handle, stream)
  type(cublasHandle) :: handle
  integer(kind=cuda_stream_kind()) :: stream

2.1.6. cublasGetStatusName

This function returns the cuBLAS status name associated with a given status value.

character(128) function cublasGetStatusName(ierr)
  integer(4) :: ierr

2.1.7. cublasGetStatusString

This function returns the cuBLAS status string associated with a given status value.

character(128) function cublasGetStatusString(ierr)
  integer(4) :: ierr

2.1.8. cublasGetPointerMode

This function obtains the pointer mode used by the cuBLAS library. In the cublas module, the pointer mode is set and reset on a call-by-call basis depending on the whether the device attribute is set on scalar actual arguments. See section 1.6 for a discussion of pointer modes.

integer(4) function cublasGetPointerMode(handle, mode)
  type(cublasHandle) :: handle
  integer(4) :: mode

2.1.9. cublasSetPointerMode

This function sets the pointer mode used by the cuBLAS library. When using the cublas module, the pointer mode is set on a call-by-call basis depending on the whether the device attribute is set on scalar actual arguments. When using the cublas_v2 module with v2 interfaces, it is the programmer’s responsibility to make calls to cublasSetPointerMode so scalar arguments are handled correctly by the library. See section 1.6 for a discussion of pointer modes.

integer(4) function cublasSetPointerMode(handle, mode)
  type(cublasHandle) :: handle
  integer(4) :: mode

2.1.10. cublasGetAtomicsMode

This function obtains the atomics mode used by the cuBLAS library.

integer(4) function cublasGetAtomicsMode(handle, mode)
  type(cublasHandle) :: handle
  integer(4) :: mode

2.1.11. cublasSetAtomicsMode

This function sets the atomics mode used by the cuBLAS library. Some routines in the cuBLAS library have alternate implementations that use atomics to accumulate results. These alternate implementations may run faster but may also generate results which are not identical from one run to the other. The default is to not allow atomics in cuBLAS functions.

integer(4) function cublasSetAtomicsMode(handle, mode)
  type(cublasHandle) :: handle
  integer(4) :: mode

2.1.12. cublasGetMathMode

This function obtains the math mode used by the cuBLAS library.

integer(4) function cublasGetMathMode(handle, mode)
  type(cublasHandle) :: handle
  integer(4) :: mode

2.1.13. cublasSetMathMode

This function sets the math mode used by the cuBLAS library. Some routines in the cuBLAS library allow you to choose the compute precision used to generate results. These alternate approaches may run faster but may also generate different, less accurate results.

integer(4) function cublasSetMathMode(handle, mode)
  type(cublasHandle) :: handle
  integer(4) :: mode

2.1.14. cublasGetSmCountTarget

This function obtains the SM count target used by the cuBLAS library.

integer(4) function cublasGetSmCountTarget(handle, counttarget)
  type(cublasHandle) :: handle
  integer(4) :: counttarget

2.1.15. cublasSetSmCountTarget

This function sets the SM count target used by the cuBLAS library.

integer(4) function cublasSetSmCountTarget(handle, counttarget)
  type(cublasHandle) :: handle
  integer(4) :: counttarget

2.1.16. cublasGetHandle

This function gets the cuBLAS handle currently in use by a thread. The CUDA Fortran runtime keeps track of a CPU thread’s current handle, if you are either using the legacy BLAS API, or do not wish to pass the handle through to low-level functions or subroutines manually.

type(cublashandle) function cublasGetHandle()

integer(4) function cublasGetHandle(handle)
  type(cublasHandle) :: handle

2.1.17. cublasSetVector

This function copies n elements from a vector x in host memory space to a vector y in GPU memory space. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of vector x and y is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpy or array assignment statements.

integer(4) function cublassetvector(n, elemsize, x, incx, y, incy)
  integer :: n, elemsize, incx, incy
  integer*1, dimension(*) :: x
  integer*1, device, dimension(*) :: y

2.1.18. cublasGetVector

This function copies n elements from a vector x in GPU memory space to a vector y in host memory space. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of vector x and y is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpy or array assignment statements.

integer(4) function cublasgetvector(n, elemsize, x, incx, y, incy)
  integer :: n, elemsize, incx, incy
  integer*1, device, dimension(*) :: x
  integer*1, dimension(*) :: y

2.1.19. cublasSetMatrix

This function copies a tile of rows x cols elements from a matrix A in host memory space to a matrix B in GPU memory space. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of Matrix A and B is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpy, cudaMemcpy2D, or array assignment statements.

integer(4) function cublassetmatrix(rows, cols, elemsize, a, lda, b, ldb)
  integer :: rows, cols, elemsize, lda, ldb
  integer*1, dimension(lda, *) :: a
  integer*1, device, dimension(ldb, *) :: b

2.1.20. cublasGetMatrix

This function copies a tile of rows x cols elements from a matrix A in GPU memory space to a matrix B in host memory space. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of Matrix A and B is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpy, cudaMemcpy2D, or array assignment statements.

integer(4) function cublasgetmatrix(rows, cols, elemsize, a, lda, b, ldb)
  integer :: rows, cols, elemsize, lda, ldb
  integer*1, device, dimension(lda, *) :: a
  integer*1, dimension(ldb, *) :: b

2.1.21. cublasSetVectorAsync

This function copies n elements from a vector x in host memory space to a vector y in GPU memory space, asynchronously, on the given CUDA stream. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of vector x and y is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpyAsync.

integer(4) function cublassetvectorasync(n, elemsize, x, incx, y, incy, stream)
  integer :: n, elemsize, incx, incy
  integer*1, dimension(*) :: x
  integer*1, device, dimension(*) :: y
  integer(kind=cuda_stream_kind()) :: stream

2.1.22. cublasGetVectorAsync

This function copies n elements from a vector x in host memory space to a vector y in GPU memory space, asynchronously, on the given CUDA stream. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of vector x and y is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpyAsync.

integer(4) function cublasgetvectorasync(n, elemsize, x, incx, y, incy, stream)
  integer :: n, elemsize, incx, incy
  integer*1, device, dimension(*) :: x
  integer*1, dimension(*) :: y
  integer(kind=cuda_stream_kind()) :: stream

2.1.23. cublasSetMatrixAsync

This function copies a tile of rows x cols elements from a matrix A in host memory space to a matrix B in GPU memory space, asynchronously using the specified stream. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of Matrix A and B is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpyAsync or cudaMemcpy2DAsync.

integer(4) function cublassetmatrixasync(rows, cols, elemsize, a, lda, b, ldb, stream)
  integer :: rows, cols, elemsize, lda, ldb
  integer*1, dimension(lda, *) :: a
  integer*1, device, dimension(ldb, *) :: b
  integer(kind=cuda_stream_kind()) :: stream

2.1.24. cublasGetMatrixAsync

This function copies a tile of rows x cols elements from a matrix A in GPU memory space to a matrix B in host memory space, asynchronously, using the specified stream. It is assumed that each element requires storage of elemSize bytes. In CUDA Fortran, the type of Matrix A and B is overloaded to take any data type, but the size of the data type must still be specified in bytes. This functionality can also be implemented using cudaMemcpyAsync or cudaMemcpy2DAsync.

integer(4) function cublasgetmatrixasync(rows, cols, elemsize, a, lda, b, ldb, stream)
  integer :: rows, cols, elemsize, lda, ldb
  integer*1, device, dimension(lda, *) :: a
  integer*1, dimension(ldb, *) :: b
  integer(kind=cuda_stream_kind()) :: stream

2.2. Single Precision Functions and Subroutines

This section contains interfaces to the single precision BLAS and cuBLAS functions and subroutines.

2.2.1. isamax

ISAMAX finds the index of the element having the maximum absolute value.

integer(4) function isamax(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIsamax(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIsamax_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.2.2. isamin

ISAMIN finds the index of the element having the minimum absolute value.

integer(4) function isamin(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIsamin(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIsamin_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.2.3. sasum

SASUM takes the sum of the absolute values.

real(4) function sasum(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(4) function cublasSasum(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasSasum_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.2.4. saxpy

SAXPY constant times a vector plus a vector.

subroutine saxpy(n, a, x, incx, y, incy)
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasSaxpy(n, a, x, incx, y, incy)
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasSaxpy_v2(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.2.5. scopy

SCOPY copies a vector, x, to a vector, y.

subroutine scopy(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasScopy(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasScopy_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.2.6. sdot

SDOT forms the dot product of two vectors.

real(4) function sdot(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

real(4) function cublasSdot(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasSdot_v2(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy
  real(4), device :: res ! device or host variable

2.2.7. snrm2

SNRM2 returns the euclidean norm of a vector via the function name, so that SNRM2 := sqrt( x’*x ).

real(4) function snrm2(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(4) function cublasSnrm2(n, x, incx)
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasSnrm2_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.2.8. srot

SROT applies a plane rotation.

subroutine srot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasSrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasSrot_v2(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.2.9. srotg

SROTG constructs a Givens plane rotation.

subroutine srotg(sa, sb, sc, ss)
  real(4), device :: sa, sb, sc, ss ! device or host variable

subroutine cublasSrotg(sa, sb, sc, ss)
  real(4), device :: sa, sb, sc, ss ! device or host variable

integer(4) function cublasSrotg_v2(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  real(4), device :: sa, sb, sc, ss ! device or host variable

2.2.10. srotm

SROTM applies the modified Givens transformation, H, to the 2 by N matrix (SX**T) , where **T indicates transpose. The elements of SX are in (SX**T) SX(LX+I*INCX), I = 0 to N-1, where LX = 1 if INCX .GE. 0, ELSE LX = (-INCX)*N, and similarly for SY using LY and INCY. With SPARAM(1)=SFLAG, H has one of the following forms.. SFLAG=-1.E0 SFLAG=0.E0 SFLAG=1.E0 SFLAG=-2.E0 (SH11 SH12) (1.E0 SH12) (SH11 1.E0) (1.E0 0.E0) H=( ) ( ) ( ) ( ) (SH21 SH22), (SH21 1.E0), (-1.E0 SH22), (0.E0 1.E0). See SROTMG for a description of data storage in SPARAM.

subroutine srotm(n, x, incx, y, incy, param)
  integer :: n
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasSrotm(n, x, incx, y, incy, param)
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy
  real(4), device :: param(*) ! device or host variable

integer(4) function cublasSrotm_v2(h, n, x, incx, y, incy, param)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: param(*) ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.2.11. srotmg

SROTMG constructs the modified Givens transformation matrix H which zeros the second component of the 2-vector (SQRT(SD1)*SX1,SQRT(SD2)*SY2)**T. With SPARAM(1)=SFLAG, H has one of the following forms..SFLAG=-1.E0 SFLAG=0.E0 SFLAG=1.E0 SFLAG=-2.E0 (SH11 SH12) (1.E0 SH12) (SH11 1.E0) (1.E0 0.E0) H=( ) ( ) ( ) ( ) (SH21 SH22), (SH21 1.E0), (-1.E0 SH22), (0.E0 1.E0). Locations 2-4 of SPARAM contain SH11,SH21,SH12, and SH22 respectively. (Values of 1.E0, -1.E0, or 0.E0 implied by the value of SPARAM(1) are not stored in SPARAM.)

subroutine srotmg(d1, d2, x1, y1, param)
  real(4), device :: d1, d2, x1, y1, param(*) ! device or host variable

subroutine cublasSrotmg(d1, d2, x1, y1, param)
  real(4), device :: d1, d2, x1, y1, param(*) ! device or host variable

integer(4) function cublasSrotmg_v2(h, d1, d2, x1, y1, param)
  type(cublasHandle) :: h
  real(4), device :: d1, d2, x1, y1, param(*) ! device or host variable

2.2.12. sscal

SSCAL scales a vector by a constant.

subroutine sscal(n, a, x, incx)
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

subroutine cublasSscal(n, a, x, incx)
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasSscal_v2(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x
  integer :: incx

2.2.13. sswap

SSWAP interchanges two vectors.

subroutine sswap(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasSswap(n, x, incx, y, incy)
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasSswap_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.2.14. sgbmv

SGBMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n band matrix, with kl sub-diagonals and ku super-diagonals.

subroutine sgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSgbmv_v2(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.2.15. sgemv

SGEMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n matrix.

subroutine sgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSgemv_v2(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.2.16. sger

SGER performs the rank 1 operation A := alpha*x*y**T + A, where alpha is a scalar, x is an m element vector, y is an n element vector and A is an m by n matrix.

subroutine sger(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasSger(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha ! device or host variable

integer(4) function cublasSger_v2(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha ! device or host variable

2.2.17. ssbmv

SSBMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric band matrix, with k super-diagonals.

subroutine ssbmv(t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: k, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSsbmv(t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: k, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSsbmv_v2(h, t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: k, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.2.18. sspmv

SSPMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric matrix, supplied in packed form.

subroutine sspmv(t, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSspmv(t, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSspmv_v2(h, t, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y
  real(4), device :: alpha, beta ! device or host variable

2.2.19. sspr

SSPR performs the symmetric rank 1 operation A := alpha*x*x**T + A, where alpha is a real scalar, x is an n element vector and A is an n by n symmetric matrix, supplied in packed form.

subroutine sspr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  real(4), device, dimension(*) :: a, x ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasSspr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  real(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

integer(4) function cublasSspr_v2(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  real(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

2.2.20. sspr2

SSPR2 performs the symmetric rank 2 operation A := alpha*x*y**T + alpha*y*x**T + A, where alpha is a scalar, x and y are n element vectors and A is an n by n symmetric matrix, supplied in packed form.

subroutine sspr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasSspr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y
  real(4), device :: alpha ! device or host variable

integer(4) function cublasSspr2_v2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y
  real(4), device :: alpha ! device or host variable

2.2.21. ssymv

SSYMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric matrix.

subroutine ssymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSsymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSsymv_v2(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.2.22. ssyr

SSYR performs the symmetric rank 1 operation A := alpha*x*x**T + A, where alpha is a real scalar, x is an n element vector and A is an n by n symmetric matrix.

subroutine ssyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasSsyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x
  real(4), device :: alpha ! device or host variable

integer(4) function cublasSsyr_v2(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x
  real(4), device :: alpha ! device or host variable

2.2.23. ssyr2

SSYR2 performs the symmetric rank 2 operation A := alpha*x*y**T + alpha*y*x**T + A, where alpha is a scalar, x and y are n element vectors and A is an n by n symmetric matrix.

subroutine ssyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x, y ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasSsyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha ! device or host variable

integer(4) function cublasSsyr2_v2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha ! device or host variable

2.2.24. stbmv

STBMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals.

subroutine stbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x ! device or host variable

subroutine cublasStbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

integer(4) function cublasStbmv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.2.25. stbsv

STBSV solves one of the systems of equations A*x = b, or A**T*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine stbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x ! device or host variable

subroutine cublasStbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

integer(4) function cublasStbsv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.2.26. stpmv

STPMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form.

subroutine stpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x ! device or host variable

subroutine cublasStpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x

integer(4) function cublasStpmv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x

2.2.27. stpsv

STPSV solves one of the systems of equations A*x = b, or A**T*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine stpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x ! device or host variable

subroutine cublasStpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x

integer(4) function cublasStpsv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x

2.2.28. strmv

STRMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix.

subroutine strmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x ! device or host variable

subroutine cublasStrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

integer(4) function cublasStrmv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.2.29. strsv

STRSV solves one of the systems of equations A*x = b, or A**T*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine strsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(*) :: x ! device or host variable

subroutine cublasStrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

integer(4) function cublasStrsv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.2.30. sgemm

SGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

subroutine sgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldb, *) :: b ! device or host variable
  real(4), device, dimension(ldc, *) :: c ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSgemm_v2(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.2.31. ssymm

SSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

subroutine ssymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldb, *) :: b ! device or host variable
  real(4), device, dimension(ldc, *) :: c ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSsymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSsymm_v2(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.2.32. ssyrk

SSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

subroutine ssyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldc, *) :: c ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSsyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSsyrk_v2(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.2.33. ssyr2k

SSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

subroutine ssyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldb, *) :: b ! device or host variable
  real(4), device, dimension(ldc, *) :: c ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSsyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSsyr2k_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.2.34. ssyrkx

SSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

subroutine ssyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldb, *) :: b ! device or host variable
  real(4), device, dimension(ldc, *) :: c ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasSsyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c

  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasSsyrkx_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.2.35. strmm

STRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ), where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T.

subroutine strmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldb, *) :: b ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasStrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device :: alpha ! device or host variable

integer(4) function cublasStrmm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha ! device or host variable

2.2.36. strsm

STRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T. The matrix X is overwritten on B.

subroutine strsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(4), device, dimension(lda, *) :: a ! device or host variable
  real(4), device, dimension(ldb, *) :: b ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasStrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device :: alpha ! device or host variable

integer(4) function cublasStrsm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device :: alpha ! device or host variable

2.2.37. cublasSgemvBatched

SGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasSgemvBatched(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

integer(4) function cublasSgemvBatched_v2(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

2.2.38. cublasSgemmBatched

SGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasSgemmBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

integer(4) function cublasSgemmBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

2.2.39. cublasSgelsBatched

SGELS solves overdetermined or underdetermined real linear systems involving an M-by-N matrix A, or its transpose, using a QR or LQ factorization of A. It is assumed that A has full rank. The following options are provided: 1. If TRANS = ‘N’ and m >= n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A*X ||. 2. If TRANS = ‘N’ and m < n: find the minimum norm solution of an underdetermined system A * X = B. 3. If TRANS = ‘T’ and m >= n: find the minimum norm solution of an undetermined system A**T * X = B. 4. If TRANS = ‘T’ and m < n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A**T * X ||. Several right hand side vectors b and solution vectors x can be handled in a single call; they are stored as the columns of the M-by-NRHS right hand side matrix B and the N-by-NRHS solution matrix X.

integer(4) function cublasSgelsBatched(h, trans, m, n, nrhs, Aarray, lda, Carray, ldc, info, devinfo, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: info(*)
  integer, device :: devinfo(*)
  integer :: batchCount

2.2.40. cublasSgeqrfBatched

SGEQRF computes a QR factorization of a real M-by-N matrix A: A = Q * R.

integer(4) function cublasSgeqrfBatched(h, m, n, Aarray, lda, Tau, info, batchCount)
  type(cublasHandle) :: h
  integer :: m, n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Tau(*)
  integer :: info(*)
  integer :: batchCount

2.2.41. cublasSgetrfBatched

SGETRF computes an LU factorization of a general M-by-N matrix A using partial pivoting with row interchanges. The factorization has the form A = P * L * U where P is a permutation matrix, L is lower triangular with unit diagonal elements (lower trapezoidal if m > n), and U is upper triangular (upper trapezoidal if m < n). This is the right-looking Level 3 BLAS version of the algorithm.

integer(4) function cublasSgetrfBatched(h, n, Aarray, lda, ipvt, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  integer, device :: info(*)
  integer :: batchCount

2.2.42. cublasSgetriBatched

SGETRI computes the inverse of a matrix using the LU factorization computed by SGETRF. This method inverts U and then computes inv(A) by solving the system inv(A)*L = inv(U) for inv(A).

integer(4) function cublasSgetriBatched(h, n, Aarray, lda, ipvt, Carray, ldc, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer, device :: info(*)
  integer :: batchCount

2.2.43. cublasSgetrsBatched

SGETRS solves a system of linear equations A * X = B or A**T * X = B with a general N-by-N matrix A using the LU factorization computed by SGETRF.

integer(4) function cublasSgetrsBatched(h, trans, n, nrhs, Aarray, lda, ipvt, Barray, ldb, info, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  integer :: info(*)
  integer :: batchCount

2.2.44. cublasSmatinvBatched

cublasSmatinvBatched is a short cut of cublasSgetrfBatched plus cublasSgetriBatched. However it only works if n is less than 32. If not, the user has to go through cublasSgetrfBatched and cublasSgetriBatched.

integer(4) function cublasSmatinvBatched(h, n, Aarray, lda, Ainv, lda_inv, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Ainv(*)
  integer :: lda_inv
  integer, device :: info(*)
  integer :: batchCount

2.2.45. cublasStrsmBatched

STRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T. The matrix X is overwritten on B.

integer(4) function cublasStrsmBatched( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side ! integer or character(1) variable
  integer :: uplo ! integer or character(1) variable
  integer :: trans ! integer or character(1) variable
  integer :: diag ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

integer(4) function cublasStrsmBatched_v2( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side
  integer :: uplo
  integer :: trans
  integer :: diag
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

2.2.46. cublasSgemvStridedBatched

SGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasSgemvStridedBatched(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  real(4), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(4), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(4), device :: beta ! device or host variable
  real(4), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

integer(4) function cublasSgemvStridedBatched_v2(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  real(4), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(4), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(4), device :: beta ! device or host variable
  real(4), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

2.2.47. cublasSgemmStridedBatched

SGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasSgemmStridedBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  real(4), device :: alpha ! device or host variable
  real(4), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  real(4), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  real(4), device :: beta ! device or host variable
  real(4), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

integer(4) function cublasSgemmStridedBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  real(4), device :: alpha ! device or host variable
  real(4), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  real(4), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  real(4), device :: beta ! device or host variable
  real(4), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

2.3. Double Precision Functions and Subroutines

This section contains interfaces to the double precision BLAS and cuBLAS functions and subroutines.

2.3.1. idamax

IDAMAX finds the the index of the element having the maximum absolute value.

integer(4) function idamax(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIdamax(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIdamax_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.3.2. idamin

IDAMIN finds the index of the element having the minimum absolute value.

integer(4) function idamin(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIdamin(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIdamin_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.3.3. dasum

DASUM takes the sum of the absolute values.

real(8) function dasum(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(8) function cublasDasum(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasDasum_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.3.4. daxpy

DAXPY constant times a vector plus a vector.

subroutine daxpy(n, a, x, incx, y, incy)
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasDaxpy(n, a, x, incx, y, incy)
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasDaxpy_v2(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.3.5. dcopy

DCOPY copies a vector, x, to a vector, y.

subroutine dcopy(n, x, incx, y, incy)
  integer :: n
  real(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasDcopy(n, x, incx, y, incy)
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasDcopy_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.3.6. ddot

DDOT forms the dot product of two vectors.

real(8) function ddot(n, x, incx, y, incy)
  integer :: n
  real(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

real(8) function cublasDdot(n, x, incx, y, incy)
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasDdot_v2(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy
  real(8), device :: res ! device or host variable

2.3.7. dnrm2

DNRM2 returns the euclidean norm of a vector via the function name, so that DNRM2 := sqrt( x’*x )

real(8) function dnrm2(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(8) function cublasDnrm2(n, x, incx)
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasDnrm2_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.3.8. drot

DROT applies a plane rotation.

subroutine drot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasDrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasDrot_v2(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.3.9. drotg

DROTG constructs a Givens plane rotation.

subroutine drotg(sa, sb, sc, ss)
  real(8), device :: sa, sb, sc, ss ! device or host variable

subroutine cublasDrotg(sa, sb, sc, ss)
  real(8), device :: sa, sb, sc, ss ! device or host variable

integer(4) function cublasDrotg_v2(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  real(8), device :: sa, sb, sc, ss ! device or host variable

2.3.10. drotm

DROTM applies the modified Givens transformation, H, to the 2 by N matrix (DX**T) , where **T indicates transpose. The elements of DX are in (DX**T) DX(LX+I*INCX), I = 0 to N-1, where LX = 1 if INCX .GE. 0, ELSE LX = (-INCX)*N, and similarly for DY using LY and INCY. With DPARAM(1)=DFLAG, H has one of the following forms.. DFLAG=-1.D0 DFLAG=0.D0 DFLAG=1.D0 DFLAG=-2.D0 (DH11 DH12) (1.D0 DH12) (DH11 1.D0) (1.D0 0.D0) H=( ) ( ) ( ) ( ) (DH21 DH22), (DH21 1.D0), (-1.D0 DH22), (0.D0 1.D0). See DROTMG for a description of data storage in DPARAM.

subroutine drotm(n, x, incx, y, incy, param)
  integer :: n
  real(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasDrotm(n, x, incx, y, incy, param)
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy
  real(8), device :: param(*) ! device or host variable

integer(4) function cublasDrotm_v2(h, n, x, incx, y, incy, param)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: param(*) ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.3.11. drotmg

DROTMG constructs the modified Givens transformation matrix H which zeros the second component of the 2-vector (SQRT(DD1)*DX1,SQRT(DD2)*DY2)**T. With DPARAM(1)=DFLAG, H has one of the following forms.. DFLAG=-1.D0 DFLAG=0.D0 DFLAG=1.D0 DFLAG=-2.D0 (DH11 DH12) (1.D0 DH12) (DH11 1.D0) (1.D0 0.D0) H=( ) ( ) ( ) ( ) (DH21 DH22), (DH21 1.D0), (-1.D0 DH22), (0.D0 1.D0). Locations 2-4 of DPARAM contain DH11, DH21, DH12, and DH22 respectively. (Values of 1.D0, -1.D0, of 0.D0 implied by the value of DPARAM(1) are not stored in DPARAM.)

subroutine drotmg(d1, d2, x1, y1, param)
  real(8), device :: d1, d2, x1, y1, param(*) ! device or host variable

subroutine cublasDrotmg(d1, d2, x1, y1, param)
  real(8), device :: d1, d2, x1, y1, param(*) ! device or host variable

integer(4) function cublasDrotmg_v2(h, d1, d2, x1, y1, param)
  type(cublasHandle) :: h
  real(8), device :: d1, d2, x1, y1, param(*) ! device or host variable

2.3.12. dscal

DSCAL scales a vector by a constant.

subroutine dscal(n, a, x, incx)
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

subroutine cublasDscal(n, a, x, incx)
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasDscal_v2(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x
  integer :: incx

2.3.13. dswap

interchanges two vectors.

subroutine dswap(n, x, incx, y, incy)
  integer :: n
  real(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasDswap(n, x, incx, y, incy)
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasDswap_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.3.14. dgbmv

DGBMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n band matrix, with kl sub-diagonals and ku super-diagonals.

subroutine dgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDgbmv_v2(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.3.15. dgemv

DGEMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n matrix.

subroutine dgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDgemv_v2(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.3.16. dger

DGER performs the rank 1 operation A := alpha*x*y**T + A, where alpha is a scalar, x is an m element vector, y is an n element vector and A is an m by n matrix.

subroutine dger(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDger(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDger_v2(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha ! device or host variable

2.3.17. dsbmv

DSBMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric band matrix, with k super-diagonals.

subroutine dsbmv(t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: k, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDsbmv(t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: k, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDsbmv_v2(h, t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: k, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.3.18. dspmv

DSPMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric matrix, supplied in packed form.

subroutine dspmv(t, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDspmv(t, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDspmv_v2(h, t, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y
  real(8), device :: alpha, beta ! device or host variable

2.3.19. dspr

DSPR performs the symmetric rank 1 operation A := alpha*x*x**T + A, where alpha is a real scalar, x is an n element vector and A is an n by n symmetric matrix, supplied in packed form.

subroutine dspr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  real(8), device, dimension(*) :: a, x ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDspr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  real(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDspr_v2(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  real(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

2.3.20. dspr2

DSPR2 performs the symmetric rank 2 operation A := alpha*x*y**T + alpha*y*x**T + A, where alpha is a scalar, x and y are n element vectors and A is an n by n symmetric matrix, supplied in packed form.

subroutine dspr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDspr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDspr2_v2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y
  real(8), device :: alpha ! device or host variable

2.3.21. dsymv

DSYMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric matrix.

subroutine dsymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDsymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDsymv_v2(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.3.22. dsyr

DSYR performs the symmetric rank 1 operation A := alpha*x*x**T + A, where alpha is a real scalar, x is an n element vector and A is an n by n symmetric matrix.

subroutine dsyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDsyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDsyr_v2(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x
  real(8), device :: alpha ! device or host variable

2.3.23. dsyr2

DSYR2 performs the symmetric rank 2 operation A := alpha*x*y**T + alpha*y*x**T + A, where alpha is a scalar, x and y are n element vectors and A is an n by n symmetric matrix.

subroutine dsyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x, y ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDsyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDsyr2_v2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha ! device or host variable

2.3.24. dtbmv

DTBMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals.

subroutine dtbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x ! device or host variable

subroutine cublasDtbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

integer(4) function cublasDtbmv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.3.25. dtbsv

DTBSV solves one of the systems of equations A*x = b, or A**T*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine dtbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x ! device or host variable

subroutine cublasDtbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

integer(4) function cublasDtbsv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.3.26. dtpmv

DTPMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form.

subroutine dtpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x ! device or host variable

subroutine cublasDtpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x

integer(4) function cublasDtpmv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x

2.3.27. dtpsv

DTPSV solves one of the systems of equations A*x = b, or A**T*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine dtpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x ! device or host variable

subroutine cublasDtpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x

integer(4) function cublasDtpsv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x

2.3.28. dtrmv

DTRMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix.

subroutine dtrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x ! device or host variable

subroutine cublasDtrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

integer(4) function cublasDtrmv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.3.29. dtrsv

DTRSV solves one of the systems of equations A*x = b, or A**T*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine dtrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(*) :: x ! device or host variable

subroutine cublasDtrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

integer(4) function cublasDtrsv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.3.30. dgemm

DGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

subroutine dgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldb, *) :: b ! device or host variable
  real(8), device, dimension(ldc, *) :: c ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDgemm_v2(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.3.31. dsymm

DSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

subroutine dsymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldb, *) :: b ! device or host variable
  real(8), device, dimension(ldc, *) :: c ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDsymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDsymm_v2(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.3.32. dsyrk

DSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

subroutine dsyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldc, *) :: c ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDsyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDsyrk_v2(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.3.33. dsyr2k

DSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

subroutine dsyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldb, *) :: b ! device or host variable
  real(8), device, dimension(ldc, *) :: c ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDsyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDsyr2k_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.3.34. dsyrkx

DSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

subroutine dsyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldb, *) :: b ! device or host variable
  real(8), device, dimension(ldc, *) :: c ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasDsyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasDsyrkx_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.3.35. dtrmm

DTRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ), where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T.

subroutine dtrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldb, *) :: b ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDtrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDtrmm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha ! device or host variable

2.3.36. dtrsm

DTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T. The matrix X is overwritten on B.

subroutine dtrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(8), device, dimension(lda, *) :: a ! device or host variable
  real(8), device, dimension(ldb, *) :: b ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasDtrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device :: alpha ! device or host variable

integer(4) function cublasDtrsm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device :: alpha ! device or host variable

2.3.37. cublasDgemvBatched

DGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasDgemvBatched(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(8), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

integer(4) function cublasDgemvBatched_v2(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(8), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

2.3.38. cublasDgemmBatched

DGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasDgemmBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  real(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  real(8), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

integer(4) function cublasDgemmBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  real(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  real(8), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

2.3.39. cublasDgelsBatched

DGELS solves overdetermined or underdetermined real linear systems involving an M-by-N matrix A, or its transpose, using a QR or LQ factorization of A. It is assumed that A has full rank. The following options are provided: 1. If TRANS = ‘N’ and m >= n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A*X ||. 2. If TRANS = ‘N’ and m < n: find the minimum norm solution of an underdetermined system A * X = B. 3. If TRANS = ‘T’ and m >= n: find the minimum norm solution of an undetermined system A**T * X = B. 4. If TRANS = ‘T’ and m < n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A**T * X ||. Several right hand side vectors b and solution vectors x can be handled in a single call; they are stored as the columns of the M-by-NRHS right hand side matrix B and the N-by-NRHS solution matrix X.

integer(4) function cublasDgelsBatched(h, trans, m, n, nrhs, Aarray, lda, Carray, ldc, info, devinfo, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: info(*)
  integer, device :: devinfo(*)
  integer :: batchCount

2.3.40. cublasDgeqrfBatched

DGEQRF computes a QR factorization of a real M-by-N matrix A: A = Q * R.

integer(4) function cublasDgeqrfBatched(h, m, n, Aarray, lda, Tau, info, batchCount)
  type(cublasHandle) :: h
  integer :: m, n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Tau(*)
  integer :: info(*)
  integer :: batchCount

2.3.41. cublasDgetrfBatched

DGETRF computes an LU factorization of a general M-by-N matrix A using partial pivoting with row interchanges. The factorization has the form A = P * L * U where P is a permutation matrix, L is lower triangular with unit diagonal elements (lower trapezoidal if m > n), and U is upper triangular (upper trapezoidal if m < n). This is the right-looking Level 3 BLAS version of the algorithm.

integer(4) function cublasDgetrfBatched(h, n, Aarray, lda, ipvt, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  integer, device :: info(*)
  integer :: batchCount

2.3.42. cublasDgetriBatched

DGETRI computes the inverse of a matrix using the LU factorization computed by DGETRF. This method inverts U and then computes inv(A) by solving the system inv(A)*L = inv(U) for inv(A).

integer(4) function cublasDgetriBatched(h, n, Aarray, lda, ipvt, Carray, ldc, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer, device :: info(*)
  integer :: batchCount

2.3.43. cublasDgetrsBatched

DGETRS solves a system of linear equations A * X = B or A**T * X = B with a general N-by-N matrix A using the LU factorization computed by DGETRF.

integer(4) function cublasDgetrsBatched(h, trans, n, nrhs, Aarray, lda, ipvt, Barray, ldb, info, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  integer :: info(*)
  integer :: batchCount

2.3.44. cublasDmatinvBatched

cublasDmatinvBatched is a short cut of cublasDgetrfBatched plus cublasDgetriBatched. However it only works if n is less than 32. If not, the user has to go through cublasDgetrfBatched and cublasDgetriBatched.

integer(4) function cublasDmatinvBatched(h, n, Aarray, lda, Ainv, lda_inv, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Ainv(*)
  integer :: lda_inv
  integer, device :: info(*)
  integer :: batchCount

2.3.45. cublasDtrsmBatched

DTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T. The matrix X is overwritten on B.

integer(4) function cublasDtrsmBatched( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side ! integer or character(1) variable
  integer :: uplo ! integer or character(1) variable
  integer :: trans ! integer or character(1) variable
  integer :: diag ! integer or character(1) variable
  integer :: m, n
  real(8), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

integer(4) function cublasDtrsmBatched_v2( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side
  integer :: uplo
  integer :: trans
  integer :: diag
  integer :: m, n
  real(8), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

2.3.46. cublasDgemvStridedBatched

DGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasDgemvStridedBatched(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(8), device :: alpha ! device or host variable
  real(8), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(8), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(8), device :: beta ! device or host variable
  real(8), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

integer(4) function cublasDgemvStridedBatched_v2(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(8), device :: alpha ! device or host variable
  real(8), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(8), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(8), device :: beta ! device or host variable
  real(8), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

2.3.47. cublasDgemmStridedBatched

DGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasDgemmStridedBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  real(8), device :: alpha ! device or host variable
  real(8), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  real(8), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  real(8), device :: beta ! device or host variable
  real(8), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

integer(4) function cublasDgemmStridedBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  real(8), device :: alpha ! device or host variable
  real(8), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  real(8), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  real(8), device :: beta ! device or host variable
  real(8), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

2.4. Single Precision Complex Functions and Subroutines

This section contains interfaces to the single precision complex BLAS and cuBLAS functions and subroutines.

2.4.1. icamax

ICAMAX finds the index of the element having the maximum absolute value.

integer(4) function icamax(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIcamax(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIcamax_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.4.2. icamin

ICAMIN finds the index of the element having the minimum absolute value.

integer(4) function icamin(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIcamin(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIcamin_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.4.3. scasum

SCASUM takes the sum of the absolute values of a complex vector and returns a single precision result.

real(4) function scasum(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(4) function cublasScasum(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasScasum_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.4.4. caxpy

CAXPY constant times a vector plus a vector.

subroutine caxpy(n, a, x, incx, y, incy)
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasCaxpy(n, a, x, incx, y, incy)
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCaxpy_v2(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.4.5. ccopy

CCOPY copies a vector x to a vector y.

subroutine ccopy(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasCcopy(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCcopy_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.4.6. cdotc

forms the dot product of two vectors, conjugating the first vector.

complex(4) function cdotc(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

complex(4) function cublasCdotc(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCdotc_v2(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(4), device :: res ! device or host variable

2.4.7. cdotu

CDOTU forms the dot product of two vectors.

complex(4) function cdotu(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

complex(4) function cublasCdotu(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCdotu_v2(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(4), device :: res ! device or host variable

2.4.8. scnrm2

SCNRM2 returns the euclidean norm of a vector via the function name, so that SCNRM2 := sqrt( x**H*x )

real(4) function scnrm2(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(4) function cublasScnrm2(n, x, incx)
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasScnrm2_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.4.9. crot

CROT applies a plane rotation, where the cos (C) is real and the sin (S) is complex, and the vectors CX and CY are complex.

subroutine crot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(4), device :: sc ! device or host variable
  complex(4), device :: ss ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasCrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(4), device :: sc ! device or host variable
  complex(4), device :: ss ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCrot_v2(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: sc ! device or host variable
  complex(4), device :: ss ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.4.10. csrot

CSROT applies a plane rotation, where the cos and sin (c and s) are real and the vectors cx and cy are complex.

subroutine csrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasCsrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCsrot_v2(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.4.11. crotg

CROTG determines a complex Givens rotation.

subroutine crotg(sa, sb, sc, ss)
  complex(4), device :: sa, sb, ss ! device or host variable
  real(4), device :: sc ! device or host variable

subroutine cublasCrotg(sa, sb, sc, ss)
  complex(4), device :: sa, sb, ss ! device or host variable
  real(4), device :: sc ! device or host variable

integer(4) function cublasCrotg_v2(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  complex(4), device :: sa, sb, ss ! device or host variable
  real(4), device :: sc ! device or host variable

2.4.12. cscal

CSCAL scales a vector by a constant.

subroutine cscal(n, a, x, incx)
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

subroutine cublasCscal(n, a, x, incx)
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasCscal_v2(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x
  integer :: incx

2.4.13. csscal

CSSCAL scales a complex vector by a real constant.

subroutine csscal(n, a, x, incx)
  integer :: n
  real(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable
  integer :: incx

subroutine cublasCsscal(n, a, x, incx)
  integer :: n
  real(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasCsscal_v2(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x
  integer :: incx

2.4.14. cswap

CSWAP interchanges two vectors.

subroutine cswap(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasCswap(n, x, incx, y, incy)
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasCswap_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.4.15. cgbmv

CGBMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, or y := alpha*A**H*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n band matrix, with kl sub-diagonals and ku super-diagonals.

subroutine cgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCgbmv_v2(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.4.16. cgemv

CGEMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, or y := alpha*A**H*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n matrix.

subroutine cgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCgemv_v2(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.4.17. cgerc

CGERC performs the rank 1 operation A := alpha*x*y**H + A, where alpha is a scalar, x is an m element vector, y is an n element vector and A is an m by n matrix.

subroutine cgerc(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCgerc(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCgerc_v2(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

2.4.18. cgeru

CGERU performs the rank 1 operation A := alpha*x*y**T + A, where alpha is a scalar, x is an m element vector, y is an n element vector and A is an m by n matrix.

subroutine cgeru(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCgeru(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCgeru_v2(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

2.4.19. csymv

CSYMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric matrix.

subroutine csymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCsymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCsymv_v2(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.4.20. csyr

CSYR performs the symmetric rank 1 operation A := alpha*x*x**H + A, where alpha is a complex scalar, x is an n element vector and A is an n by n symmetric matrix.

subroutine csyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCsyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCsyr_v2(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x
  complex(4), device :: alpha ! device or host variable

2.4.21. csyr2

CSYR2 performs the symmetric rank 2 operation A := alpha*x*y’ + alpha*y*x’ + A, where alpha is a complex scalar, x and y are n element vectors and A is an n by n SY matrix.

subroutine csyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCsyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCsyr2_v2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

2.4.22. ctbmv

CTBMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, or x := A**H*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals.

subroutine ctbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable

subroutine cublasCtbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

integer(4) function cublasCtbmv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.4.23. ctbsv

CTBSV solves one of the systems of equations A*x = b, or A**T*x = b, or A**H*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine ctbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable

subroutine cublasCtbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

integer(4) function cublasCtbsv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.4.24. ctpmv

CTPMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, or x := A**H*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form.

subroutine ctpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x ! device or host variable

subroutine cublasCtpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x

integer(4) function cublasCtpmv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x

2.4.25. ctpsv

CTPSV solves one of the systems of equations A*x = b, or A**T*x = b, or A**H*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine ctpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x ! device or host variable

subroutine cublasCtpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x

integer(4) function cublasCtpsv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x

2.4.26. ctrmv

CTRMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, or x := A**H*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix.

subroutine ctrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable

subroutine cublasCtrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

integer(4) function cublasCtrmv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.4.27. ctrsv

CTRSV solves one of the systems of equations A*x = b, or A**T*x = b, or A**H*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine ctrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x ! device or host variable

subroutine cublasCtrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

integer(4) function cublasCtrsv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.4.28. chbmv

CHBMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n hermitian band matrix, with k super-diagonals.

subroutine chbmv(uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: k, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasChbmv(uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: k, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasChbmv_v2(h, uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: k, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.4.29. chemv

CHEMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n hermitian matrix.

subroutine chemv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasChemv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasChemv_v2(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.4.30. chpmv

CHPMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n hermitian matrix, supplied in packed form.

subroutine chpmv(uplo, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasChpmv(uplo, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasChpmv_v2(h, uplo, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha, beta ! device or host variable

2.4.31. cher

CHER performs the hermitian rank 1 operation A := alpha*x*x**H + A, where alpha is a real scalar, x is an n element vector and A is an n by n hermitian matrix.

subroutine cher(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(4), device, dimension(*) :: a, x ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasCher(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

integer(4) function cublasCher_v2(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

2.4.32. cher2

CHER2 performs the hermitian rank 2 operation A := alpha*x*y**H + conjg( alpha )*y*x**H + A, where alpha is a scalar, x and y are n element vectors and A is an n by n hermitian matrix.

subroutine cher2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(*) :: a, x, y ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCher2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCher2_v2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha ! device or host variable

2.4.33. chpr

CHPR performs the hermitian rank 1 operation A := alpha*x*x**H + A, where alpha is a real scalar, x is an n element vector and A is an n by n hermitian matrix, supplied in packed form.

subroutine chpr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x ! device or host variable
  real(4), device :: alpha ! device or host variable

subroutine cublasChpr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

integer(4) function cublasChpr_v2(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

2.4.34. chpr2

CHPR2 performs the hermitian rank 2 operation A := alpha*x*y**H + conjg( alpha )*y*x**H + A, where alpha is a scalar, x and y are n element vectors and A is an n by n hermitian matrix, supplied in packed form.

subroutine chpr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasChpr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasChpr2_v2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha ! device or host variable

2.4.35. cgemm

CGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T or op( X ) = X**H, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

subroutine cgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCgemm_v2(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.4.36. csymm

CSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

subroutine csymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCsymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCsymm_v2(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.4.37. csyrk

CSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

subroutine csyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCsyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCsyrk_v2(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.4.38. csyr2k

CSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

subroutine csyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCsyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCsyr2k_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.4.39. csyrkx

CSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

subroutine csyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasCsyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCsyrkx_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.4.40. ctrmm

CTRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ) where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H.

subroutine ctrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCtrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCtrmm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable

2.4.41. ctrsm

CTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H. The matrix X is overwritten on B.

subroutine ctrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device :: alpha ! device or host variable

subroutine cublasCtrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device :: alpha ! device or host variable

integer(4) function cublasCtrsm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device :: alpha ! device or host variable

2.4.42. chemm

CHEMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is an hermitian matrix and B and C are m by n matrices.

subroutine chemm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha, beta ! device or host variable

subroutine cublasChemm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

integer(4) function cublasChemm_v2(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.4.43. cherk

CHERK performs one of the hermitian rank k operations C := alpha*A*A**H + beta*C, or C := alpha*A**H*A + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

subroutine cherk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  real(4), device :: alpha, beta ! device or host variable

subroutine cublasCherk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

integer(4) function cublasCherk_v2(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.4.44. cher2k

CHER2K performs one of the hermitian rank 2k operations C := alpha*A*B**H + conjg( alpha )*B*A**H + beta*C, or C := alpha*A**H*B + conjg( alpha )*B**H*A + beta*C, where alpha and beta are scalars with beta real, C is an n by n hermitian matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

subroutine cher2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

subroutine cublasCher2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

integer(4) function cublasCher2k_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

2.4.45. cherkx

CHERKX performs a variation of the hermitian rank k operations C := alpha*A*B**H + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix stored in lower or upper mode, and A and B are n by k matrices. See the CUBLAS documentation for more details.

subroutine cherkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a ! device or host variable
  complex(4), device, dimension(ldb, *) :: b ! device or host variable
  complex(4), device, dimension(ldc, *) :: c ! device or host variable
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

subroutine cublasCherkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

integer(4) function cublasCherkx_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

2.4.46. cublasCgemvBatched

CGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasCgemvBatched(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  complex(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  complex(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

integer(4) function cublasCgemvBatched_v2(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  complex(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  complex(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

2.4.47. cublasCgemmBatched

CGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T or op( X ) = X**H, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasCgemmBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  complex(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  complex(4), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

integer(4) function cublasCgemmBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  complex(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  complex(4), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

2.4.48. cublasCgelsBatched

CGELS solves overdetermined or underdetermined complex linear systems involving an M-by-N matrix A, or its conjugate-transpose, using a QR or LQ factorization of A. It is assumed that A has full rank. The following options are provided: 1. If TRANS = ‘N’ and m >= n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A*X ||. 2. If TRANS = ‘N’ and m < n: find the minimum norm solution of an underdetermined system A * X = B. 3. If TRANS = ‘C’ and m >= n: find the minimum norm solution of an undetermined system A**H * X = B. 4. If TRANS = ‘C’ and m < n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A**H * X ||. Several right hand side vectors b and solution vectors x can be handled in a single call; they are stored as the columns of the M-by-NRHS right hand side matrix B and the N-by-NRHS solution matrix X.

integer(4) function cublasCgelsBatched(h, trans, m, n, nrhs, Aarray, lda, Carray, ldc, info, devinfo, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: info(*)
  integer, device :: devinfo(*)
  integer :: batchCount

2.4.49. cublasCgeqrfBatched

CGEQRF computes a QR factorization of a complex M-by-N matrix A: A = Q * R.

integer(4) function cublasCgeqrfBatched(h, m, n, Aarray, lda, Tau, info, batchCount)
  type(cublasHandle) :: h
  integer :: m, n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Tau(*)
  integer :: info(*)
  integer :: batchCount

2.4.50. cublasCgetrfBatched

CGETRF computes an LU factorization of a general M-by-N matrix A using partial pivoting with row interchanges. The factorization has the form A = P * L * U where P is a permutation matrix, L is lower triangular with unit diagonal elements (lower trapezoidal if m > n), and U is upper triangular (upper trapezoidal if m < n). This is the right-looking Level 3 BLAS version of the algorithm.

integer(4) function cublasCgetrfBatched(h, n, Aarray, lda, ipvt, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  integer, device :: info(*)
  integer :: batchCount

2.4.51. cublasCgetriBatched

CGETRI computes the inverse of a matrix using the LU factorization computed by CGETRF. This method inverts U and then computes inv(A) by solving the system inv(A)*L = inv(U) for inv(A).

integer(4) function cublasCgetriBatched(h, n, Aarray, lda, ipvt, Carray, ldc, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer, device :: info(*)
  integer :: batchCount

2.4.52. cublasCgetrsBatched

CGETRS solves a system of linear equations A * X = B, A**T * X = B, or A**H * X = B with a general N-by-N matrix A using the LU factorization computed by CGETRF.

integer(4) function cublasCgetrsBatched(h, trans, n, nrhs, Aarray, lda, ipvt, Barray, ldb, info, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  integer :: info(*)
  integer :: batchCount

2.4.53. cublasCmatinvBatched

cublasCmatinvBatched is a short cut of cublasCgetrfBatched plus cublasCgetriBatched. However it only works if n is less than 32. If not, the user has to go through cublasCgetrfBatched and cublasCgetriBatched.

integer(4) function cublasCmatinvBatched(h, n, Aarray, lda, Ainv, lda_inv, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Ainv(*)
  integer :: lda_inv
  integer, device :: info(*)
  integer :: batchCount

2.4.54. cublasCtrsmBatched

CTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H. The matrix X is overwritten on B.

integer(4) function cublasCtrsmBatched( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side ! integer or character(1) variable
  integer :: uplo ! integer or character(1) variable
  integer :: trans ! integer or character(1) variable
  integer :: diag ! integer or character(1) variable
  integer :: m, n
  complex(4), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

integer(4) function cublasCtrsmBatched_v2( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side
  integer :: uplo
  integer :: trans
  integer :: diag
  integer :: m, n
  complex(4), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

2.4.55. cublasCgemvStridedBatched

CGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasCgemvStridedBatched(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  complex(4), device :: alpha ! device or host variable
  complex(4), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  complex(4), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  complex(4), device :: beta ! device or host variable
  complex(4), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

integer(4) function cublasCgemvStridedBatched_v2(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  complex(4), device :: alpha ! device or host variable
  complex(4), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  complex(4), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  complex(4), device :: beta ! device or host variable
  complex(4), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

2.4.56. cublasCgemmStridedBatched

CGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasCgemmStridedBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  complex(4), device :: alpha ! device or host variable
  complex(4), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  complex(4), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  complex(4), device :: beta ! device or host variable
  complex(4), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

integer(4) function cublasCgemmStridedBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  complex(4), device :: alpha ! device or host variable
  complex(4), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  complex(4), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  complex(4), device :: beta ! device or host variable
  complex(4), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

2.5. Double Precision Complex Functions and Subroutines

This section contains interfaces to the double precision complex BLAS and cuBLAS functions and subroutines.

2.5.1. izamax

IZAMAX finds the index of the element having the maximum absolute value.

integer(4) function izamax(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIzamax(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIzamax_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.5.2. izamin

IZAMIN finds the index of the element having the minimum absolute value.

integer(4) function izamin(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

integer(4) function cublasIzamin(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasIzamin_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.5.3. dzasum

DZASUM takes the sum of the absolute values.

real(8) function dzasum(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(8) function cublasDzasum(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasDzasum_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.5.4. zaxpy

ZAXPY constant times a vector plus a vector.

subroutine zaxpy(n, a, x, incx, y, incy)
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasZaxpy(n, a, x, incx, y, incy)
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZaxpy_v2(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.5.5. zcopy

ZCOPY copies a vector, x, to a vector, y.

subroutine zcopy(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasZcopy(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZcopy_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.5.6. zdotc

ZDOTC forms the dot product of a vector.

complex(8) function zdotc(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

complex(8) function cublasZdotc(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZdotc_v2(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(8), device :: res ! device or host variable

2.5.7. zdotu

ZDOTU forms the dot product of two vectors.

complex(8) function zdotu(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

complex(8) function cublasZdotu(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZdotu_v2(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(8), device :: res ! device or host variable

2.5.8. dznrm2

DZNRM2 returns the euclidean norm of a vector via the function name, so that DZNRM2 := sqrt( x**H*x )

real(8) function dznrm2(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

real(8) function cublasDznrm2(n, x, incx)
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasDznrm2_v2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.5.9. zrot

ZROT applies a plane rotation, where the cos (C) is real and the sin (S) is complex, and the vectors CX and CY are complex.

subroutine zrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(8), device :: sc ! device or host variable
  complex(8), device :: ss ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasZrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(8), device :: sc ! device or host variable
  complex(8), device :: ss ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZrot_v2(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: sc ! device or host variable
  complex(8), device :: ss ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.5.10. zsrot

ZSROT applies a plane rotation, where the cos and sin (c and s) are real and the vectors cx and cy are complex.

subroutine zsrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasZsrot(n, x, incx, y, incy, sc, ss)
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZsrot_v2(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.5.11. zrotg

ZROTG determines a double complex Givens rotation.

subroutine zrotg(sa, sb, sc, ss)
  complex(8), device :: sa, sb, ss ! device or host variable
  real(8), device :: sc ! device or host variable

subroutine cublasZrotg(sa, sb, sc, ss)
  complex(8), device :: sa, sb, ss ! device or host variable
  real(8), device :: sc ! device or host variable

integer(4) function cublasZrotg_v2(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  complex(8), device :: sa, sb, ss ! device or host variable
  real(8), device :: sc ! device or host variable

2.5.12. zscal

ZSCAL scales a vector by a constant.

subroutine zscal(n, a, x, incx)
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

subroutine cublasZscal(n, a, x, incx)
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasZscal_v2(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x
  integer :: incx

2.5.13. zdscal

ZDSCAL scales a vector by a constant.

subroutine zdscal(n, a, x, incx)
  integer :: n
  real(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable
  integer :: incx

subroutine cublasZdscal(n, a, x, incx)
  integer :: n
  real(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x
  integer :: incx

integer(4) function cublasZdscal_v2(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x
  integer :: incx

2.5.14. zswap

ZSWAP interchanges two vectors.

subroutine zswap(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y ! device or host variable
  integer :: incx, incy

subroutine cublasZswap(n, x, incx, y, incy)
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

integer(4) function cublasZswap_v2(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.5.15. zgbmv

ZGBMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, or y := alpha*A**H*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n band matrix, with kl sub-diagonals and ku super-diagonals.

subroutine zgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZgbmv(t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZgbmv_v2(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.5.16. zgemv

ZGEMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, or y := alpha*A**H*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m by n matrix.

subroutine zgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZgemv(t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: t
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZgemv_v2(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.5.17. zgerc

ZGERC performs the rank 1 operation A := alpha*x*y**H + A, where alpha is a scalar, x is an m element vector, y is an n element vector and A is an m by n matrix.

subroutine zgerc(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZgerc(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZgerc_v2(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

2.5.18. zgeru

ZGERU performs the rank 1 operation A := alpha*x*y**T + A, where alpha is a scalar, x is an m element vector, y is an n element vector and A is an m by n matrix.

subroutine zgeru(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZgeru(m, n, alpha, x, incx, y, incy, a, lda)
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZgeru_v2(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

2.5.19. zsymv

ZSYMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n symmetric matrix.

subroutine zsymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZsymv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZsymv_v2(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.5.20. zsyr

ZSYR performs the symmetric rank 1 operation A := alpha*x*x**H + A, where alpha is a complex scalar, x is an n element vector and A is an n by n symmetric matrix.

subroutine zsyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZsyr(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZsyr_v2(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x
  complex(8), device :: alpha ! device or host variable

2.5.21. zsyr2

ZSYR2 performs the symmetric rank 2 operation A := alpha*x*y’ + alpha*y*x’ + A, where alpha is a complex scalar, x and y are n element vectors and A is an n by n SY matrix.

subroutine zsyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZsyr2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZsyr2_v2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

2.5.22. ztbmv

ZTBMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, or x := A**H*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals.

subroutine ztbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable

subroutine cublasZtbmv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

integer(4) function cublasZtbmv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.5.23. ztbsv

ZTBSV solves one of the systems of equations A*x = b, or A**T*x = b, or A**H*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular band matrix, with ( k + 1 ) diagonals. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine ztbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable

subroutine cublasZtbsv(u, t, d, n, k, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

integer(4) function cublasZtbsv_v2(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.5.24. ztpmv

ZTPMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, or x := A**H*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form.

subroutine ztpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x ! device or host variable

subroutine cublasZtpmv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x

integer(4) function cublasZtpmv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x

2.5.25. ztpsv

ZTPSV solves one of the systems of equations A*x = b, or A**T*x = b, or A**H*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix, supplied in packed form. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine ztpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x ! device or host variable

subroutine cublasZtpsv(u, t, d, n, a, x, incx)
  character*1 :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x

integer(4) function cublasZtpsv_v2(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x

2.5.26. ztrmv

ZTRMV performs one of the matrix-vector operations x := A*x, or x := A**T*x, or x := A**H*x, where x is an n element vector and A is an n by n unit, or non-unit, upper or lower triangular matrix.

subroutine ztrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable

subroutine cublasZtrmv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

integer(4) function cublasZtrmv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.5.27. ztrsv

ZTRSV solves one of the systems of equations A*x = b, or A**T*x = b, or A**H*x = b, where b and x are n element vectors and A is an n by n unit, or non-unit, upper or lower triangular matrix. No test for singularity or near-singularity is included in this routine. Such tests must be performed before calling this routine.

subroutine ztrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x ! device or host variable

subroutine cublasZtrsv(u, t, d, n, a, lda, x, incx)
  character*1 :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

integer(4) function cublasZtrsv_v2(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.5.28. zhbmv

ZHBMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n hermitian band matrix, with k super-diagonals.

subroutine zhbmv(uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: k, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZhbmv(uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: k, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZhbmv_v2(h, uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: k, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.5.29. zhemv

ZHEMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n hermitian matrix.

subroutine zhemv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZhemv(uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZhemv_v2(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.5.30. zhpmv

ZHPMV performs the matrix-vector operation y := alpha*A*x + beta*y, where alpha and beta are scalars, x and y are n element vectors and A is an n by n hermitian matrix, supplied in packed form.

subroutine zhpmv(uplo, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZhpmv(uplo, n, alpha, a, x, incx, beta, y, incy)
  character*1 :: uplo
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZhpmv_v2(h, uplo, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha, beta ! device or host variable

2.5.31. zher

ZHER performs the hermitian rank 1 operation A := alpha*x*x**H + A, where alpha is a real scalar, x is an n element vector and A is an n by n hermitian matrix.

subroutine zher(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(8), device, dimension(*) :: a, x ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasZher(t, n, alpha, x, incx, a, lda)
  character*1 :: t
  integer :: n, incx, lda
  complex(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

integer(4) function cublasZher_v2(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

2.5.32. zher2

ZHER2 performs the hermitian rank 2 operation A := alpha*x*y**H + conjg( alpha )*y*x**H + A, where alpha is a scalar, x and y are n element vectors and A is an n by n hermitian matrix.

subroutine zher2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZher2(t, n, alpha, x, incx, y, incy, a, lda)
  character*1 :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZher2_v2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha ! device or host variable

2.5.33. zhpr

ZHPR performs the hermitian rank 1 operation A := alpha*x*x**H + A, where alpha is a real scalar, x is an n element vector and A is an n by n hermitian matrix, supplied in packed form.

subroutine zhpr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x ! device or host variable
  real(8), device :: alpha ! device or host variable

subroutine cublasZhpr(t, n, alpha, x, incx, a)
  character*1 :: t
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

integer(4) function cublasZhpr_v2(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

2.5.34. zhpr2

ZHPR2 performs the hermitian rank 2 operation A := alpha*x*y**H + conjg( alpha )*y*x**H + A, where alpha is a scalar, x and y are n element vectors and A is an n by n hermitian matrix, supplied in packed form.

subroutine zhpr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZhpr2(t, n, alpha, x, incx, y, incy, a)
  character*1 :: t
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZhpr2_v2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha ! device or host variable

2.5.35. zgemm

ZGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T or op( X ) = X**H, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

subroutine zgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZgemm_v2(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.5.36. zsymm

ZSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

subroutine zsymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZsymm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZsymm_v2(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.5.37. zsyrk

ZSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

subroutine zsyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZsyrk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZsyrk_v2(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.5.38. zsyr2k

ZSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

subroutine zsyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZsyr2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZsyr2k_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.5.39. zsyrkx

ZSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

subroutine zsyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZsyrkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZsyrkx_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.5.40. ztrmm

ZTRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ) where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H.

subroutine ztrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZtrmm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZtrmm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable

2.5.41. ztrsm

ZTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H. The matrix X is overwritten on B.

subroutine ztrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device :: alpha ! device or host variable

subroutine cublasZtrsm(side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  character*1 :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device :: alpha ! device or host variable

integer(4) function cublasZtrsm_v2(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device :: alpha ! device or host variable

2.5.42. zhemm

ZHEMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is an hermitian matrix and B and C are m by n matrices.

subroutine zhemm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha, beta ! device or host variable

subroutine cublasZhemm(side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZhemm_v2(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.5.43. zherk

ZHERK performs one of the hermitian rank k operations C := alpha*A*A**H + beta*C, or C := alpha*A**H*A + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

subroutine zherk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  real(8), device :: alpha, beta ! device or host variable

subroutine cublasZherk(uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

integer(4) function cublasZherk_v2(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.5.44. zher2k

ZHER2K performs one of the hermitian rank 2k operations C := alpha*A*B**H + conjg( alpha )*B*A**H + beta*C, or C := alpha*A**H*B + conjg( alpha )*B**H*A + beta*C, where alpha and beta are scalars with beta real, C is an n by n hermitian matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

subroutine zher2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

subroutine cublasZher2k(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

integer(4) function cublasZher2k_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

2.5.45. zherkx

ZHERKX performs a variation of the hermitian rank k operations C := alpha*A*B**H + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix stored in lower or upper mode, and A and B are n by k matrices. See the CUBLAS documentation for more details.

subroutine zherkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a ! device or host variable
  complex(8), device, dimension(ldb, *) :: b ! device or host variable
  complex(8), device, dimension(ldc, *) :: c ! device or host variable
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

subroutine cublasZherkx(uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  character*1 :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

integer(4) function cublasZherkx_v2(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

2.5.46. cublasZgemvBatched

ZGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasZgemvBatched(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  complex(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  complex(8), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

integer(4) function cublasZgemvBatched_v2(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  complex(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  complex(8), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

2.5.47. cublasZgemmBatched

ZGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T or op( X ) = X**H, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasZgemmBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  complex(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  complex(8), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

integer(4) function cublasZgemmBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  complex(8), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  complex(8), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

2.5.48. cublasZgelsBatched

ZGELS solves overdetermined or underdetermined complex linear systems involving an M-by-N matrix A, or its conjugate-transpose, using a QR or LQ factorization of A. It is assumed that A has full rank. The following options are provided: 1. If TRANS = ‘N’ and m >= n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A*X ||. 2. If TRANS = ‘N’ and m < n: find the minimum norm solution of an underdetermined system A * X = B. 3. If TRANS = ‘C’ and m >= n: find the minimum norm solution of an undetermined system A**H * X = B. 4. If TRANS = ‘C’ and m < n: find the least squares solution of an overdetermined system, i.e., solve the least squares problem minimize || B - A**H * X ||. Several right hand side vectors b and solution vectors x can be handled in a single call; they are stored as the columns of the M-by-NRHS right hand side matrix B and the N-by-NRHS solution matrix X.

integer(4) function cublasZgelsBatched(h, trans, m, n, nrhs, Aarray, lda, Carray, ldc, info, devinfo, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: info(*)
  integer, device :: devinfo(*)
  integer :: batchCount

2.5.49. cublasZgeqrfBatched

ZGEQRF computes a QR factorization of a complex M-by-N matrix A: A = Q * R.

integer(4) function cublasZgeqrfBatched(h, m, n, Aarray, lda, Tau, info, batchCount)
  type(cublasHandle) :: h
  integer :: m, n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Tau(*)
  integer :: info(*)
  integer :: batchCount

2.5.50. cublasZgetrfBatched

ZGETRF computes an LU factorization of a general M-by-N matrix A using partial pivoting with row interchanges. The factorization has the form A = P * L * U where P is a permutation matrix, L is lower triangular with unit diagonal elements (lower trapezoidal if m > n), and U is upper triangular (upper trapezoidal if m < n). This is the right-looking Level 3 BLAS version of the algorithm.

integer(4) function cublasZgetrfBatched(h, n, Aarray, lda, ipvt, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  integer, device :: info(*)
  integer :: batchCount

2.5.51. cublasZgetriBatched

ZGETRI computes the inverse of a matrix using the LU factorization computed by ZGETRF. This method inverts U and then computes inv(A) by solving the system inv(A)*L = inv(U) for inv(A).

integer(4) function cublasZgetriBatched(h, n, Aarray, lda, ipvt, Carray, ldc, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer, device :: info(*)
  integer :: batchCount

2.5.52. cublasZgetrsBatched

ZGETRS solves a system of linear equations A * X = B, A**T * X = B, or A**H * X = B with a general N-by-N matrix A using the LU factorization computed by ZGETRF.

integer(4) function cublasZgetrsBatched(h, trans, n, nrhs, Aarray, lda, ipvt, Barray, ldb, info, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: n, nrhs
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  integer, device :: ipvt(*)
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  integer :: info(*)
  integer :: batchCount

2.5.53. cublasZmatinvBatched

cublasZmatinvBatched is a short cut of cublasZgetrfBatched plus cublasZgetriBatched. However it only works if n is less than 32. If not, the user has to go through cublasZgetrfBatched and cublasZgetriBatched.

integer(4) function cublasZmatinvBatched(h, n, Aarray, lda, Ainv, lda_inv, info, batchCount)
  type(cublasHandle) :: h
  integer :: n
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Ainv(*)
  integer :: lda_inv
  integer, device :: info(*)
  integer :: batchCount

2.5.54. cublasZtrsmBatched

ZTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H. The matrix X is overwritten on B.

integer(4) function cublasZtrsmBatched( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side ! integer or character(1) variable
  integer :: uplo ! integer or character(1) variable
  integer :: trans ! integer or character(1) variable
  integer :: diag ! integer or character(1) variable
  integer :: m, n
  complex(8), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

integer(4) function cublasZtrsmBatched_v2( h, side, uplo, trans, diag, m, n, alpha, A, lda, B, ldb, batchCount)
  type(cublasHandle) :: h
  integer :: side
  integer :: uplo
  integer :: trans
  integer :: diag
  integer :: m, n
  complex(8), device :: alpha ! device or host variable
  type(c_devptr), device :: A(*)
  integer :: lda
  type(c_devptr), device :: B(*)
  integer :: ldb
  integer :: batchCount

2.5.55. cublasZgemvStridedBatched

ZGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

integer(4) function cublasZgemvStridedBatched(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  complex(8), device :: alpha ! device or host variable
  complex(8), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  complex(8), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  complex(8), device :: beta ! device or host variable
  complex(8), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

integer(4) function cublasZgemvStridedBatched_v2(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  complex(8), device :: alpha ! device or host variable
  complex(8), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  complex(8), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  complex(8), device :: beta ! device or host variable
  complex(8), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

2.5.56. cublasZgemmStridedBatched

ZGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasZgemmStridedBatched(h, transa, transb, m, n, k, alpha, Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  complex(8), device :: alpha ! device or host variable
  complex(8), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  complex(8), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  complex(8), device :: beta ! device or host variable
  complex(8), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

integer(4) function cublasZgemmStridedBatched_v2(h, transa, transb, m, n, k, alpha, &
           Aarray, lda, strideA, Barray, ldb, strideB, beta, Carray, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  complex(8), device :: alpha ! device or host variable
  complex(8), device :: Aarray(*)
  integer :: lda
  integer :: strideA
  complex(8), device :: Barray(*)
  integer :: ldb
  integer :: strideB
  complex(8), device :: beta ! device or host variable
  complex(8), device :: Carray(*)
  integer :: ldc
  integer :: strideC
  integer :: batchCount

2.6. Half Precision Functions and Extension Functions

This section contains interfaces to the half precision cuBLAS functions and the BLAS extension functions which allow the user to individually specify the types of the arrays and computation (many or all of which support half precision).

The extension functions can accept one of many supported datatypes. Users should always check the latest cuBLAS documentation for supported combinations. In this document we will use the real(2) datatype since those functions are not otherwise supported by the S, D, C, and Z variants in the libraries. In addition, the user is responsible for properly setting the pointer mode by making calls to cublasSetPointerMode for all extension functions.

The type(cudaDataType) is now common to several of the newer library functions covered in this document. Though some functions will accept an appropriately valued integer, the use of type(cudaDataType) is now recommended going forward.

2.6.1. cublasHgemvBatched

HGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

In the HSH versions, alpha, beta are real(4), and the arrays which are pointed to should all contain real(2) data.

integer(4) function cublasHSHgemvBatched(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

integer(4) function cublasHSHgemvBatched_v2(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

In the HSS versions, alpha, beta are real(4), the Aarray, xarray arrays which are pointed to should contain real(2) data, and yarray should contain real(4) data.

integer(4) function cublasHSSgemvBatched(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

integer(4) function cublasHSSgemvBatched_v2(h, trans, m, n, alpha, &
      Aarray, lda, xarray, incx, beta, yarray, incy, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: xarray(*)
  integer :: incx
  real(4), device :: beta ! device or host variable
  type(c_devptr), device :: yarray(*)
  integer :: incy
  integer :: batchCount

2.6.2. cublasHgemvStridedBatched

HGEMV performs a batch of the matrix-vector operations Y := alpha*op( A ) * X + beta*Y, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars, A is an m by n matrix, and X and Y are vectors.

In the HSH versions, alpha, beta are real(4), and the arrays A, X, Y are all real(2) data.

integer(4) function cublasHSHgemvStridedBatched(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(2), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(4), device :: beta ! device or host variable
  real(2), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

integer(4) function cublasHSHgemvStridedBatched_v2(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(2), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(4), device :: beta ! device or host variable
  real(2), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

In the HSS versions, alpha, beta are real(4), the A, X arrays contain real(2) data, and the Y array contains real(4) data.

integer(4) function cublasHSSgemvStridedBatched(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans ! integer or character(1) variable
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(2), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(4), device :: beta ! device or host variable
  real(4), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

integer(4) function cublasHSSgemvStridedBatched_v2(h, trans, m, n, alpha, &
      A, lda, strideA, X, incx, strideX, beta, Y, incy, strideY, batchCount)
  type(cublasHandle) :: h
  integer :: trans
  integer :: m, n
  real(4), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(2), device :: X(*)
  integer :: incx
  integer(8) :: strideX
  real(4), device :: beta ! device or host variable
  real(4), device :: Y(*)
  integer :: incy
  integer(8) :: strideY
  integer :: batchCount

2.6.3. cublasHgemm

HGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

subroutine cublasHgemm(transa, transb, m, n, k, alpha, a, lda, b, ldb, &
      beta, c, ldc)
  integer :: transa  ! integer or character(1) variable
  integer :: transb  ! integer or character(1) variable
  integer :: m, n, k, lda, ldb, ldc
  real(2), device, dimension(lda, *) :: a
  real(2), device, dimension(ldb, *) :: b
  real(2), device, dimension(ldc, *) :: c
  real(2), device :: alpha, beta ! device or host variable

In the v2 version, the user is responsible for setting the pointer mode for the alpha, beta arguments.

integer(4) function cublasHgemm_v2(h, transa, transb, m, n, k, alpha, &
      a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(2), device, dimension(lda, *) :: a
  real(2), device, dimension(ldb, *) :: b
  real(2), device, dimension(ldc, *) :: c
  real(2), device :: alpha, beta ! device or host variable

2.6.4. cublasHgemmBatched

HGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasHgemmBatched(h, transa, transb, m, n, k, &
      alpha, Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  real(2), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

integer(4) function cublasHgemmBatched_v2(h, transa, transb, m, n, k, &
      alpha, Aarray, lda, Barray, ldb, beta, Carray, ldc, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  integer :: lda
  type(c_devptr), device :: Barray(*)
  integer :: ldb
  real(2), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  integer :: ldc
  integer :: batchCount

2.6.5. cublasHgemmStridedBatched

HGEMM performs a set of matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasHgemmStridedBatched(h, transa, transb, m, n, k, &
    alpha, A, lda, strideA, B, ldb, strideB, beta, C, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa ! integer or character(1) variable
  integer :: transb ! integer or character(1) variable
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(2), device :: B(ldb,*)
  integer :: ldb
  integer(8) :: strideB
  real(2), device :: beta ! device or host variable
  real(2), device :: C(ldc,*)
  integer :: ldc
  integer(8) :: strideC
  integer :: batchCount

integer(4) function cublasHgemmStridedBatched_v2(h, transa, transb, m, n, k, &
    alpha, A, lda, strideA, B, ldb, strideB, beta, C, ldc, strideC, batchCount)
  type(cublasHandle) :: h
  integer :: transa
  integer :: transb
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  integer :: lda
  integer(8) :: strideA
  real(2), device :: B(ldb,*)
  integer :: ldb
  integer(8) :: strideB
  real(2), device :: beta ! device or host variable
  real(2), device :: C(ldc,*)
  integer :: ldc
  integer(8) :: strideC
  integer :: batchCount

2.6.6. cublasIamaxEx

IAMAX finds the index of the element having the maximum absolute value.

integer(4) function cublasIamaxEx(h, n, x, xtype, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  integer, device :: res ! device or host variable

2.6.7. cublasIaminEx

IAMIN finds the index of the element having the minimum absolute value.

integer(4) function cublasIaminEx(h, n, x, xtype, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  integer, device :: res ! device or host variable

2.6.8. cublasAsumEx

ASUM takes the sum of the absolute values.

integer(4) function cublasAsumEx(h, n, x, xtype, incx, res, &
      restype, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device :: res ! device or host variable
  type(cudaDataType) :: restype
  type(cudaDataType) :: extype

2.6.9. cublasAxpyEx

AXPY computes a constant times a vector plus a vector.

integer(4) function cublasAxpyEx(h, n, alpha, alphatype, &
      x, xtype, incx, y, ytype, incy, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device :: alpha
  type(cudaDataType) :: alphatype
  real(2), device, dimension(*) :: x
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y
  type(cudaDataType) :: ytype
  integer :: incy
  type(cudaDataType) :: extype

2.6.10. cublasCopyEx

COPY copies a vector, x, to a vector, y.

integer(4) function cublasCopyEx(h, n, x, xtype, incx, &
      y, ytype, incy)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y
  type(cudaDataType) :: ytype
  integer :: incy

2.6.11. cublasDotEx

DOT forms the dot product of two vectors.

integer(4) function cublasDotEx(h, n, x, xtype, incx, &
      y, ytype, incy, res, restype, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y  ! Type and kind as specified by ytype
  type(cudaDataType) :: ytype
  integer :: incy
  real(2), device :: res ! device or host variable
  type(cudaDataType) :: restype
  type(cudaDataType) :: extype

2.6.12. cublasDotcEx

DOTC forms the conjugated dot product of two vectors.

integer(4) function cublasDotcEx(h, n, x, xtype, incx, &
      y, ytype, incy, res, restype, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y  ! Type and kind as specified by ytype
  type(cudaDataType) :: ytype
  integer :: incy
  real(2), device :: res ! device or host variable
  type(cudaDataType) :: restype
  type(cudaDataType) :: extype

2.6.13. cublasNrm2Ex

NRM2 produces the euclidean norm of a vector.

integer(4) function cublasNrm2Ex(h, n, x, xtype, incx, res, &
      restype, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device :: res ! device or host variable
  type(cudaDataType) :: restype
  type(cudaDataType) :: extype

2.6.14. cublasRotEx

ROT applies a plane rotation.

integer(4) function cublasRotEx(h, n, x, xtype, incx, &
      y, ytype, incy, c, s, cstype, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y  ! Type and kind as specified by ytype
  type(cudaDataType) :: ytype
  integer :: incy
  real(2), device :: c, s ! device or host variable
  type(cudaDataType) :: cstype
  type(cudaDataType) :: extype

2.6.15. cublasRotgEx

ROTG constructs a Givens plane rotation

integer(4) function cublasRotgEx(h, a, b, abtype, &
      c, s, cstype, extype)
  type(cublasHandle) :: h
  real(2), device :: a, b  ! Type and kind as specified by abtype
  type(cudaDataType) :: abtype
  real(2), device :: c, s ! device or host variable
  type(cudaDataType) :: cstype
  type(cudaDataType) :: extype

2.6.16. cublasRotmEx

ROTM applies a modified Givens transformation.

integer(4) function cublasRotmEx(h, n, x, xtype, incx, &
      y, ytype, incy, param, paramtype, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x  ! Type and kind as specified by xtype
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y  ! Type and kind as specified by ytype
  type(cudaDataType) :: ytype
  integer :: incy
  real(2), device, dimension(*) :: param
  type(cudaDataType) :: paramtype
  type(cudaDataType) :: extype

2.6.17. cublasRotmgEx

ROTMG constructs a modified Givens transformation matrix.

integer(4) function cublasRotmgEx(h, d1, d1type, d2, d2type, &
      x1, x1type, y1, y1type, param, paramtype, extype)
  type(cublasHandle) :: h
  real(2), device :: d1  ! Type and kind as specified by d1type
  type(cudaDataType) :: d1type
  real(2), device :: d2  ! Type and kind as specified by d2type
  type(cudaDataType) :: d2type
  real(2), device :: x1  ! Type and kind as specified by x1type
  type(cudaDataType) :: x1type
  real(2), device :: y1  ! Type and kind as specified by y1type
  type(cudaDataType) :: y1type
  real(2), device, dimension(*) :: param
  type(cudaDataType) :: paramtype
  type(cudaDataType) :: extype

2.6.18. cublasScalEx

SCAL scales a vector by a constant.

integer(4) function cublasScalEx(h, n, alpha, alphatype, &
      x, xtype, incx, extype)
  type(cublasHandle) :: h
  integer :: n
  real(2), device :: alpha
  type(cudaDataType) :: alphatype
  real(2), device, dimension(*) :: x
  type(cudaDataType) :: xtype
  integer :: incx
  type(cudaDataType) :: extype

2.6.19. cublasSwapEx

SWAP interchanges two vectors.

integer(4) function cublasSwapEx(h, n, x, xtype, incx, &
      y, ytype, incy)
  type(cublasHandle) :: h
  integer :: n
  real(2), device, dimension(*) :: x
  type(cudaDataType) :: xtype
  integer :: incx
  real(2), device, dimension(*) :: y
  type(cudaDataType) :: ytype
  integer :: incy

2.6.20. cublasGemmEx

GEMM performs the matrix-matrix multiply operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix, and C an m by n matrix.

The data type of alpha, beta mainly follows the computeType argument. See the cuBLAS documentation for data type combinations currently supported.

integer(4) function cublasGemmEx(h, transa, transb, m, n, k, alpha, &
      A, atype, lda, B, btype, ldb, beta, C, ctype, ldc, computeType, algo)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  type(cudaDataType) :: atype
  integer :: lda
  real(2), device :: B(ldb,*)
  type(cudaDataType) :: btype
  integer :: ldb
  real(2), device :: beta ! device or host variable
  real(2), device :: C(ldc,*)
  type(cudaDataType) :: ctype
  integer :: ldc
  type(cublasComputeType) :: computeType  ! also accept integer
  type(cublasGemmAlgoType) :: algo        ! also accept integer

2.6.21. cublasGemmBatchedEx

GEMM performs a batch of matrix-matrix multiply operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix, and C an m by n matrix.

The data type of alpha, beta mainly follows the computeType argument. See the cuBLAS documentation for data type combinations currently supported.

integer(4) function cublasGemmBatchedEx(h, transa, transb, m, n, k, &
      alpha, Aarray, atype, lda, Barray, btype, ldb, beta, &
      Carray, ctype, ldc, batchCount, computeType, algo)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  type(c_devptr), device :: Aarray(*)
  type(cudaDataType) :: atype
  integer :: lda
  type(c_devptr), device :: Barray(*)
  type(cudaDataType) :: btype
  integer :: ldb
  real(2), device :: beta ! device or host variable
  type(c_devptr), device :: Carray(*)
  type(cudaDataType) :: ctype
  integer :: ldc
  integer :: batchCount
  type(cublasComputeType) :: computeType  ! also accept integer
  type(cublasGemmAlgoType) :: algo        ! also accept integer

2.6.22. cublasGemmStridedBatchedEx

GEMM performs a batch of matrix-matrix multiply operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix, and C an m by n matrix.

The data type of alpha, beta mainly follows the computeType argument. See the cuBLAS documentation for data type combinations currently supported.

integer(4) function cublasGemmStridedBatchedEx(h, transa, transb, m, n, k, &
      alpha, A, atype, lda, strideA, B, btype, ldb, strideB, beta, &
      C, ctype, ldc, strideC, batchCount, computeType, algo)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k
  real(2), device :: alpha ! device or host variable
  real(2), device :: A(lda,*)
  type(cudaDataType) :: atype
  integer :: lda
  integer(8) :: strideA
  real(2), device :: B(ldb,*)
  type(cudaDataType) :: btype
  integer :: ldb
  integer(8) :: strideB
  real(2), device :: beta ! device or host variable
  real(2), device :: C(ldc,*)
  type(cudaDataType) :: ctype
  integer :: ldc
  integer(8) :: strideC
  integer :: batchCount
  type(cublasComputeType) :: computeType  ! also accept integer
  type(cublasGemmAlgoType) :: algo        ! also accept integer

2.7. CUBLAS V2 Module Functions

This section contains interfaces to the cuBLAS V2 Module Functions. Users can access this module by inserting the line use cublas_v2 into the program unit. One major difference in the cublas_v2 versus the cublas module is the cublas entry points, such as cublasIsamax are changed to take the handle as the first argument. The second difference in the cublas_v2 module is the v2 entry points, such as cublasIsamax_v2 do not implicitly handle the pointer modes for the user. It is up to the programmer to make calls to cublasSetPointerMode to tell the library if scalar arguments reside on the host or device. The actual interfaces to the v2 entry points do not change, and are not listed in this section.

2.7.1. Single Precision Functions and Subroutines

This section contains the V2 interfaces to the single precision BLAS and cuBLAS functions and subroutines.

2.7.1.1. isamax

If you use the cublas_v2 module, the interface for cublasIsamax is changed to the following:

integer(4) function cublasIsamax(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.1.2. isamin

If you use the cublas_v2 module, the interface for cublasIsamin is changed to the following:

integer(4) function cublasIsamin(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.1.3. sasum

If you use the cublas_v2 module, the interface for cublasSasum is changed to the following:

integer(4) function cublasSasum(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.7.1.4. saxpy

If you use the cublas_v2 module, the interface for cublasSaxpy is changed to the following:

integer(4) function cublasSaxpy(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.1.5. scopy

If you use the cublas_v2 module, the interface for cublasScopy is changed to the following:

integer(4) function cublasScopy(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.1.6. sdot

If you use the cublas_v2 module, the interface for cublasSdot is changed to the following:

integer(4) function cublasSdot(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy
  real(4), device :: res ! device or host variable

2.7.1.7. snrm2

If you use the cublas_v2 module, the interface for cublasSnrm2 is changed to the following:

integer(4) function cublasSnrm2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.7.1.8. srot

If you use the cublas_v2 module, the interface for cublasSrot is changed to the following:

integer(4) function cublasSrot(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.1.9. srotg

If you use the cublas_v2 module, the interface for cublasSrotg is changed to the following:

integer(4) function cublasSrotg(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  real(4), device :: sa, sb, sc, ss ! device or host variable

2.7.1.10. srotm

If you use the cublas_v2 module, the interface for cublasSrotm is changed to the following:

integer(4) function cublasSrotm(h, n, x, incx, y, incy, param)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: param(*) ! device or host variable
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.1.11. srotmg

If you use the cublas_v2 module, the interface for cublasSrotmg is changed to the following:

integer(4) function cublasSrotmg(h, d1, d2, x1, y1, param)
  type(cublasHandle) :: h
  real(4), device :: d1, d2, x1, y1, param(*) ! device or host variable

2.7.1.12. sscal

If you use the cublas_v2 module, the interface for cublasSscal is changed to the following:

integer(4) function cublasSscal(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: a ! device or host variable
  real(4), device, dimension(*) :: x
  integer :: incx

2.7.1.13. sswap

If you use the cublas_v2 module, the interface for cublasSswap is changed to the following:

integer(4) function cublasSswap(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.1.14. sgbmv

If you use the cublas_v2 module, the interface for cublasSgbmv is changed to the following:

integer(4) function cublasSgbmv(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.7.1.15. sgemv

If you use the cublas_v2 module, the interface for cublasSgemv is changed to the following:

integer(4) function cublasSgemv(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.7.1.16. sger

If you use the cublas_v2 module, the interface for cublasSger is changed to the following:

integer(4) function cublasSger(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha ! device or host variable

2.7.1.17. ssbmv

If you use the cublas_v2 module, the interface for cublasSsbmv is changed to the following:

integer(4) function cublasSsbmv(h, t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: k, n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.7.1.18. sspmv

If you use the cublas_v2 module, the interface for cublasSspmv is changed to the following:

integer(4) function cublasSspmv(h, t, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y
  real(4), device :: alpha, beta ! device or host variable

2.7.1.19. sspr

If you use the cublas_v2 module, the interface for cublasSspr is changed to the following:

integer(4) function cublasSspr(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  real(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

2.7.1.20. sspr2

If you use the cublas_v2 module, the interface for cublasSspr2 is changed to the following:

integer(4) function cublasSspr2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(4), device, dimension(*) :: a, x, y
  real(4), device :: alpha ! device or host variable

2.7.1.21. ssymv

If you use the cublas_v2 module, the interface for cublasSsymv is changed to the following:

integer(4) function cublasSsymv(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha, beta ! device or host variable

2.7.1.22. ssyr

If you use the cublas_v2 module, the interface for cublasSsyr is changed to the following:

integer(4) function cublasSsyr(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x
  real(4), device :: alpha ! device or host variable

2.7.1.23. ssyr2

If you use the cublas_v2 module, the interface for cublasSsyr2 is changed to the following:

integer(4) function cublasSsyr2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x, y
  real(4), device :: alpha ! device or host variable

2.7.1.24. stbmv

If you use the cublas_v2 module, the interface for cublasStbmv is changed to the following:

integer(4) function cublasStbmv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.7.1.25. stbsv

If you use the cublas_v2 module, the interface for cublasStbsv is changed to the following:

integer(4) function cublasStbsv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.7.1.26. stpmv

If you use the cublas_v2 module, the interface for cublasStpmv is changed to the following:

integer(4) function cublasStpmv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x

2.7.1.27. stpsv

If you use the cublas_v2 module, the interface for cublasStpsv is changed to the following:

integer(4) function cublasStpsv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(4), device, dimension(*) :: a, x

2.7.1.28. strmv

If you use the cublas_v2 module, the interface for cublasStrmv is changed to the following:

integer(4) function cublasStrmv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.7.1.29. strsv

If you use the cublas_v2 module, the interface for cublasStrsv is changed to the following:

integer(4) function cublasStrsv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(*) :: x

2.7.1.30. sgemm

If you use the cublas_v2 module, the interface for cublasSgemm is changed to the following:

integer(4) function cublasSgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.7.1.31. ssymm

If you use the cublas_v2 module, the interface for cublasSsymm is changed to the following:

integer(4) function cublasSsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.7.1.32. ssyrk

If you use the cublas_v2 module, the interface for cublasSsyrk is changed to the following:

integer(4) function cublasSsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.7.1.33. ssyr2k

If you use the cublas_v2 module, the interface for cublasSsyr2k is changed to the following:

integer(4) function cublasSsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.7.1.34. ssyrkx

If you use the cublas_v2 module, the interface for cublasSsyrkx is changed to the following:

integer(4) function cublasSsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.7.1.35. strmm

If you use the cublas_v2 module, the interface for cublasStrmm is changed to the following:

integer(4) function cublasStrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha ! device or host variable

2.7.1.36. strsm

If you use the cublas_v2 module, the interface for cublasStrsm is changed to the following:

integer(4) function cublasStrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(4), device, dimension(lda, *) :: a
  real(4), device, dimension(ldb, *) :: b
  real(4), device :: alpha ! device or host variable

2.7.2. Double Precision Functions and Subroutines

This section contains the V2 interfaces to the double precision BLAS and cuBLAS functions and subroutines.

2.7.2.1. idamax

If you use the cublas_v2 module, the interface for cublasIdamax is changed to the following:

integer(4) function cublasIdamax(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.2.2. idamin

If you use the cublas_v2 module, the interface for cublasIdamin is changed to the following:

integer(4) function cublasIdamin(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.2.3. dasum

If you use the cublas_v2 module, the interface for cublasDasum is changed to the following:

integer(4) function cublasDasum(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.7.2.4. daxpy

If you use the cublas_v2 module, the interface for cublasDaxpy is changed to the following:

integer(4) function cublasDaxpy(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.2.5. dcopy

If you use the cublas_v2 module, the interface for cublasDcopy is changed to the following:

integer(4) function cublasDcopy(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.2.6. ddot

If you use the cublas_v2 module, the interface for cublasDdot is changed to the following:

integer(4) function cublasDdot(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy
  real(8), device :: res ! device or host variable

2.7.2.7. dnrm2

If you use the cublas_v2 module, the interface for cublasDnrm2 is changed to the following:

integer(4) function cublasDnrm2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.7.2.8. drot

If you use the cublas_v2 module, the interface for cublasDrot is changed to the following:

integer(4) function cublasDrot(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.2.9. drotg

If you use the cublas_v2 module, the interface for cublasDrotg is changed to the following:

integer(4) function cublasDrotg(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  real(8), device :: sa, sb, sc, ss ! device or host variable

2.7.2.10. drotm

If you use the cublas_v2 module, the interface for cublasDrotm is changed to the following:

integer(4) function cublasDrotm(h, n, x, incx, y, incy, param)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: param(*) ! device or host variable
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.2.11. drotmg

If you use the cublas_v2 module, the interface for cublasDrotmg is changed to the following:

integer(4) function cublasDrotmg(h, d1, d2, x1, y1, param)
  type(cublasHandle) :: h
  real(8), device :: d1, d2, x1, y1, param(*) ! device or host variable

2.7.2.12. dscal

If you use the cublas_v2 module, the interface for cublasDscal is changed to the following:

integer(4) function cublasDscal(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: a ! device or host variable
  real(8), device, dimension(*) :: x
  integer :: incx

2.7.2.13. dswap

If you use the cublas_v2 module, the interface for cublasDswap is changed to the following:

integer(4) function cublasDswap(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  real(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.2.14. dgbmv

If you use the cublas_v2 module, the interface for cublasDgbmv is changed to the following:

integer(4) function cublasDgbmv(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.7.2.15. dgemv

If you use the cublas_v2 module, the interface for cublasDgemv is changed to the following:

integer(4) function cublasDgemv(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.7.2.16. dger

If you use the cublas_v2 module, the interface for cublasDger is changed to the following:

integer(4) function cublasDger(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha ! device or host variable

2.7.2.17. dsbmv

If you use the cublas_v2 module, the interface for cublasDsbmv is changed to the following:

integer(4) function cublasDsbmv(h, t, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: k, n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.7.2.18. dspmv

If you use the cublas_v2 module, the interface for cublasDspmv is changed to the following:

integer(4) function cublasDspmv(h, t, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y
  real(8), device :: alpha, beta ! device or host variable

2.7.2.19. dspr

If you use the cublas_v2 module, the interface for cublasDspr is changed to the following:

integer(4) function cublasDspr(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  real(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

2.7.2.20. dspr2

If you use the cublas_v2 module, the interface for cublasDspr2 is changed to the following:

integer(4) function cublasDspr2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  real(8), device, dimension(*) :: a, x, y
  real(8), device :: alpha ! device or host variable

2.7.2.21. dsymv

If you use the cublas_v2 module, the interface for cublasDsymv is changed to the following:

integer(4) function cublasDsymv(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha, beta ! device or host variable

2.7.2.22. dsyr

If you use the cublas_v2 module, the interface for cublasDsyr is changed to the following:

integer(4) function cublasDsyr(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x
  real(8), device :: alpha ! device or host variable

2.7.2.23. dsyr2

If you use the cublas_v2 module, the interface for cublasDsyr2 is changed to the following:

integer(4) function cublasDsyr2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x, y
  real(8), device :: alpha ! device or host variable

2.7.2.24. dtbmv

If you use the cublas_v2 module, the interface for cublasDtbmv is changed to the following:

integer(4) function cublasDtbmv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.7.2.25. dtbsv

If you use the cublas_v2 module, the interface for cublasDtbsv is changed to the following:

integer(4) function cublasDtbsv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.7.2.26. dtpmv

If you use the cublas_v2 module, the interface for cublasDtpmv is changed to the following:

integer(4) function cublasDtpmv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x

2.7.2.27. dtpsv

If you use the cublas_v2 module, the interface for cublasDtpsv is changed to the following:

integer(4) function cublasDtpsv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  real(8), device, dimension(*) :: a, x

2.7.2.28. dtrmv

If you use the cublas_v2 module, the interface for cublasDtrmv is changed to the following:

integer(4) function cublasDtrmv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.7.2.29. dtrsv

If you use the cublas_v2 module, the interface for cublasDtrsv is changed to the following:

integer(4) function cublasDtrsv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(*) :: x

2.7.2.30. dgemm

If you use the cublas_v2 module, the interface for cublasDgemm is changed to the following:

integer(4) function cublasDgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.7.2.31. dsymm

If you use the cublas_v2 module, the interface for cublasDsymm is changed to the following:

integer(4) function cublasDsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.7.2.32. dsyrk

If you use the cublas_v2 module, the interface for cublasDsyrk is changed to the following:

integer(4) function cublasDsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.7.2.33. dsyr2k

If you use the cublas_v2 module, the interface for cublasDsyr2k is changed to the following:

integer(4) function cublasDsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.7.2.34. dsyrkx

If you use the cublas_v2 module, the interface for cublasDsyrkx is changed to the following:

integer(4) function cublasDsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.7.2.35. dtrmm

If you use the cublas_v2 module, the interface for cublasDtrmm is changed to the following:

integer(4) function cublasDtrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha ! device or host variable

2.7.2.36. dtrsm

If you use the cublas_v2 module, the interface for cublasDtrsm is changed to the following:

integer(4) function cublasDtrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  real(8), device, dimension(lda, *) :: a
  real(8), device, dimension(ldb, *) :: b
  real(8), device :: alpha ! device or host variable

2.7.3. Single Precision Complex Functions and Subroutines

This section contains the V2 interfaces to the single precision complex BLAS and cuBLAS functions and subroutines.

2.7.3.1. icamax

If you use the cublas_v2 module, the interface for cublasIcamax is changed to the following:

integer(4) function cublasIcamax(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.3.2. icamin

If you use the cublas_v2 module, the interface for cublasIcamin is changed to the following:

integer(4) function cublasIcamin(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.3.3. scasum

If you use the cublas_v2 module, the interface for cublasScasum is changed to the following:

integer(4) function cublasScasum(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.7.3.4. caxpy

If you use the cublas_v2 module, the interface for cublasCaxpy is changed to the following:

integer(4) function cublasCaxpy(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.3.5. ccopy

If you use the cublas_v2 module, the interface for cublasCcopy is changed to the following:

integer(4) function cublasCcopy(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.3.6. cdotc

If you use the cublas_v2 module, the interface for cublasCdotc is changed to the following:

integer(4) function cublasCdotc(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(4), device :: res ! device or host variable

2.7.3.7. cdotu

If you use the cublas_v2 module, the interface for cublasCdotu is changed to the following:

integer(4) function cublasCdotu(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(4), device :: res ! device or host variable

2.7.3.8. scnrm2

If you use the cublas_v2 module, the interface for cublasScnrm2 is changed to the following:

integer(4) function cublasScnrm2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x
  integer :: incx
  real(4), device :: res ! device or host variable

2.7.3.9. crot

If you use the cublas_v2 module, the interface for cublasCrot is changed to the following:

integer(4) function cublasCrot(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: sc ! device or host variable
  complex(4), device :: ss ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.3.10. csrot

If you use the cublas_v2 module, the interface for cublasCsrot is changed to the following:

integer(4) function cublasCsrot(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: sc, ss ! device or host variable
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.3.11. crotg

If you use the cublas_v2 module, the interface for cublasCrotg is changed to the following:

integer(4) function cublasCrotg(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  complex(4), device :: sa, sb, ss ! device or host variable
  real(4), device :: sc ! device or host variable

2.7.3.12. cscal

If you use the cublas_v2 module, the interface for cublasCscal is changed to the following:

integer(4) function cublasCscal(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x
  integer :: incx

2.7.3.13. csscal

If you use the cublas_v2 module, the interface for cublasCsscal is changed to the following:

integer(4) function cublasCsscal(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(4), device :: a ! device or host variable
  complex(4), device, dimension(*) :: x
  integer :: incx

2.7.3.14. cswap

If you use the cublas_v2 module, the interface for cublasCswap is changed to the following:

integer(4) function cublasCswap(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(4), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.3.15. cgbmv

If you use the cublas_v2 module, the interface for cublasCgbmv is changed to the following:

integer(4) function cublasCgbmv(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.16. cgemv

If you use the cublas_v2 module, the interface for cublasCgemv is changed to the following:

integer(4) function cublasCgemv(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.17. cgerc

If you use the cublas_v2 module, the interface for cublasCgerc is changed to the following:

integer(4) function cublasCgerc(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

2.7.3.18. cgeru

If you use the cublas_v2 module, the interface for cublasCgeru is changed to the following:

integer(4) function cublasCgeru(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

2.7.3.19. csymv

If you use the cublas_v2 module, the interface for cublasCsymv is changed to the following:

integer(4) function cublasCsymv(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.20. csyr

If you use the cublas_v2 module, the interface for cublasCsyr is changed to the following:

integer(4) function cublasCsyr(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x
  complex(4), device :: alpha ! device or host variable

2.7.3.21. csyr2

If you use the cublas_v2 module, the interface for cublasCsyr2 is changed to the following:

integer(4) function cublasCsyr2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha ! device or host variable

2.7.3.22. ctbmv

If you use the cublas_v2 module, the interface for cublasCtbmv is changed to the following:

integer(4) function cublasCtbmv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.7.3.23. ctbsv

If you use the cublas_v2 module, the interface for cublasCtbsv is changed to the following:

integer(4) function cublasCtbsv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.7.3.24. ctpmv

If you use the cublas_v2 module, the interface for cublasCtpmv is changed to the following:

integer(4) function cublasCtpmv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x

2.7.3.25. ctpsv

If you use the cublas_v2 module, the interface for cublasCtpsv is changed to the following:

integer(4) function cublasCtpsv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x

2.7.3.26. ctrmv

If you use the cublas_v2 module, the interface for cublasCtrmv is changed to the following:

integer(4) function cublasCtrmv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.7.3.27. ctrsv

If you use the cublas_v2 module, the interface for cublasCtrsv is changed to the following:

integer(4) function cublasCtrsv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x

2.7.3.28. chbmv

If you use the cublas_v2 module, the interface for cublasChbmv is changed to the following:

integer(4) function cublasChbmv(h, uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: k, n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.29. chemv

If you use the cublas_v2 module, the interface for cublasChemv is changed to the following:

integer(4) function cublasChemv(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(*) :: x, y
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.30. chpmv

If you use the cublas_v2 module, the interface for cublasChpmv is changed to the following:

integer(4) function cublasChpmv(h, uplo, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.31. cher

If you use the cublas_v2 module, the interface for cublasCher is changed to the following:

integer(4) function cublasCher(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

2.7.3.32. cher2

If you use the cublas_v2 module, the interface for cublasCher2 is changed to the following:

integer(4) function cublasCher2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha ! device or host variable

2.7.3.33. chpr

If you use the cublas_v2 module, the interface for cublasChpr is changed to the following:

integer(4) function cublasChpr(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  complex(4), device, dimension(*) :: a, x
  real(4), device :: alpha ! device or host variable

2.7.3.34. chpr2

If you use the cublas_v2 module, the interface for cublasChpr2 is changed to the following:

integer(4) function cublasChpr2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  complex(4), device, dimension(*) :: a, x, y
  complex(4), device :: alpha ! device or host variable

2.7.3.35. cgemm

If you use the cublas_v2 module, the interface for cublasCgemm is changed to the following:

integer(4) function cublasCgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.36. csymm

If you use the cublas_v2 module, the interface for cublasCsymm is changed to the following:

integer(4) function cublasCsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.37. csyrk

If you use the cublas_v2 module, the interface for cublasCsyrk is changed to the following:

integer(4) function cublasCsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.38. csyr2k

If you use the cublas_v2 module, the interface for cublasCsyr2k is changed to the following:

integer(4) function cublasCsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.39. csyrkx

If you use the cublas_v2 module, the interface for cublasCsyrkx is changed to the following:

integer(4) function cublasCsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.40. ctrmm

If you use the cublas_v2 module, the interface for cublasCtrmm is changed to the following:

integer(4) function cublasCtrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable

2.7.3.41. ctrsm

If you use the cublas_v2 module, the interface for cublasCtrsm is changed to the following:

integer(4) function cublasCtrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device :: alpha ! device or host variable

2.7.3.42. chemm

If you use the cublas_v2 module, the interface for cublasChemm is changed to the following:

integer(4) function cublasChemm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha, beta ! device or host variable

2.7.3.43. cherk

If you use the cublas_v2 module, the interface for cublasCherk is changed to the following:

integer(4) function cublasCherk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldc, *) :: c
  real(4), device :: alpha, beta ! device or host variable

2.7.3.44. cher2k

If you use the cublas_v2 module, the interface for cublasCher2k is changed to the following:

integer(4) function cublasCher2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

2.7.3.45. cherkx

If you use the cublas_v2 module, the interface for cublasCherkx is changed to the following:

integer(4) function cublasCherkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(4), device, dimension(lda, *) :: a
  complex(4), device, dimension(ldb, *) :: b
  complex(4), device, dimension(ldc, *) :: c
  complex(4), device :: alpha ! device or host variable
  real(4), device :: beta ! device or host variable

2.7.4. Double Precision Complex Functions and Subroutines

This section contains the V2 interfaces to the double precision complex BLAS and cuBLAS functions and subroutines.

2.7.4.1. izamax

If you use the cublas_v2 module, the interface for cublasIzamax is changed to the following:

integer(4) function cublasIzamax(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.4.2. izamin

If you use the cublas_v2 module, the interface for cublasIzamin is changed to the following:

integer(4) function cublasIzamin(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  integer, device :: res ! device or host variable

2.7.4.3. dzasum

If you use the cublas_v2 module, the interface for cublasDzasum is changed to the following:

integer(4) function cublasDzasum(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.7.4.4. zaxpy

If you use the cublas_v2 module, the interface for cublasZaxpy is changed to the following:

integer(4) function cublasZaxpy(h, n, a, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.4.5. zcopy

If you use the cublas_v2 module, the interface for cublasZcopy is changed to the following:

integer(4) function cublasZcopy(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.4.6. zdotc

If you use the cublas_v2 module, the interface for cublasZdotc is changed to the following:

integer(4) function cublasZdotc(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(8), device :: res ! device or host variable

2.7.4.7. zdotu

If you use the cublas_v2 module, the interface for cublasZdotu is changed to the following:

integer(4) function cublasZdotu(h, n, x, incx, y, incy, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy
  complex(8), device :: res ! device or host variable

2.7.4.8. dznrm2

If you use the cublas_v2 module, the interface for cublasDznrm2 is changed to the following:

integer(4) function cublasDznrm2(h, n, x, incx, res)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x
  integer :: incx
  real(8), device :: res ! device or host variable

2.7.4.9. zrot

If you use the cublas_v2 module, the interface for cublasZrot is changed to the following:

integer(4) function cublasZrot(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: sc ! device or host variable
  complex(8), device :: ss ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.4.10. zsrot

If you use the cublas_v2 module, the interface for cublasZsrot is changed to the following:

integer(4) function cublasZsrot(h, n, x, incx, y, incy, sc, ss)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: sc, ss ! device or host variable
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.4.11. zrotg

If you use the cublas_v2 module, the interface for cublasZrotg is changed to the following:

integer(4) function cublasZrotg(h, sa, sb, sc, ss)
  type(cublasHandle) :: h
  complex(8), device :: sa, sb, ss ! device or host variable
  real(8), device :: sc ! device or host variable

2.7.4.12. zscal

If you use the cublas_v2 module, the interface for cublasZscal is changed to the following:

integer(4) function cublasZscal(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x
  integer :: incx

2.7.4.13. zdscal

If you use the cublas_v2 module, the interface for cublasZdscal is changed to the following:

integer(4) function cublasZdscal(h, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: n
  real(8), device :: a ! device or host variable
  complex(8), device, dimension(*) :: x
  integer :: incx

2.7.4.14. zswap

If you use the cublas_v2 module, the interface for cublasZswap is changed to the following:

integer(4) function cublasZswap(h, n, x, incx, y, incy)
  type(cublasHandle) :: h
  integer :: n
  complex(8), device, dimension(*) :: x, y
  integer :: incx, incy

2.7.4.15. zgbmv

If you use the cublas_v2 module, the interface for cublasZgbmv is changed to the following:

integer(4) function cublasZgbmv(h, t, m, n, kl, ku, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, kl, ku, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.16. zgemv

If you use the cublas_v2 module, the interface for cublasZgemv is changed to the following:

integer(4) function cublasZgemv(h, t, m, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: t
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.17. zgerc

If you use the cublas_v2 module, the interface for cublasZgerc is changed to the following:

integer(4) function cublasZgerc(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

2.7.4.18. zgeru

If you use the cublas_v2 module, the interface for cublasZgeru is changed to the following:

integer(4) function cublasZgeru(h, m, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: m, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

2.7.4.19. zsymv

If you use the cublas_v2 module, the interface for cublasZsymv is changed to the following:

integer(4) function cublasZsymv(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.20. zsyr

If you use the cublas_v2 module, the interface for cublasZsyr is changed to the following:

integer(4) function cublasZsyr(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x
  complex(8), device :: alpha ! device or host variable

2.7.4.21. zsyr2

If you use the cublas_v2 module, the interface for cublasZsyr2 is changed to the following:

integer(4) function cublasZsyr2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha ! device or host variable

2.7.4.22. ztbmv

If you use the cublas_v2 module, the interface for cublasZtbmv is changed to the following:

integer(4) function cublasZtbmv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.7.4.23. ztbsv

If you use the cublas_v2 module, the interface for cublasZtbsv is changed to the following:

integer(4) function cublasZtbsv(h, u, t, d, n, k, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, k, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.7.4.24. ztpmv

If you use the cublas_v2 module, the interface for cublasZtpmv is changed to the following:

integer(4) function cublasZtpmv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x

2.7.4.25. ztpsv

If you use the cublas_v2 module, the interface for cublasZtpsv is changed to the following:

integer(4) function cublasZtpsv(h, u, t, d, n, a, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x

2.7.4.26. ztrmv

If you use the cublas_v2 module, the interface for cublasZtrmv is changed to the following:

integer(4) function cublasZtrmv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.7.4.27. ztrsv

If you use the cublas_v2 module, the interface for cublasZtrsv is changed to the following:

integer(4) function cublasZtrsv(h, u, t, d, n, a, lda, x, incx)
  type(cublasHandle) :: h
  integer :: u, t, d
  integer :: n, incx, lda
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x

2.7.4.28. zhbmv

If you use the cublas_v2 module, the interface for cublasZhbmv is changed to the following:

integer(4) function cublasZhbmv(h, uplo, n, k, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: k, n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.29. zhemv

If you use the cublas_v2 module, the interface for cublasZhemv is changed to the following:

integer(4) function cublasZhemv(h, uplo, n, alpha, a, lda, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, lda, incx, incy
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(*) :: x, y
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.30. zhpmv

If you use the cublas_v2 module, the interface for cublasZhpmv is changed to the following:

integer(4) function cublasZhpmv(h, uplo, n, alpha, a, x, incx, beta, y, incy)
  type(cublasHandle) :: h
  integer :: uplo
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.31. zher

If you use the cublas_v2 module, the interface for cublasZher is changed to the following:

integer(4) function cublasZher(h, t, n, alpha, x, incx, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, lda
  complex(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

2.7.4.32. zher2

If you use the cublas_v2 module, the interface for cublasZher2 is changed to the following:

integer(4) function cublasZher2(h, t, n, alpha, x, incx, y, incy, a, lda)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy, lda
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha ! device or host variable

2.7.4.33. zhpr

If you use the cublas_v2 module, the interface for cublasZhpr is changed to the following:

integer(4) function cublasZhpr(h, t, n, alpha, x, incx, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx
  complex(8), device, dimension(*) :: a, x
  real(8), device :: alpha ! device or host variable

2.7.4.34. zhpr2

If you use the cublas_v2 module, the interface for cublasZhpr2 is changed to the following:

integer(4) function cublasZhpr2(h, t, n, alpha, x, incx, y, incy, a)
  type(cublasHandle) :: h
  integer :: t
  integer :: n, incx, incy
  complex(8), device, dimension(*) :: a, x, y
  complex(8), device :: alpha ! device or host variable

2.7.4.35. zgemm

If you use the cublas_v2 module, the interface for cublasZgemm is changed to the following:

integer(4) function cublasZgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: transa, transb
  integer :: m, n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.36. zsymm

If you use the cublas_v2 module, the interface for cublasZsymm is changed to the following:

integer(4) function cublasZsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.37. zsyrk

If you use the cublas_v2 module, the interface for cublasZsyrk is changed to the following:

integer(4) function cublasZsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.38. zsyr2k

If you use the cublas_v2 module, the interface for cublasZsyr2k is changed to the following:

integer(4) function cublasZsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.39. zsyrkx

If you use the cublas_v2 module, the interface for cublasZsyrkx is changed to the following:

integer(4) function cublasZsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.40. ztrmm

If you use the cublas_v2 module, the interface for cublasZtrmm is changed to the following:

integer(4) function cublasZtrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable

2.7.4.41. ztrsm

If you use the cublas_v2 module, the interface for cublasZtrsm is changed to the following:

integer(4) function cublasZtrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasHandle) :: h
  integer :: side, uplo, transa, diag
  integer :: m, n, lda, ldb
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device :: alpha ! device or host variable

2.7.4.42. zhemm

If you use the cublas_v2 module, the interface for cublasZhemm is changed to the following:

integer(4) function cublasZhemm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: side, uplo
  integer :: m, n, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha, beta ! device or host variable

2.7.4.43. zherk

If you use the cublas_v2 module, the interface for cublasZherk is changed to the following:

integer(4) function cublasZherk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldc, *) :: c
  real(8), device :: alpha, beta ! device or host variable

2.7.4.44. zher2k

If you use the cublas_v2 module, the interface for cublasZher2k is changed to the following:

integer(4) function cublasZher2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

2.7.4.45. zherkx

If you use the cublas_v2 module, the interface for cublasZherkx is changed to the following:

integer(4) function cublasZherkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasHandle) :: h
  integer :: uplo, trans
  integer :: n, k, lda, ldb, ldc
  complex(8), device, dimension(lda, *) :: a
  complex(8), device, dimension(ldb, *) :: b
  complex(8), device, dimension(ldc, *) :: c
  complex(8), device :: alpha ! device or host variable
  real(8), device :: beta ! device or host variable

2.8. CUBLAS XT Module Functions

This section contains interfaces to the cuBLAS XT Module Functions. Users can access this module by inserting the line use cublasXt into the program unit. The cublasXt library is a host-side library, which supports multiple GPUs. Here is an example:

subroutine testxt(n)
use cublasXt
complex*16 :: a(n,n), b(n,n), c(n,n), alpha, beta
type(cublasXtHandle) :: h
integer ndevices(1)
a = cmplx(1.0d0,0.0d0)
b = cmplx(2.0d0,0.0d0)
c = cmplx(-1.0d0,0.0d0)
alpha = cmplx(1.0d0,0.0d0)
beta = cmplx(0.0d0,0.0d0)
istat = cublasXtCreate(h)
if (istat .ne. CUBLAS_STATUS_SUCCESS) print *,istat
ndevices(1) = 0
istat = cublasXtDeviceSelect(h, 1, ndevices)
if (istat .ne. CUBLAS_STATUS_SUCCESS) print *,istat
istat = cublasXtZgemm(h, CUBLAS_OP_N, CUBLAS_OP_N, &
                      n, n, n, &
                      alpha, A, n, B, n, beta, C, n)
if (istat .ne. CUBLAS_STATUS_SUCCESS) print *,istat
istat = cublasXtDestroy(h)
if (istat .ne. CUBLAS_STATUS_SUCCESS) print *,istat
if (all(dble(c).eq.2.0d0*n)) then
    print *,"Test PASSED"
else
    print *,"Test FAILED"
endif
end

The cublasXt module contains all the types and definitions from the cublas module, and these additional types and enumerations:

TYPE cublasXtHandle
  TYPE(C_PTR)  :: handle
END TYPE

! Pinned memory mode
enum, bind(c)
    enumerator :: CUBLASXT_PINNING_DISABLED=0
    enumerator :: CUBLASXT_PINNING_ENABLED=1
end enum

! cublasXtOpType
enum, bind(c)
    enumerator :: CUBLASXT_FLOAT=0
    enumerator :: CUBLASXT_DOUBLE=1
    enumerator :: CUBLASXT_COMPLEX=2
    enumerator :: CUBLASXT_DOUBLECOMPLEX=3
end enum

! cublasXtBlasOp
enum, bind(c)
    enumerator :: CUBLASXT_GEMM=0
    enumerator :: CUBLASXT_SYRK=1
    enumerator :: CUBLASXT_HERK=2
    enumerator :: CUBLASXT_SYMM=3
    enumerator :: CUBLASXT_HEMM=4
    enumerator :: CUBLASXT_TRSM=5
    enumerator :: CUBLASXT_SYR2K=6
    enumerator :: CUBLASXT_HER2K=7
    enumerator :: CUBLASXT_SPMM=8
    enumerator :: CUBLASXT_SYRKX=9
    enumerator :: CUBLASXT_HERKX=10
    enumerator :: CUBLASXT_TRMM=11
    enumerator :: CUBLASXT_ROUTINE_MAX=12
end enum

2.8.1. cublasXtCreate

This function initializes the cublasXt API and creates a handle to an opaque structure holding the cublasXT library context. It allocates hardware resources on the host and device and must be called prior to making any other cublasXt API library calls.

integer(4) function cublasXtcreate(h)
  type(cublasXtHandle) :: h

2.8.2. cublasXtDestroy

This function releases hardware resources used by the cublasXt API context. This function is usually the last call with a particular handle to the cublasXt API.

integer(4) function cublasXtdestroy(h)
  type(cublasXtHandle) :: h

2.8.3. cublasXtDeviceSelect

This function allows the user to provide the number of GPU devices and their respective Ids that will participate to the subsequent cublasXt API math function calls. This function will create a cuBLAS context for every GPU provided in that list. Currently the device configuration is static and cannot be changed between math function calls. In that regard, this function should be called only once after cublasXtCreate. To be able to run multiple configurations, multiple cublasXt API contexts should be created.

integer(4) function cublasXtdeviceselect(h, ndevices, deviceid)
  type(cublasXtHandle) :: h
  integer :: ndevices
  integer, dimension(*) :: deviceid

2.8.4. cublasXtSetBlockDim

This function allows the user to set the block dimension used for the tiling of the matrices for the subsequent Math function calls. Matrices are split in square tiles of blockDim x blockDim dimension. This function can be called anytime and will take effect for the following math function calls. The block dimension should be chosen in a way to optimize the math operation and to make sure that the PCI transfers are well overlapped with the computation.

integer(4) function cublasXtsetblockdim(h, blockdim)
  type(cublasXtHandle) :: h
  integer :: blockdim

2.8.5. cublasXtGetBlockDim

This function allows the user to query the block dimension used for the tiling of the matrices.

integer(4) function cublasXtgetblockdim(h, blockdim)
  type(cublasXtHandle) :: h
  integer :: blockdim

2.8.6. cublasXtSetCpuRoutine

This function allows the user to provide a CPU implementation of the corresponding BLAS routine. This function can be used with the function cublasXtSetCpuRatio() to define an hybrid computation between the CPU and the GPUs. Currently the hybrid feature is only supported for the xGEMM routines.

integer(4) function cublasXtsetcpuroutine(h, blasop, blastype)
  type(cublasXtHandle) :: h
  integer :: blasop, blastype

2.8.7. cublasXtSetCpuRatio

This function allows the user to define the percentage of workload that should be done on a CPU in the context of an hybrid computation. This function can be used with the function cublasXtSetCpuRoutine() to define an hybrid computation between the CPU and the GPUs. Currently the hybrid feature is only supported for the xGEMM routines.

integer(4) function cublasXtsetcpuratio(h, blasop, blastype, ratio)
  type(cublasXtHandle) :: h
  integer :: blasop, blastype
  real(4) :: ratio

2.8.8. cublasXtSetPinningMemMode

This function allows the user to enable or disable the Pinning Memory mode. When enabled, the matrices passed in subsequent cublasXt API calls will be pinned/unpinned using the CUDART routine cudaHostRegister and cudaHostUnregister respectively if the matrices are not already pinned. If a matrix happened to be pinned partially, it will also not be pinned. Pinning the memory improve PCI transfer performace and allows to overlap PCI memory transfer with computation. However pinning/unpinning the memory takes some time which might not be amortized. It is advised that the user pins the memory on its own using cudaMallocHost or cudaHostRegister and unpins it when the computation sequence is completed. By default, the Pinning Memory mode is disabled.

integer(4) function cublasXtsetpinningmemmode(h, mode)
  type(cublasXtHandle) :: h
  integer :: mode

2.8.9. cublasXtGetPinningMemMode

This function allows the user to query the Pinning Memory mode. By default, the Pinning Memory mode is disabled.

integer(4) function cublasXtgetpinningmemmode(h, mode)
  type(cublasXtHandle) :: h
  integer :: mode

2.8.10. cublasXtSgemm

SGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasXtsgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: transa, transb
  integer(kind=c_intptr_t) :: m, n, k, lda, ldb, ldc
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldb, *) :: b
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.11. cublasXtSsymm

SSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

integer(4) function cublasXtssymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldb, *) :: b
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.12. cublasXtSsyrk

SSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

integer(4) function cublasXtssyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldc
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.13. cublasXtSsyr2k

SSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

integer(4) function cublasXtssyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldb, *) :: b
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.14. cublasXtSsyrkx

SSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

integer(4) function cublasXtssyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldb, *) :: b
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.15. cublasXtStrmm

STRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ), where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T.

integer(4) function cublasXtstrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldb, *) :: b
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha

2.8.16. cublasXtStrsm

STRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T. The matrix X is overwritten on B.

integer(4) function cublasXtstrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb
  real(4), dimension(lda, *) :: a
  real(4), dimension(ldb, *) :: b
  real(4) :: alpha

2.8.17. cublasXtSspmm

SSPMM performs one of the symmetric packed matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a n by n symmetric matrix stored in packed format, and B and C are m by n matrices.

integer(4) function cublasXtsspmm(h, side, uplo, m, n, alpha, ap, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, ldb, ldc
  real(4), dimension(*) :: ap
  real(4), dimension(ldb, *) :: b
  real(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.18. cublasXtCgemm

CGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T or op( X ) = X**H, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasXtcgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: transa, transb
  integer(kind=c_intptr_t) :: m, n, k, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.19. cublasXtChemm

CHEMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is an hermitian matrix and B and C are m by n matrices.

integer(4) function cublasXtchemm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.20. cublasXtCherk

CHERK performs one of the hermitian rank k operations C := alpha*A*A**H + beta*C, or C := alpha*A**H*A + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

integer(4) function cublasXtcherk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldc, *) :: c
  real(4) :: alpha, beta

2.8.21. cublasXtCher2k

CHER2K performs one of the hermitian rank 2k operations C := alpha*A*B**H + conjg( alpha )*B*A**H + beta*C, or C := alpha*A**H*B + conjg( alpha )*B**H*A + beta*C, where alpha and beta are scalars with beta real, C is an n by n hermitian matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

integer(4) function cublasXtcher2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha
  real(4) :: beta

2.8.22. cublasXtCherkx

CHERKX performs a variation of the hermitian rank k operations C := alpha*A*B**H + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix stored in lower or upper mode, and A and B are n by k matrices. See the CUBLAS documentation for more details.

integer(4) function cublasXtcherkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha
  real(4) :: beta

2.8.23. cublasXtCsymm

CSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

integer(4) function cublasXtcsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.24. cublasXtCsyrk

CSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

integer(4) function cublasXtcsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.25. cublasXtCsyr2k

CSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

integer(4) function cublasXtcsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.26. cublasXtCsyrkx

CSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

integer(4) function cublasXtcsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.27. cublasXtCtrmm

CTRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ) where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H.

integer(4) function cublasXtctrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha

2.8.28. cublasXtCtrsm

CTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H. The matrix X is overwritten on B.

integer(4) function cublasXtctrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb
  complex(4), dimension(lda, *) :: a
  complex(4), dimension(ldb, *) :: b
  complex(4) :: alpha

2.8.29. cublasXtCspmm

CSPMM performs one of the symmetric packed matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a n by n symmetric matrix stored in packed format, and B and C are m by n matrices.

integer(4) function cublasXtcspmm(h, side, uplo, m, n, alpha, ap, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, ldb, ldc
  complex(4), dimension(*) :: ap
  complex(4), dimension(ldb, *) :: b
  complex(4), dimension(ldc, *) :: c
  complex(4) :: alpha, beta

2.8.30. cublasXtDgemm

DGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasXtdgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: transa, transb
  integer(kind=c_intptr_t) :: m, n, k, lda, ldb, ldc
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldb, *) :: b
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.31. cublasXtDsymm

DSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

integer(4) function cublasXtdsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldb, *) :: b
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.32. cublasXtDsyrk

DSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

integer(4) function cublasXtdsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldc
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.33. cublasXtDsyr2k

DSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

integer(4) function cublasXtdsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldb, *) :: b
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.34. cublasXtDsyrkx

DSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

integer(4) function cublasXtdsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldb, *) :: b
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.35. cublasXtDtrmm

DTRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ), where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T.

integer(4) function cublasXtdtrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldb, *) :: b
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha

2.8.36. cublasXtDtrsm

DTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T. The matrix X is overwritten on B.

integer(4) function cublasXtdtrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb
  real(8), dimension(lda, *) :: a
  real(8), dimension(ldb, *) :: b
  real(8) :: alpha

2.8.37. cublasXtDspmm

DSPMM performs one of the symmetric packed matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a n by n symmetric matrix stored in packed format, and B and C are m by n matrices.

integer(4) function cublasXtdspmm(h, side, uplo, m, n, alpha, ap, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, ldb, ldc
  real(8), dimension(*) :: ap
  real(8), dimension(ldb, *) :: b
  real(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.38. cublasXtZgemm

ZGEMM performs one of the matrix-matrix operations C := alpha*op( A )*op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T or op( X ) = X**H, alpha and beta are scalars, and A, B and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix.

integer(4) function cublasXtzgemm(h, transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: transa, transb
  integer(kind=c_intptr_t) :: m, n, k, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.8.39. cublasXtZhemm

ZHEMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is an hermitian matrix and B and C are m by n matrices.

integer(4) function cublasXtzhemm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.8.40. cublasXtZherk

ZHERK performs one of the hermitian rank k operations C := alpha*A*A**H + beta*C, or C := alpha*A**H*A + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

integer(4) function cublasXtzherk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldc, *) :: c
  real(8) :: alpha, beta

2.8.41. cublasXtZher2k

ZHER2K performs one of the hermitian rank 2k operations C := alpha*A*B**H + conjg( alpha )*B*A**H + beta*C, or C := alpha*A**H*B + conjg( alpha )*B**H*A + beta*C, where alpha and beta are scalars with beta real, C is an n by n hermitian matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

integer(4) function cublasXtzher2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha
  real(8) :: beta

2.8.42. cublasXtZherkx

ZHERKX performs a variation of the hermitian rank k operations C := alpha*A*B**H + beta*C, where alpha and beta are real scalars, C is an n by n hermitian matrix stored in lower or upper mode, and A and B are n by k matrices. See the CUBLAS documentation for more details.

integer(4) function cublasXtzherkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha
  real(8) :: beta

2.8.43. cublasXtZsymm

ZSYMM performs one of the matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a symmetric matrix and B and C are m by n matrices.

integer(4) function cublasXtzsymm(h, side, uplo, m, n, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.8.44. cublasXtZsyrk

ZSYRK performs one of the symmetric rank k operations C := alpha*A*A**T + beta*C, or C := alpha*A**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A is an n by k matrix in the first case and a k by n matrix in the second case.

integer(4) function cublasXtzsyrk(h, uplo, trans, n, k, alpha, a, lda, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.8.45. cublasXtZsyr2k

ZSYR2K performs one of the symmetric rank 2k operations C := alpha*A*B**T + alpha*B*A**T + beta*C, or C := alpha*A**T*B + alpha*B**T*A + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix and A and B are n by k matrices in the first case and k by n matrices in the second case.

integer(4) function cublasXtzsyr2k(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.8.46. cublasXtZsyrkx

ZSYRKX performs a variation of the symmetric rank k update C := alpha*A*B**T + beta*C, where alpha and beta are scalars, C is an n by n symmetric matrix stored in lower or upper mode, and A and B are n by k matrices. This routine can be used when B is in such a way that the result is guaranteed to be symmetric. See the CUBLAS documentation for more details.

integer(4) function cublasXtzsyrkx(h, uplo, trans, n, k, alpha, a, lda, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: uplo, trans
  integer(kind=c_intptr_t) :: n, k, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.8.47. cublasXtZtrmm

ZTRMM performs one of the matrix-matrix operations B := alpha*op( A )*B, or B := alpha*B*op( A ) where alpha is a scalar, B is an m by n matrix, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H.

integer(4) function cublasXtztrmm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb, ldc
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha

2.8.48. cublasXtZtrsm

ZTRSM solves one of the matrix equations op( A )*X = alpha*B, or X*op( A ) = alpha*B, where alpha is a scalar, X and B are m by n matrices, A is a unit, or non-unit, upper or lower triangular matrix and op( A ) is one of op( A ) = A or op( A ) = A**T or op( A ) = A**H. The matrix X is overwritten on B.

integer(4) function cublasXtztrsm(h, side, uplo, transa, diag, m, n, alpha, a, lda, b, ldb)
  type(cublasXtHandle) :: h
  integer :: side, uplo, transa, diag
  integer(kind=c_intptr_t) :: m, n, lda, ldb
  complex(8), dimension(lda, *) :: a
  complex(8), dimension(ldb, *) :: b
  complex(8) :: alpha

2.8.49. cublasXtZspmm

ZSPMM performs one of the symmetric packed matrix-matrix operations C := alpha*A*B + beta*C, or C := alpha*B*A + beta*C, where alpha and beta are scalars, A is a n by n symmetric matrix stored in packed format, and B and C are m by n matrices.

integer(4) function cublasXtzspmm(h, side, uplo, m, n, alpha, ap, b, ldb, beta, c, ldc)
  type(cublasXtHandle) :: h
  integer :: side, uplo
  integer(kind=c_intptr_t) :: m, n, ldb, ldc
  complex(8), dimension(*) :: ap
  complex(8), dimension(ldb, *) :: b
  complex(8), dimension(ldc, *) :: c
  complex(8) :: alpha, beta

2.9. CUBLAS MP Module Functions

This section contains interfaces to the cuBLAS MP Module Functions. Users can access this module by inserting the line use cublasMp into the program unit. The cublasMp library is a host-side library which operates on distributed device data, and which supports multiple processes and GPUs. It is based on the ScaLAPACK PBLAS library.

Beginning with the 25.1 release, the cublasMp library has a newer API for CUDA versions > 12.0, specifically cublasMp version 0.3.0 and higher. For users of CUDA versions <= 11.8, the old module has been renamed, and you can access it by inserting the line use cublasMp02 in the program unit. One major difference in version 0.3.x is that all cublasMp functions now return a type(cublasMpStatus) rather than an integer(4). There are other additions and changes which we will point out in the individual descriptions below. For complete documentation of the Fortran interfaces for cublasMp 0.2.x, please see the documentation from a 2024 NVHPC release.

Some overloaded operations for comparing and assigning type(cublasMpStatus) variables and expressions are provided in the new module.

The cublasMp module contains all the common types and definitions from the cublas module, types and interfaces from the nvf_cal_comm module, and these additional types and enumerations:

! Version information
integer, parameter :: CUBLASMP_VER_MAJOR = 0
integer, parameter :: CUBLASMP_VER_MINOR = 3
integer, parameter :: CUBLASMP_VER_PATCH = 0
integer, parameter :: CUBLASMP_VERSION = &
     (CUBLASMP_VER_MAJOR * 1000 + CUBLASMP_VER_MINOR * 100 + CUBLASMP_VER_PATCH)

! New status type, with version 0.3.0
TYPE cublasMpStatus
  integer(4) :: stat
END TYPE
TYPE(cublasMpStatus), parameter :: &
  CUBLASMP_STATUS_SUCCESS                = cublasMpStatus(0), &
  CUBLASMP_STATUS_NOT_INITIALIZED        = cublasMpStatus(1), &
  CUBLASMP_STATUS_ALLOCATION_FAILED      = cublasMpStatus(2), &
  CUBLASMP_STATUS_INVALID_VALUE          = cublasMpStatus(3), &
  CUBLASMP_STATUS_ARCHITECTURE_MISMATCH  = cublasMpStatus(4), &
  CUBLASMP_STATUS_EXECUTION_FAILED       = cublasMpStatus(5), &
  CUBLASMP_STATUS_INTERNAL_ERROR         = cublasMpStatus(6), &
  CUBLASMP_STATUS_NOT_SUPPORTED          = cublasMpStatus(7)

! Grid Layout
TYPE cublasMpGridLayout
  integer(4) :: grid
END TYPE
TYPE(cublasMpGridLayout), parameter :: &
  CUBLASMP_GRID_LAYOUT_COL_MAJOR = cublasMpGridLayout(0), &
  CUBLASMP_GRID_LAYOUT_ROW_MAJOR = cublasMpGridLayout(1)

! Matmul Descriptor Attributes
TYPE cublasMpMatmulDescriptorAttribute
  integer(4) :: attr
END TYPE
TYPE(cublasMpMatmulDescriptorAttribute), parameter :: &
  CUBLASMP_MATMUL_DESCRIPTOR_ATTRIBUTE_TRANSA       = cublasMpMatmulDescriptorAttribute(0), &
  CUBLASMP_MATMUL_DESCRIPTOR_ATTRIBUTE_TRANSB       = cublasMpMatmulDescriptorAttribute(1), &
  CUBLASMP_MATMUL_DESCRIPTOR_ATTRIBUTE_COMPUTE_TYPE = cublasMpMatmulDescriptorAttribute(2), &
  CUBLASMP_MATMUL_DESCRIPTOR_ATTRIBUTE_ALGO_TYPE    = cublasMpMatmulDescriptorAttribute(3)

! Matmul Algorithm Type
TYPE cublasMpMatmulAlgoType
  integer(4) :: atyp
END TYPE
TYPE(cublasMpMatmulAlgoType), parameter :: &
  CUBLASMP_MATMUL_ALGO_TYPE_DEFAULT          = cublasMpMatmulAlgoType(0), &
  CUBLASMP_MATMUL_ALGO_TYPE_SPLIT_P2P        = cublasMpMatmulAlgoType(1), &
  CUBLASMP_MATMUL_ALGO_TYPE_SPLIT_MULTICAST  = cublasMpMatmulAlgoType(2), &
  CUBLASMP_MATMUL_ALGO_TYPE_ATOMIC_P2P       = cublasMpMatmulAlgoType(3), &
  CUBLASMP_MATMUL_ALGO_TYPE_ATOMIC_MULTICAST = cublasMpMatmulAlgoType(4)

TYPE cublasMpHandle
  TYPE(C_PTR)  :: handle
END TYPE

TYPE cublasMpGrid
  TYPE(C_PTR)  :: handle
END TYPE

TYPE cublasMpMatrixDescriptor
  TYPE(C_PTR)  :: handle
END TYPE

TYPE cublasMpMatmulDescriptor
  TYPE(C_PTR)  :: handle
END TYPE

2.9.1. cublasMpCreate

This function initializes the cublasMp API and creates a handle to an opaque structure holding the cublasMp library context. It allocates hardware resources on the host and device and must be called prior to making any other cublasMp library calls.

type(cublasMpStatus) function cublasMpCreate(handle, stream)
  type(cublasMpHandle) :: handle
  integer(kind=cuda_stream_kind()) :: stream

2.9.2. cublasMpDestroy

This function releases resources used by the cublasMp handle and context.

type(cublasMpStatus) function cublasMpDestroy(handle)
  type(cublasMpHandle) :: handle

2.9.3. cublasMpStreamSet

This function sets the CUDA stream to be used in the cublasMp computations.

type(cublasMpStatus) function cublasMpStreamSet(handle, stream)
  type(cublasMpHandle) :: handle
  integer(kind=cuda_stream_kind()) :: stream

2.9.4. cublasMpStreamGet

This function returns the current CUDA stream used in the cublasMp computations.

type(cublasMpStatus) function cublasMpStreamGet(handle, stream)
  type(cublasMpHandle) :: handle
  integer(kind=cuda_stream_kind()) :: stream

2.9.5. cublasMpGetVersion

This function returns the version number of the cublasMp library.

type(cublasMpStatus) function cublasMpGetVersion(handle, version)
  type(cublasMpHandle) :: handle
  integer(4) :: version

2.9.6. cublasMpGridCreate

This function initializes the grid data structure used in the cublasMp library. It takes a communicator, and other information related to the data layout as inputs. Starting in version 0.3.0, it no longer takes a handle argument.

type(cublasMpStatus) function cublasMpGridCreate(nprow, npcol, &
          layout, comm, grid)
  integer(8) :: nprow, npcol
  type(cublasMpGridLayout) :: layout ! usually column major in Fortran
  type(cal_comm) :: comm
  type(cublasMpGrid), intent(out) :: grid

2.9.7. cublasMpGridDestroy

This function releases the grid data structure used in the cublasMp library. Starting in version 0.3.0, it no longer takes a handle argument.

type(cublasMpStatus) function cublasMpGridDestroy(grid)
  type(cublasMpGrid) :: grid

2.9.8. cublasMpMatrixDescriptorCreate

This function initializes the matrix descriptor object used in the cublasMp library. It takes the number of rows (M) and the number of columns (N) in the global array, along with the blocking factor over each dimension. RSRC and CSRC must currently be 0. LLD is the leading dimension of the local matrix, after blocking and distributing the matrix. Starting in version 0.3.0, it no longer takes a handle argument.

type(cublasMpStatus) function cublasMpMatrixDescriptorCreate(M, N, MB, NB, &
          RSRC, CSRC, LLD, dataType, grid, descr)
  integer(8) :: M, N, MB, NB, RSRC, CSRC, LLD
  type(cudaDataType) :: dataType
  type(cublasMpGrid) :: grid
  type(cublasMpMatrixDescriptor), intent(out)  :: descr

2.9.9. cublasMpMatrixDescriptorDestroy

This function frees the matrix descriptor object used in the cublasMp library. Starting in version 0.3.0, it no longer takes a handle argument.

type(cublasMpStatus) function cublasMpMatrixDescriptorDestroy(descr)
  type(cublasMpMatrixDescriptor) :: descr

2.9.10. cublasMpMatrixDescriptorInit

This function initializes the values within the matrix descriptor object used in the cublasMp library. It takes the number of rows (M) and the number of columns (N) in the global array, along with the blocking factor over each dimension. RSRC and CSRC must currently be 0. LLD is the leading dimension of the local matrix, after blocking and distributing the matrix.

type(cublasMpStatus) function cublasMpMatrixDescriptorInit(M, N, MB, NB, &
          RSRC, CSRC, LLD, dataType, grid, descr)
  integer(8) :: M, N, MB, NB, RSRC, CSRC, LLD
  type(cudaDataType) :: dataType
  type(cublasMpGrid) :: grid
  type(cublasMpMatrixDescriptor), intent(out)  :: descr

2.9.11. cublasMpNumroc

This function computes (and returns) the local number of rows or columns of a distributed matrix, similar to the ScaLAPACK NUMROC function.

type(cublasMpStatus) function cublasMpNumroc(N, NB, iproc, isrcproc, nprocs)
  integer(8) :: N, NB
  integer(4) :: iproc, isrcproc, nprocs

2.9.12. cublasMpMatmulDescriptorCreate

This function initializes the matmul descriptor object used in the cublasMp library.

type(cublasMpStatus) function cublasMpMatmulDescriptorCreate(descr, computeType)
  type(cublasMpMatmulDescriptor)  :: descr
  type(cublasComputeType) :: computeType

2.9.13. cublasMpMatmulDescriptorDestroy

This function destroys the matmul descriptor object used in the cublasMp library.

type(cublasMpStatus) function cublasMpMatmulDescriptorDestroy(descr)
  type(cublasMpMatmulDescriptor)  :: descr

2.9.14. cublasMpMatmulDescriptorAttributeSet

This function sets attributes within the matmul descriptor object used in the cublasMp library.

type(cublasMpStatus) function cublasMpMatmulDescriptorAttributeSet(descr, attr &
          buf, sizeInBytes)
  type(cublasMpMatmulDescriptor)  :: descr
  type(cublasMpMatmulDescriptorAttribute)  :: attr
  integer(1) :: buf(sizeInBytes) ! Any type, kind, or rank allowed
  integer(8) :: sizeInBytes

2.9.15. cublasMpMatmulDescriptorAttributeGet

This function retrieves attributes within the matmul descriptor object used in the cublasMp library.

type(cublasMpStatus) function cublasMpMatmulDescriptorAttributeGet(descr, attr &
          buf, sizeInBytes, sizeWritten)
  type(cublasMpMatmulDescriptor)  :: descr
  type(cublasMpMatmulDescriptorAttribute)  :: attr
  integer(1) :: buf(sizeInBytes) ! Any type, kind, or rank allowed
  integer(8) :: sizeInBytes, sizeWritten

2.9.16. cublasMpGemr2D_bufferSize

This functions computes the workspace requirements of cublasMpGemr2D

type(cublasMpStatus) function cublasMpGemr2D_bufferSize(handle, M, N, &
   A, IA, JA, descrA, B, IB, JB, descrB, &
   devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes, comm)
   type(cublasMpHandle) :: handle
   integer(8), intent(in) :: M, N, IA, JA, IB, JB
   real(4), device, dimension(*) :: A, B  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   type(cal_comm) :: comm

2.9.17. cublasMpGemr2D

This functions copies a matrix from one distributed form to another. The layout of each matrix is defined in the matrix descriptor. M and N are the global matrix dimensions. IA, JA, IB, and JB are 1-based, and typically equal to 1 for a full matrix.

type(cublasMpStatus) function cublasMpGemr2D(handle, M, N,  &
   A, IA, JA, descrA, B, IB, JB, descrB, &
   bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes, comm)
   type(cublasMpHandle) :: handle
   integer(8), intent(in) :: M, N, IA, JA, IB, JB
   real(4), device, dimension(*) :: A, B  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)  ! Any type
   type(cal_comm) :: comm

2.9.18. cublasMpTrmr2D_bufferSize

This functions computes the workspace requirements of cublasMpTrmr2D

type(cublasMpStatus) function cublasMpTrmr2D_bufferSize(handle, uplo, diag, &
   M, N, A, IA, JA, descrA, B, IB, JB, descrB, &
   devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes, comm)
   type(cublasMpHandle) :: handle
   integer(4), intent(in) :: uplo, diag
   integer(8), intent(in) :: M, N, IA, JA, IB, JB
   real(4), device, dimension(*) :: A, B  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   type(cal_comm) :: comm

2.9.19. cublasMpTrmr2D

This functions copies a trapezoidal matrix from one distributed form to another. The layout of each matrix is defined in the matrix descriptor. M and N are the global matrix dimensions. IA, JA, IB, and JB are 1-based, and typically equal to 1 for a full matrix.

type(cublasMpStatus) function cublasMpTrmr2D(handle, uplo, diag,  &
   M, N, A, IA, JA, descrA, B, IB, JB, descrB, &
   bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes, comm)
   type(cublasMpHandle) :: handle
   integer(4), intent(in) :: uplo, diag
   integer(8), intent(in) :: M, N, IA, JA, IB, JB
   real(4), device, dimension(*) :: A, B  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)  ! Any type
   type(cal_comm) :: comm

2.9.20. cublasMpGemm_bufferSize

This functions computes the workspace requirements of cublasMpGemm.

type(cublasMpStatus) function cublasMpGemm_bufferSize(handle, transA, transB, M, N, K, &
   alpha, A, IA, JA, descrA, B, IB, JB, descrB, beta, C, IC, JC, descrC, &
   computeType, devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: transA, transB
   integer(8), intent(in) :: M, N, K, IA, JA, IB, JB, IC, JC
   real(4) :: alpha, beta  ! type and kind compatible with computeType
   real(4), device, dimension(*) :: A, B, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB, descrC
   type(cublasComputeType) :: computeType
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes

2.9.21. cublasMpGemm

This is the multi-processor version of the BLAS GEMM operation, similar to the ScaLAPACK PBLAS functions pdgemm, pzgemm, etc.

GEMM performs one of the matrix-matrix operations

C := alpha*op( A )*op( B ) + beta*C,

where op( X ) is one of

op( X ) = X or op( X ) = X**T,

alpha and beta are scalars, and A, B, and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C an m by n matrix. The data for A, B, and C should be properly distributed over the process grid. That mapping is contained within the descriptors descrA, descrB, and descrC via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified then. M, N, and K are the global matrix dimensions. IA, JA, IB, JB, IC, and JC are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpGemm(handle, transA, transB, M, N, K, &
   alpha, A, IA, JA, descrA, B, IB, JB, descrB, beta, C, IC, JC, descrC, &
   computeType, bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: transA, transB
   integer(8), intent(in) :: M, N, K, IA, JA, IB, JB, IC, JC
   real(4) :: alpha, beta  ! type and kind compatible with computeType
   real(4), device, dimension(*) :: A, B, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB, descrC
   type(cublasComputeType) :: computeType
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceInBytes)  ! Any type

2.9.22. cublasMpMatmul_bufferSize

This functions computes the workspace requirements of cublasMpMatmul.

type(cublasMpStatus) function cublasMpMatmul_bufferSize(handle, matmulDescr, M, N, K, &
   alpha, A, IA, JA, descrA, B, IB, JB, descrB, beta, C, IC, JC, descrC, &
   D, ID, JD, descrD, devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   type(cublasMpMatmulDescriptor) :: matmulDescr
   integer(8), intent(in) :: M, N, K, IA, JA, IB, JB, IC, JC, ID, JD
   real(4) :: alpha, beta  ! Any compatible kind
   real(4), device, dimension(*) :: A, B, C, D  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB, descrC, descrD
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes

2.9.23. cublasMpMatmul

This is the multi-processor version of the matrix multiplication operation.

Matmul performs one of the matrix-matrix operations

D := alpha*op( A )*op( B ) + beta*C,

where op( X ) is one of

op( X ) = X or op( X ) = X**T, as set by a call to cublasMpMatmulDescriptorAttributeSet().

alpha and beta are scalars, and A, B, C, and D are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix and C and D are m by n matrices. The data for A, B, C, and D should be properly distributed over the process grid. That mapping is contained within the descriptors descrA, descrB, descrC, and descrD via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified there. M, N, and K are the global matrix dimensions. IA, JA, IB, JB, IC, JC, ID, and JD are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpMatmul(handle, matmulDescr, M, N, K, &
   alpha, A, IA, JA, descrA, B, IB, JB, descrB, beta, C, IC, JC, descrC, &
   D, ID, JD, descrD, bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   type(cublasMpMatmulDescriptor) :: matmulDescr
   integer(8), intent(in) :: M, N, K, IA, JA, IB, JB, IC, JC, ID, JD
   real(4) :: alpha, beta  ! Any supported type and kind
   real(4), device, dimension(*) :: A, B, C, D  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB, descrC, descrD
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceInBytes)  ! Any type

2.9.24. cublasMpSyrk

This is the multi-processor version of the BLAS SYRK operation, similar to the ScaLAPACK PBLAS functions pdsyrk, pzsyrk, etc.

SYRK performs one of the symmetric rank k operations

C := alpha*A*A**T + beta*C, or

C := alpha*A**T*A + beta*C

alpha and beta are scalars, and A and C are matrices. A is either N x K or K x N depending on the trans argument, and C is N x N. The data for A and C should be properly distributed over the process grid. That mapping is contained within the descriptors descrA and descrC via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified then. N and K are the global matrix dimensions. IA, JA, IC, and JC are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpSyrk(handle, uplo, trans, &
   N, K, alpha, A, IA, JA, descrA, beta, C, IC, JC, descrC, &
   computeType, bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: uplo, trans
   integer(8), intent(in) :: N, K, IA, JA, IC, JC
   real(4) :: alpha, beta  ! type and kind compatible with computeType
   real(4), device, dimension(*) :: A, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrC
   type(cublasComputeType) :: computeType
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)  ! Any type

2.9.25. cublasMpSyrk

This is the multi-processor version of the BLAS SYRK operation, similar to the ScaLAPACK PBLAS functions pdsyrk, pzsyrk, etc.

SYRK performs one of the symmetric rank k operations

C := alpha*A*A**T + beta*C, or

C := alpha*A**T*A + beta*C

alpha and beta are scalars, and A and C are matrices. A is either N x K or K x N depending on the trans argument, and C is N x N. The data for A and C should be properly distributed over the process grid. That mapping is contained within the descriptors descrA and descrC via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified then. N and K are the global matrix dimensions. IA, JA, IC, and JC are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpSyrk(handle, uplo, trans, &
   N, K, alpha, A, IA, JA, descrA, beta, C, IC, JC, descrC, &
   computeType, bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: uplo, trans
   integer(8), intent(in) :: N, K, IA, JA, IC, JC
   real(4) :: alpha, beta  ! type and kind compatible with computeType
   real(4), device, dimension(*) :: A, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrC
   type(cublasComputeType) :: computeType
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)  ! Any type

2.9.26. cublasMpTrsm_bufferSize

This functions computes the workspace requirements of cublasMpTrsm.

type(cublasMpStatus) function cublasMpTrsm_bufferSize(handle, side, uplo, trans, diag, &
   M, N, alpha, A, IA, JA, descrA, B, IB, JB, descrB, &
   computeType, devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: side, uplo, trans, diag
   integer(8), intent(in) :: M, N, IA, JA, IB, JB
   real(4) :: alpha  ! type and kind compatible with computeType
   real(4), device, dimension(*) :: A, B  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB
   type(cublasComputeType) :: computeType
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes

2.9.27. cublasMpTrsm

This is the multi-processor version of the BLAS TRSM operation, similar to the ScaLAPACK PBLAS functions pdtrsm, pztrsm, etc.

TRSM solves one of the matrix equations

op( A )*X = alpha*B, or

X*op( A ) = alpha*B

alpha is a scalar, A and B are matrices whose dimensions are determined by the side argument. The data for A and B should be properly distributed over the process grid. That mapping is contained within the descriptors descrA and descrB via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified then. M and N are the global matrix dimensions. IA, JA, IB, and JB are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpTrsm(handle, side, uplo, trans, diag,  &
   M, N, alpha, A, IA, JA, descrA, B, IB, JB, descrB, &
   computeType, bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: side, uplo, trans, diag
   integer(8), intent(in) :: M, N, IA, JA, IB, JB
   real(4) :: alpha  ! type and kind compatible with computeType
   real(4), device, dimension(*) :: A, B  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrB
   type(cublasComputeType) :: computeType
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)     ! Any type

2.9.28. cublasMpGeadd_bufferSize

This functions computes the workspace requirements of cublasMpGeadd.

type(cublasMpStatus) function cublasMpGeadd_bufferSize(handle, trans, &
   M, N, alpha, A, IA, JA, descrA, beta, C, IC, JC, descrC, &
   devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: trans
   integer(8), intent(in) :: M, N, IA, JA, IC, JC
   real(4) :: alpha, beta  ! Any compatible kind
   real(4), device, dimension(*) :: A, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrC
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes

2.9.29. cublasMpGeadd

This is the multi-processor version of a general matrix addition function.

GEADD performs the matrix-matrix addition operation

C := alpha*A + beta*C

alpha and beta are scalars, and A and C are matrices. A is either M x N or N x M depending on the trans argument, and C is M x N. The data for A and C should be properly distributed over the process grid. That mapping is contained within the descriptors descrA and descrC via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified then. M and N are the global matrix dimensions. IA, JA, IC, and JC are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpGeadd(handle, trans, &
   M, N, alpha, A, IA, JA, descrA, beta, C, IC, JC, descrC, &
   bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: trans
   integer(8), intent(in) :: M, N, IA, JA, IC, JC
   real(4) :: alpha, beta  ! Any compatible type and kind
   real(4), device, dimension(*) :: A, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrC
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)  ! Any type

2.9.30. cublasMpTradd_bufferSize

This functions computes the workspace requirements of cublasMpTradd.

type(cublasMpStatus) function cublasMpTradd_bufferSize(handle, uplo, trans, &
   M, N, alpha, A, IA, JA, descrA, beta, C, IC, JC, descrC, &
   devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: uplo, trans
   integer(8), intent(in) :: M, N, IA, JA, IC, JC
   real(4) :: alpha, beta  ! Any compatible kind
   real(4), device, dimension(*) :: A, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrC
   integer(8), intent(out) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes

2.9.31. cublasMpTradd

This is the multi-processor version of a trapezoidal matrix addition function.

TRADD performs the trapezoidal matrix-matrix addition operation

C := alpha*A + beta*C

alpha and beta are scalars, and A and C are matrices. A is either M x N or N x M depending on the trans argument, and C is M x N. The data for A and C should be properly distributed over the process grid. That mapping is contained within the descriptors descrA and descrC via the cublasMpMatrixDescriptorCreate() function. The datatype is also specified then. M and N are the global matrix dimensions. IA, JA, IC, and JC are 1-based, and typically equal to 1 for a full matrix. Integer(4) input values will be promoted to integer(8) according to the interface.

type(cublasMpStatus) function cublasMpTradd(handle, uplo, trans, &
   M, N, alpha, A, IA, JA, descrA, beta, C, IC, JC, descrC, &
   bufferOnDevice, devWorkspaceSizeInBytes, &
   bufferOnHost, hostWorkspaceSizeInBytes)
   type(cublasMpHandle) :: handle
   integer(4) :: uplo, trans
   integer(8), intent(in) :: M, N, IA, JA, IC, JC
   real(4) :: alpha, beta  ! Any compatible type and kind
   real(4), device, dimension(*) :: A, C  ! Any supported type and kind
   type(cublasMpMatrixDescriptor) :: descrA, descrC
   integer(8), intent(in) :: devWorkspaceSizeInBytes, hostWorkspaceSizeInBytes
   integer(1), device :: bufferOnDevice(devWorkspaceSizeInBytes) ! Any type
   integer(1)         :: bufferOnHost(hostWorkspaceSizeInBytes)  ! Any type

2.9.32. cublasMpLoggerSetFile

This function specifies the Fortran unit to be used as the cublasMp logfile.

type(cublasMpStatus) function cublasMpLoggerSetFile(unit)
  integer :: unit

2.9.33. cublasMpLoggerOpenFile

This function specifies a Fortran character string to be opened and used as the cublasMp logfile.

type(cublasMpStatus) function cublasMpLoggerOpenFile(logFile)
  character*(*) :: logFile

2.9.34. cublasMpLoggerSetLevel

This function specifies the cublasMp logging level.

type(cublasMpStatus) function cublasMpLoggerSetLevel(level)
  integer :: level

2.9.35. cublasMpLoggerSetMask

This function specifies the cublasMp logging mask.

type(cublasMpStatus) function cublasMpLoggerSetMask(mask)
  integer :: mask

2.9.36. cublasMpLoggerForceDisable

This function disables cublasMp logging.

type(cublasMpStatus) function cublasMpLoggerForceDisable()

3. FFT Runtime Library APIs

This section describes the Fortran interfaces to the cuFFT library. The FFT functions are only accessible from host code. All of the runtime API routines are integer functions that return an error code; they return a value of CUFFT_SUCCESS if the call was successful, or another cuFFT status return value if there was an error.

Chapter 10 contains examples of accessing the cuFFT library routines from OpenACC and CUDA Fortran. In both cases, the interfaces to the library can be exposed by adding the line

use cufft

to your program unit.

Beginning with our 21.9 release, we also support a cufftXt module, which provides interfaces to the multi-gpu support available in the cuFFT library. These interfaces can be used within any Fortran program by adding the line

use cufftxt

to your program unit. The cufftXt interfaces are documented beginning in section 4 of this chapter.

Unless a specific kind is provided in the following interfaces, the plain integer type implies integer(4) and the plain real type implies real(4).

3.1. CUFFT Definitions and Helper Functions

This section contains definitions and data types used in the cuFFT library and interfaces to the cuFFT helper functions.

The cuFFT module contains the following constants and enumerations:

integer, parameter :: CUFFT_FORWARD = -1
integer, parameter :: CUFFT_INVERSE = 1

! CUFFT Status
enum, bind(C)
    enumerator :: CUFFT_SUCCESS        = 0
    enumerator :: CUFFT_INVALID_PLAN   = 1
    enumerator :: CUFFT_ALLOC_FAILED   = 2
    enumerator :: CUFFT_INVALID_TYPE   = 3
    enumerator :: CUFFT_INVALID_VALUE  = 4
    enumerator :: CUFFT_INTERNAL_ERROR = 5
    enumerator :: CUFFT_EXEC_FAILED    = 6
    enumerator :: CUFFT_SETUP_FAILED   = 7
    enumerator :: CUFFT_INVALID_SIZE   = 8
    enumerator :: CUFFT_UNALIGNED_DATA = 9
end enum

! CUFFT Transform Types
enum, bind(C)
    enumerator :: CUFFT_R2C = z'2a'     ! Real to Complex (interleaved)
    enumerator :: CUFFT_C2R = z'2c'     ! Complex (interleaved) to Real
    enumerator :: CUFFT_C2C = z'29'     ! Complex to Complex, interleaved
    enumerator :: CUFFT_D2Z = z'6a'     ! Double to Double-Complex
    enumerator :: CUFFT_Z2D = z'6c'     ! Double-Complex to Double
    enumerator :: CUFFT_Z2Z = z'69'     ! Double-Complex to Double-Complex
end enum

! CUFFT Data Layouts
enum, bind(C)
    enumerator :: CUFFT_COMPATIBILITY_NATIVE          = 0
    enumerator :: CUFFT_COMPATIBILITY_FFTW_PADDING    = 1
    enumerator :: CUFFT_COMPATIBILITY_FFTW_ASYMMETRIC = 2
    enumerator :: CUFFT_COMPATIBILITY_FFTW_ALL        = 3
end enum

integer, parameter :: CUFFT_COMPATIBILITY_DEFAULT = CUFFT_COMPATIBILITY_FFTW_PADDING

3.1.1. cufftSetCompatibilityMode

This function configures the layout of cuFFT output in FFTW-compatible modes.

integer(4) function cufftSetCompatibilityMode( plan, mode )
  integer :: plan
  integer :: mode

3.1.2. cufftSetStream

This function sets the stream to be used by the cuFFT library to execute its routines.

integer(4) function cufftSetStream(plan, stream)
  integer :: plan
  integer(kind=cuda_stream_kind) :: stream

3.1.3. cufftGetVersion

This function returns the version number of cuFFT.

integer(4) function cufftGetVersion( version )
  integer :: version

3.1.4. cufftSetAutoAllocation

This function indicates that the caller intends to allocate and manage work areas for plans that have been generated. cuFFT default behavior is to allocate the work area at plan generation time. If cufftSetAutoAllocation() has been called with autoAllocate set to 0 prior to one of the cufftMakePlan*() calls, cuFFT does not allocate the work area. This is the preferred sequence for callers wishing to manage work area allocation.

integer(4) function cufftSetAutoAllocation(plan, autoAllocate)
  integer(4) :: plan, autoallocate

3.1.5. cufftSetWorkArea

This function overrides the work area pointer associated with a plan. If the work area was auto-allocated, cuFFT frees the auto-allocated space. The cufftExecute*() calls assume that the work area pointer is valid and that it points to a contiguous region in device memory that does not overlap with any other work area. If this is not the case, results are indeterminate.

integer(4) function cufftSetWorkArea(plan, workArea)
  integer(4) :: plan
  integer, device :: workArea(*) ! Can be integer, real, complex
                                 ! or a type(c_devptr)

3.1.6. cufftDestroy

This function frees all GPU resources associated with a cuFFT plan and destroys the internal plan data structure.

integer(4) function cufftDestroy( plan )
  integer :: plan

3.2. CUFFT Plans and Estimated Size Functions

This section contains functions from the cuFFT library used to create plans and estimate work buffer size.

3.2.1. cufftPlan1d

This function creates a 1D FFT plan configuration for a specified signal size and data type. Nx is the size of the transform; batch is the number of transforms of size nx.

integer(4) function cufftPlan1d(plan, nx, ffttype, batch)
  integer :: plan
  integer :: nx
  integer :: ffttype
  integer :: batch

3.2.2. cufftPlan2d

This function creates a 2D FFT plan configuration according to a specified signal size and data type. For a Fortran array(nx,ny), nx is the size of the of the 1st dimension in the transform, but the 2nd size argument to the function; ny is the size of the 2nd dimension, and the 1st size argument to the function.

integer(4) function cufftPlan2d( plan, ny, nx, ffttype )
  integer :: plan
  integer :: ny, nx
  integer :: ffttype

3.2.3. cufftPlan3d

This function creates a 3D FFT plan configuration according to a specified signal size and data type. For a Fortran array(nx,ny,nz), nx is the size of the of the 1st dimension in the transform, but the 3rd size argument to the function; nz is the size of the 3rd dimension, and the 1st size argument to the function.

integer(4) function cufftPlan3d( plan, nz, ny, nx, ffttype )
  integer :: plan
  integer :: nz, ny, nx
  integer :: ffttype

3.2.4. cufftPlanMany

This function creates an FFT plan configuration of dimension rank, with sizes specified in the array n. Batch is the number of transforms to configure. This function supports more complicated input and output data layouts using the arguments inembed, istride, idist, onembed, ostride, and odist. In the C function, if inembed and onembed are set to NULL, all other stride information is ignored. Fortran programmers can pass NULL when using the NVIDIA cufft module by setting an F90 pointer to null(), either through direct assignment, using c_f_pointer() with c_null_ptr as the first argument, or the nullify statement, then passing the nullified F90 pointer as the actual argument for the inembed and onembed dummies.

integer(4) function cufftPlanMany(plan, rank, n, inembed, istride, idist, onembed, ostride, odist, ffttype, batch )
  integer :: plan
  integer :: rank
  integer :: n
  integer :: inembed, onembed
  integer :: istride, idist, ostride, odist
  integer :: ffttype, batch

3.2.5. cufftCreate

This function creates an opaque handle for further cuFFT calls and allocates some small data structures on the host. In C, the handle type is currently typedef’ed to an int, so in Fortran we use an integer*4 to hold the plan.

integer(4) function cufftCreate(plan)
  integer(4) :: plan

3.2.6. cufftMakePlan1d

Following a call to cufftCreate(), this function creates a 1D FFT plan configuration for a specified signal size and data type. Nx is the size of the transform; batch is the number of transforms of size nx. If cufftXtSetGPUs was called prior to this call with multiple GPUs, then workSize is an array containing multiple sizes. The workSize values are in bytes.

integer(4) function cufftMakePlan1d(plan, nx, ffttype, batch, worksize)
  integer(4) :: plan
  integer(4) :: nx
  integer(4) :: ffttype
  integer(4) :: batch
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.7. cufftMakePlan2d

Following a call to cufftCreate(), this function creates a 2D FFT plan configuration according to a specified signal size and data type. For a Fortran array(nx,ny), nx is the size of the of the 1st dimension in the transform, but the 2nd size argument to the function; ny is the size of the 2nd dimension, and the 1st size argument to the function. If cufftXtSetGPUs was called prior to this call with multiple GPUs, then workSize is an array containing multiple sizes. The workSize values are in bytes.

integer(4) function cufftMakePlan2d(plan, ny, nx, ffttype, workSize)
  integer(4) :: plan
  integer(4) :: ny, nx
  integer(4) :: ffttype
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.8. cufftMakePlan3d

Following a call to cufftCreate(), this function creates a 3D FFT plan configuration according to a specified signal size and data type. For a Fortran array(nx,ny,nz), nx is the size of the of the 1st dimension in the transform, but the 3rd size argument to the function; nz is the size of the 3rd dimension, and the 1st size argument to the function. If cufftXtSetGPUs was called prior to this call with multiple GPUs, then workSize is an array containing multiple sizes. The workSize values are in bytes.

integer(4) function cufftMakePlan3d(plan, nz, ny, nx, ffttype, workSize)
  integer(4) :: plan
  integer(4) :: nz, ny, nx
  integer(4) :: ffttype
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.9. cufftMakePlanMany

Following a call to cufftCreate(), this function creates an FFT plan configuration of dimension rank, with sizes specified in the array n. Batch is the number of transforms to configure. This function supports more complicated input and output data layouts using the arguments inembed, istride, idist, onembed, ostride, and odist.

In the C function, if inembed and onembed are set to NULL, all other stride information is ignored. Fortran programmers can pass NULL when using the NVIDIA cufft module by setting an F90 pointer to null(), either through direct assignment, using c_f_pointer() with c_null_ptr as the first argument, or the nullify statement, then passing the nullified F90 pointer as the actual argument for the inembed and onembed dummies.

If cufftXtSetGPUs was called prior to this call with multiple GPUs, then workSize is an array containing multiple sizes. The workSize values are in bytes.

integer(4) function cufftMakePlanMany(plan, rank, n, inembed, istride, idist, onembed, ostride, odist, ffttype, batch, workSize)
  integer(4) :: plan
  integer(4) :: rank
  integer :: n(rank)
  integer :: inembed(rank), onembed(rank)
  integer(4) :: istride, idist, ostride, odist
  integer(4) :: ffttype, batch
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.10. cufftEstimate1d

This function returns an estimate for the size of the work area required, in bytes, given the specified size and data type, and assuming default plan settings.

integer(4) function cufftEstimate1d(nx, ffttype, batch, workSize)
  integer(4) :: nx
  integer(4) :: ffttype
  integer(4) :: batch
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.11. cufftEstimate2d

This function returns an estimate for the size of the work area required, in bytes, given the specified size and data type, and assuming default plan settings.

integer(4) function cufftEstimate2d(ny, nx, ffttype, workSize)
  integer(4) :: ny, nx
  integer(4) :: ffttype
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.12. cufftEstimate3d

This function returns an estimate for the size of the work area required, in bytes, given the specified size and data type, and assuming default plan settings.

integer(4) function cufftEstimate3d(nz, ny, nx, ffttype, workSize)
  integer(4) :: nz, ny, nx
  integer(4) :: ffttype
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.13. cufftEstimateMany

This function returns an estimate for the size of the work area required, in bytes, given the specified size and data type, and assuming default plan settings.

integer(4) function cufftEstimateMany(rank, n, inembed, istride, idist, onembed, ostride, odist, ffttype, batch, workSize)
  integer(4) :: rank, istride, idist, ostride, odist
  integer(4), dimension(rank) :: n, inembed, onembed
  integer(4) :: ffttype
  integer(4) :: batch
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.14. cufftGetSize1d

This function gives a more accurate estimate than cufftEstimate1d() of the size of the work area required, in bytes, given the specified plan parameters and taking into account any plan settings which may have been made.

integer(4) function cufftGetSize1d(plan, nx, ffttype, batch, workSize)
  integer(4) :: plan, nx, ffttype, batch
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.15. cufftGetSize2d

This function gives a more accurate estimate than cufftEstimate2d() of the size of the work area required, in bytes, given the specified plan parameters and taking into account any plan settings which may have been made.

integer(4) function cufftGetSize2d(plan, ny, nx, ffttype, workSize)
  integer(4) :: plan, ny, nx, ffttype
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.16. cufftGetSize3d

This function gives a more accurate estimate than cufftEstimate3d() of the size of the work area required, in bytes, given the specified plan parameters and taking into account any plan settings which may have been made.

integer(4) function cufftGetSize3d(plan, nz, ny, nx, ffttype, workSize)
  integer(4) :: plan, nz, ny, nx, ffttype
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.17. cufftGetSizeMany

This function gives a more accurate estimate than cufftEstimateMany() of the size of the work area required, in bytes, given the specified plan parameters and taking into account any plan settings which may have been made.

integer(4) function cufftGetSizeMany(plan, rank, n, inembed, istride, idist, onembed, ostride, odist, ffttype, batch, workSize)
  integer(4) :: plan, rank, istride, idist, ostride, odist
  integer(4), dimension(rank) :: n, inembed, onembed
  integer(4) :: ffttype
  integer(4) :: batch
  integer(kind=int_ptr_kind()) :: workSize(*)

3.2.18. cufftGetSize

Once plan generation has been done, either with the original API or the extensible API, this call returns the actual size of the work area required, in bytes, to support the plan. Callers who choose to manage work area allocation within their application must use this call after plan generation, and after any cufftSet*() calls subsequent to plan generation, if those calls might alter the required work space size.

integer(4) function cufftGetSize(plan, workSize)
  integer(4) :: plan
  integer(kind=int_ptr_kind()) :: workSize(*)

3.3. CUFFT Execution Functions

This section contains the execution functions, which perform the actual Fourier transform, in the cuFFT library.

3.3.1. cufftExecC2C

This function executes a single precision complex-to-complex transform plan in the transform direction as specified by the direction parameter. If idata and odata are the same, this function does an in-place transform.

integer(4) function cufftExecC2C( plan, idata, odata, direction )
  integer :: plan
  complex(4), device, dimension(*) :: idata, odata
  integer :: direction

3.3.2. cufftExecR2C

This function executes a single precision real-to-complex, implicity forward, cuFFT transform plan. If idata and odata are the same, this function does an in-place transform, but note there are data layout differences between in-place and out-of-place transforms for real-to- complex FFTs in cuFFT.

integer(4) function cufftExecR2C( plan, idata, odata )
  integer :: plan
  real(4), device, dimension(*) :: idata
  complex(4), device, dimension(*) :: odata

3.3.3. cufftExecC2R

This function executes a single precision complex-to-real, implicity inverse, cuFFT transform plan. If idata and odata are the same, this function does an in-place transform.

integer(4) function cufftExecC2R( plan, idata, odata )
  integer :: plan
  complex(4), device, dimension(*) :: idata
  real(4), device, dimension(*) :: odata

3.3.4. cufftExecZ2Z

This function executes a double precision complex-to-complex transform plan in the transform direction as specified by the direction parameter. If idata and odata are the same, this function does an in-place transform.

integer(4) function cufftExecZ2Z( plan, idata, odata, direction )
  integer :: plan
  complex(8), device, dimension(*) :: idata, odata
  integer :: direction

3.3.5. cufftExecD2Z

This function executes a double precision real-to-complex, implicity forward, cuFFT transform plan. If idata and odata are the same, this function does an in-place transform, but note there are data layout differences between in-place and out-of-place transforms for real-to- complex FFTs in cuFFT.

integer(4) function cufftExecD2Z( plan, idata, odata )
  integer :: plan
  real(8), device, dimension(*) :: idata
  complex(8), device, dimension(*) :: odata

3.3.6. cufftExecZ2D

This function executes a double precision complex-to-real, implicity inverse, cuFFT transform plan. If idata and odata are the same, this function does an in-place transform.

integer(4) function cufftExecZ2D( plan, idata, odata )
  integer :: plan
  complex(8), device, dimension(*) :: idata
  real(8), device, dimension(*) :: odata

3.4. CUFFTXT Definitions and Helper Functions

This section contains definitions and data types used in the cufftXt library and interfaces to helper functions. Beginning with NVHPC version 22.5, this module also contains some interfaces and definitions used with the cuFFTMp library.

The cufftXt module contains the following constants and enumerations:

integer, parameter :: MAX_CUDA_DESCRIPTOR_GPUS = 64

! libFormat enum is used for the library member of cudaLibXtDesc
enum, bind(C)
    enumerator :: LIB_FORMAT_CUFFT     = 0
    enumerator :: LIB_FORMAT_UNDEFINED = 1
end enum

! cufftXtSubFormat identifies the data layout of a memory descriptor
enum, bind(C)
    ! by default input is in linear order across GPUs
    enumerator :: CUFFT_XT_FORMAT_INPUT = 0

    ! by default output is in scrambled order depending on transform
    enumerator :: CUFFT_XT_FORMAT_OUTPUT = 1

    ! by default inplace is input order, which is linear across GPUs
    enumerator :: CUFFT_XT_FORMAT_INPLACE = 2

    ! shuffled output order after execution of the transform
    enumerator :: CUFFT_XT_FORMAT_INPLACE_SHUFFLED = 3

    ! shuffled input order prior to execution of 1D transforms
    enumerator :: CUFFT_XT_FORMAT_1D_INPUT_SHUFFLED = 4

    ! distributed input order
    enumerator :: CUFFT_XT_FORMAT_DISTRIBUTED_INPUT = 5

    ! distributed output order
    enumerator :: CUFFT_XT_FORMAT_DISTRIBUTED_OUTPUT = 6

    enumerator :: CUFFT_FORMAT_UNDEFINED = 7
end enum

! cufftXtCopyType specifies the type of copy for cufftXtMemcpy
enum, bind(C)
    enumerator :: CUFFT_COPY_HOST_TO_DEVICE   = 0
    enumerator :: CUFFT_COPY_DEVICE_TO_HOST   = 1
    enumerator :: CUFFT_COPY_DEVICE_TO_DEVICE = 2
    enumerator :: CUFFT_COPY_UNDEFINED        = 3
end enum

! cufftXtQueryType specifies the type of query for cufftXtQueryPlan
enum, bind(c)
    enumerator :: CUFFT_QUERY_1D_FACTORS = 0
    enumerator :: CUFFT_QUERY_UNDEFINED  = 1
end enum

! cufftXtWorkAreaPolicy specifies the policy for cufftXtSetWorkAreaPolicy
enum, bind(c)
    enumerator :: CUFFT_WORKAREA_MINIMAL     = 0 ! maximum reduction
    enumerator :: CUFFT_WORKAREA_USER        = 1 ! use workSize parameter as limit
    enumerator :: CUFFT_WORKAREA_PERFORMANCE = 2 ! default - 1x overhead or more, max perf
end enum

! cufftMpCommType specifies how to initialize cuFFTMp
enum, bind(c)
    enumerator :: CUFFT_COMM_MPI       = 0
    enumerator :: CUFFT_COMM_NVSHMEM   = 1
    enumerator :: CUFFT_COMM_UNDEFINED = 2
end enum

The cufftXt module contains the following derived type definitions:

! cufftXt1dFactors type
type, bind(c) :: cufftXt1dFactors
    integer(8) :: size
    integer(8) :: stringCount
    integer(8) :: stringLength
    integer(8) :: subStringLength
    integer(8) :: factor1
    integer(8) :: factor2
    integer(8) :: stringMask
    integer(8) :: subStringMask
    integer(8) :: factor1Mask
    integer(8) :: factor2Mask
    integer(4) :: stringShift
    integer(4) :: subStringShift
    integer(4) :: factor1Shift
    integer(4) :: factor2Shift
end type cufftXt1dFactors

type, bind(C) :: cudaXtDesc
    integer(4) :: version
    integer(4) :: nGPUs
    integer(4) :: GPUs(MAX_CUDA_DESCRIPTOR_GPUS)
    type(c_devptr) :: data(MAX_CUDA_DESCRIPTOR_GPUS)
    integer(8) :: size(MAX_CUDA_DESCRIPTOR_GPUS)
    type(c_ptr) :: cudaXtState
end type cudaXtDesc

type, bind(C) :: cudaLibXtDesc
    integer(4) :: version
    type(c_ptr) :: descriptor     ! cudaXtDesc *descriptor
    integer(4) :: library         ! libFormat library
    integer(4) :: subFormat
    type(c_ptr) :: libDescriptor  ! void *libDescriptor
end type cudaLibXtDesc

type, bind(C) :: cufftBox3d
    integer(8) :: lower(3)
    integer(8) :: upper(3)
    integer(8) :: strides(3)
end type cufftBox3d

3.4.1. cufftXtSetGPUs

This function identifies which GPUs are to be used with the plan. The call to cufftXtSetGPUs must occur after the call to cufftCreate but before the call to cufftMakePlan*.

integer(4) function cufftXtSetGPUs( plan, nGPUs, whichGPUs )
  integer(4) :: plan
  integer(4) :: nGPUs
  integer(4) :: whichGPUs(*)

3.4.2. cufftXtMalloc

This function allocates a cufftXt descriptor, and memory for data in the GPUs associated with the plan. The value of cufftXtSubFormat determines if the buffer will be used for input or output. Fortran programmers should declare and pass a pointer to a type(cudaLibXtDesc) variable so the entire information can be stored, and also freed in subsequent calls to cufftXtFree. For programmers comfortable with the C interface, a variant of this function can take a type(c_ptr) for the 2nd argument.

integer(4) function cufftXtMalloc( plan, descriptor, format )
  integer(4) :: plan
  type(cudaLibXtDesc), pointer :: descriptor  ! A type(c_ptr) is also accepted.
  integer(4) :: format ! cufftXtSubFormat value

3.4.3. cufftXtFree

This function frees the cufftXt descriptor, and all memory associated with it. The descriptor and memory must have been allocated by a previous call to cufftXtMalloc. Fortran programmers should declare and pass a pointer to a type(cudaLibXtDesc) variable. For programmers comfortable with the C interface, a variant of this function can take a type(c_ptr) as the only argument.

integer(4) function cufftXtFree( descriptor )
  type(cudaLibXtDesc), pointer :: descriptor  ! A type(c_ptr) is also accepted.

3.4.4. cufftXtMemcpy

This function copies data between buffers on the host and GPUs, or between GPUs. The value of the type argument determines the copy direction. In addition, this Fortran function is overloaded to take a type(cudaLibXtDesc) variable for the destination (H2D transfer), for the source (D2H transfer), or for both (D2D transfer), in which case the type argument is not required.

integer(4) function cufftXtMemcpy( plan, dst, src, type )
  integer(4) :: plan
  type(cudaLibXtDesc) :: dst  ! Or any host buffer, depending on the type
  type(cudaLibXtDesc) :: src  ! Or any host buffer, depending on the type
  integer(4) :: type          ! optional cufftXtCopyType value

3.5. CUFFTXT Plans and Work Area Functions

This section contains functions from the cufftXt library used to create plans and manage work buffers.

3.5.1. cufftXtMakePlanMany

Following a call to cufftCreate(), this function creates an FFT plan configuration of dimension rank, with sizes specified in the array n. Batch is the number of transforms to configure. This function supports more complicated input and output data layouts using the arguments inembed, istride, idist, onembed, ostride, and odist. In the C function, if inembed and onembed are set to NULL, all other stride information is ignored. Fortran programmers can pass NULL when using the NVIDIA cufft module by setting an F90 pointer to null(), either through direct assignment, using c_f_pointer() with c_null_ptr as the first argument, or the nullify statement, then passing the nullified F90 pointer as the actual argument for the inembed and onembed dummies.

integer(4) function cufftXtMakePlanMany(plan, rank, n, inembed, istride, &
    idist, inputType, onembed, ostride, odist, outputType, batch, workSize, &
    executionType)
  integer(4) :: plan
  integer(4) :: rank
  integer(8) :: n(*)
  integer(8) :: inembed(*), onembed(*)
  integer(8) :: istride, idist, ostride, odist
  type(cudaDataType) :: inputType, outputType, executionType
  integer(4) :: batch
  integer(8) :: workSize(*)

3.5.2. cufftXtQueryPlan

This function only supports multi-gpu 1D transforms. It returns a derived type, factors, which contains the number of strings, the decomposition of factors, and (in the case of power of 2 sizes) some other useful mask and shift elements, used in converting between permuted and linear indexes.

integer(4) function cufftXtQueryPlan(plan, factors, queryType)
  integer(4) :: plan
  type(cufftXt1DFactors) :: factors
  integer(4) :: queryType

3.5.3. cufftXtSetWorkAreaPolicy

This function overrides the work area associated with a plan. Currently, the workAreaPolicy can be specified as CUFFT_WORKAREA_MINIMAL and cuFFT will attempt to re-plan to use zero bytes of work area memory. See the CUFFT documentation for support of other features.

integer(4) function cufftXtSetWorkAreaPolicy(plan, workAreaPolicy, workSize)
  integer(4) :: plan
  integer(4) :: workAreaPolicy
  integer(8) :: workSize

3.5.4. cufftXtGetSizeMany

This function gives a more accurate estimate than cufftEstimateMany() of the size of the work area required, in bytes, given the specified plan parameters used for cufftXtMakePlanMany and taking into account any plan settings which may have been made.

integer(4) function cufftXtGetSizeMany(plan, rank, n, inembed, istride, &
    idist, inputType, onembed, ostride, odist, outputType, batch, workSize, &
    executionType)
  integer(4) :: plan
  integer(4) :: rank
  integer(8) :: n(*)
  integer(8) :: inembed(*), onembed(*)
  integer(8) :: istride, idist, ostride, odist
  type(cudaDataType) :: inputType, outputType, executionType
  integer(4) :: batch
  integer(8) :: workSize(*)

3.5.5. cufftXtSetWorkArea

This function overrides the work areas associated with a plan. If the work area was auto-allocated, cuFFT frees the auto-allocated space. The cufftExecute*() calls assume that the work area pointer is valid and that it points to a contiguous region in device memory that does not overlap with any other work area. If this is not the case, results are indeterminate.

integer(4) function cufftXtSetWorkArea(plan, workArea)
  integer(4) :: plan
  type(c_devptr) :: workArea(*)

3.5.6. cufftXtSetDistribution

This function registers and describes the data distribution for a subsequent FFT operation. The call to cufftXtSetDistribution must occur after the call to cufftCreate but before the call to cufftMakePlan*.

integer(4) function cufftXtSetDistribution( plan, boxIn, boxOut )
  integer(4) :: plan
  type(cufftBox3d) :: boxIn
  type(cufftBox3d) :: boxOut

3.6. CUFFTXT Execution Functions

This section contains the execution functions, which perform the actual Fourier transform, in the cufftXt library.

3.6.1. cufftXtExec

This function executes any Fourier transform regardless of precision and type. In case of complex-to-real and real-to-complex transforms, the direction argument is ignored. Otherwise, the transform direction is specified by the direction parameter. This function uses the GPU memory pointed to by input as input data, and stores the computed Fourier coefficients in the output array. If those are the same, this method does an in-place transform. Any valid data type for the input and output arrays are accepted.

integer(4) function cufftXtExec( plan, input, output, direction )
  integer :: plan
  real, dimension(*) :: input, output  ! Any data type is allowed
  integer :: direction

3.6.2. cufftXtExecDescriptor

This function executes any Fourier transform regardless of precision and type. In case of complex-to-real and real-to-complex transforms, the direction argument is ignored. Otherwise, the transform direction is specified by the direction parameter. This function stores the result in the specified output arrays.

integer(4) function cufftXtExecDescriptor( plan, input, output, direction )
  integer :: plan
  type(cudaLibXtDesc) :: input, output
  integer :: direction

3.6.3. cufftXtExecDescriptorC2C

This function executes a single precision complex-to-complex transform plan in the transform direction as specified by the direction parameter. This multiple GPU function currently supports in-place transforms only; the result will be stored in the input arrays.

integer(4) function cufftXtExecDescriptorC2C( plan, input, output, direction )
  integer :: plan
  type(cudaLibXtDesc) :: input, output
  integer :: direction

3.6.4. cufftXtExecDescriptorZ2Z

This function executes a double precision complex-to-complex transform plan in the transform direction as specified by the direction parameter. This multiple GPU function currently supports in-place transforms only; the result will be stored in the input arrays.

integer(4) function cufftXtExecDescriptorZ2Z( plan, input, output, direction )
  integer :: plan
  type(cudaLibXtDesc) :: input, output
  integer :: direction

3.6.5. cufftXtExecDescriptorR2C

This function executes a single precision real-to-complex transform plan. This multiple GPU function currently supports in-place transforms only; the result will be stored in the input arrays.

integer(4) function cufftXtExecDescriptorR2C( plan, input, output )
  integer :: plan
  type(cudaLibXtDesc) :: input, output

3.6.6. cufftXtExecDescriptorD2Z

This function executes a double precision real-to-complex transform plan. This multiple GPU function currently supports in-place transforms only; the result will be stored in the input arrays.

integer(4) function cufftXtExecDescriptorD2Z( plan, input, output )
  integer :: plan
  type(cudaLibXtDesc) :: input, output

3.6.7. cufftXtExecDescriptorC2R

This function executes a single precision complex-to-real transform plan. This multiple GPU function currently supports in-place transforms only; the result will be stored in the input arrays.

integer(4) function cufftXtExecDescriptorC2R( plan, input, output )
  integer :: plan
  type(cudaLibXtDesc) :: input, output

3.6.8. cufftXtExecDescriptorZ2D

This function executes a double precision complex-to-real transform plan. This multiple GPU function currently supports in-place transforms only; the result will be stored in the input arrays.

integer(4) function cufftXtExecDescriptorZ2D( plan, input, output )
  integer :: plan
  type(cudaLibXtDesc) :: input, output

3.7. CUFFTMP Functions

This section contains the cuFFTMp functions which extend the cuFFTXt library functionality to multiple processes and multiple GPUs.

3.7.1. cufftMpNvshmemMalloc

This function allocates space from the NVSHMEM symmetric heap. The cuFFTMp library is based on NVSHMEM. However, the user is not allowd to link and use NVSHMEM in their own application. This may cause a crash at applicaton start time. This limitation will be lifted in a future release of cuFFTMp.

However, some functionality of cuFFTMp requires NVSHMEM-allocated memory, so this function is currently exposed and supported. This function requires that at least one cuFFTMp plan is active prior to its use.

integer(4) function cufftMpNvshmemMalloc( size, workArea )
  integer(8) :: size  ! Size is in bytes
  type(c_devptr) :: workArea

3.7.2. cufftMpNvshmemFree

This function frees the space previously allocated from the NVSHMEM symmetric heap. The cuFFTMp library is based on NVSHMEM. However, the user is not allowd to link and use NVSHMEM in their own application. This may cause a crash at applicaton start time. This limitation will be lifted in a future release of cuFFTMp.

However, some functionality of cuFFTMp requires NVSHMEM-allocated memory, so this function is currently exposed and supported. This function requires that at least one cuFFTMp plan is active prior to its use.

integer(4) function cufftMpNvshmemFree( workArea )
  type(c_devptr) :: workArea

3.7.3. cufftMpAttachComm

This function attaches a communicator, such as MPI_COMM_WORLD, to a cuFFT plan, for later application of a distributed FFT operation

integer(4) function cufftMpAttachComm( plan, commType, fcomm )
  integer(4) :: plan
  integer(4) :: commType
  integer(4) :: fcomm

3.7.4. cufftMpCreateReshape

This function creates a cuFFTMp reshape handle for later application of a distributed FFT operation

integer(4) function cufftMpCreateReshape( reshapeHandle )
  type(c_ptr) :: reshapeHandle

3.7.5. cufftMpAttachReshapeComm

This function attaches a communicator, such as MPI_COMM_WORLD, to a cuFFTMp reshape handle, for later application of a distributed FFT operation

integer(4) function cufftMpAttachReshapeComm( reshapeHandle, commType, fcomm )
  type(c_ptr) :: reshapeHandle
  integer(4) :: commType
  integer(4) :: fcomm

3.7.6. cufftMpGetReshapeSize

This function returns the size needed for work space in the subsequent cuFFTMp reshape execution. Currently, a work area is not required, but that may change in future releases.

integer(4) function cufftMpGetReshapeSize( reshapeHandle, workSize )
   type(c_ptr) :: reshapeHandle
   integer(8)  :: workSize

3.7.7. cufftMpMakeReshape

This function creates a cuFFTMp reshape plan based on the input and output boxes. Note that the boxes use C conventions for bounds and strides.

integer(4) function cufftMpMakeReshape( reshapeHandle, &
       elementSize, boxIn, boxOut )
   type(c_ptr) :: reshapeHandle
   integer(8)  :: elementSize
   type(cufftBox3d) :: boxIn
   type(cufftBox3d) :: boxOut

3.7.8. cufftMpExecReshapeAsync

This function executes a cuFFTMp reshape plan on the specified stream.

integer(4) function cufftMpExecReshapeAsync( reshapeHandle, &
       dataOut, dataIn, workSpace, stream )
   type(c_ptr) :: reshapeHandle
   type(c_devptr) :: dataOut
   type(c_devptr) :: dataIn
   type(c_devptr) :: workSpace
   integer(kind=cuda_stream_kind) :: stream

3.7.9. cufftMpDestroyReshape

This function destroys a cuFFTMp reshape handle.

integer(4) function cufftMpDestroyReshape( reshapeHandle )
  type(c_ptr) :: reshapeHandle

4. Random Number Runtime Library APIs

This section describes the Fortran interfaces to the CUDA cuRAND library. The cuRAND functionality is accessible from both host and device code. In the host library, all of the runtime API routines are integer functions that return an error code; they return a value of CURAND_STATUS_SUCCESS if the call was successful, or other cuRAND return status value if there was an error. The host library routines are meant to produce a series or array of random numbers. In the device library, the init routines are subroutines and the generator functions return the type of the value being generated. The device library routines are meant for producing a single value per thread per call.

Chapter 10 contains examples of accessing the cuRAND library routines from OpenACC and CUDA Fortran. In both cases, the interfaces to the library can be exposed in host code by adding the line

use curand

to your program unit.

Unless a specific kind is provided, the plain integer type implies integer(4) and the plain real type implies real(4).

4.1. CURAND Definitions and Helper Functions

This section contains definitions and data types used in the cuRAND library and interfaces to the cuRAND helper functions.

The curand module contains the following derived type definitions:

TYPE curandGenerator
  TYPE(C_PTR)  :: handle
END TYPE

The curand module contains the following enumerations:

! CURAND Status
enum, bind(c)
    enumerator :: CURAND_STATUS_SUCCESS                   = 0
    enumerator :: CURAND_STATUS_VERSION_MISMATCH          = 100
    enumerator :: CURAND_STATUS_NOT_INITIALIZED           = 101
    enumerator :: CURAND_STATUS_ALLOCATION_FAILED         = 102
    enumerator :: CURAND_STATUS_TYPE_ERROR                = 103
    enumerator :: CURAND_STATUS_OUT_OF_RANGE              = 104
    enumerator :: CURAND_STATUS_LENGTH_NOT_MULTIPLE       = 105
    enumerator :: CURAND_STATUS_DOUBLE_PRECISION_REQUIRED = 106
    enumerator :: CURAND_STATUS_LAUNCH_FAILURE            = 201
    enumerator :: CURAND_STATUS_PREEXISTING_FAILURE       = 202
    enumerator :: CURAND_STATUS_INITIALIZATION_FAILED     = 203
    enumerator :: CURAND_STATUS_ARCH_MISMATCH             = 204
    enumerator :: CURAND_STATUS_INTERNAL_ERROR            = 999
end enum

! CURAND Generator Types
enum, bind(c)
    enumerator :: CURAND_RNG_TEST                    = 0
    enumerator :: CURAND_RNG_PSEUDO_DEFAULT          = 100
    enumerator :: CURAND_RNG_PSEUDO_XORWOW           = 101
    enumerator :: CURAND_RNG_PSEUDO_MRG32K3A         = 121
    enumerator :: CURAND_RNG_PSEUDO_MTGP32           = 141
    enumerator :: CURAND_RNG_PSEUDO_MT19937          = 142
    enumerator :: CURAND_RNG_PSEUDO_PHILOX4_32_10    = 161
    enumerator :: CURAND_RNG_QUASI_DEFAULT           = 200
    enumerator :: CURAND_RNG_QUASI_SOBOL32           = 201
    enumerator :: CURAND_RNG_QUASI_SCRAMBLED_SOBOL32 = 202
    enumerator :: CURAND_RNG_QUASI_SOBOL64           = 203
    enumerator :: CURAND_RNG_QUASI_SCRAMBLED_SOBOL64 = 204
end enum

! CURAND Memory Ordering
enum, bind(c)
    enumerator :: CURAND_ORDERING_PSEUDO_BEST    = 100
    enumerator :: CURAND_ORDERING_PSEUDO_DEFAULT = 101
    enumerator :: CURAND_ORDERING_PSEUDO_SEEDED  = 102
    enumerator :: CURAND_ORDERING_QUASI_DEFAULT  = 201
end enum

! CURAND Direction Vectors
enum, bind(c)
    enumerator :: CURAND_DIRECTION_VECTORS_32_JOEKUO6           = 101
    enumerator :: CURAND_SCRAMBLED_DIRECTION_VECTORS_32_JOEKUO6 = 102
    enumerator :: CURAND_DIRECTION_VECTORS_64_JOEKUO6           = 103
    enumerator :: CURAND_SCRAMBLED_DIRECTION_VECTORS_64_JOEKUO6 = 104
end enum

! CURAND Methods
enum, bind(c)
    enumerator :: CURAND_CHOOSE_BEST    = 0
    enumerator :: CURAND_ITR            = 1
    enumerator :: CURAND_KNUTH          = 2
    enumerator :: CURAND_HITR           = 3
    enumerator :: CURAND_M1             = 4
    enumerator :: CURAND_M2             = 5
    enumerator :: CURAND_BINARY_SEARCH  = 6
    enumerator :: CURAND_DISCRETE_GAUSS = 7
    enumerator :: CURAND_REJECTION      = 8
    enumerator :: CURAND_DEVICE_API     = 9
    enumerator :: CURAND_FAST_REJECTION = 10
    enumerator :: CURAND_3RD            = 11
    enumerator :: CURAND_DEFINITION     = 12
    enumerator :: CURAND_POISSON        = 13
end enum

4.1.1. curandCreateGenerator

This function creates a new random number generator of type rng. See the beginning of this section for valid values of rng.

integer(4) function curandCreateGenerator(generator, rng)
  type(curandGenerator) :: generator
  integer :: rng

4.1.2. curandCreateGeneratorHost

This function creates a new host CPU random number generator of type rng. See the beginning of this section for valid values of rng.

integer(4) function curandCreateGeneratorHost(generator, rng)
  type(curandGenerator) :: generator
  integer :: rng

4.1.3. curandDestroyGenerator

This function destroys an existing random number generator.

integer(4) function curandDestroyGenerator(generator)
  type(curandGenerator) :: generator

4.1.4. curandGetVersion

This function returns the version number of the cuRAND library.

integer(4) function curandGetVersion(version)
  integer(4) :: version

4.1.5. curandSetStream

This function sets the current stream for the cuRAND kernel launches.

integer(4) function curandSetStream(generator, stream)
  type(curandGenerator) :: generator
  integer(kind=c_intptr_t) :: stream

4.1.6. curandSetPseudoRandomGeneratorSeed

This function sets the seed value of the pseudo-random number generator.

integer(4) function curandSetPseudoRandomGeneratorSeed(generator, seed)
  type(curandGenerator) :: generator
  integer(8) :: seed

4.1.7. curandSetGeneratorOffset

This function sets the absolute offset of the pseudo or quasirandom number generator.

integer(4) function curandSetGeneratorOffset(generator, offset)
  type(curandGenerator) :: generator
  integer(8) :: offset

4.1.8. curandSetGeneratorOrdering

This function sets the ordering of results of the pseudo or quasirandom number generator.

integer(4) function curandSetGeneratorOrdering(generator, order)
  type(curandGenerator) :: generator
  integer(4) :: order

4.1.9. curandSetQuasiRandomGeneratorDimensions

This function sets number of dimensions of the quasirandom number generator.

integer(4) function curandSetQuasiRandomGeneratorDimensions(generator, num)
  type(curandGenerator) :: generator
  integer(4) :: num

4.2. CURAND Generator Functions

This section contains interfaces for the cuRAND generator functions.

4.2.1. curandGenerate

This function generates 32-bit pseudo or quasirandom numbers.

integer(4) function curandGenerate(generator, array, num )
  type(curandGenerator) :: generator
  integer(4), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num

4.2.2. curandGenerateLongLong

This function generates 64-bit integer quasirandom numbers. The function curandGenerate() has also been overloaded to accept these function arguments.

integer(4) function curandGenerateLongLong(generator, array, num )
  type(curandGenerator) :: generator
  integer(8), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num

4.2.3. curandGenerateUniform

This function generates 32-bit floating point uniformly distributed random numbers. The function curandGenerate() has also been overloaded to accept these function arguments.

integer(4) function curandGenerateUniform(generator, array, num )
  type(curandGenerator) :: generator
  real(4), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num

4.2.4. curandGenerateUniformDouble

This function generates 64-bit floating point uniformly distributed random numbers. The function curandGenerate() has also been overloaded to accept these function arguments.

integer(4) function curandGenerateUniformDouble(generator, array, num )
  type(curandGenerator) :: generator
  real(8), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num

4.2.5. curandGenerateNormal

This function generates 32-bit floating point normally distributed random numbers. The function curandGenerate() has also been overloaded to accept these function arguments.

integer(4) function curandGenerateNormal(generator, array, num, mean, stddev )
  type(curandGenerator) :: generator
  real(4), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num
  real(4) :: mean, stddev

4.2.6. curandGenerateNormalDouble

This function generates 64-bit floating point normally distributed random numbers. The function curandGenerate() has also been overloaded to accept these function arguments.

integer(4) function curandGenerateNormalDouble(generator, array, num, mean, stddev )
  type(curandGenerator) :: generator
  real(8), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num
  real(8) :: mean, stddev

4.2.7. curandGeneratePoisson

This function generates Poisson-distributed random numbers. The function curandGenerate() has also been overloaded to accept these function arguments.

integer(4) function curandGeneratePoisson(generator, array, num, lambda )
  type(curandGenerator) :: generator
  real(8), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num
  real(8) :: lambda

4.2.8. curandGenerateSeeds

This function sets the starting state of the generator.

integer(4) function curandGenerateSeeds(generator)
  type(curandGenerator) :: generator

4.2.9. curandGenerateLogNormal

This function generates 32-bit floating point log-normally distributed random numbers.

integer(4) function curandGenerateLogNormal(generator, array, num, mean, stddev )
  type(curandGenerator) :: generator
  real(4), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num
  real(4) :: mean, stddev

4.2.10. curandGenerateLogNormalDouble

This function generates 64-bit floating point log-normally distributed random numbers.

integer(4) function curandGenerateLogNormalDouble(generator, array, num, mean, stddev )
  type(curandGenerator) :: generator
  real(8), device :: array(*) ! Host or device depending on the generator
  integer(kind=c_intptr_t) :: num
  real(8) :: mean, stddev

4.3. CURAND Device Definitions and Functions

This section contains definitions and data types used in the cuRAND device library and interfaces to the cuRAND functions.

The curand device module contains the following derived type definitions:

TYPE curandStateXORWOW
    integer(4) :: d
    integer(4) :: v(5)
    integer(4) :: boxmuller_flag
    integer(4) :: boxmuller_flag_double
    real(4)    :: boxmuller_extra
    real(8)    :: boxmuller_extra_double
END TYPE curandStateXORWOW

TYPE curandStateMRG32k3a
    real(8)    :: s1(3)
    real(8)    :: s2(3)
    integer(4) :: boxmuller_flag
    integer(4) :: boxmuller_flag_double
    real(4)    :: boxmuller_extra
    real(8)    :: boxmuller_extra_double
END TYPE curandStateMRG32k3a

TYPE curandStateSobol32
    integer(4) :: d
    integer(4) :: x
    integer(4) :: c
    integer(4) :: direction_vectors(32)
END TYPE curandStateSobol32

TYPE curandStateScrambledSobol32
    integer(4) :: d
    integer(4) :: x
    integer(4) :: c
    integer(4) :: direction_vectors(32)
END TYPE curandStateScrambledSobol32

TYPE curandStateSobol64
    integer(8) :: d
    integer(8) :: x
    integer(8) :: c
    integer(8) :: direction_vectors(32)
END TYPE curandStateSobol64

TYPE curandStateScrambledSobol64
    integer(8) :: d
    integer(8) :: x
    integer(8) :: c
    integer(8) :: direction_vectors(32)
END TYPE curandStateScrambledSobol64

TYPE curandStateMtgp32
    integer(4) :: s(MTGP32_STATE_SIZE)
    integer(4) :: offset
    integer(4) :: pIdx
    integer(kind=int_ptr_kind()) :: k
    integer(4) :: precise_double_flag
END TYPE curandStateMtgp32

TYPE curandStatePhilox4_32_10
    integer(4) :: ctr
    integer(4) :: output
    integer(2) :: key
    integer(4) :: state
    integer(4) :: boxmuller_flag
    integer(4) :: boxmuller_flag_double
    real(4)    :: boxmuller_extra
    real(8)    :: boxmuller_extra_double
END TYPE curandStatePhilox4_32_10

4.3.1. curand_Init

This overloaded device subroutine initializes the state for the random number generator. These device subroutines are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.1.1. curandInitXORWOW

This function initializes the state for the XORWOW random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitXORWOW(seed, sequence, offset, state)
  integer(8) :: seed
  integer(8) :: sequence
  integer(8) :: offset
  TYPE(curandStateXORWOW) :: state

4.3.1.2. curandInitMRG32k3a

This function initializes the state for the MRG32k3a random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitMRG32k3a(seed, sequence, offset, state)
  integer(8) :: seed
  integer(8) :: sequence
  integer(8) :: offset
  TYPE(curandStateMRG32k3a) :: state

4.3.1.3. curandInitPhilox4_32_10

This function initializes the state for the Philox4_32_10 random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitPhilox4_32_10(seed, sequence, offset, state)
  integer(8) :: seed
  integer(8) :: sequence
  integer(8) :: offset
  TYPE(curandStatePhilox4_32_10) :: state

4.3.1.4. curandInitSobol32

This function initializes the state for the Sobol32 random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitSobol32(direction_vectors, offset, state)
  integer :: direction_vectors(*)
  integer(4) :: offset
  TYPE(curandStateSobol32) :: state

4.3.1.5. curandInitScrambledSobol32

This function initializes the state for the scrambled Sobol32 random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitScrambledSobol32(direction_vectors, scramble, offset, state)
  integer :: direction_vectors(*)
  integer(4) :: scramble
  integer(4) :: offset
  TYPE(curandStateScrambledSobol32) :: state

4.3.1.6. curandInitSobol64

This function initializes the state for the Sobol64 random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitSobol64(direction_vectors, offset, state)
  integer :: direction_vectors(*)
  integer(8) :: offset
  TYPE(curandStateSobol64) :: state

4.3.1.7. curandInitScrambledSobol64

This function initializes the state for the scrambled Sobol64 random number generator. The function curand_init() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

subroutine curandInitScrambledSobol64(direction_vectors, scramble, offset, state)
  integer :: direction_vectors(*)
  integer(8) :: scramble
  integer(8) :: offset
  TYPE(curandStateScrambledSobol64) :: state

4.3.2. curand

This overloaded device function returns 32 or 64 bits or random data based on the state argument. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.2.1. curandGetXORWOW

This function returns 32 bits of pseudorandomness from the XORWOW random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.2.2. curandGetMRG32k3a

This function returns 32 bits of pseudorandomness from the MRG32k3a random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.2.3. curandGetPhilox4_32_10

This function returns 32 bits of pseudorandomness from the Philox4_32_10 random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetPhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.2.4. curandGetSobol32

This function returns 32 bits of quasirandomness from the Sobol32 random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.2.5. curandGetScrambledSobol32

This function returns 32 bits of quasirandomness from the scrambled Sobol32 random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.2.6. curandGetSobol64

This function returns 64 bits of quasirandomness from the Sobol64 random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.2.7. curandGetScrambledSobol64

This function returns 64 bits of quasirandomness from the scrambled Sobol64 random number generator. The function curand() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

integer(4) function curandGetScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

4.3.3. Curand_Normal

This overloaded device function returns a 32-bit floating point normally distributed random number. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.3.1. curandNormalXORWOW

This function returns a 32-bit floating point normally distributed random number from an XORWOW generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.3.2. curandNormalMRG32k3a

This function returns a 32-bit floating point normally distributed random number from an MRG32k3a generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.3.3. curandNormalPhilox4_32_10

This function returns a 32-bit floating point normally distributed random number from a Philox4_32_10 generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalPhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.3.4. curandNormalSobol32

This function returns a 32-bit floating point normally distributed random number from an Sobol32 generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.3.5. curandNormalScrambledSobol32

This function returns a 32-bit floating point normally distributed random number from an scrambled Sobol32 generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.3.6. curandNormalSobol64

This function returns a 32-bit floating point normally distributed random number from an Sobol64 generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.3.7. curandNormalScrambledSobol64

This function returns a 32-bit floating point normally distributed random number from an scrambled Sobol64 generator. The function curand_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandNormalScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

4.3.4. Curand_Normal_Double

This overloaded device function returns a 64-bit floating point normally distributed random number. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.4.1. curandNormalDoubleXORWOW

This function returns a 64-bit floating point normally distributed random number from an XORWOW generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoubleXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.4.2. curandNormalDoubleMRG32k3a

This function returns a 64-bit floating point normally distributed random number from an MRG32k3a generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoubleMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.4.3. curandNormalDoublePhilox4_32_10

This function returns a 64-bit floating point normally distributed random number from a Philox4_32_10 generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoublePhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.4.4. curandNormalDoubleSobol32

This function returns a 64-bit floating point normally distributed random number from an Sobol32 generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoubleSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.4.5. curandNormalDoubleScrambledSobol32

This function returns a 64-bit floating point normally distributed random number from an scrambled Sobol32 generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoubleScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.4.6. curandNormalDoubleSobol64

This function returns a 64-bit floating point normally distributed random number from an Sobol64 generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoubleSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.4.7. curandNormalDoubleScrambledSobol64

This function returns a 64-bit floating point normally distributed random number from an scrambled Sobol64 generator. The function curand_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandNormalDoubleScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

4.3.5. Curand_Log_Normal

This overloaded device function returns a 32-bit floating point log-normally distributed random number. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.5.1. curandLogNormalXORWOW

This function returns a 32-bit floating point log-normally distributed random number from an XORWOW generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.5.2. curandLogNormalMRG32k3a

This function returns a 32-bit floating point log-normally distributed random number from an MRG32k3a generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.5.3. curandLogNormalPhilox4_32_10

This function returns a 32-bit floating point log-normally distributed random number from a Philox4_32_10 generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalPhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.5.4. curandLogNormalSobol32

This function returns a 32-bit floating point log-normally distributed random number from an Sobol32 generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.5.5. curandLogNormalScrambledSobol32

This function returns a 32-bit floating point log-normally distributed random number from an scrambled Sobol32 generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.5.6. curandLogNormalSobol64

This function returns a 32-bit floating point log-normally distributed random number from an Sobol64 generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.5.7. curandLogNormalScrambledSobol64

This function returns a 32-bit floating point log-normally distributed random number from an scrambled Sobol64 generator. The function curand_log_normal() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandLogNormalScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

4.3.6. Curand_Log_Normal_Double

This overloaded device function returns a 64-bit floating point log-normally distributed random number. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.6.1. curandLogNormalDoubleXORWOW

This function returns a 64-bit floating point log-normally distributed random number from an XORWOW generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoubleXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.6.2. curandLogNormalDoubleMRG32k3a

This function returns a 64-bit floating point log-normally distributed random number from an MRG32k3a generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoubleMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.6.3. curandLogNormalDoublePhilox4_32_10

This function returns a 64-bit floating point log-normally distributed random number from a Philox4_32_10 generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoublePhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.6.4. curandLogNormalDoubleSobol32

This function returns a 64-bit floating point log-normally distributed random number from an Sobol32 generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoubleSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.6.5. curandLogNormalDoubleScrambledSobol32

This function returns a 64-bit floating point log-normally distributed random number from an scrambled Sobol32 generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoubleScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.6.6. curandLogNormalDoubleSobol64

This function returns a 64-bit floating point log-normally distributed random number from an Sobol64 generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoubleSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.6.7. curandLogNormalDoubleScrambledSobol64

This function returns a 64-bit floating point log-normally distributed random number from an scrambled Sobol64 generator. The function curand_log_normal_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandLogNormalDoubleScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

4.3.7. Curand_Uniform

This overloaded device function returns a 32-bit floating point uniformly distributed random number. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.7.1. curandUniformXORWOW

This function returns a 32-bit floating point uniformly distributed random number from an XORWOW generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.7.2. curandUniformMRG32k3a

This function returns a 32-bit floating point uniformly distributed random number from an MRG32k3a generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.7.3. curandUniformPhilox4_32_10

This function returns a 32-bit floating point uniformly distributed random number from a Philox4_32_10 generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformPhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.7.4. curandUniformSobol32

This function returns a 32-bit floating point uniformly distributed random number from an Sobol32 generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.7.5. curandUniformScrambledSobol32

This function returns a 32-bit floating point uniformly distributed random number from an scrambled Sobol32 generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.7.6. curandUniformSobol64

This function returns a 32-bit floating point uniformly distributed random number from an Sobol64 generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.7.7. curandUniformScrambledSobol64

This function returns a 32-bit floating point uniformly distributed random number from an scrambled Sobol64 generator. The function curand_uniform() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(4) function curandUniformScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

4.3.8. Curand_Uniform_Double

This overloaded device function returns a 64-bit floating point uniformly distributed random number. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

4.3.8.1. curandUniformDoubleXORWOW

This function returns a 64-bit floating point uniformly distributed random number from an XORWOW generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoubleXORWOW(state)
  TYPE(curandStateXORWOW) :: state

4.3.8.2. curandUniformDoubleMRG32k3a

This function returns a 64-bit floating point uniformly distributed random number from an MRG32k3a generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoubleMRG32k3a(state)
  TYPE(curandStateMRG32k3a) :: state

4.3.8.3. curandUniformDoublePhilox4_32_10

This function returns a 64-bit floating point uniformly distributed random number from a Philox4_32_10 generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoublePhilox4_32_10(state)
  TYPE(curandStatePhilox4_32_10) :: state

4.3.8.4. curandUniformDoubleSobol32

This function returns a 64-bit floating point uniformly distributed random number from an Sobol32 generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoubleSobol32(state)
  TYPE(curandStateSobol32) :: state

4.3.8.5. curandUniformDoubleScrambledSobol32

This function returns a 64-bit floating point uniformly distributed random number from an scrambled Sobol32 generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoubleScrambledSobol32(state)
  TYPE(curandStateScrambledSobol32) :: state

4.3.8.6. curandUniformDoubleSobol64

This function returns a 64-bit floating point uniformly distributed random number from an Sobol64 generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoubleSobol64(state)
  TYPE(curandStateSobol64) :: state

4.3.8.7. curandUniformDoubleScrambledSobol64

This function returns a 64-bit floating point uniformly distributed random number from an scrambled Sobol64 generator. The function curand_uniform_double() has also been overloaded to accept these function arguments, as in CUDA C++. Device Functions are declared attributes(device) in CUDA Fortran and !$acc routine() seq in OpenACC.

real(8) function curandUniformDoubleScrambledSobol64(state)
  TYPE(curandStateScrambledSobol64) :: state

5. SPARSE Matrix Runtime Library APIs

This section describes the Fortran interfaces to the CUDA cuSPARSE library. The cuSPARSE functions are only accessible from host code. All of the runtime API routines are integer functions that return an error code; they return a value of CUSPARSE_STATUS_SUCCESS if the call was successful, or another cuSPARSE status return value if there was an error.

Chapter 10 contains examples of accessing the cuSPARSE library routines from OpenACC and CUDA Fortran. In both cases, the interfaces to the library can be exposed by adding the line

use cusparse

to your program unit.

A number of the function interfaces listed in this chapter can take host or device scalar arguments. Those functions have an additional v2 interface, which does not implicitly manage the pointer mode for these calls. See section 1.6 for further discussion on the handling of pointer modes.

Unless a specific kind is provided, the plain integer type used in the interfaces implies integer(4) and the plain real type implies real(4).

5.1. CUSPARSE Definitions and Helper Functions

This section contains definitions and data types used in the cuSPARSE library and interfaces to the cuSPARSE helper functions.

The cuSPARSE module contains the following derived type definitions:

type cusparseHandle
  type(c_ptr) :: handle
end type cusparseHandle

type :: cusparseMatDescr
     type(c_ptr) :: descr
end type cusparseMatDescr

! This type was removed in CUDA 11.0
type cusparseSolveAnalysisInfo
     type(c_ptr) :: info
end type cusparseSolveAnalysisInfo

! This type was removed in CUDA 11.0
type cusparseHybMat
     type(c_ptr) :: mat
end type cusparseHybMat

type cusparseCsrsv2Info
     type(c_ptr) :: info
end type cusparseCsrsv2Info

type cusparseCsric02Info
     type(c_ptr) :: info
end type cusparseCsric02Info

type cusparseCsrilu02Info
     type(c_ptr) :: info
end type cusparseCsrilu02Info

type cusparseBsrsv2Info
     type(c_ptr) :: info
end type cusparseBsrsv2Info

type cusparseBsric02Info
     type(c_ptr) :: info
end type cusparseBsric02Info

type cusparseBsrilu02Info
     type(c_ptr) :: info
end type cusparseBsrilu02Info

type cusparseBsrsm2Info
     type(c_ptr) :: info
end type cusparseBsrsm2Info

type cusparseCsrgemm2Info
     type(c_ptr) :: info
end type cusparseCsrgemm2Info

type cusparseColorInfo
     type(c_ptr) :: info
end type cusparseColorInfo

type cusparseCsru2csrInfo
     type(c_ptr) :: info
end type cusparseCsru2csrInfo

type cusparseSpVecDescr
     type(c_ptr) :: descr
end type cusparseSpVecDescr

type cusparseDnVecDescr
     type(c_ptr) :: descr
end type cusparseDnVecDescr

type cusparseSpMatDescr
     type(c_ptr) :: descr
end type cusparseSpMatDescr

type cusparseDnMatDescr
     type(c_ptr) :: descr
end type cusparseDnMatDescr

type cusparseSpSVDescr
     type(c_ptr) :: descr
end type cusparseSpSVDescr

type cusparseSpSMDescr
     type(c_ptr) :: descr
end type cusparseSpSMDescr

type cusparseSpGEMMDescr
     type(c_ptr) :: descr
end type cusparseSpGEMMDescr

The cuSPARSE module contains the following constants and enumerations:

! cuSPARSE Version Info
  integer, parameter :: CUSPARSE_VER_MAJOR = 12
  integer, parameter :: CUSPARSE_VER_MINOR = 1
  integer, parameter :: CUSPARSE_VER_PATCH = 2
  integer, parameter :: CUSPARSE_VER_BUILD = 129
  integer, parameter :: CUSPARSE_VERSION   = (CUSPARSE_VER_MAJOR * 1000 + &
                          CUSPARSE_VER_MINOR *  100 + CUSPARSE_VER_PATCH)

! cuSPARSE status return values
enum, bind(C) ! cusparseStatus_t
    enumerator :: CUSPARSE_STATUS_SUCCESS=0
    enumerator :: CUSPARSE_STATUS_NOT_INITIALIZED=1
    enumerator :: CUSPARSE_STATUS_ALLOC_FAILED=2
    enumerator :: CUSPARSE_STATUS_INVALID_VALUE=3
    enumerator :: CUSPARSE_STATUS_ARCH_MISMATCH=4
    enumerator :: CUSPARSE_STATUS_MAPPING_ERROR=5
    enumerator :: CUSPARSE_STATUS_EXECUTION_FAILED=6
    enumerator :: CUSPARSE_STATUS_INTERNAL_ERROR=7
    enumerator :: CUSPARSE_STATUS_MATRIX_TYPE_NOT_SUPPORTED=8
    enumerator :: CUSPARSE_STATUS_ZERO_PIVOT=9
    enumerator :: CUSPARSE_STATUS_NOT_SUPPORTED=10
    enumerator :: CUSPARSE_STATUS_INSUFFICIENT_RESOURCES=11
end enum

enum, bind(c) ! cusparsePointerMode_t
    enumerator :: CUSPARSE_POINTER_MODE_HOST = 0
    enumerator :: CUSPARSE_POINTER_MODE_DEVICE = 1
end enum

enum, bind(c) ! cusparseAction_t
    enumerator :: CUSPARSE_ACTION_SYMBOLIC = 0
    enumerator :: CUSPARSE_ACTION_NUMERIC = 1
end enum

enum, bind(C) ! cusparseMatrixType_t
    enumerator :: CUSPARSE_MATRIX_TYPE_GENERAL = 0
    enumerator :: CUSPARSE_MATRIX_TYPE_SYMMETRIC = 1
    enumerator :: CUSPARSE_MATRIX_TYPE_HERMITIAN = 2
    enumerator :: CUSPARSE_MATRIX_TYPE_TRIANGULAR = 3
end enum

enum, bind(C) ! cusparseFillMode_t
    enumerator :: CUSPARSE_FILL_MODE_LOWER = 0
    enumerator :: CUSPARSE_FILL_MODE_UPPER = 1
end enum

enum, bind(C) ! cusparseDiagType_t
    enumerator :: CUSPARSE_DIAG_TYPE_NON_UNIT = 0
    enumerator :: CUSPARSE_DIAG_TYPE_UNIT = 1
end enum

enum, bind(C) ! cusparseIndexBase_t
    enumerator :: CUSPARSE_INDEX_BASE_ZERO = 0
    enumerator :: CUSPARSE_INDEX_BASE_ONE = 1
end enum

enum, bind(C) ! cusparseOperation_t
    enumerator :: CUSPARSE_OPERATION_NON_TRANSPOSE = 0
    enumerator :: CUSPARSE_OPERATION_TRANSPOSE = 1
    enumerator :: CUSPARSE_OPERATION_CONJUGATE_TRANSPOSE = 2
end enum

enum, bind(C) ! cusparseDirection_t
    enumerator :: CUSPARSE_DIRECTION_ROW = 0
    enumerator :: CUSPARSE_DIRECTION_COLUMN = 1
end enum

enum, bind(C) ! cusparseHybPartition_t
    enumerator :: CUSPARSE_HYB_PARTITION_AUTO = 0
    enumerator :: CUSPARSE_HYB_PARTITION_USER = 1
    enumerator :: CUSPARSE_HYB_PARTITION_MAX = 2
end enum

enum, bind(C) ! cusparseSolvePolicy_t
    enumerator :: CUSPARSE_SOLVE_POLICY_NO_LEVEL = 0
    enumerator :: CUSPARSE_SOLVE_POLICY_USE_LEVEL = 1
end enum

enum, bind(C) ! cusparseSideMode_t
    enumerator :: CUSPARSE_SIDE_LEFT  = 0
    enumerator :: CUSPARSE_SIDE_RIGHT = 1
end enum

enum, bind(C) ! cusparseColorAlg_t
    enumerator :: CUSPARSE_COLOR_ALG0 = 0
    enumerator :: CUSPARSE_COLOR_ALG1 = 1
end enum

enum, bind(C) ! cusparseAlgMode_t;
    enumerator :: CUSPARSE_ALG0           = 0
    enumerator :: CUSPARSE_ALG1           = 1
    enumerator :: CUSPARSE_ALG_NAIVE      = 0
    enumerator :: CUSPARSE_ALG_MERGE_PATH = 0
end enum

enum, bind(C) ! cusparseCsr2CscAlg_t;
    enumerator :: CUSPARSE_CSR2CSC_ALG_DEFAULT = 1
    enumerator :: CUSPARSE_CSR2CSC_ALG1 = 1
    enumerator :: CUSPARSE_CSR2CSC_ALG2 = 2
end enum

enum, bind(C) ! cusparseFormat_t;
    enumerator :: CUSPARSE_FORMAT_CSR     = 1
    enumerator :: CUSPARSE_FORMAT_CSC     = 2
    enumerator :: CUSPARSE_FORMAT_COO     = 3
    enumerator :: CUSPARSE_FORMAT_COO_AOS = 4
    enumerator :: CUSPARSE_FORMAT_BLOCKED_ELL = 5
    enumerator :: CUSPARSE_FORMAT_BSR     = 6
    enumerator :: CUSPARSE_FORMAT_SLICED_ELLPACK = 7
end enum

enum, bind(C) ! cusparseOrder_t;
    enumerator :: CUSPARSE_ORDER_COL = 1
    enumerator :: CUSPARSE_ORDER_ROW = 2
end enum

enum, bind(C) ! cusparseSpMVAlg_t;
    enumerator :: CUSPARSE_MV_ALG_DEFAULT = 0
    enumerator :: CUSPARSE_COOMV_ALG      = 1
    enumerator :: CUSPARSE_CSRMV_ALG1     = 2
    enumerator :: CUSPARSE_CSRMV_ALG2     = 3
    enumerator :: CUSPARSE_SPMV_ALG_DEFAULT = 0
    enumerator :: CUSPARSE_SPMV_CSR_ALG1    = 2
    enumerator :: CUSPARSE_SPMV_CSR_ALG2    = 3
    enumerator :: CUSPARSE_SPMV_COO_ALG1    = 1
    enumerator :: CUSPARSE_SPMV_COO_ALG2    = 4
    enumerator :: CUSPARSE_SPMV_SELL_ALG1   = 5
end enum

enum, bind(C) ! cusparseSpMMAlg_t;
    enumerator :: CUSPARSE_MM_ALG_DEFAULT = 0
    enumerator :: CUSPARSE_COOMM_ALG1 = 1
    enumerator :: CUSPARSE_COOMM_ALG2 = 2
    enumerator :: CUSPARSE_COOMM_ALG3 = 3
    enumerator :: CUSPARSE_CSRMM_ALG1 = 4
    enumerator :: CUSPARSE_SPMM_ALG_DEFAULT = 0
    enumerator :: CUSPARSE_SPMM_COO_ALG1    = 1
    enumerator :: CUSPARSE_SPMM_COO_ALG2    = 2
    enumerator :: CUSPARSE_SPMM_COO_ALG3    = 3
    enumerator :: CUSPARSE_SPMM_COO_ALG4    = 5
    enumerator :: CUSPARSE_SPMM_CSR_ALG1    = 4
    enumerator :: CUSPARSE_SPMM_CSR_ALG2    = 6
    enumerator :: CUSPARSE_SPMM_CSR_ALG3    = 12
    enumerator :: CUSPARSE_SPMM_BLOCKED_ELL_ALG1 = 13
end enum

enum, bind(C) ! cusparseIndexType_t;
    enumerator :: CUSPARSE_INDEX_16U = 1
    enumerator :: CUSPARSE_INDEX_32I = 2
    enumerator :: CUSPARSE_INDEX_64I = 3
end enum

enum, bind(C) ! cusparseSpMatAttribute_t;
    enumerator :: CUSPARSE_SPMAT_FILL_MODE = 0
    enumerator :: CUSPARSE_SPMAT_DIAG_TYPE = 1
end enum

enum, bind(C) ! cusparseSparseToDenseAlg_t;
    enumerator :: CUSPARSE_SPARSETODENSE_ALG_DEFAULT = 0
    enumerator :: CUSPARSE_DENSETOSPARSE_ALG_DEFAULT = 0
end enum

enum, bind(C) ! cusparseSpSVAlg_t;
    enumerator :: CUSPARSE_SPSV_ALG_DEFAULT = 0
end enum

enum, bind(C) ! cusparseSpSVUpdate_t;
    enumerator :: CUSPARSE_SPSV_UPDATE_GENERAL  = 0
    enumerator :: CUSPARSE_SPSV_UPDATE_DIAGONAL = 1
end enum

enum, bind(C) ! cusparseSpSMAlg_t;
    enumerator :: CUSPARSE_SPSM_ALG_DEFAULT = 0
end enum

enum, bind(C) ! cusparseSpMMOpAlg_t;
    enumerator :: CUSPARSE_SPMM_OP_ALG_DEFAULT = 0
end enum

enum, bind(C) ! cusparseSpGEMMAlg_t;
    enumerator :: CUSPARSE_SPGEMM_DEFAULT = 0
    enumerator :: CUSPARSE_SPGEMM_CSR_ALG_DETERMINISTIC = 1
    enumerator :: CUSPARSE_SPGEMM_CSR_ALG_DETERMINITIC  = 1
    enumerator :: CUSPARSE_SPGEMM_CSR_ALG_NONDETERMINISTIC = 2
    enumerator :: CUSPARSE_SPGEMM_CSR_ALG_NONDETERMINITIC  = 2
    enumerator :: CUSPARSE_SPGEMM_ALG1 = 3
    enumerator :: CUSPARSE_SPGEMM_ALG2 = 4
    enumerator :: CUSPARSE_SPGEMM_ALG3 = 5
end enum

enum, bind(C) ! cusparseSDDMMAlg_t;
    enumerator :: CUSPARSE_SDDMM_ALG_DEFAULT = 0
end enum

5.1.1. cusparseCreate

This function initializes the cuSPARSE library and creates a handle on the cuSPARSE context. It must be called before any other cuSPARSE API function is invoked. It allocates hardware resources necessary for accessing the GPU.

integer(4) function cusparseCreate(handle)
  type(cusparseHandle) :: handle

5.1.2. cusparseDestroy

This function releases CPU-side resources used by the cuSPARSE library. The release of GPU-side resources may be deferred until the application shuts down.

integer(4) function cusparseDestroy(handle)
  type(cusparseHandle) :: handle

5.1.3. cusparseGetErrorName

This function returns the error code name.

character*128 function cusparseGetErrorName(ierr)
   integer(c_int) :: ierr

5.1.4. cusparseGetErrorString

This function returns the description string for an error code.

character*128 function cusparseGetErrorString(ierr)
   integer(c_int) :: ierr

5.1.5. cusparseGetVersion

This function returns the version number of the cuSPARSE library.

integer(4) function cusparseGetVersion(handle, version)
  type(cusparseHandle) :: handle
  integer(c_int) :: version

5.1.6. cusparseSetStream

This function sets the stream to be used by the cuSPARSE library to execute its routines.

integer(4) function cusparseSetStream(handle, stream)
  type(cusparseHandle) :: handle
  integer(cuda_stream_kind) :: stream

5.1.7. cusparseGetStream

This function gets the stream used by the cuSPARSE library to execute its routines. If the cuSPARSE library stream is not set, all kernels use the default NULL stream.

integer(4) function cusparseGetStream(handle, stream)
  type(cusparseHandle) :: handle
  integer(cuda_stream_kind) :: stream

5.1.8. cusparseGetPointerMode

This function obtains the pointer mode used by the cuSPARSE library. Please see section 1.6 for more details on pointer modes.

integer(4) function cusparseGetPointerMode(handle, mode)
  type(cusparseHandle) :: handle
  integer(c_int) :: mode

5.1.9. cusparseSetPointerMode

This function sets the pointer mode used by the cuSPARSE library. In these Fortran interfaces, this only has an effect when using the *_v2 interfaces. The default is for the values to be passed by reference on the host. Please see section 1.6 for more details on pointer modes.

integer(4) function cusparseSetPointerMode(handle, mode)
  type(cusparseHandle) :: handle
  integer(4) :: mode

5.1.10. cusparseCreateMatDescr

This function initializes the matrix descriptor. It sets the fields MatrixType and IndexBase to the default values CUSPARSE_MATRIX_TYPE_GENERAL and CUSPARSE_INDEX_BASE_ZERO , respectively, while leaving other fields uninitialized.

integer(4) function cusparseCreateMatDescr(descrA)
  type(cusparseMatDescr) :: descrA

5.1.11. cusparseDestroyMatDescr

This function releases the memory allocated for the matrix descriptor.

integer(4) function cusparseDestroyMatDescr(descrA)
  type(cusparseMatDescr) :: descrA

5.1.12. cusparseSetMatType

This function sets the MatrixType of the matrix descriptor descrA.

integer(4) function cusparseSetMatType(descrA, type)
  type(cusparseMatDescr) :: descrA
  integer(4) :: type

5.1.13. cusparseGetMatType

This function returns the MatrixType of the matrix descriptor descrA.

integer(4) function cusparseGetMatType(descrA)
  type(cusparseMatDescr) :: descrA

5.1.14. cusparseSetMatFillMode

This function sets the FillMode field of the matrix descriptor descrA.

integer(4) function cusparseSetMatFillMode(descrA, mode)
  type(cusparseMatDescr) :: descrA
  integer(4) :: mode

5.1.15. cusparseGetMatFillMode

This function returns the FillMode field of the matrix descriptor descrA.

integer(4) function cusparseGetMatFillMode(descrA)
  type(cusparseMatDescr) :: descrA

5.1.16. cusparseSetMatDiagType

This function sets the DiagType of the matrix descriptor descrA.

integer(4) function cusparseSetMatDiagType(descrA, type)
  type(cusparseMatDescr) :: descrA
  integer(4) :: type

5.1.17. cusparseGetMatDiagType

This function returns the DiagType of the matrix descriptor descrA.

integer(4) function cusparseGetMatDiagType(descrA)
  type(cusparseMatDescr) :: descrA

5.1.18. cusparseSetMatIndexBase

This function sets the IndexBase field of the matrix descriptor descrA.

integer(4) function cusparseSetMatIndexBase(descrA, base)
  type(cusparseMatDescr) :: descrA
  integer(4) :: base

5.1.19. cusparseGetMatIndexBase

This function returns the IndexBase field of the matrix descriptor descrA.

integer(4) function cusparseGetMatIndexBase(descrA)
  type(cusparseMatDescr) :: descrA

5.1.20. cusparseCreateSolveAnalysisInfo

This function creates and initializes the solve and analysis structure to default values. This function, and all functions which use the cusparseSolveAnalysisInfo type, were removed in CUDA 11.0.

integer(4) function cusparseCreateSolveAnalysisInfo(info)
  type(cusparseSolveAnalysisinfo) :: info

5.1.21. cusparseDestroySolveAnalysisInfo

This function destroys and releases any memory required by the structure. This function, and all functions which use the cusparseSolveAnalysisInfo type, were removed in CUDA 11.0.

integer(4) function cusparseDestroySolveAnalysisInfo(info)
  type(cusparseSolveAnalysisinfo) :: info

5.1.22. cusparseGetLevelInfo

This function returns the number of levels and the assignment of rows into the levels computed by either the csrsv_analysis, csrsm_analysis or hybsv_analysis routines.

integer(4) function cusparseGetLevelInfo(handle, info, nlevels, levelPtr, levelInd)
  type(cusparseHandle) :: handle
  type(cusparseSolveAnalysisinfo) :: info
  integer(c_int) :: nlevels
  type(c_ptr) :: levelPtr
  type(c_ptr) :: levelInd

5.1.23. cusparseCreateHybMat

This function creates and initializes the hybA opaque data structure. This function, and all functions which use the cusparseHybMat type, were removed in CUDA 11.0.

integer(4) function cusparseCreateHybMat(hybA)
  type(cusparseHybMat) :: hybA

5.1.24. cusparseDestroyHybMat

This function destroys and releases any memory required by the hybA structure. This function, and all functions which use the cusparseHybMat type, were removed in CUDA 11.0.

integer(4) function cusparseDestroyHybMat(hybA)
  type(cusparseHybMat) :: hybA

5.1.25. cusparseCreateCsrsv2Info

This function creates and initializes the solve and analysis structure of csrsv2 to default values.

integer(4) function cusparseCreateCsrsv2Info(info)
  type(cusparseCsrsv2Info) :: info

5.1.26. cusparseDestroyCsrsv2Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyCsrsv2Info(info)
  type(cusparseCsrsv2Info) :: info

5.1.27. cusparseCreateCsric02Info

This function creates and initializes the solve and analysis structure of incomplete Cholesky to default values.

integer(4) function cusparseCreateCsric02Info(info)
  type(cusparseCsric02Info) :: info

5.1.28. cusparseDestroyCsric02Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyCsric02Info(info)
  type(cusparseCsric02Info) :: info

5.1.29. cusparseCreateCsrilu02Info

This function creates and initializes the solve and analysis structure of incomplete LU to default values.

integer(4) function cusparseCreateCsrilu02Info(info)
  type(cusparseCsrilu02Info) :: info

5.1.30. cusparseDestroyCsrilu02Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyCsrilu02Info(info)
  type(cusparseCsrilu02Info) :: info

5.1.31. cusparseCreateBsrsv2Info

This function creates and initializes the solve and analysis structure of bsrsv2 to default values.

integer(4) function cusparseCreateBsrsv2Info(info)
  type(cusparseBsrsv2Info) :: info

5.1.32. cusparseDestroyBsrsv2Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyBsrsv2Info(info)
  type(cusparseBsrsv2Info) :: info

5.1.33. cusparseCreateBsric02Info

This function creates and initializes the solve and analysis structure of block incomplete Cholesky to default values.

integer(4) function cusparseCreateBsric02Info(info)
  type(cusparseBsric02Info) :: info

5.1.34. cusparseDestroyBsric02Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyBsric02Info(info)
  type(cusparseBsric02Info) :: info

5.1.35. cusparseCreateBsrilu02Info

This function creates and initializes the solve and analysis structure of block incomplete LU to default values.

integer(4) function cusparseCreateBsrilu02Info(info)
  type(cusparseBsrilu02Info) :: info

5.1.36. cusparseDestroyBsrilu02Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyBsrilu02Info(info)
  type(cusparseBsrilu02Info) :: info

5.1.37. cusparseCreateBsrsm2Info

This function creates and initializes the solve and analysis structure of bsrsm2 to default values.

integer(4) function cusparseCreateBsrsm2Info(info)
  type(cusparseBsrsm2Info) :: info

5.1.38. cusparseDestroyBsrsm2Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyBsrsm2Info(info)
  type(cusparseBsrsm2Info) :: info

5.1.39. cusparseCreateCsrgemm2Info

This function creates and initializes the analysis structure of general sparse matrix-matrix multiplication.

integer(4) function cusparseCreateCsrgemm2Info(info)
  type(cusparseCsrgemm2Info) :: info

5.1.40. cusparseDestroyCsrgemm2Info

This function destroys and releases any memory required by the structure.

integer(4) function cusparseDestroyCsrgemm2Info(info)
  type(cusparseCsrgemm2Info) :: info

5.1.41. cusparseCreateColorInfo

This function creates coloring information used in calls like CSRCOLOR.

integer(4) function cusparseCreateColorInfo(info)
  type(cusparseColorInfo) :: info

5.1.42. cusparseDestroyColorInfo

This function destroys coloring information used in calls like CSRCOLOR.

integer(4) function cusparseDestroyColorInfo(info)
  type(cusparseColorInfo) :: info

5.1.43. cusparseCreateCsru2csrInfo

This function creates sorting information used in calls like CSRU2CSR.

integer(4) function cusparseCreateCsru2csrInfo(info)
  type(cusparseCsru2csrInfo) :: info

5.1.44. cusparseDestroyCsru2csrInfo

This function creates sorting information used in calls like CSRU2CSR.

integer(4) function cusparseDestroyCsru2csrInfo(info)
  type(cusparseCsru2csrInfo) :: info

5.2. CUSPARSE Level 1 Functions

This section contains interfaces for the level 1 sparse linear algebra functions that perform operations between dense and sparse vectors.

5.2.1. cusparseSaxpyi

SAXPY performs constant times a vector plus a vector. This function multiplies the vector x in sparse format by the constant alpha and adds the result to the vector y in dense format, i.e. y = y + alpha * xVal(xInd)

integer(4) function cusparseSaxpyi(handle, nnz, alpha, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  real(4), device :: alpha ! device or host variable
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(4), device :: y(*)
  integer :: idxBase

5.2.2. cusparseDaxpyi

DAXPY performs constant times a vector plus a vector. This function multiplies the vector x in sparse format by the constant alpha and adds the result to the vector y in dense format, i.e. y = y + alpha * xVal(xInd)

integer(4) function cusparseDaxpyi(handle, nnz, alpha, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  real(8), device :: alpha ! device or host variable
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(8), device :: y(*)
  integer :: idxBase

5.2.3. cusparseCaxpyi

CAXPY performs constant times a vector plus a vector. This function multiplies the vector x in sparse format by the constant alpha and adds the result to the vector y in dense format, i.e. y = y + alpha * xVal(xInd)

integer(4) function cusparseCaxpyi(handle, nnz, alpha, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  complex(4), device :: alpha ! device or host variable
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(4), device :: y(*)
  integer :: idxBase

5.2.4. cusparseZaxpyi

ZAXPY performs constant times a vector plus a vector. This function multiplies the vector x in sparse format by the constant alpha and adds the result to the vector y in dense format, i.e. y = y + alpha * xVal(xInd)

integer(4) function cusparseZaxpyi(handle, nnz, alpha, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  complex(8), device :: alpha ! device or host variable
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(8), device :: y(*)
  integer :: idxBase

5.2.5. cusparseSdoti

SDOT forms the dot product of two vectors. This function returns the dot product of a vector x in sparse format and vector y in dense format, i.e. res = sum(y * xVal(xInd))

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpVV

integer(4) function cusparseSdoti(handle, nnz, xVal, xInd, y, res, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(4), device :: y(*)
  real(4), device :: res ! device or host variable
  integer :: idxBase

5.2.6. cusparseDdoti

DDOT forms the dot product of two vectors. This function returns the dot product of a vector x in sparse format and vector y in dense format, i.e. res = sum(y * xVal(xInd))

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpVV

integer(4) function cusparseDdoti(handle, nnz, xVal, xInd, y, res, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(8), device :: y(*)
  real(8), device :: res ! device or host variable
  integer :: idxBase

5.2.7. cusparseCdoti

CDOT forms the dot product of two vectors. This function returns the dot product of a vector x in sparse format and vector y in dense format, i.e. res = sum(y * xVal(xInd))

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpVV

integer(4) function cusparseCdoti(handle, nnz, xVal, xInd, y, res, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(4), device :: y(*)
  complex(4), device :: res ! device or host variable
  integer :: idxBase

5.2.8. cusparseZdoti

ZDOT forms the dot product of two vectors. This function returns the dot product of a vector x in sparse format and vector y in dense format, i.e. res = sum(y * xVal(xInd))

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpVV

integer(4) function cusparseZdoti(handle, nnz, xVal, xInd, y, res, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(8), device :: y(*)
  complex(8), device :: res ! device or host variable
  integer :: idxBase

5.2.9. cusparseCdotci

CDOTC forms the dot product of two vectors, conjugating the first vector. This function returns the dot product of a vector x in sparse format and vector y in dense format, i.e. res = sum(y * conjg(xVal(xInd))

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpVV

integer(4) function cusparseCdotci(handle, nnz, xVal, xInd, y, res, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(4), device :: y(*)
  complex(4), device :: res ! device or host variable
  integer :: idxBase

5.2.10. cusparseZdotci

ZDOTC forms the dot product of two vectors, conjugating the first vector. This function returns the dot product of a vector x in sparse format and vector y in dense format, i.e. res = sum(y * conjg(xVal(xInd))

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpVV

integer(4) function cusparseZdotci(handle, nnz, xVal, xInd, y, res, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(8), device :: y(*)
  complex(8), device :: res ! device or host variable
  integer :: idxBase

5.2.11. cusparseSgthr

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd) Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseSgthr(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  real(4), device :: y(*)
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.12. cusparseDgthr

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd) Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseDgthr(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  real(8), device :: y(*)
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.13. cusparseCgthr

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd) Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseCgthr(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  complex(4), device :: y(*)
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.14. cusparseZgthr

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd) Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseZgthr(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  complex(8), device :: y(*)
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.15. cusparseSgthrz

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd); y(xInd) = 0.0 Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseSgthrz(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  real(4), device :: y(*)
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.16. cusparseDgthrz

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd); y(xInd) = 0.0 Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseDgthrz(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  real(8), device :: y(*)
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.17. cusparseCgthrz

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd); y(xInd) = 0.0 Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseCgthrz(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  complex(4), device :: y(*)
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.18. cusparseZgthrz

This function gathers the elements of the vector y listed in the index array xInd into data array xVal, i.e. xVal = y(xInd); y(xInd) = 0.0 Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseZgthrz(handle, nnz, y, xVal, xInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  complex(8), device :: y(*)
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  integer(4) :: idxBase

5.2.19. cusparseSsctr

This function scatters the elements of the dense format vector x into the vector y in sparse format, i.e. y(xInd) = x Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseSsctr(handle, nnz, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(4), device :: y(*)
  integer(4) :: idxBase

5.2.20. cusparseDsctr

This function scatters the elements of the dense format vector x into the vector y in sparse format, i.e. y(xInd) = x Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseDsctr(handle, nnz, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(8), device :: y(*)
  integer(4) :: idxBase

5.2.21. cusparseCsctr

This function scatters the elements of the dense format vector x into the vector y in sparse format, i.e. y(xInd) = x Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseCsctr(handle, nnz, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(4), device :: y(*)
  integer(4) :: idxBase

5.2.22. cusparseZsctr

This function scatters the elements of the dense format vector x into the vector y in sparse format, i.e. y(xInd) = x Fortran programmers should normally use idxBase == 1.

integer(4) function cusparseZsctr(handle, nnz, xVal, xInd, y, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(8), device :: y(*)
  integer(4) :: idxBase

5.2.23. cusparseSroti

SROT applies a plane rotation. X is a sparse vector and Y is dense.

integer(4) function cusparseSroti(handle, nnz, xVal, xInd, y, c, s, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(4), device :: y(*)
  real(4), device :: c, s ! device or host variable
  integer :: idxBase

5.2.24. cusparseDroti

DROT applies a plane rotation. X is a sparse vector and Y is dense.

integer(4) function cusparseDroti(handle, nnz, xVal, xInd, y, c, s, idxBase)
  type(cusparseHandle) :: handle
  integer :: nnz
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(8), device :: y(*)
  real(8), device :: c, s ! device or host variable
  integer :: idxBase

5.3. CUSPARSE Level 2 Functions

This section contains interfaces for the level 2 sparse linear algebra functions that perform operations between sparse matrices and dense vectors.

5.3.1. cusparseSbsrmv

BSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an (mb*blockDim) x (nb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrVal, bsrRowPtr, and bsrColInd

integer(4) function cusparseSbsrmv(handle, dir, trans, mb, nb, nnzb, alpha, descr, bsrVal, bsrRowPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: mb, nb, nnzb
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  real(4), device :: x(*)
  real(4), device :: beta ! device or host variable
  real(4), device :: y(*)

5.3.2. cusparseDbsrmv

BSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an (mb*blockDim) x (nb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrVal, bsrRowPtr, and bsrColInd

integer(4) function cusparseDbsrmv(handle, dir, trans, mb, nb, nnzb, alpha, descr, bsrVal, bsrRowPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: mb, nb, nnzb
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  real(8), device :: x(*)
  real(8), device :: beta ! device or host variable
  real(8), device :: y(*)

5.3.3. cusparseCbsrmv

BSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an (mb*blockDim) x (nb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrVal, bsrRowPtr, and bsrColInd

integer(4) function cusparseCbsrmv(handle, dir, trans, mb, nb, nnzb, alpha, descr, bsrVal, bsrRowPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: mb, nb, nnzb
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  complex(4), device :: x(*)
  complex(4), device :: beta ! device or host variable
  complex(4), device :: y(*)

5.3.4. cusparseZbsrmv

BSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an (mb*blockDim) x (nb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrVal, bsrRowPtr, and bsrColInd

integer(4) function cusparseZbsrmv(handle, dir, trans, mb, nb, nnzb, alpha, &
           descr, bsrVal, bsrRowPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: mb, nb, nnzb
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  complex(8), device :: x(*)
  complex(8), device :: beta ! device or host variable
  complex(8), device :: y(*)

5.3.5. cusparseSbsrxmv

BSRXMV performs a BSRMV and a mask operation.

integer(4) function cusparseSbsrxmv(handle, dir, trans, sizeOfMask, mb, nb, nnzb, alpha, &
           descr, bsrVal, bsrMaskPtr, bsrRowPtr, bsrEndPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: sizeOfMask
  integer :: mb, nb, nnzb
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(4), device :: bsrVal(*)
  integer(4), device :: bsrMaskPtr(*), bsrRowPtr(*), bsrEndPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  real(4), device :: x(*)
  real(4), device :: beta ! device or host variable
  real(4), device :: y(*)

5.3.6. cusparseDbsrxmv

BSRXMV performs a BSRMV and a mask operation.

integer(4) function cusparseDbsrxmv(handle, dir, trans, sizeOfMask, mb, nb, nnzb, alpha, &
           descr, bsrVal, bsrMaskPtr, bsrRowPtr, bsrEndPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: sizeOfMask
  integer :: mb, nb, nnzb
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(8), device :: bsrVal(*)
  integer(4), device :: bsrMaskPtr(*), bsrRowPtr(*), bsrEndPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  real(8), device :: x(*)
  real(8), device :: beta ! device or host variable
  real(8), device :: y(*)

5.3.7. cusparseCbsrxmv

BSRXMV performs a BSRMV and a mask operation.

integer(4) function cusparseCbsrxmv(handle, dir, trans, sizeOfMask, mb, nb, nnzb, alpha, &
           descr, bsrVal, bsrMaskPtr, bsrRowPtr, bsrEndPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: sizeOfMask
  integer :: mb, nb, nnzb
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(4), device :: bsrVal(*)
  integer(4), device :: bsrMaskPtr(*), bsrRowPtr(*), bsrEndPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  complex(4), device :: x(*)
  complex(4), device :: beta ! device or host variable
  complex(4), device :: y(*)

5.3.8. cusparseZbsrxmv

BSRXMV performs a BSRMV and a mask operation.

integer(4) function cusparseZbsrxmv(handle, dir, trans, sizeOfMask, mb, nb, nnzb, alpha, &
           descr, bsrVal, bsrMaskPtr, bsrRowPtr, bsrEndPtr, bsrColInd, blockDim, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: dir
  integer :: trans
  integer :: sizeOfMask
  integer :: mb, nb, nnzb
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(8), device :: bsrVal(*)
  integer(4), device :: bsrMaskPtr(*), bsrRowPtr(*), bsrEndPtr(*)
  integer(4), device :: bsrColInd(*)
  integer :: blockDim
  complex(8), device :: x(*)
  complex(8), device :: beta ! device or host variable
  complex(8), device :: y(*)

5.3.9. cusparseScsrmv

CSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMV

integer(4) function cusparseScsrmv(handle, trans, m, n, nnz, alpha, descr, csrVal, csrRowPtr, csrColInd, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m, n, nnz
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  real(4), device :: x(*)
  real(4), device :: beta ! device or host variable
  real(4), device :: y(*)

5.3.10. cusparseDcsrmv

CSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMV

integer(4) function cusparseDcsrmv(handle, trans, m, n, nnz, alpha, descr, csrVal, csrRowPtr, csrColInd, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m, n, nnz
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  real(8), device :: x(*)
  real(8), device :: beta ! device or host variable
  real(8), device :: y(*)

5.3.11. cusparseCcsrmv

CSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMV

integer(4) function cusparseCcsrmv(handle, trans, m, n, nnz, alpha, descr, csrVal, csrRowPtr, csrColInd, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m, n, nnz
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  complex(4), device :: x(*)
  complex(4), device :: beta ! device or host variable
  complex(4), device :: y(*)

5.3.12. cusparseZcsrmv

CSRMV performs one of the matrix-vector operations y := alpha*A*x + beta*y, or y := alpha*A**T*x + beta*y, where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMV

integer(4) function cusparseZcsrmv(handle, trans, m, n, nnz, alpha, descr, csrVal, csrRowPtr, csrColInd, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m, n, nnz
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  complex(8), device :: x(*)
  complex(8), device :: beta ! device or host variable
  complex(8), device :: y(*)

5.3.13. cusparseScsrsv_analysis

This function performs the analysis phase of csrsv.

integer(4) function cusparseScsrsv_analysis(handle, trans, m, nnz, descr, csrVal, csrRowPtr, csrColInd, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descr
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info

5.3.14. cusparseDcsrsv_analysis

This function performs the analysis phase of csrsv.

integer(4) function cusparseDcsrsv_analysis(handle, trans, m, nnz, descr, csrVal, csrRowPtr, csrColInd, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descr
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info

5.3.15. cusparseCcsrsv_analysis

This function performs the analysis phase of csrsv.

integer(4) function cusparseCcsrsv_analysis(handle, trans, m, nnz, descr, csrVal, csrRowPtr, csrColInd, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descr
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info

5.3.16. cusparseZcsrsv_analysis

This function performs the analysis phase of csrsv.

integer(4) function cusparseZcsrsv_analysis(handle, trans, m, nnz, descr, csrVal, csrRowPtr, csrColInd, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descr
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info

5.3.17. cusparseScsrsv_solve

This function performs the solve phase of csrsv.

integer(4) function cusparseScsrsv_solve(handle, trans, m, alpha, descr, csrVal, csrRowPtr, csrColInd, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info
  real(4), device :: x(*)
  real(4), device :: y(*)

5.3.18. cusparseDcsrsv_solve

This function performs the solve phase of csrsv.

integer(4) function cusparseDcsrsv_solve(handle, trans, m, alpha, descr, csrVal, csrRowPtr, csrColInd, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info
  real(8), device :: x(*)
  real(8), device :: y(*)

5.3.19. cusparseCcsrsv_solve

This function performs the solve phase of csrsv.

integer(4) function cusparseCcsrsv_solve(handle, trans, m, alpha, descr, csrVal, csrRowPtr, csrColInd, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info
  complex(4), device :: x(*)
  complex(4), device :: y(*)

5.3.20. cusparseZcsrsv_solve

This function performs the solve phase of csrsv.

integer(4) function cusparseZcsrsv_solve(handle, trans, m, alpha, descr, csrVal, csrRowPtr, csrColInd, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  integer :: m
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*)
  integer(4), device :: csrColInd(*)
  type(cusparseSolveAnalysisInfo) :: info
  complex(8), device :: x(*)
  complex(8), device :: y(*)

5.3.21. cusparseSgemvi_bufferSize

This function returns the buffer size, in bytes, needed by cusparseSgemvi.

integer(4) function cusparseSgemvi_bufferSize(handle, transA, m, n, nnz, pBufferSize)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, nnz
  integer(4) :: pBufferSize

5.3.22. cusparseDgemvi_bufferSize

This function returns the buffer size, in bytes, needed by cusparseDgemvi.

integer(4) function cusparseDgemvi_bufferSize(handle, transA, m, n, nnz, pBufferSize)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, nnz
  integer(4) :: pBufferSize

5.3.23. cusparseCgemvi_bufferSize

This function returns the buffer size, in bytes, needed by cusparseCgemvi.

integer(4) function cusparseCgemvi_bufferSize(handle, transA, m, n, nnz, pBufferSize)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, nnz
  integer(4) :: pBufferSize

5.3.24. cusparseZgemvi_bufferSize

This function returns the buffer size, in bytes, needed by cusparseZgemvi.

integer(4) function cusparseZgemvi_bufferSize(handle, transA, m, n, nnz, pBufferSize)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, nnz
  integer(4) :: pBufferSize

5.3.25. cusparseSgemvi

GEMVI performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, A is an m x n dense matrix, x is a sparse vector, and y is a dense vector.

integer(4) function cusparseSgemvi(handle, transA, m, n, alpha, A, lda, nnz, xVal, xInd, beta, y, idxBase, pBuffer)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, lda, nnz, idxBase
  real(4), device :: alpha, beta ! device or host variable
  real(4), device :: A(lda,*)
  real(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(4), device :: y(*)
  integer(1), device :: pBuffer(*) ! Any data type is allowed

5.3.26. cusparseDgemvi

GEMVI performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, A is an m x n dense matrix, x is a sparse vector, and y is a dense vector.

integer(4) function cusparseDgemvi(handle, transA, m, n, alpha, A, lda, nnz, xVal, xInd, beta, y, idxBase, pBuffer)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, lda, nnz, idxBase
  real(8), device :: alpha, beta ! device or host variable
  real(8), device :: A(lda,*)
  real(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  real(8), device :: y(*)
  integer(1), device :: pBuffer(*) ! Any data type is allowed

5.3.27. cusparseCgemvi

GEMVI performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, A is an m x n dense matrix, x is a sparse vector, and y is a dense vector.

integer(4) function cusparseCgemvi(handle, transA, m, n, alpha, A, lda, nnz, xVal, xInd, beta, y, idxBase, pBuffer)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, lda, nnz, idxBase
  complex(4), device :: alpha, beta ! device or host variable
  complex(4), device :: A(lda,*)
  complex(4), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(4), device :: y(*)
  integer(1), device :: pBuffer(*) ! Any data type is allowed

5.3.28. cusparseZgemvi

GEMVI performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, A is an m x n dense matrix, x is a sparse vector, and y is a dense vector.

integer(4) function cusparseZgemvi(handle, transA, m, n, alpha, A, lda, nnz, xVal, xInd, beta, y, idxBase, pBuffer)
  type(cusparseHandle) :: handle
  integer :: transA
  integer :: m, n, lda, nnz, idxBase
  complex(8), device :: alpha, beta ! device or host variable
  complex(8), device :: A(lda,*)
  complex(8), device :: xVal(*)
  integer(4), device :: xInd(*)
  complex(8), device :: y(*)
  integer(1), device :: pBuffer(*) ! Any data type is allowed

5.3.29. cusparseShybmv

HYBMV performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in the HYB storage format.

This function was removed in CUDA 11.0.

integer(4) function cusparseShybmv(handle, trans, alpha, descr, hyb, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  real(4), device :: x(*)
  real(4), device :: beta ! device or host variable
  real(4), device :: y(*)

5.3.30. cusparseDhybmv

HYBMV performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in the HYB storage format.

This function was removed in CUDA 11.0.

integer(4) function cusparseDhybmv(handle, trans, alpha, descr, hyb, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  real(8), device :: x(*)
  real(8), device :: beta ! device or host variable
  real(8), device :: y(*)

5.3.31. cusparseChybmv

HYBMV performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in the HYB storage format.

This function was removed in CUDA 11.0.

integer(4) function cusparseChybmv(handle, trans, alpha, descr, hyb, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  complex(4), device :: x(*)
  complex(4), device :: beta ! device or host variable
  complex(4), device :: y(*)

5.3.32. cusparseZhybmv

HYBMV performs the matrix-vector operations y := alpha*A*x + beta*y where alpha and beta are scalars, x and y are vectors and A is an m x n sparse matrix that is defined in the HYB storage format.

This function was removed in CUDA 11.0.

integer(4) function cusparseZhybmv(handle, trans, alpha, descr, hyb, x, beta, y)
  type(cusparseHandle) :: handle
  integer :: trans
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  complex(8), device :: x(*)
  complex(8), device :: beta ! device or host variable
  complex(8), device :: y(*)

5.3.33. cusparseShybsv_analysis

This function performs the analysis phase of hybsv.

integer(4) function cusparseShybsv_analysis(handle, trans, descr, hyb, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info

5.3.34. cusparseDhybsv_analysis

This function performs the analysis phase of hybsv.

integer(4) function cusparseDhybsv_analysis(handle, trans, descr, hyb, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info

5.3.35. cusparseChybsv_analysis

This function performs the analysis phase of hybsv.

integer(4) function cusparseChybsv_analysis(handle, trans, descr, hyb, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info

5.3.36. cusparseZhybsv_analysis

This function performs the analysis phase of hybsv.

integer(4) function cusparseZhybsv_analysis(handle, trans, descr, hyb, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info

5.3.37. cusparseShybsv_solve

This function performs the solve phase of hybsv.

integer(4) function cusparseShybsv_solve(handle, trans, alpha, descr, hyb, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info
  real(4), device :: x(*)
  real(4), device :: y(*)

5.3.38. cusparseDhybsv_solve

This function performs the solve phase of hybsv.

integer(4) function cusparseDhybsv_solve(handle, trans, alpha, descr, hyb, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info
  real(8), device :: x(*)
  real(8), device :: y(*)

5.3.39. cusparseChybsv_solve

This function performs the solve phase of hybsv.

integer(4) function cusparseChybsv_solve(handle, trans, alpha, descr, hyb, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info
  complex(4), device :: x(*)
  complex(4), device :: y(*)

5.3.40. cusparseZhybsv_solve

This function performs the solve phase of hybsv.

integer(4) function cusparseZhybsv_solve(handle, trans, alpha, descr, hyb, info, x, y)
  type(cusparseHandle) :: handle
  integer :: trans
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descr
  type(cusparseHybMat) :: hyb
  type(cusparseSolveAnalysisInfo) :: info
  complex(8), device :: x(*)
  complex(8), device :: y(*)

5.3.41. cusparseSbsrsv2_bufferSize

This function returns the size of the buffer used in bsrsv2.

integer(4) function cusparseSbsrsv2_bufferSize(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.42. cusparseDbsrsv2_bufferSize

This function returns the size of the buffer used in bsrsv2.

integer(4) function cusparseDbsrsv2_bufferSize(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.43. cusparseCbsrsv2_bufferSize

This function returns the size of the buffer used in bsrsv2.

integer(4) function cusparseCbsrsv2_bufferSize(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.44. cusparseZbsrsv2_bufferSize

This function returns the size of the buffer used in bsrsv2.

integer(4) function cusparseZbsrsv2_bufferSize(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.45. cusparseSbsrsv2_analysis

This function performs the analysis phase of bsrsv2.

integer(4) function cusparseSbsrsv2_analysis(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.46. cusparseDbsrsv2_analysis

This function performs the analysis phase of bsrsv2.

integer(4) function cusparseDbsrsv2_analysis(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.47. cusparseCbsrsv2_analysis

This function performs the analysis phase of bsrsv2.

integer(4) function cusparseCbsrsv2_analysis(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.48. cusparseZbsrsv2_analysis

This function performs the analysis phase of bsrsv2.

integer(4) function cusparseZbsrsv2_analysis(handle, dirA, transA, mb, nnzb, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.49. cusparseSbsrsv2_solve

This function performs the solve phase of bsrsv2.

integer(4) function cusparseSbsrsv2_solve(handle, dirA, transA, mb, nnzb, &
           alpha, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, mb, nnzb
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim
  type(cusparseBsrsv2Info) :: info
  real(4), device :: x(*), y(*)
  integer :: policy
  character, device :: pBuffer(*)

5.3.50. cusparseDbsrsv2_solve

This function performs the solve phase of bsrsv2.

integer(4) function cusparseDbsrsv2_solve(handle, dirA, transA, mb, nnzb, &
           alpha, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, mb, nnzb
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim
  type(cusparseBsrsv2Info) :: info
  real(8), device :: x(*), y(*)
  integer :: policy
  character, device :: pBuffer(*)

5.3.51. cusparseCbsrsv2_solve

This function performs the solve phase of bsrsv2.

integer(4) function cusparseCbsrsv2_solve(handle, dirA, transA, mb, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, mb, nnzb
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim
  type(cusparseBsrsv2Info) :: info
  complex(4), device :: x(*), y(*)
  integer :: policy
  character, device :: pBuffer(*)

5.3.52. cusparseZbsrsv2_solve

This function performs the solve phase of bsrsv2.

integer(4) function cusparseZbsrsv2_solve(handle, dirA, transA, mb, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, mb, nnzb
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim
  type(cusparseBsrsv2Info) :: info
  complex(8), device :: x(*), y(*)
  integer :: policy
  character, device :: pBuffer(*)

5.3.53. cusparseXbsrsv2_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXbsrsv2_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseBsrsv2Info) :: info
  integer(4), device :: position ! device or host variable

5.3.54. cusparseScsrsv2_bufferSize

This function returns the size of the buffer used in csrsv2.

integer(4) function cusparseScsrsv2_bufferSize(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.55. cusparseDcsrsv2_bufferSize

This function returns the size of the buffer used in csrsv2.

integer(4) function cusparseDcsrsv2_bufferSize(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.56. cusparseCcsrsv2_bufferSize

This function returns the size of the buffer used in csrsv2.

integer(4) function cusparseCcsrsv2_bufferSize(handle, transA, m, nnz, descrA, csrValA, &
           csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.57. cusparseZcsrsv2_bufferSize

This function returns the size of the buffer used in csrsv2.

integer(4) function cusparseZcsrsv2_bufferSize(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.3.58. cusparseScsrsv2_analysis

This function performs the analysis phase of csrsv2.

integer(4) function cusparseScsrsv2_analysis(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.59. cusparseDcsrsv2_analysis

This function performs the analysis phase of csrsv2.

integer(4) function cusparseDcsrsv2_analysis(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.60. cusparseCcsrsv2_analysis

This function performs the analysis phase of csrsv2.

integer(4) function cusparseCcsrsv2_analysis(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.61. cusparseZcsrsv2_analysis

This function performs the analysis phase of csrsv2.

integer(4) function cusparseZcsrsv2_analysis(handle, transA, m, nnz, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.3.62. cusparseScsrsv2_solve

This function performs the solve phase of csrsv2.

integer(4) function cusparseScsrsv2_solve(handle, transA, m, nnz, alpha, descrA, &
           csrValA, csrRowPtrA, csrColIndA, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*), x(*), y(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer :: policy
  character, device :: pBuffer(*)

5.3.63. cusparseDcsrsv2_solve

This function performs the solve phase of csrsv2.

integer(4) function cusparseDcsrsv2_solve(handle, transA, m, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*), x(*), y(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer :: policy
  character, device :: pBuffer(*)

5.3.64. cusparseCcsrsv2_solve

This function performs the solve phase of csrsv2.

integer(4) function cusparseCcsrsv2_solve(handle, transA, m, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*), x(*), y(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer :: policy
  character, device :: pBuffer(*)

5.3.65. cusparseZcsrsv2_solve

This function performs the solve phase of csrsv2.

integer(4) function cusparseZcsrsv2_solve(handle, transA, m, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, x, y, policy, pBuffer)
  type(cusparseHandle) :: handle
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*), x(*), y(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrsv2Info) :: info
  integer :: policy
  character, device :: pBuffer(*)

5.3.66. cusparseXcsrsv2_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXcsrsv2_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseCsrsv2Info) :: info
  integer(4), device :: position ! device or host variable

5.4. CUSPARSE Level 3 Functions

This section contains interfaces for the level 3 sparse linear algebra functions that perform operations between sparse and dense matrices.

5.4.1. cusparseScsrmm

CSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * B + beta*C, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseScsrmm(handle, transA, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, m, n, k, nnz
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.2. cusparseDcsrmm

CSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * B + beta*C, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseDcsrmm(handle, transA, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, m, n, k, nnz
  real(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.3. cusparseCcsrmm

CSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * B + beta*C, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseCcsrmm(handle, transA, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, m, n, k, nnz
  complex(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.4. cusparseZcsrmm

CSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * B + beta*C, where op( A ) is one of op( A ) = A or op( A ) = A**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseZcsrmm(handle, transA, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, m, n, k, nnz
  complex(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.5. cusparseScsrmm2

CSRMM2 performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( A ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseScsrmm2(handle, transA, transB, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, transB, m, n, k, nnz
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.6. cusparseDcsrmm2

CSRMM2 performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( A ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseDcsrmm2(handle, transA, transB, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, transB, m, n, k, nnz
  real(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.7. cusparseCcsrmm2

CSRMM2 performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( A ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseCcsrmm2(handle, transA, transB, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, transB, m, n, k, nnz
  complex(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.8. cusparseZcsrmm2

CSRMM2 performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( A ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an m x k sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA. B and C are dense matrices.

This function was removed in CUDA 11.0. It should be replaced with a call to cusparseSpMM

integer(4) function cusparseZcsrmm2(handle, transA, transB, m, n, k, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: transA, transB, m, n, k, nnz
  complex(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*), B(*), C(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  integer :: ldb, ldc

5.4.9. cusparseScsrsm_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseScsrsm_analysis(handle, transA, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.4.10. cusparseDcsrsm_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseDcsrsm_analysis(handle, transA, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.4.11. cusparseCcsrsm_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseCcsrsm_analysis(handle, transA, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.4.12. cusparseZcsrsm_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseZcsrsm_analysis(handle, transA, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: transA, m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.4.13. cusparseScsrsm_solve

This function performs the solve phase of csrsm.

integer(4) function cusparseScsrsm_solve(handle, transA, m, n, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, X, ldx, Y, ldy)
  type(cusparseHandle) :: handle
  integer :: transA, m, n
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info
  real(4), device :: X(*), Y(*)
  integer :: ldx, ldy

5.4.14. cusparseDcsrsm_solve

This function performs the solve phase of csrsm.

integer(4) function cusparseDcsrsm_solve(handle, transA, m, n, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, X, ldx, Y, ldy)
  type(cusparseHandle) :: handle
  integer :: transA, m, n
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info
  real(8), device :: X(*), Y(*)
  integer :: ldx, ldy

5.4.15. cusparseCcsrsm_solve

This function performs the solve phase of csrsm.

integer(4) function cusparseCcsrsm_solve(handle, transA, m, n, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, X, ldx, Y, ldy)
  type(cusparseHandle) :: handle
  integer :: transA, m, n
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info
  complex(4), device :: X(*), Y(*)
  integer :: ldx, ldy

5.4.16. cusparseZcsrsm_solve

This function performs the solve phase of csrsm.

integer(4) function cusparseZcsrsm_solve(handle, transA, m, n, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, info, X, ldx, Y, ldy)
  type(cusparseHandle) :: handle
  integer :: transA, m, n
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info
  complex(8), device :: X(*), Y(*)
  integer :: ldx, ldy

5.4.17. cusparseScsrsm2_bufferSizeExt

This function computes the work buffer size needed for the cusparseScsrsm2 routines.

integer(4) function cusparseScsrsm2_bufferSizeExt(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  real(4) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  real(4), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(8) :: pBufferSize

5.4.18. cusparseDcsrsm2_bufferSizeExt

This function computes the work buffer size needed for the cusparseDcsrsm2 routines.

integer(4) function cusparseDcsrsm2_bufferSizeExt(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  real(8) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  real(8), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(8) :: pBufferSize

5.4.19. cusparseCcsrsm2_bufferSizeExt

This function computes the work buffer size needed for the cusparseCcsrsm2 routines.

integer(4) function cusparseCcsrsm2_bufferSizeExt(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  complex(4) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  complex(4), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(8) :: pBufferSize

5.4.20. cusparseZcsrsm2_bufferSizeExt

This function computes the work buffer size needed for the cusparseZcsrsm2 routines.

integer(4) function cusparseZcsrsm2_bufferSizeExt(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  complex(8) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  complex(8), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(8) :: pBufferSize

5.4.21. cusparseScsrsm2_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseScsrsm2_analysis(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  real(4) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  real(4), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.22. cusparseDcsrsm2_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseDcsrsm2_analysis(handle, algo, transA, transB, m, nrhs, nnz, alpha, descrA, &
           csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  real(8) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  real(8), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.23. cusparseCcsrsm2_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseCcsrsm2_analysis(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  complex(4) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  complex(4), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.24. cusparseZcsrsm2_analysis

This function performs the analysis phase of csrsm.

integer(4) function cusparseZcsrsm2_analysis(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  complex(8) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  complex(8), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.25. cusparseScsrsm2_solve

This function performs the solve phase of csrsm2, solving the sparse triangular linear system op(A) * op(X) = alpha * op(B). A is an m x m sparse matrix in CSR storage format; B and X are the right-hand side matrix and the solution matrix, and B is overwritten with X.

integer(4) function cusparseScsrsm2_solve(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  real(4) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  real(4), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.26. cusparseDcsrsm2_solve

This function performs the solve phase of csrsm2, solving the sparse triangular linear system op(A) * op(X) = alpha * op(B). A is an m x m sparse matrix in CSR storage format; B and X are the right-hand side matrix and the solution matrix, and B is overwritten with X.

integer(4) function cusparseDcsrsm2_solve(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  real(8) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  real(8), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.27. cusparseCcsrsm2_solve

This function performs the solve phase of csrsm2, solving the sparse triangular linear system op(A) * op(X) = alpha * op(B). A is an m x m sparse matrix in CSR storage format; B and X are the right-hand side matrix and the solution matrix, and B is overwritten with X.

integer(4) function cusparseCcsrsm2_solve(handle, algo, transA, transB, m, nrhs, nnz, alpha, descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  complex(4) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  complex(4), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.28. cusparseZcsrsm2_solve

This function performs the solve phase of csrsm2, solving the sparse triangular linear system op(A) * op(X) = alpha * op(B). A is an m x m sparse matrix in CSR storage format; B and X are the right-hand side matrix and the solution matrix, and B is overwritten with X.

integer(4) function cusparseZcsrsm2_solve(handle, algo, transA, transB, m, nrhs, nnz, alpha, &
           descrA, csrValA, csrRowPtrA, csrColIndA, B, ldb, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, transA, transB, m, nrhs, nnz, ldb, policy
  complex(8) :: alpha ! host or device variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  complex(8), device :: B(ldb,*)
  type(cusparseCsrsm2Info) :: info
  integer(1), device :: pBuffer ! Any data type

5.4.29. cusparseXcsrsm2_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXcsrsm2_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseCsrsm2Info) :: info
  integer(4), device :: position ! device or host variable

5.4.30. cusparseSbsrmm

BSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an mb x kb sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA. B and C are dense matrices.

integer(4) function cusparseSbsrmm(handle, dirA, transA, transB, mb, n, kb, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transB, mb, n, kb, nnzb, blockDim
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*), B(*), C(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: ldb, ldc

5.4.31. cusparseDbsrmm

BSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an mb x kb sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA. B and C are dense matrices.

integer(4) function cusparseDbsrmm(handle, dirA, transA, transB, mb, n, kb, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transB, mb, n, kb, nnzb, blockDim
  real(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*), B(*), C(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: ldb, ldc

5.4.32. cusparseCbsrmm

BSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an mb x kb sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA. B and C are dense matrices.

integer(4) function cusparseCbsrmm(handle, dirA, transA, transB, mb, n, kb, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transB, mb, n, kb, nnzb, blockDim
  complex(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*), B(*), C(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: ldb, ldc

5.4.33. cusparseZbsrmm

BSRMM performs one of the matrix-matrix operations C := alpha*op( A ) * op( B ) + beta*C, where op( X ) is one of op( X ) = X or op( X ) = X**T, alpha and beta are scalars. A is an mb x kb sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA. B and C are dense matrices.

integer(4) function cusparseZbsrmm(handle, dirA, transA, transB, mb, n, kb, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, B, ldb, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transB, mb, n, kb, nnzb, blockDim
  complex(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*), B(*), C(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: ldb, ldc

5.4.34. cusparseSbsrsm2_bufferSize

This function returns the size of the buffer used in bsrsm2.

integer(4) function cusparseSbsrsm2_bufferSize(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.4.35. cusparseDbsrsm2_bufferSize

This function returns the size of the buffer used in bsrsm2.

integer(4) function cusparseDbsrsm2_bufferSize(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.4.36. cusparseCbsrsm2_bufferSize

This function returns the size of the buffer used in bsrsm2.

integer(4) function cusparseCbsrsm2_bufferSize(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.4.37. cusparseZbsrsm2_bufferSize

This function returns the size of the buffer used in bsrsm2.

integer(4) function cusparseZbsrsm2_bufferSize(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.4.38. cusparseSbsrsm2_analysis

This function performs the analysis phase of bsrsm2.

integer(4) function cusparseSbsrsm2_analysis(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.4.39. cusparseDbsrsm2_analysis

This function performs the analysis phase of bsrsm2.

integer(4) function cusparseDbsrsm2_analysis(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.4.40. cusparseCbsrsm2_analysis

This function performs the analysis phase of bsrsm2.

integer(4) function cusparseCbsrsm2_analysis(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.4.41. cusparseZbsrsm2_analysis

This function performs the analysis phase of bsrsm2.

integer(4) function cusparseZbsrsm2_analysis(handle, dirA, transA, transX, mb, n, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, transA, transX, mb, n, nnzb, blockDim
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  type(cusparseBsrsm2Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.4.42. cusparseSbsrsm2_solve

This function performs the solve phase of bsrsm2.

integer(4) function cusparseSbsrsm2_solve(handle, dirA, transA, transX, mb, n, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, ldx, y, ldy, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transX, mb, n, nnzb
  real(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*), x(*), y(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim, policy, ldx, ldy
  type(cusparseBsrsm2Info) :: info
  character, device :: pBuffer(*)

5.4.43. cusparseDbsrsm2_solve

This function performs the solve phase of bsrsm2.

integer(4) function cusparseDbsrsm2_solve(handle, dirA, transA, transX, mb, n, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, ldx, y, ldy, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transX, mb, n, nnzb
  real(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*), x(*), y(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim, policy, ldx, ldy
  type(cusparseBsrsm2Info) :: info
  character, device :: pBuffer(*)

5.4.44. cusparseCbsrsm2_solve

This function performs the solve phase of bsrsm2.

integer(4) function cusparseCbsrsm2_solve(handle, dirA, transA, transX, mb, n, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, ldx, y, ldy, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transX, mb, n, nnzb
  complex(4), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*), x(*), y(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim, policy, ldx, ldy
  type(cusparseBsrsm2Info) :: info
  character, device :: pBuffer(*)

5.4.45. cusparseZbsrsm2_solve

This function performs the solve phase of bsrsm2.

integer(4) function cusparseZbsrsm2_solve(handle, dirA, transA, transX, mb, n, nnzb, alpha, &
           descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, x, ldx, y, ldy, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dirA, transA, transX, mb, n, nnzb
  complex(8), device :: alpha ! device or host variable
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*), x(*), y(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: blockDim, policy, ldx, ldy
  type(cusparseBsrsm2Info) :: info
  character, device :: pBuffer(*)

5.4.46. cusparseXbsrsm2_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXbsrsm2_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseBsrsm2Info) :: info
  integer(4), device :: position ! device or host variable

5.4.47. cusparseSgemmi

GEMMI performs the matrix-matrix operations C := alpha*A*B + beta*C where alpha and beta are scalars, A is an m x k dense matrix, B is a k x n sparse matrix, and C is a m x n dense matrix. Fortran programmers should be aware that this function only uses zero-based indexing for B.

This function is deprecated, and will be removed in a future release. It is recommended to use cusparseSpMM instead.

integer(4) function cusparseSgemmi(handle, m, n, k, nnz, alpha, &
           A, lda, cscValB, cscColPtrB, cscRowIndB, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: m, n, k, nnz, lda, ldc
  real(4), device :: alpha, beta ! device or host variable
  real(4), device :: A(lda,*)
  real(4), device :: cscValB(*)
  real(4), device :: C(ldc,*)
  integer(4), device :: cscColPtrB(*), cscRowIndB(*)

5.4.48. cusparseDgemmi

GEMMI performs the matrix-matrix operations C := alpha*A*B + beta*C where alpha and beta are scalars, A is an m x k dense matrix, B is a k x n sparse matrix, and C is a m x n dense matrix. Fortran programmers should be aware that this function only uses zero-based indexing for B.

This function is deprecated, and will be removed in a future release. It is recommended to use cusparseSpMM instead.

integer(4) function cusparseDgemmi(handle, m, n, k, nnz, alpha, &
           A, lda, cscValB, cscColPtrB, cscRowIndB, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: m, n, k, nnz, lda, ldc
  real(8), device :: alpha, beta ! device or host variable
  real(8), device :: A(lda,*)
  real(8), device :: cscValB(*)
  real(8), device :: C(ldc,*)
  integer(4), device :: cscColPtrB(*), cscRowIndB(*)

5.4.49. cusparseCgemmi

GEMMI performs the matrix-matrix operations C := alpha*A*B + beta*C where alpha and beta are scalars, A is an m x k dense matrix, B is a k x n sparse matrix, and C is a m x n dense matrix. Fortran programmers should be aware that this function only uses zero-based indexing for B.

This function is deprecated, and will be removed in a future release. It is recommended to use cusparseSpMM instead.

integer(4) function cusparseCgemmi(handle, m, n, k, nnz, alpha, &
           A, lda, cscValB, cscColPtrB, cscRowIndB, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: m, n, k, nnz, lda, ldc
  complex(4), device :: alpha, beta ! device or host variable
  complex(4), device :: A(lda,*)
  complex(4), device :: cscValB(*)
  complex(4), device :: C(ldc,*)
  integer(4), device :: cscColPtrB(*), cscRowIndB(*)

5.4.50. cusparseZgemmi

GEMMI performs the matrix-matrix operations C := alpha*A*B + beta*C where alpha and beta are scalars, A is an m x k dense matrix, B is a k x n sparse matrix, and C is a m x n dense matrix. Fortran programmers should be aware that this function only uses zero-based indexing for B.

This function is deprecated, and will be removed in a future release. It is recommended to use cusparseSpMM instead.

integer(4) function cusparseZgemmi(handle, m, n, k, nnz, alpha, &
           A, lda, cscValB, cscColPtrB, cscRowIndB, beta, C, ldc)
  type(cusparseHandle) :: handle
  integer :: m, n, k, nnz, lda, ldc
  complex(8), device :: alpha, beta ! device or host variable
  complex(8), device :: A(lda,*)
  complex(8), device :: cscValB(*)
  complex(8), device :: C(ldc,*)
  integer(4), device :: cscColPtrB(*), cscRowIndB(*)

5.5. CUSPARSE Extra Functions

This section contains interfaces for the extra functions that are used to manipulate sparse matrices.

5.5.1. cusparseXcsrgeamNnz

cusparseXcsrgeamNnz computes the number of nonzero elements which will be produced by CSRGEAM.

This function was removed in CUDA 11.0. It should be replaced with cusparseXcsrgeam2Nnz

integer(4) function cusparseXcsrgeamNnz(handle, m, n, descrA, nnzA, csrRowPtrA, csrColIndA, descrB, nnzB, csrRowPtrB, csrColIndB, descrC, csrRowPtrC, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  type(cusparseMatDescr) :: descrA, descrB, descrC
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.5.2. cusparseScsrgeam

CSRGEAM performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeamNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseScsrgeam2 routines

integer(4) function cusparseScsrgeam(handle, m, n, &
           alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  real(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.3. cusparseDcsrgeam

CSRGEAM performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeamNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseDcsrgeam2 routines

integer(4) function cusparseDcsrgeam(handle, m, n, &
           alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  real(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  real(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.4. cusparseCcsrgeam

CSRGEAM performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeamNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseCcsrgeam2 routines

integer(4) function cusparseCcsrgeam(handle, m, n, &
        alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
        beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  complex(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  complex(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.5. cusparseZcsrgeam

CSRGEAM performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeamNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseZcsrgeam2 routines

integer(4) function cusparseZcsrgeam(handle, m, n, alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  complex(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  complex(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.6. cusparseScsrgeam2_bufferSizeExt

This function determines the work buffer size for cusparseScsrgeam2. CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseScsrgeam2_bufferSizeExt(handle, m, n, alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  real(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(8) :: pBufferSizeInBytes

5.5.7. cusparseDcsrgeam2_bufferSizeExt

This function determines the work buffer size for cusparseDcsrgeam2. CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseDcsrgeam2_bufferSizeExt(handle, m, n, alpha, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, beta, descrB, nnzB, &
           csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  real(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  real(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(8) :: pBufferSizeInBytes

5.5.8. cusparseCcsrgeam2_bufferSizeExt

This function determines the work buffer size for cusparseCcsrgeam2. CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseCcsrgeam2_bufferSizeExt(handle, m, n, alpha, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, beta, descrB, nnzB, &
           csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  complex(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  complex(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(8) :: pBufferSizeInBytes

5.5.9. cusparseZcsrgeam2_bufferSizeExt

This function determines the work buffer size for cusparseZcsrgeam2. CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseZcsrgeam2_bufferSizeExt(handle, m, n, alpha, descrA, &
           nnzA, csrValA, csrRowPtrA, csrColIndA, beta, descrB, nnzB, csrValB, &
           csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  complex(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  complex(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(8) :: pBufferSizeInBytes

5.5.10. cusparseXcsrgeam2Nnz

cusparseXcsrgeam2Nnz computes the number of nonzero elements which will be produced by CSRGEAM2.

integer(4) function cusparseXcsrgeam2Nnz(handle, m, n, descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, descrC, csrRowPtrC, nnzTotalDevHostPtr, pBuffer)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA, descrB, descrC
  integer(4) :: m, n, nnzA, nnzB
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*)
  integer(c_int) :: nnzTotalDevHostPtr
  character(c_char), device :: pBuffer(*)

5.5.11. cusparseScsrgeam2

CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseCcsrgeam2(handle, m, n, alpha, descrA, nnzA, csrValA, csrRowPtrA, &
           csrColIndA, beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBuffer)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  real(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(1), device :: pBuffer ! can be of any type

5.5.12. cusparseDcsrgeam2

CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseCcsrgeam2(handle, m, n, alpha, descrA, nnzA, csrValA, csrRowPtrA, &
           csrColIndA, beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBuffer)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  real(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  real(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(1), device :: pBuffer ! can be of any type

5.5.13. cusparseCcsrgeam2

CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseCcsrgeam2(handle, m, n, alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBuffer)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  complex(4), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  complex(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(1), device :: pBuffer ! can be of any type

5.5.14. cusparseZcsrgeam2

CSRGEAM2 performs the matrix-matrix operation C := alpha * A + beta * B, alpha and beta are scalars. A, B, and C are m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgeam2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseCcsrgeam2(handle, m, n, alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           beta, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, descrC, csrValC, csrRowPtrC, csrColIndC, pBuffer)
  type(cusparseHandle) :: handle
  integer :: m, n, nnzA, nnzB
  complex(8), device :: alpha, beta ! device or host variable
  type(cusparseMatDescr):: descrA, descrB, descrC
  complex(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)
  integer(1), device :: pBuffer ! can be of any type

5.5.15. cusparseXcsrgemmNnz

cusparseXcsrgemmNnz computes the number of nonzero elements which will be produced by CSRGEMM.

This function was removed in CUDA 11.0. It should be replaced with the cusparseXcsrgemm2Nnz routines

integer(4) function cusparseXcsrgemmNnz(handle, transA, transB, m, n, k, &
           descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, descrC, csrRowPtrC, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: transA, transB, m, n, k, nnzA, nnzB
  type(cusparseMatDescr) :: descrA, descrB, descrC
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.5.16. cusparseScsrgemm

CSRGEMM performs the matrix-matrix operation C := op( A ) * op( B ), where op( X ) is one of op( X ) = X or op( X ) = X**T, A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgemmNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseScsrgemm2 routines

integer(4) function cusparseScsrgemm(handle, transA, transB, m, n, k, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, &
           descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: transA, transB, m, n, k, nnzA, nnzB
  type(cusparseMatDescr) :: descrA, descrB, descrC
  real(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.17. cusparseDcsrgemm

CSRGEMM performs the matrix-matrix operation C := op( A ) * op( B ), where op( X ) is one of op( X ) = X or op( X ) = X**T, A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgemmNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseDcsrgemm2 routines

integer(4) function cusparseDcsrgemm(handle, transA, transB, m, n, k, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, &
           descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: transA, transB, m, n, k, nnzA, nnzB
  type(cusparseMatDescr) :: descrA, descrB, descrC
  real(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.18. cusparseCcsrgemm

CSRGEMM performs the matrix-matrix operation C := op( A ) * op( B ), where op( X ) is one of op( X ) = X or op( X ) = X**T, A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgemmNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseCcsrgemm2 routines

integer(4) function cusparseCcsrgemm(handle, transA, transB, m, n, k, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, &
           descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: transA, transB, m, n, k, nnzA, nnzB
  type(cusparseMatDescr) :: descrA, descrB, descrC
  complex(4), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.19. cusparseZcsrgemm

CSRGEMM performs the matrix-matrix operation C := op( A ) * op( B ), where op( X ) is one of op( X ) = X or op( X ) = X**T, A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C}, csrRowPtr{A|B|C}, and csrColInd{A|B|C}. cusparseXcsrgemmNnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

This function was removed in CUDA 11.0. It should be replaced with the cusparseZcsrgemm2 routines

integer(4) function cusparseZcsrgemm(handle, transA, transB, m, n, k, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, &
           descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: transA, transB, m, n, k, nnzA, nnzB
  type(cusparseMatDescr) :: descrA, descrB, descrC
  complex(8), device :: csrValA(*), csrValB(*), csrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrC(*), csrColIndC(*)

5.5.20. cusparseScsrgemm2_bufferSizeExt

This function returns the size of the buffer used in csrgemm2.

integer(4) function cusparseScsrgemm2_bufferSizeExt(handle, m, n, k, alpha, &
           descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrRowPtrD, csrColIndD, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  real(4), device :: alpha, beta ! device or host variable
  integer :: m, n, k, nnzA, nnzB, nnzD
  type(cusparseMatDescr) :: descrA, descrB, descrD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*)
  type(cusparseCsrgemm2Info) :: info
  integer(8) :: pBufferSizeInBytes

5.5.21. cusparseDcsrgemm2_bufferSizeExt

This function returns the size of the buffer used in csrgemm2.

integer(4) function cusparseDcsrgemm2_bufferSizeExt(handle, m, n, k, alpha, &
           descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrRowPtrD, csrColIndD, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  real(8), device :: alpha, beta ! device or host variable
  integer :: m, n, k, nnzA, nnzB, nnzD
  type(cusparseMatDescr) :: descrA, descrB, descrD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*)
  type(cusparseCsrgemm2Info) :: info
  integer(8) :: pBufferSizeInBytes

5.5.22. cusparseCcsrgemm2_bufferSizeExt

This function returns the size of the buffer used in csrgemm2.

integer(4) function cusparseCcsrgemm2_bufferSizeExt(handle, m, n, k, alpha, &
           descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrRowPtrD, csrColIndD, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  complex(4), device :: alpha, beta ! device or host variable
  integer :: m, n, k, nnzA, nnzB, nnzD
  type(cusparseMatDescr) :: descrA, descrB, descrD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*)
  type(cusparseCsrgemm2Info) :: info
  integer(8) :: pBufferSizeInBytes

5.5.23. cusparseZcsrgemm2_bufferSizeExt

This function returns the size of the buffer used in csrgemm2.

integer(4) function cusparseZcsrgemm2_bufferSizeExt(handle, m, n, k, alpha, &
           descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrRowPtrD, csrColIndD, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  complex(8), device :: alpha, beta ! device or host variable
  integer :: m, n, k, nnzA, nnzB, nnzD
  type(cusparseMatDescr) :: descrA, descrB, descrD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*)
  type(cusparseCsrgemm2Info) :: info
  integer(8) :: pBufferSizeInBytes

5.5.24. cusparseXcsrgemm2Nnz

cusparseXcsrgemm2Nnz computes the number of nonzero elements which will be produced by CSRGEMM2.

integer(4) function cusparseXcsrgemm2Nnz(handle, m, n, k, &
           descrA, nnzA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrRowPtrB, csrColIndB, &
           descrD, nnzD, csrRowPtrD, csrColIndD, &
           descrC, csrRowPtrC, nnzTotalDevHostPtr, info, pBuffer)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA, descrB, descrD, descrC
  type(cusparseCsrgemm2Info) :: info
  integer(4) :: m, n, k, nnzA, nnzB, nnzD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*), csrRowPtrC(*)
  integer(c_int) :: nnzTotalDevHostPtr
  character(c_char), device :: pBuffer(*)

5.5.25. cusparseScsrgemm2

CSRGEMM2 performs the matrix-matrix operation C := alpha * A * B + beta * D alpha and beta are scalars. A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C|D}, csrRowPtr{A|B|C|D}, and csrColInd{A|B|C|D}. cusparseXcsrgemm2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseScsrgemm2(handle, m, n, k, alpha, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrValD, csrRowPtrD, csrColIndD, &
           descrC, csrValC, csrRowPtrC, csrColIndC, info, pBuffer)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA, descrB, descrD, descrC
  type(cusparseCsrgemm2Info) :: info
  integer :: m, n, k, nnzA, nnzB, nnzD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*), csrRowPtrC(*), csrColIndC(*)
  real(4), device :: csrValA(*), csrValB(*), csrValD(*), csrValC(*)
  real(4), device :: alpha, beta ! device or host variable
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable
  character, device :: pBuffer(*)

5.5.26. cusparseDcsrgemm2

CSRGEMM2 performs the matrix-matrix operation C := alpha * A * B + beta * D alpha and beta are scalars. A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C|D}, csrRowPtr{A|B|C|D}, and csrColInd{A|B|C|D}. cusparseXcsrgemm2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseDcsrgemm2(handle, m, n, k, alpha, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrValD, csrRowPtrD, csrColIndD, &
           descrC, csrValC, csrRowPtrC, csrColIndC, info, pBuffer)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA, descrB, descrD, descrC
  type(cusparseCsrgemm2Info) :: info
  integer :: m, n, k, nnzA, nnzB, nnzD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*), csrRowPtrC(*), csrColIndC(*)
  real(8), device :: csrValA(*), csrValB(*), csrValD(*), csrValC(*)
  real(8), device :: alpha, beta ! device or host variable
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable
  character, device :: pBuffer(*)

5.5.27. cusparseCcsrgemm2

CSRGEMM2 performs the matrix-matrix operation C := alpha * A * B + beta * D alpha and beta are scalars. A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C|D}, csrRowPtr{A|B|C|D}, and csrColInd{A|B|C|D}. cusparseXcsrgemm2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseCcsrgemm2(handle, m, n, k, alpha, &
           descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, &
           descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, beta, &
           descrD, nnzD, csrValD, csrRowPtrD, csrColIndD, &
           descrC, csrValC, csrRowPtrC, csrColIndC, info, pBuffer)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA, descrB, descrD, descrC
  type(cusparseCsrgemm2Info) :: info
  integer :: m, n, k, nnzA, nnzB, nnzD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), csrRowPtrB(*), csrColIndB(*), csrRowPtrD(*), csrColIndD(*), csrRowPtrC(*), csrColIndC(*)
  complex(4), device :: csrValA(*), csrValB(*), csrValD(*), csrValC(*)
  complex(4), device :: alpha, beta ! device or host variable
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable
  character, device :: pBuffer(*)

5.5.28. cusparseZcsrgemm2

CSRGEMM2 performs the matrix-matrix operation C := alpha * A * B + beta * D alpha and beta are scalars. A, B, and C are m x k, k x n, and m x n sparse matrices that are defined in CSR storage format by the three arrays csrVal{A|B|C|D}, csrRowPtr{A|B|C|D}, and csrColInd{A|B|C|D}. cusparseXcsrgemm2Nnz should be used to determine csrRowPtrC and the number of nonzero elements in the result.

integer(4) function cusparseZcsrgemm2(handle, m, n, k, alpha, descrA, nnzA, csrValA, csrRowPtrA, csrColIndA, descrB, nnzB, csrValB, csrRowPtrB, csrColIndB, beta, descrD, nnzD, csrValD, csrRowPtrD, csrColIndD, descrC, csrValC, csrRowPtrC, csrColIndC, info, pBuffer)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA, descrB, descrD, descrC
  type(cusparseCsrgemm2Info) :: info
  integer :: m, n, k, nnzA, nnzB, nnzD
  integer(4), device :: csrRowPtrA(*), csrColIndA(*),   csrRowPtrB(*), csrColIndB(*),   csrRowPtrD(*), csrColIndD(*), csrRowPtrC(*), csrColIndC(*)
  complex(8), device :: csrValA(*), csrValB(*), csrValD(*), csrValC(*)
  complex(8), device :: alpha, beta ! device or host variable
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable
  character, device :: pBuffer(*)

5.6. CUSPARSE Preconditioning Functions

This section contains interfaces for the preconditioning functions that are used in processing sparse matrices.

5.6.1. cusparseScsric0

CSRIC0 computes the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an m x n Hermitian/symmetric positive definite sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseScsric0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.2. cusparseDcsric0

CSRIC0 computes the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an m x n Hermitian/symmetric positive definite sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseDcsric0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.3. cusparseCcsric0

CSRIC0 computes the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an m x n Hermitian/symmetric positive definite sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseCcsric0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.4. cusparseZcsric0

CSRIC0 computes the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an m x n Hermitian/symmetric positive definite sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseZcsric0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.5. cusparseScsrilu0

CSRILU0 computes the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseScsrilu0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.6. cusparseDcsrilu0

CSRILU0 computes the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseDcsrilu0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.7. cusparseCcsrilu0

CSRILU0 computes the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseCcsrilu0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.8. cusparseZcsrilu0

CSRILU0 computes the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x n sparse matrix that is defined in CSR storage format by the three arrays csrValA, csrRowPtrA, and csrColIndA.

integer(4) function cusparseZcsrilu0(handle, trans, m, descrA, csrValM, csrRowPtrA, csrColIndA, info)
  type(cusparseHandle) :: handle
  integer(4) :: trans, m
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValM(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseSolveAnalysisInfo) :: info

5.6.9. cusparseSgtsv

GTSV computes the solution of a tridiagonal linear system with multiple right hand sides: A * Y = a * x The coefficient matrix A of this tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix X. The solution Y overwrites the righthand-side matrix X on exit.

This function was removed in CUDA 11.0. It and routines like it should be replaced with the cusparseSgtsv2 variants.

integer(4) function cusparseSgtsv(handle, m, n, dl, d, du, B, ldb)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(4), device :: dl(*), d(*), du(*), B(*)

5.6.10. cusparseDgtsv

GTSV computes the solution of a tridiagonal linear system with multiple right hand sides: A * Y = a * x The coefficient matrix A of this tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix X. The solution Y overwrites the righthand-side matrix X on exit.

This function was removed in CUDA 11.0. It and routines like it should be replaced with the cusparseDgtsv2 variants.

integer(4) function cusparseDgtsv(handle, m, n, dl, d, du, B, ldb)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(8), device :: dl(*), d(*), du(*), B(*)

5.6.11. cusparseCgtsv

GTSV computes the solution of a tridiagonal linear system with multiple right hand sides: A * Y = a * x The coefficient matrix A of this tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix X. The solution Y overwrites the righthand-side matrix X on exit.

This function was removed in CUDA 11.0. It and routines like it should be replaced with the cusparseCgtsv2 variants.

integer(4) function cusparseCgtsv(handle, m, n, dl, d, du, B, ldb)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(4), device :: dl(*), d(*), du(*), B(*)

5.6.12. cusparseZgtsv

GTSV computes the solution of a tridiagonal linear system with multiple right hand sides: A * Y = a * x The coefficient matrix A of this tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix X. The solution Y overwrites the righthand-side matrix X on exit.

This function was removed in CUDA 11.0. It and routines like it should be replaced with the cusparseZgtsv2 variants.

integer(4) function cusparseZgtsv(handle, m, n, dl, d, du, B, ldb)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(8), device :: dl(*), d(*), du(*), B(*)

5.6.13. cusparseSgtsv2_buffersize

Sgtsv2_buffersize returns the size of the buffer, in bytes, required in Sgtsv2().

integer(4) function cusparseSgtsv2_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(4), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.14. cusparseDgtsv2_buffersize

Dgtsv2_buffersize returns the size of the buffer, in bytes, required in Dgtsv2().

integer(4) function cusparseDgtsv2_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(8), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.15. cusparseCgtsv2_buffersize

Cgtsv2_buffersize returns the size of the buffer, in bytes, required in Cgtsv2().

integer(4) function cusparseCgtsv2_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(4), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.16. cusparseZgtsv2_buffersize

Zgtsv2_buffersize returns the size of the buffer, in bytes, required in Zgtsv2().

integer(4) function cusparseZgtsv2_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(8), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.17. cusparseSgtsv2

Sgtsv2 computes the solution of a tridiagonal linear system with multiple right hand sides: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseSgtsv2(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(4), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.18. cusparseDgtsv2

Dgtsv2 computes the solution of a tridiagonal linear system with multiple right hand sides: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseDgtsv2(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(8), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.19. cusparseCgtsv2

Cgtsv2 computes the solution of a tridiagonal linear system with multiple right hand sides: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseCgtsv2(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(4), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.20. cusparseZgtsv2

Zgtsv2 computes the solution of a tridiagonal linear system with multiple right hand sides: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseZgtsv2(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(8), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.21. cusparseSgtsv2_nopivot_buffersize

Sgtsv2_nopivot_buffersize returns the size of the buffer, in bytes, required in Sgtsv2_nopivot().

integer(4) function cusparseSgtsv2_nopivot_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(4), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.22. cusparseDgtsv2_nopivot_buffersize

Dgtsv2_nopivot_buffersize returns the size of the buffer, in bytes, required in Dgtsv2_nopivot().

integer(4) function cusparseDgtsv2_nopivot_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(8), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.23. cusparseCgtsv2_nopivot_buffersize

Cgtsv2_nopivot_buffersize returns the size of the buffer, in bytes, required in Cgtsv2_nopivot().

integer(4) function cusparseCgtsv2_nopivot_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(4), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.24. cusparseZgtsv2_nopivot_buffersize

Zgtsv2_nopivot_buffersize returns the size of the buffer, in bytes, required in Zgtsv2_nopivot().

integer(4) function cusparseZgtsv2_nopivot_bufferSize(handle, m, n, dl, d, du, B, ldb, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(8), device :: dl(m), d(m), du(m), B(ldb,n)
  integer(8) :: pBufferSizeInBytes

5.6.25. cusparseSgtsv2_nopivot

Sgtsv2_nopivot computes the solution of a tridiagonal linear system with multiple right hand sides, without pivoting: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseSgtsv2_nopivot(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(4), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.26. cusparseDgtsv2_nopivot

Dgtsv2_nopivot computes the solution of a tridiagonal linear system with multiple right hand sides, without pivoting: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseDgtsv2_nopivot(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  real(8), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.27. cusparseCgtsv2_nopivot

Cgtsv2_nopivot computes the solution of a tridiagonal linear system with multiple right hand sides, without pivoting: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseCgtsv2_nopivot(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(4), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.28. cusparseZgtsv2_nopivot

Zgtsv2_nopivot computes the solution of a tridiagonal linear system with multiple right hand sides, without pivoting: A * X = B The coefficient matrix A of the tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. The input m is the size of the linear system. The input n is the number or right-hand sides in B.

integer(4) function cusparseZgtsv2_nopivot(handle, m, n, dl, d, du, B, ldb, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, ldb
  complex(8), device :: dl(m), d(m), du(m), B(ldb,n)
  character(1), device :: pBuffer(*)

5.6.29. cusparseSgtsv2StridedBatch_buffersize

Sgtsv2StridedBatch_buffersize returns the size of the buffer, in bytes, required in Sgtsv2StridedBatch().

integer(4) function cusparseSgtsv2StridedBatch_bufferSize(handle, m, dl, d, du, x, batchCount, batchStride, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  real(4), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.30. cusparseDgtsv2StridedBatch_buffersize

Dgtsv2StridedBatch_buffersize returns the size of the buffer, in bytes, required in Dgtsv2StridedBatch().

integer(4) function cusparseDgtsv2StridedBatch_bufferSize(handle, m, dl, d, du, x, batchCount, batchStride, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  real(8), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.31. cusparseCgtsv2StridedBatch_buffersize

Cgtsv2StridedBatch_buffersize returns the size of the buffer, in bytes, required in Cgtsv2StridedBatch().

integer(4) function cusparseCgtsv2StridedBatch_bufferSize(handle, m, dl, d, du, x, batchCount, batchStride, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  complex(4), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.32. cusparseZgtsv2StridedBatch_buffersize

Zgtsv2StridedBatch_buffersize returns the size of the buffer, in bytes, required in Zgtsv2StridedBatch().

integer(4) function cusparseZgtsv2StridedBatch_bufferSize(handle, m, dl, d, du, x, batchCount, batchStride, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  complex(8), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.33. cusparseSgtsv2StridedBatch

Sgtsv2StridedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit.

integer(4) function cusparseSgtsv2StridedBatch(handle, m, dl, d, du, x, batchCount, batchStride, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  real(4), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.34. cusparseDgtsv2StridedBatch

Dgtsv2StridedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit.

integer(4) function cusparseDgtsv2StridedBatch(handle, m, dl, d, du, x, batchCount, batchStride, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  real(8), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.35. cusparseCgtsv2StridedBatch

Cgtsv2StridedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit.

integer(4) function cusparseCgtsv2StridedBatch(handle, m, dl, d, du, x, batchCount, batchStride, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  complex(4), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.36. cusparseZgtsv2StridedBatch

Zgtsv2StridedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit.

integer(4) function cusparseZgtsv2StridedBatch(handle, m, dl, d, du, x, batchCount, batchStride, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, batchCount, batchStride
  complex(8), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.37. cusparseSgtsvInterleavedBatch_buffersize

SgtsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in SgtsvInterleavedBatch().

integer(4) function cusparseSgtsvInterleavedBatch_bufferSize(handle, algo, m, dl, d, du, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(4), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.38. cusparseDgtsvInterleavedBatch_buffersize

DgtsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in DgtsvInterleavedBatch().

integer(4) function cusparseDgtsvInterleavedBatch_bufferSize(handle, algo, m, dl, d, du, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(8), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.39. cusparseCgtsvInterleavedBatch_buffersize

CgtsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in CgtsvInterleavedBatch().

integer(4) function cusparseCgtsvInterleavedBatch_bufferSize(handle, algo, m, dl, d, du, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(4), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.40. cusparseZgtsvInterleavedBatch_buffersize

ZgtsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in ZgtsvInterleavedBatch().

integer(4) function cusparseZgtsvInterleavedBatch_bufferSize(handle, algo, m, dl, d, du, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(8), device :: dl(*), d(*), du(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.41. cusparseSgtsvInterleavedBatch

SgtsvInterleavedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from the SgtsvStridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseSgtsvInterleavedBatch(handle, algo, m, dl, d, du, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(4), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.42. cusparseDgtsvInterleavedBatch

DgtsvInterleavedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from the DgtsvStridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseDgtsvInterleavedBatch(handle, algo, m, dl, d, du, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(8), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.43. cusparseCgtsvInterleavedBatch

CgtsvInterleavedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from the CgtsvStridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseCgtsvInterleavedBatch(handle, algo, m, dl, d, du, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(4), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.44. cusparseZgtsvInterleavedBatch

ZgtsvInterleavedBatch computes the solution of multiple tridiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each tri-diagonal linear system is defined with three vectors corresponding to its lower (dl), main (d), and upper (du) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from the ZgtsvStridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseZgtsvInterleavedBatch(handle, algo, m, dl, d, du, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(8), device :: dl(*), d(*), du(*), x(*)
  character(1), device :: pBuffer(*)

5.6.45. cusparseSgpsvInterleavedBatch_buffersize

SgpsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in SgpsvInterleavedBatch().

integer(4) function cusparseSgpsvInterleavedBatch_bufferSize(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(4), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.46. cusparseDgpsvInterleavedBatch_buffersize

DgpsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in DgpsvInterleavedBatch().

integer(4) function cusparseDgpsvInterleavedBatch_bufferSize(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(8), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.47. cusparseCgpsvInterleavedBatch_buffersize

CgpsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in CgpsvInterleavedBatch().

integer(4) function cusparseCgpsvInterleavedBatch_bufferSize(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(4), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.48. cusparseZgpsvInterleavedBatch_buffersize

ZgpsvInterleavedBatch_buffersize returns the size of the buffer, in bytes, required in ZgpsvInterleavedBatch().

integer(4) function cusparseZgpsvInterleavedBatch_bufferSize(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(8), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  integer(8) :: pBufferSizeInBytes

5.6.49. cusparseSgpsvInterleavedBatch

SgpsvInterleavedBatch computes the solution of multiple pentadiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each penta-diagonal linear system is defined with five vectors corresponding to its lower (ds, dl), main (d), and upper (du, dw) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from StridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseSgpsvInterleavedBatch(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(4), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  character(1), device :: pBuffer(*)

5.6.50. cusparseDgpsvInterleavedBatch

DgpsvInterleavedBatch computes the solution of multiple pentadiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each penta-diagonal linear system is defined with five vectors corresponding to its lower (ds, dl), main (d), and upper (du, dw) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from StridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseDgpsvInterleavedBatch(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  real(8), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  character(1), device :: pBuffer(*)

5.6.51. cusparseCgpsvInterleavedBatch

CgpsvInterleavedBatch computes the solution of multiple pentadiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each penta-diagonal linear system is defined with five vectors corresponding to its lower (ds, dl), main (d), and upper (du, dw) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from StridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseCgpsvInterleavedBatch(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(4), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  character(1), device :: pBuffer(*)

5.6.52. cusparseZgpsvInterleavedBatch

ZgpsvInterleavedBatch computes the solution of multiple pentadiagonal linear systems with multiple right hand sides: A * X = B The coefficient matrix A of each penta-diagonal linear system is defined with five vectors corresponding to its lower (ds, dl), main (d), and upper (du, dw) matrix diagonals; the right-hand sides are stored in the dense matrix B. The solution X overwrites the righthand-side matrix B on exit. This routine differs from StridedBatch routines in that the data for the diagonals, RHS, and solution vectors are interleaved, from one to batchCount, rather than stored one after another. See the cuSPARSE Library document for currently supported algo values.

integer(4) function cusparseZgpsvInterleavedBatch(handle, algo, m, ds, dl, d, du, dw, x, batchCount, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: algo, m, batchCount
  complex(8), device :: ds(*), dl(*), d(*), du(*), dw(*), x(*)
  character(1), device :: pBuffer(*)

5.6.53. cusparseScsric02_bufferSize

This function returns the size of the buffer used in csric02.

integer(4) function cusparseScsric02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.54. cusparseDcsric02_bufferSize

This function returns the size of the buffer used in csric02.

integer(4) function cusparseDcsric02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.55. cusparseCcsric02_bufferSize

This function returns the size of the buffer used in csric02.

integer(4) function cusparseCcsric02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.56. cusparseZcsric02_bufferSize

This function returns the size of the buffer used in csric02.

integer(4) function cusparseZcsric02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.57. cusparseScsric02_analysis

This function performs the analysis phase of csric02.

integer(4) function cusparseScsric02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.58. cusparseDcsric02_analysis

This function performs the analysis phase of csric02.

integer(4) function cusparseDcsric02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.59. cusparseCcsric02_analysis

This function performs the analysis phase of csric02.

integer(4) function cusparseCcsric02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.60. cusparseZcsric02_analysis

This function performs the analysis phase of csric02.

integer(4) function cusparseZcsric02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.61. cusparseScsric02

CSRIC02 performs the solve phase of computing the incomplete-Cholesky factorization with zero fill-in and no pivoting.

integer(4) function cusparseScsric02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.62. cusparseDcsric02

CSRIC02 performs the solve phase of computing the incomplete-Cholesky factorization with zero fill-in and no pivoting.

integer(4) function cusparseDcsric02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.63. cusparseCcsric02

CSRIC02 performs the solve phase of computing the incomplete-Cholesky factorization with zero fill-in and no pivoting.

integer(4) function cusparseCcsric02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.64. cusparseZcsric02

CSRIC02 performs the solve phase of computing the incomplete-Cholesky factorization with zero fill-in and no pivoting.

integer(4) function cusparseZcsric02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.65. cusparseXcsric02_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXcsric02_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseCsric02Info) :: info
  integer(4), device :: position ! device or host variable

5.6.66. cusparseScsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseScsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseCsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  real(4), device :: boost_val ! device or host variable

5.6.67. cusparseDcsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseDcsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseCsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  real(8), device :: boost_val ! device or host variable

5.6.68. cusparseCcsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseCcsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseCsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  complex(4), device :: boost_val ! device or host variable

5.6.69. cusparseZcsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseZcsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseCsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  complex(8), device :: boost_val ! device or host variable

5.6.70. cusparseScsrilu02_bufferSize

This function returns the size of the buffer used in csrilu02.

integer(4) function cusparseScsrilu02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.71. cusparseDcsrilu02_bufferSize

This function returns the size of the buffer used in csrilu02.

integer(4) function cusparseDcsrilu02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.72. cusparseCcsrilu02_bufferSize

This function returns the size of the buffer used in csrilu02.

integer(4) function cusparseCcsrilu02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.73. cusparseZcsrilu02_bufferSize

This function returns the size of the buffer used in csrilu02.

integer(4) function cusparseZcsrilu02_bufferSize(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.74. cusparseScsrilu02_analysis

This function performs the analysis phase of csrilu02.

integer(4) function cusparseScsrilu02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.75. cusparseDcsrilu02_analysis

This function performs the analysis phase of csrilu02.

integer(4) function cusparseDcsrilu02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.76. cusparseCcsrilu02_analysis

This function performs the analysis phase of csrilu02.

integer(4) function cusparseCcsrilu02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.77. cusparseZcsrilu02_analysis

This function performs the analysis phase of csrilu02.

integer(4) function cusparseZcsrilu02_analysis(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.78. cusparseScsrilu02

CSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x m sparse matrix that is defined in CSR storage format by the three arrays csrValA_valM, csrRowPtrA, and csrColIndA.

integer(4) function cusparseScsrilu02(handle, m, nnz, descrA,
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.79. cusparseDcsrilu02

CSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x m sparse matrix that is defined in CSR storage format by the three arrays csrValA_valM, csrRowPtrA, and csrColIndA.

integer(4) function cusparseDcsrilu02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.80. cusparseCcsrilu02

CSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x m sparse matrix that is defined in CSR storage format by the three arrays csrValA_valM, csrRowPtrA, and csrColIndA.

integer(4) function cusparseCcsrilu02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.81. cusparseZcsrilu02

CSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an m x m sparse matrix that is defined in CSR storage format by the three arrays csrValA_valM, csrRowPtrA, and csrColIndA.

integer(4) function cusparseZcsrilu02(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseCsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.82. cusparseXcsrilu02_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXcsrilu02_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseCsrilu02Info) :: info
  integer(4), device :: position ! device or host variable

5.6.83. cusparseSbsric02_bufferSize

This function returns the size of the buffer used in bsric02.

integer(4) function cusparseSbsric02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.84. cusparseDbsric02_bufferSize

This function returns the size of the buffer used in bsric02.

integer(4) function cusparseDbsric02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.85. cusparseCbsric02_bufferSize

This function returns the size of the buffer used in bsric02.

integer(4) function cusparseCbsric02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.86. cusparseZbsric02_bufferSize

This function returns the size of the buffer used in bsric02.

integer(4) function cusparseZbsric02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.87. cusparseSbsric02_analysis

This function performs the analysis phase of bsric02.

integer(4) function cusparseSbsric02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.88. cusparseDbsric02_analysis

This function performs the analysis phase of bsric02.

integer(4) function cusparseDbsric02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.89. cusparseCbsric02_analysis

This function performs the analysis phase of bsric02.

integer(4) function cusparseCbsric02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.90. cusparseZbsric02_analysis

This function performs the analysis phase of bsric02.

integer(4) function cusparseZbsric02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.91. cusparseSbsric02

BSRIC02 performs the solve phase of the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseSbsric02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.92. cusparseDbsric02

BSRIC02 performs the solve phase of the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseDbsric02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.93. cusparseCbsric02

BSRIC02 performs the solve phase of the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseCbsric02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.94. cusparseZbsric02

BSRIC02 performs the solve phase of the incomplete-Cholesky factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseZbsric02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsric02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.95. cusparseXbsric02_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXbsric02_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseBsric02Info) :: info
  integer(4), device :: position ! device or host variable

5.6.96. cusparseSbsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseSbsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseBsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  real(4), device :: boost_val ! device or host variable

5.6.97. cusparseDbsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseDbsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseBsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  real(8), device :: boost_val ! device or host variable

5.6.98. cusparseCbsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseCbsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseBsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  complex(4), device :: boost_val ! device or host variable

5.6.99. cusparseZbsrilu02_numericBoost

This function boosts the value to replace a numerical value in incomplete LU factorization, based on the tol input argument.

integer(4) function cusparseZbsrilu02_numericBoost(handle, info, enable_boost, tol, boost_val)
  type(cusparseHandle) :: handle
  type(cusparseBsrilu02Info) :: info
  integer :: enable_boost
  real(8), device :: tol ! device or host variable
  complex(8), device :: boost_val ! device or host variable

5.6.100. cusparseSbsrilu02_bufferSize

This function returns the size of the buffer used in bsrilu02.

integer(4) function cusparseSbsrilu02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.101. cusparseDbsrilu02_bufferSize

This function returns the size of the buffer used in bsrilu02.

integer(4) function cusparseDbsrilu02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.102. cusparseCbsrilu02_bufferSize

This function returns the size of the buffer used in bsrilu02.

integer(4) function cusparseCbsrilu02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.103. cusparseZbsrilu02_bufferSize

This function returns the size of the buffer used in bsrilu02.

integer(4) function cusparseZbsrilu02_bufferSize(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: pBufferSize ! integer(8) also accepted

5.6.104. cusparseSbsrilu02_analysis

This function performs the analysis phase of bsrilu02.

integer(4) function cusparseSbsrilu02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.105. cusparseDbsrilu02_analysis

This function performs the analysis phase of bsrilu02.

integer(4) function cusparseDbsrilu02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.106. cusparseCbsrilu02_analysis

This function performs the analysis phase of bsrilu02.

integer(4) function cusparseCbsrilu02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.107. cusparseZbsrilu02_analysis

This function performs the analysis phase of bsrilu02.

integer(4) function cusparseZbsrilu02_analysis(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.108. cusparseSbsrilu02

BSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseSbsrilu02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.109. cusparseDbsrilu02

BSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseDbsrilu02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.110. cusparseCbsrilu02

BSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseCbsrilu02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.111. cusparseZbsrilu02

BSRILU02 performs the solve phase of the incomplete-LU factorization with zero fill-in and no pivoting. A is an (mb*blockDim) x (mb*blockDim) sparse matrix that is defined in BSR storage format by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA.

integer(4) function cusparseZbsrilu02(handle, dirA, mb, nnzb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, info, policy, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dirA
  integer(4) :: mb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: blockDim
  type(cusparseBsrilu02Info) :: info
  integer(4) :: policy
  character(c_char), device :: pBuffer(*)

5.6.112. cusparseXbsrilu02_zeroPivot

This function returns an error code equal to CUSPARSE_STATUS_ZERO_PIVOT and sets position to j when A(j,j) is either structural zero or numerical zero. Otherwise, position is set to -1.

integer(4) function cusparseXbsrilu02_zeroPivot(handle, info, position)
  type(cusparseHandle) :: handle
  type(cusparseBsrilu02Info) :: info
  integer(4), device :: position ! device or host variable

5.7. CUSPARSE Reordering Functions

This section contains interfaces for the reordering functions that are used to manipulate sparse matrices.

5.7.1. cusparseScsrColor

This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format.

integer(4) function cusparseScsrColor(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, fractionToColor, ncolors, coloring, reordering, info)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseColorInfo) :: info
  integer :: m, nnz
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), coloring(*), reordering(*)
  real(4), device :: fractionToColor ! device or host variable
  integer(4), device :: ncolors ! device or host variable

5.7.2. cusparseDcsrColor

This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format.

integer(4) function cusparseDcsrColor(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, fractionToColor, ncolors, coloring, reordering, info)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseColorInfo) :: info
  integer :: m, nnz
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), coloring(*), reordering(*)
  real(8), device :: fractionToColor ! device or host variable
  integer(4), device :: ncolors ! device or host variable

5.7.3. cusparseCcsrColor

This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format.

integer(4) function cusparseCcsrColor(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, fractionToColor, ncolors, coloring, reordering, info)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseColorInfo) :: info
  integer :: m, nnz
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), coloring(*), reordering(*)
  real(4), device :: fractionToColor ! device or host variable
  integer(4), device :: ncolors ! device or host variable

5.7.4. cusparseZcsrColor

This function performs the coloring of the adjacency graph associated with the matrix A stored in CSR format.

integer(4) function cusparseZcsrColor(handle, m, nnz, descrA, csrValA, csrRowPtrA, csrColIndA, fractionToColor, ncolors, coloring, reordering, info)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseColorInfo) :: info
  integer :: m, nnz
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), coloring(*), reordering(*)
  real(8), device :: fractionToColor ! device or host variable
  integer(4), device :: ncolors ! device or host variable

5.8. CUSPARSE Format Conversion Functions

This section contains interfaces for the conversion functions that are used to switch between different sparse and dense matrix storage formats.

5.8.1. cusparseSbsr2csr

This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by the arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseSbsr2csr(handle, dirA, nm, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, mb, nb, blockDim
  type(cusparseMatDescr) :: descrA, descrC
  real(4), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*), csrRowPtrC(*), csrColIndC(*)

5.8.2. cusparseDbsr2csr

This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by the arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseDbsr2csr(handle, dirA, nm, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, mb, nb, blockDim
  type(cusparseMatDescr) :: descrA, descrC
  real(8), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*), csrRowPtrC(*), csrColIndC(*)

5.8.3. cusparseCbsr2csr

This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by the arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseCbsr2csr(handle, dirA, nm, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, mb, nb, blockDim
  type(cusparseMatDescr) :: descrA, descrC
  complex(4), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*), csrRowPtrC(*), csrColIndC(*)

5.8.4. cusparseZbsr2csr

This function converts a sparse matrix in BSR format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by the arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseZbsr2csr(handle, dirA, nm, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, blockDim, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, mb, nb, blockDim
  type(cusparseMatDescr) :: descrA, descrC
  complex(8), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*), csrRowPtrC(*), csrColIndC(*)

5.8.5. cusparseXcoo2csr

This function converts the array containing the uncompressed row indices (corresponding to COO format) into an array of compressed row pointers (corresponding to CSR format).

integer(4) function cusparseXcoo2csr(handle, cooRowInd, nnz, m, csrRowPtr, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz, m, idxBase
  integer(4), device :: cooRowInd(*), csrRowPtr(*)

5.8.6. cusparseScsc2dense

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseScsc2dense(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(4), device :: cscValA(*), A(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.7. cusparseDcsc2dense

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseDcsc2dense(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(8), device :: cscValA(*), A(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.8. cusparseCcsc2dense

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseCcsc2dense(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(4), device :: cscValA(*), A(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.9. cusparseZcsc2dense

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseZcsc2dense(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(8), device :: cscValA(*), A(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.10. cusparseScsc2hyb

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the sparse matrix A in HYB format.

integer(4) function cusparseScsc2hyb(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  real(4), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)
  type(cusparseHybMat) :: hybA

5.8.11. cusparseDcsc2hyb

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the sparse matrix A in HYB format.

integer(4) function cusparseDcsc2hyb(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  real(8), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)
  type(cusparseHybMat) :: hybA

5.8.12. cusparseCcsc2hyb

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the sparse matrix A in HYB format.

integer(4) function cusparseCcsc2hyb(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  complex(4), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)
  type(cusparseHybMat) :: hybA

5.8.13. cusparseZcsc2hyb

This function converts the sparse matrix in CSC format that is defined by the three arrays cscValA, cscColPtrA, and cscRowIndA into the sparse matrix A in HYB format.

integer(4) function cusparseZcsc2hyb(handle, m, n, descrA, cscValA, cscRowIndA, cscColPtrA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  complex(8), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)
  type(cusparseHybMat) :: hybA

5.8.14. cusparseXcsr2bsrNnz

cusparseXcsrgeamNnz computes the number of nonzero elements which will be produced by CSRGEAM.

integer(4) function cusparseXcsr2bsrNnz(handle, dirA, m, n, descrA, csrRowPtrA, csrColIndA, blockDim, descrC, bsrRowPtrC, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: dirA, m, n, blockdim
  type(cusparseMatDescr) :: descrA, descrC
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), bsrRowPtrC(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.8.15. cusparseScsr2bsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseScsr2bsr(handle, dirA, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, blockDim, descrC, bsrValC, bsrRowPtrC, bsrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, m, n, blockdim
  type(cusparseMatDescr) :: descrA, descrC
  real(4), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), bsrRowPtrC(*), bsrColIndC(*)

5.8.16. cusparseDcsr2bsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseDcsr2bsr(handle, dirA, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, blockDim, descrC, bsrValC, bsrRowPtrC, bsrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, m, n, blockdim
  type(cusparseMatDescr) :: descrA, descrC
  real(8), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), bsrRowPtrC(*), bsrColIndC(*)

5.8.17. cusparseCcsr2bsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseCcsr2bsr(handle, dirA, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, blockDim, descrC, bsrValC, bsrRowPtrC, bsrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, m, n, blockdim
  type(cusparseMatDescr) :: descrA, descrC
  complex(4), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), bsrRowPtrC(*), bsrColIndC(*)

5.8.18. cusparseZcsr2bsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseZcsr2bsr(handle, dirA, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, blockDim, descrC, bsrValC, bsrRowPtrC, bsrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dirA, m, n, blockdim
  type(cusparseMatDescr) :: descrA, descrC
  complex(8), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*), bsrRowPtrC(*), bsrColIndC(*)

5.8.19. cusparseXcsr2coo

This function converts the array containing the compressed row pointers (corresponding to CSR format) into an array of uncompressed row indices (corresponding to COO format).

integer(4) function cusparseXcsr2coo(handle, csrRowPtr, nnz, m, cooRowInd, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: nnz, m, idxBase
  integer(4), device :: csrRowPtr(*), cooRowInd(*)

5.8.20. cusparseScsr2csc

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrVal, csrRowPtr, and csrColInd into a sparse matrix in CSC format that is defined by arrays cscVal, cscRowInd, and cscColPtr.

This function was removed in CUDA 11.0. Use the cusparseCsr2cscEx2 routines instead.

integer(4) function cusparseScsr2csc(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, cscVal, cscRowInd, cscColPtr, copyValues, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz, copyValues, idxBase
  real(4), device :: csrVal(*), cscVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*), cscRowInd(*), cscColPtr(*)

5.8.21. cusparseDcsr2csc

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrVal, csrRowPtr, and csrColInd into a sparse matrix in CSC format that is defined by arrays cscVal, cscRowInd, and cscColPtr.

This function was removed in CUDA 11.0. Use the cusparseCsr2cscEx2 routines instead.

integer(4) function cusparseDcsr2csc(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, cscVal, cscRowInd, cscColPtr, copyValues, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz, copyValues, idxBase
  real(8), device :: csrVal(*), cscVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*), cscRowInd(*), cscColPtr(*)

5.8.22. cusparseCcsr2csc

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrVal, csrRowPtr, and csrColInd into a sparse matrix in CSC format that is defined by arrays cscVal, cscRowInd, and cscColPtr.

This function was removed in CUDA 11.0. Use the cusparseCsr2cscEx2 routines instead.

integer(4) function cusparseCcsr2csc(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, cscVal, cscRowInd, cscColPtr, copyValues, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz, copyValues, idxBase
  complex(4), device :: csrVal(*), cscVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*), cscRowInd(*), cscColPtr(*)

5.8.23. cusparseZcsr2csc

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrVal, csrRowPtr, and csrColInd into a sparse matrix in CSC format that is defined by arrays cscVal, cscRowInd, and cscColPtr.

This function was removed in CUDA 11.0. Use the cusparseCsr2cscEx2 routines instead.

integer(4) function cusparseZcsr2csc(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, cscVal, cscRowInd, cscColPtr, copyValues, idxBase)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz, copyValues, idxBase
  complex(8), device :: csrVal(*), cscVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*), cscRowInd(*), cscColPtr(*)

5.8.24. cusparseCsr2cscEx2_bufferSize

This function determines the size of the work buffer needed by cusparseCsr2cscEx2.

integer(4) function cusparseScsr2cscEx2_bufferSize(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, cscVal, &
           cscColPtr, cscRowInd, valType, copyValues, idxBase, alg, bufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz, valType, copyValues, idxBase, alg
  real(4), device :: csrVal(*), cscVal(*)  ! Can be any supported type
  integer(4), device :: csrRowPtr(*), csrColInd(*), cscRowInd(*), cscColPtr(*)
  integer(8) :: bufferSize

5.8.25. cusparseCsr2cscEx2

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrVal, csrRowPtr, and csrColInd into a sparse matrix in CSC format that is defined by arrays cscVal, cscRowInd, and cscColPtr. The type of the arrays is set by the valType argument.

integer(4) function cusparseScsr2cscEx2(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, cscVal, &
           cscColPtr, cscRowInd, valType, copyValues, idxBase, alg, buffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz, valType, copyValues, idxBase, alg
  real(4), device :: csrVal(*), cscVal(*)  ! Can be any supported type
  integer(4), device :: csrRowPtr(*), csrColInd(*), cscRowInd(*), cscColPtr(*)
  integer(1), device :: buffer ! Can be any type

5.8.26. cusparseScsr2dense

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseScsr2dense(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*), A(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.27. cusparseDcsr2dense

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseDcsr2dense(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*), A(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.28. cusparseCcsr2dense

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseCcsr2dense(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*), A(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.29. cusparseZcsr2dense

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseZcsr2dense(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, A, lda)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*), A(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.30. cusparseScsr2hyb

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into a sparse matrix in HYB format.

integer(4) function cusparseScsr2hyb(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.31. cusparseDcsr2hyb

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into a sparse matrix in HYB format.

integer(4) function cusparseDcsr2hyb(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.32. cusparseCcsr2hyb

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into a sparse matrix in HYB format.

integer(4) function cusparseCcsr2hyb(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.33. cusparseZcsr2hyb

This function converts the sparse matrix in CSR format that is defined by the three arrays cscValA, cscRowPtrA, and cscColIndA into a sparse matrix in HYB format.

integer(4) function cusparseZcsr2hyb(handle, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.34. cusparseSdense2csc

This function converts the matrix A in dense format into a sparse matrix in CSC format.

integer(4) function cusparseSdense2csc(handle, m, n, descrA, A, lda, nnzPerCol, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(4), device :: A(*), cscValA(*)
  integer(4), device :: nnzPerCol(*), cscRowIndA(*), cscColPtrA(*)

5.8.35. cusparseDdense2csc

This function converts the matrix A in dense format into a sparse matrix in CSC format.

integer(4) function cusparseDdense2csc(handle, m, n, descrA, A, lda, nnzPerCol, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(8), device :: A(*), cscValA(*)
  integer(4), device :: nnzPerCol(*), cscRowIndA(*), cscColPtrA(*)

5.8.36. cusparseCdense2csc

This function converts the matrix A in dense format into a sparse matrix in CSC format.

integer(4) function cusparseCdense2csc(handle, m, n, descrA, A, lda, nnzPerCol, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(4), device :: A(*), cscValA(*)
  integer(4), device :: nnzPerCol(*), cscRowIndA(*), cscColPtrA(*)

5.8.37. cusparseZdense2csc

This function converts the matrix A in dense format into a sparse matrix in CSC format.

integer(4) function cusparseZdense2csc(handle, m, n, descrA, A, lda, nnzPerCol, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(8), device :: A(*), cscValA(*)
  integer(4), device :: nnzPerCol(*), cscRowIndA(*), cscColPtrA(*)

5.8.38. cusparseSdense2csr

This function converts the matrix A in dense format into a sparse matrix in CSR format.

integer(4) function cusparseSdense2csr(handle, m, n, descrA, A, lda, nnzPerRow, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(4), device :: A(*), csrValA(*)
  integer(4), device :: nnzPerRow(*), csrRowPtrA(*), csrColIndA(*)

5.8.39. cusparseDdense2csr

This function converts the matrix A in dense format into a sparse matrix in CSR format.

integer(4) function cusparseDdense2csr(handle, m, n, descrA, A, lda, nnzPerRow, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  real(8), device :: A(*), csrValA(*)
  integer(4), device :: nnzPerRow(*), csrRowPtrA(*), csrColIndA(*)

5.8.40. cusparseCdense2csr

This function converts the matrix A in dense format into a sparse matrix in CSR format.

integer(4) function cusparseCdense2csr(handle, m, n, descrA, A, lda, nnzPerRow, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(4), device :: A(*), csrValA(*)
  integer(4), device :: nnzPerRow(*), csrRowPtrA(*), csrColIndA(*)

5.8.41. cusparseZdense2csr

This function converts the matrix A in dense format into a sparse matrix in CSR format.

integer(4) function cusparseZdense2csr(handle, m, n, descrA, A, lda, nnzPerRow, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(8), device :: A(*), csrValA(*)
  integer(4), device :: nnzPerRow(*), csrRowPtrA(*), csrColIndA(*)

5.8.42. cusparseSdense2hyb

This function converts the matrix A in dense format into a sparse matrix in HYB format.

integer(4) function cusparseSdense2hyb(handle, m, n, descrA, A, lda, nnzPerRow, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(4), device :: A(*)
  integer(4), device :: nnzPerRow(*)

5.8.43. cusparseDdense2hyb

This function converts the matrix A in dense format into a sparse matrix in HYB format.

integer(4) function cusparseDdense2hyb(handle, m, n, descrA, A, lda, nnzPerRow, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(8), device :: A(*)
  integer(4), device :: nnzPerRow(*)

5.8.44. cusparseCdense2hyb

This function converts the matrix A in dense format into a sparse matrix in HYB format.

integer(4) function cusparseCdense2hyb(handle, m, n, descrA, A, lda, nnzPerRow, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(4), device :: A(*)
  integer(4), device :: nnzPerRow(*)

5.8.45. cusparseZdense2hyb

This function converts the matrix A in dense format into a sparse matrix in HYB format.

integer(4) function cusparseZdense2hyb(handle, m, n, descrA, A, lda, nnzPerRow, hybA, userEllWidth, partitionType)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, lda, userEllWidth, partitionType
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(8), device :: A(*)
  integer(4), device :: nnzPerRow(*)

5.8.46. cusparseShyb2csc

This function converts the sparse matrix A in HYB format into a sparse matrix in CSC format.

integer(4) function cusparseShyb2csc(handle, descrA, hybA, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(4), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.47. cusparseDhyb2csc

This function converts the sparse matrix A in HYB format into a sparse matrix in CSC format.

integer(4) function cusparseDhyb2csc(handle, descrA, hybA, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(8), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.48. cusparseChyb2csc

This function converts the sparse matrix A in HYB format into a sparse matrix in CSC format.

integer(4) function cusparseChyb2csc(handle, descrA, hybA, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(4), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.49. cusparseZhyb2csc

This function converts the sparse matrix A in HYB format into a sparse matrix in CSC format.

integer(4) function cusparseZhyb2csc(handle, descrA, hybA, cscValA, cscRowIndA, cscColPtrA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(8), device :: cscValA(*)
  integer(4), device :: cscRowIndA(*), cscColPtrA(*)

5.8.50. cusparseShyb2csr

This function converts the sparse matrix A in HYB format into a sparse matrix in CSR format.

integer(4) function cusparseShyb2csr(handle, descrA, hybA, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.51. cusparseDhyb2csr

This function converts the sparse matrix A in HYB format into a sparse matrix in CSR format.

integer(4) function cusparseDhyb2csr(handle, descrA, hybA, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.52. cusparseChyb2csr

This function converts the sparse matrix A in HYB format into a sparse matrix in CSR format.

integer(4) function cusparseChyb2csr(handle, descrA, hybA, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(4), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.53. cusparseZhyb2csr

This function converts the sparse matrix A in HYB format into a sparse matrix in CSR format.

integer(4) function cusparseZhyb2csr(handle, descrA, hybA, csrValA, csrRowPtrA, csrColIndA)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(8), device :: csrValA(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)

5.8.54. cusparseShyb2dense

This function converts the sparse matrix in HYB format into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseShyb2dense(handle, descrA, hybA, A, lda)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(4), device :: A(*)
  integer(4) :: lda

5.8.55. cusparseDhyb2dense

This function converts the sparse matrix in HYB format into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseDhyb2dense(handle, descrA, hybA, A, lda)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  real(8), device :: A(*)
  integer(4) :: lda

5.8.56. cusparseChyb2dense

This function converts the sparse matrix in HYB format into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseChyb2dense(handle, descrA, hybA, A, lda)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(4), device :: A(*)
  integer(4) :: lda

5.8.57. cusparseZhyb2dense

This function converts the sparse matrix in HYB format into the matrix A in dense format. The dense matrix A is filled in with the values of the sparse matrix and with zeros elsewhere.

integer(4) function cusparseZhyb2dense(handle, descrA, hybA, A, lda)
  type(cusparseHandle) :: handle
  type(cusparseMatDescr) :: descrA
  type(cusparseHybMat) :: hybA
  complex(8), device :: A(*)
  integer(4) :: lda

5.8.58. cusparseSnnz

This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.

integer(4) function cusparseSnnz(handle, dirA, m, n, descrA, A, lda, nnzPerRowColumn, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: dirA, m, n, lda
  type(cusparseMatDescr) :: descrA
  real(4), device :: A(*)
  integer(4), device :: nnzPerRowColumn(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.8.59. cusparseDnnz

This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.

integer(4) function cusparseDnnz(handle, dirA, m, n, descrA, A, lda, nnzPerRowColumn, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: dirA, m, n, lda
  type(cusparseMatDescr) :: descrA
  real(8), device :: A(*)
  integer(4), device :: nnzPerRowColumn(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.8.60. cusparseCnnz

This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.

integer(4) function cusparseCnnz(handle, dirA, m, n, descrA, A, lda, nnzPerRowColumn, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: dirA, m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(4), device :: A(*)
  integer(4), device :: nnzPerRowColumn(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.8.61. cusparseZnnz

This function computes the number of nonzero elements per row or column and the total number of nonzero elements in a dense matrix.

integer(4) function cusparseZnnz(handle, dirA, m, n, descrA, A, lda, nnzPerRowColumn, nnzTotalDevHostPtr)
  type(cusparseHandle) :: handle
  integer :: dirA, m, n, lda
  type(cusparseMatDescr) :: descrA
  complex(8), device :: A(*)
  integer(4), device :: nnzPerRowColumn(*)
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable

5.8.62. cusparseSgebsr2gebsc_bufferSize

This function returns the size of the buffer used in gebsr2gebsc.

integer(4) function cusparseSgebsr2gebsc_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, bsrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  real(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.63. cusparseDgebsr2gebsc_bufferSize

This function returns the size of the buffer used in gebsr2gebsc.

integer(4) function cusparseDgebsr2gebsc_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, bsrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  real(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.64. cusparseCgebsr2gebsc_bufferSize

This function returns the size of the buffer used in gebsr2gebsc.

integer(4) function cusparseCgebsr2gebsc_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, bsrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  complex(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.65. cusparseZgebsr2gebsc_bufferSize

This function returns the size of the buffer used in gebsr2gebsc.

integer(4) function cusparseZgebsr2gebsc_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, bsrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  complex(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.66. cusparseSgebsr2gebsc

This function converts a sparse matrix in general block-CSR storage format to a sparse matrix in general block-CSC storage format.

integer(4) function cusparseSgebsr2gebsc(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDim, colBlockDim, bscVal, bscRowInd, bscColPtr, copyValues, baseIdx, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  real(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  real(4), device :: bscVal(*)
  integer(4), device :: bscRowInd(*), bscColPtr(*)
  integer(4) :: copyValues, baseIdx
  character(c_char), device :: pBuffer(*)

5.8.67. cusparseDgebsr2gebsc

This function converts a sparse matrix in general block-CSR storage format to a sparse matrix in general block-CSC storage format.

integer(4) function cusparseDgebsr2gebsc(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDim, colBlockDim, bscVal, bscRowInd, bscColPtr, copyValues, baseIdx, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  real(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  real(8), device :: bscVal(*)
  integer(4), device :: bscRowInd(*), bscColPtr(*)
  integer(4) :: copyValues, baseIdx
  character(c_char), device :: pBuffer(*)

5.8.68. cusparseCgebsr2gebsc

This function converts a sparse matrix in general block-CSR storage format to a sparse matrix in general block-CSC storage format.

integer(4) function cusparseCgebsr2gebsc(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDim, colBlockDim, bscVal, bscRowInd, bscColPtr, copyValues, baseIdx, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  complex(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  complex(4), device :: bscVal(*)
  integer(4), device :: bscRowInd(*), bscColPtr(*)
  integer(4) :: copyValues, baseIdx
  character(c_char), device :: pBuffer(*)

5.8.69. cusparseZgebsr2gebsc

This function converts a sparse matrix in general block-CSR storage format to a sparse matrix in general block-CSC storage format.

integer(4) function cusparseZgebsr2gebsc(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDim, colBlockDim, bscVal, bscRowInd, bscColPtr, copyValues, baseIdx, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  complex(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  complex(8), device :: bscVal(*)
  integer(4), device :: bscRowInd(*), bscColPtr(*)
  integer(4) :: copyValues, baseIdx
  character(c_char), device :: pBuffer(*)

5.8.70. cusparseSgebsr2gebsr_bufferSize

This function returns the size of the buffer used in gebsr2gebsrnnz and gebsr2gebsr.

integer(4) function cusparseSgebsr2gebsr_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  real(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.71. cusparseDgebsr2gebsr_bufferSize

This function returns the size of the buffer used in gebsr2gebsrnnz and gebsr2gebsr.

integer(4) function cusparseDgebsr2gebsr_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  real(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.72. cusparseCgebsr2gebsr_bufferSize

This function returns the size of the buffer used in gebsr2gebsrnnz and gebsr2gebsr.

integer(4) function cusparseCgebsr2gebsr_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  complex(4), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.73. cusparseZgebsr2gebsr_bufferSize

This function returns the size of the buffer used in gebsr2gebsrnnz and gebsr2gebsr.

integer(4) function cusparseZgebsr2gebsr_bufferSize(handle, mb, nb, nnzb, bsrVal, bsrRowPtr, &
           bsrColInd, rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: mb, nb, nnzb
  complex(8), device :: bsrVal(*)
  integer(4), device :: bsrRowPtr(*), bsrColInd(*)
  integer(4) :: rowBlockDimA, colBlockDimA, rowBlockDimC, colBlockDimC
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.74. cusparseXgebsr2gebsrNnz

cusparseXcsrgeamNnz computes the number of nonzero elements which will be produced by CSRGEAM.

integer(4) function cusparseXgebsr2gebsrNnz(handle, dir, mb, nb, nnzb, descrA, bsrRowPtrA, &
           bsrColIndA, rowBlockDimA, colBlockDimA, descrC, bsrRowPtrC, rowBlockDimC, colBlockDimC, nnzTotalDevHostPtr, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*)
  integer :: rowBlockDimC, colBlockDimC
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable
  character, device :: pBuffer(*)

5.8.75. cusparseSgebsr2gebsr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseSgebsr2gebsr(handle, dir, mb, nb, nnzb, descrA, bsrValA, bsrRowPtrA, &
           bsrColIndA, rowBlockDimA, colBlockDimA, descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*), bsrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.76. cusparseDgebsr2gebsr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseDgebsr2gebsr(handle, dir, mb, nb, nnzb, descrA, bsrValA, bsrRowPtrA, &
           bsrColIndA, rowBlockDimA, colBlockDimA, descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*), bsrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.77. cusparseCgebsr2gebsr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseCgebsr2gebsr(handle, dir, mb, nb, nnzb, descrA, bsrValA, bsrRowPtrA, &
           bsrColIndA, rowBlockDimA, colBlockDimA, descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*), bsrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.78. cusparseZgebsr2gebsr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in another general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseZgebsr2gebsr(handle, dir, mb, nb, nnzb, descrA, bsrValA, bsrRowPtrA, &
           bsrColIndA, rowBlockDimA, colBlockDimA, descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*), bsrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.79. cusparseSgebsr2csr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseSgebsr2csr(handle, dir, mb, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, &
           rowBlockDimA, colBlockDimA, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: csrRowPtrC(*), csrColIndC(*)

5.8.80. cusparseDgebsr2csr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseDgebsr2csr(handle, dir, mb, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, &
           rowBlockDimA, colBlockDimA, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: csrRowPtrC(*), csrColIndC(*)

5.8.81. cusparseCgebsr2csr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseCgebsr2csr(handle, dir, mb, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, &
           rowBlockDimA, colBlockDimA, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: csrRowPtrC(*), csrColIndC(*)

5.8.82. cusparseZgebsr2csr

This function converts a sparse matrix in general BSR storage format that is defined by the three arrays bsrValA, bsrRowPtrA, and bsrColIndA into a sparse matrix in CSR format that is defined by arrays csrValC, csrRowPtrC, and csrColIndC.

integer(4) function cusparseZgebsr2csr(handle, dir, mb, nb, descrA, bsrValA, bsrRowPtrA, bsrColIndA, &
           rowBlockDimA, colBlockDimA, descrC, csrValC, csrRowPtrC, csrColIndC)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: bsrValA(*), csrValC(*)
  integer(4), device :: bsrRowPtrA(*), bsrColIndA(*)
  integer(4) :: rowBlockDimA, colBlockDimA
  type(cusparseMatDescr) :: descrC
  integer(4), device :: csrRowPtrC(*), csrColIndC(*)

5.8.83. cusparseScsr2gebsr_bufferSize

This function returns the size of the buffer used in csr2gebsrnnz and csr2gebsr.

integer(4) function cusparseScsr2gebsr_bufferSize(handle, dir, m, n, descrA, csrVal, csrRowPtr, csrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dir, m, n
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.84. cusparseDcsr2gebsr_bufferSize

This function returns the size of the buffer used in csr2gebsrnnz and csr2gebsr.

integer(4) function cusparseDcsr2gebsr_bufferSize(handle, dir, m, n, descrA, csrVal, csrRowPtr, csrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dir, m, n
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.85. cusparseCcsr2gebsr_bufferSize

This function returns the size of the buffer used in csr2gebsrnnz and csr2gebsr.

integer(4) function cusparseCcsr2gebsr_bufferSize(handle, dir, m, n, descrA, csrVal, csrRowPtr, csrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dir, m, n
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.86. cusparseZcsr2gebsr_bufferSize

This function returns the size of the buffer used in csr2gebsrnnz and csr2gebsr.

integer(4) function cusparseZcsr2gebsr_bufferSize(handle, dir, m, n, descrA, csrVal, csrRowPtr, csrColInd, rowBlockDim, colBlockDim, pBufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: dir, m, n
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  integer(4) :: rowBlockDim, colBlockDim
  integer(4) :: pBufferSize ! integer(8) also accepted

5.8.87. cusparseXcsr2gebsrNnz

cusparseXcsrgeamNnz computes the number of nonzero elements which will be produced by CSRGEAM.

integer(4) function cusparseXcsr2gebsrNnz(handle, dir, m, n, descrA, csrRowPtrA, csrColIndA, &
           descrC, bsrRowPtrC, rowBlockDimC, colBlockDimC, nnzTotalDevHostPtr, pBuffer)
  type(cusparseHandle) :: handle
  integer :: dir, m, n
  type(cusparseMatDescr) :: descrA
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*)
  integer :: rowBlockDimC, colBlockDimC
  integer(4), device :: nnzTotalDevHostPtr ! device or host variable
  character, device :: pBuffer(*)

5.8.88. cusparseScsr2gebsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseScsr2gebsr(handle, dir, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, &
           descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.89. cusparseDcsr2gebsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseDcsr2gebsr(handle, dir, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, &
           descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.90. cusparseCcsr2gebsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseCcsr2gebsr(handle, dir, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, &
           descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.91. cusparseZcsr2gebsr

This function converts a sparse matrix in CSR storage format that is defined by the three arrays csrValA, csrRowPtrA, and csrColIndA into a sparse matrix in general BSR format that is defined by arrays bsrValC, bsrRowPtrC, and bsrColIndC.

integer(4) function cusparseZcsr2gebsr(handle, dir, m, n, descrA, csrValA, csrRowPtrA, csrColIndA, &
           descrC, bsrValC, bsrRowPtrC, bsrColIndC, rowBlockDimC, colBlockDimC, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: dir, mb, nb, nnzb
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrValA(*), bsrValC(*)
  integer(4), device :: csrRowPtrA(*), csrColIndA(*)
  type(cusparseMatDescr) :: descrC
  integer(4), device :: bsrRowPtrC(*), bsrColIndC(*)
  integer(4) :: rowBlockDimC, colBlockDimC
  character(c_char), device :: pBuffer(*)

5.8.92. cusparseCreateIdentityPermutation

This function creates an identity map. The output parameter p represents such map by p = 0:1:(n-1). This function is typically used with coosort, csrsort, cscsort, and csr2csc_indexOnly.

integer(4) function cusparseCreateIdentityPermutation(handle, n, p)
  type(cusparseHandle) :: handle
  integer(4) :: n
  integer(4), device :: p(*)

5.8.93. cusparseXcoosort_bufferSize

This function returns the size of the buffer used in coosort.

integer(4) function cusparseXcoosort_bufferSize(handle, m, n, nnz, cooRows, cooCols, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: cooRows(*), cooCols(*)
  integer(8) :: pBufferSizeInBytes

5.8.94. cusparseXcoosortByRow

This function sorts the sparse matrix stored in COO format.

integer(4) function cusparseXcoosortByRow(handle, m, n, nnz, cooRows, cooCols, P, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: cooRows(*), cooCols(*), P(*)
  character(c_char), device :: pBuffer(*)

5.8.95. cusparseXcoosortByColumn

This function sorts the sparse matrix stored in COO format.

integer(4) function cusparseXcoosortByColumn(handle, m, n, nnz, cooRows, cooCols, P, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: cooRows(*), cooCols(*), P(*)
  character(c_char), device :: pBuffer(*)

5.8.96. cusparseXcsrsort_bufferSize

This function returns the size of the buffer used in csrsort.

integer(4) function cusparseXcsrsort_bufferSize(handle, m, n, nnz, csrRowInd, csrColInd, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: csrRowInd(*), csrColInd(*)
  integer(8) :: pBufferSizeInBytes

5.8.97. cusparseXcsrsort

This function sorts the sparse matrix stored in CSR format.

integer(4) function cusparseXcsrsort(handle, m, n, nnz, csrRowInd, csrColInd, P, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: csrRowInd(*), csrColInd(*), P(*)
  character(c_char), device :: pBuffer(*)

5.8.98. cusparseXcscsort_bufferSize

This function returns the size of the buffer used in cscsort.

integer(4) function cusparseXcscsort_bufferSize(handle, m, n, nnz, cscColPtr, cscRowInd, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: cscColPtr(*), cscRowInd(*)
  integer(8) :: pBufferSizeInBytes

5.8.99. cusparseXcscsort

This function sorts the sparse matrix stored in CSC format.

integer(4) function cusparseXcscsort(handle, m, n, nnz, cscColPtr, cscRowInd, P, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  integer(4), device :: cscColPtr(*), cscRowInd(*), P(*)
  character(c_char), device :: pBuffer(*)

5.8.100. cusparseScsru2csr_bufferSize

This function returns the size of the buffer used in csru2csr.

integer(4) function cusparseScsru2csr_bufferSize(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  integer(8) :: pBufferSizeInBytes

5.8.101. cusparseDcsru2csr_bufferSize

This function returns the size of the buffer used in csru2csr.

integer(4) function cusparseDcsru2csr_bufferSize(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  integer(8) :: pBufferSizeInBytes

5.8.102. cusparseCcsru2csr_bufferSize

This function returns the size of the buffer used in csru2csr.

integer(4) function cusparseCcsru2csr_bufferSize(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  integer(8) :: pBufferSizeInBytes

5.8.103. cusparseZcsru2csr_bufferSize

This function returns the size of the buffer used in csru2csr.

integer(4) function cusparseZcsru2csr_bufferSize(handle, m, n, nnz, csrVal, csrRowPtr, csrColInd, info, pBufferSizeInBytes)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  integer(8) :: pBufferSizeInBytes

5.8.104. cusparseScsru2csr

This function transfers unsorted CSR format to CSR format.

integer(4) function cusparseScsru2csr(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.105. cusparseDcsru2csr

This function transfers unsorted CSR format to CSR format.

integer(4) function cusparseDcsru2csr(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.106. cusparseCcsru2csr

This function transfers unsorted CSR format to CSR format.

integer(4) function cusparseCcsru2csr(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.107. cusparseZcsru2csr

This function transfers unsorted CSR format to CSR format.

integer(4) function cusparseZcsru2csr(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.108. cusparseScsr2csru

This function performs the backwards transformation from sorted CSR format to unsorted CSR format.

integer(4) function cusparseScsr2csru(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  real(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.109. cusparseDcsr2csru

This function performs the backwards transformation from sorted CSR format to unsorted CSR format.

integer(4) function cusparseDcsr2csru(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  real(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.110. cusparseCcsr2csru

This function performs the backwards transformation from sorted CSR format to unsorted CSR format.

integer(4) function cusparseCcsr2csru(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  complex(4), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.8.111. cusparseZcsr2csru

This function performs the backwards transformation from sorted CSR format to unsorted CSR format.

integer(4) function cusparseZcsr2csru(handle, m, n, nnz, descrA, csrVal, csrRowPtr, csrColInd, info, pBuffer)
  type(cusparseHandle) :: handle
  integer(4) :: m, n, nnz
  type(cusparseMatDescr) :: descrA
  complex(8), device :: csrVal(*)
  integer(4), device :: csrRowPtr(*), csrColInd(*)
  type(cusparseCsru2csrInfo) :: info
  character(c_char), device :: pBuffer(*)

5.9. CUSPARSE Generic API Functions

This section contains interfaces for the generic API functions that perform vector-vector (SpVV), matrix-vector (SpMV), and matrix-matrix (SpMM) operations.

5.9.1. cusparseDenseToSparse_bufferSize

This function returns the size of the workspace needed by cusparseDenseToSparse_analysis(). The value returned is in bytes.

integer(4) function cusparseDenseToSparse_bufferSize(handle, matA, matB, alg, bufferSize)
  type(cusparseHandle) :: handle
  type(cusparseDnMatDescr) :: MatA
  type(cusparseSpMatDescr) :: matB
  integer(4) :: alg
  integer(8), intent(out) :: bufferSize

5.9.2. cusparseDenseToSparse_analysis

This function updates the number of non-zero elements required in the sparse matrix descriptor matB.

integer(4) function cusparseDenseToSparse_analysis(handle, matA, matB, alg, buffer)
  type(cusparseHandle) :: handle
  type(cusparseDnMatDescr) :: matA
  type(cusparseSpMatDescr) :: matB
  integer(4) :: alg
  integer(4), device :: buffer(*)

5.9.3. cusparseDenseToSparse_convert

This function fills the sparse matrix values in the area provided in descriptor matB.

integer(4) function cusparseDenseToSparse_convert(handle, matA, matB, alg, buffer)
  type(cusparseHandle) :: handle
  type(cusparseDnMatDescr) :: matA
  type(cusparseSpMatDescr) :: matB
  integer(4) :: alg
  integer(4), device :: buffer(*)

5.9.4. cusparseSparseToDense_bufferSize

This function returns the size of the workspace needed by cusparseSparseToDense_analysis(). The value returned is in bytes.

integer(4) function cusparseSparseToDense_bufferSize(handle, matA, matB, alg, bufferSize)
  type(cusparseHandle) :: handle
  type(cusparseSpMatDescr) :: MatA
  type(cusparseDnMatDescr) :: matB
  integer(4) :: alg
  integer(8), intent(out) :: bufferSize

5.9.5. cusparseSparseToDense

This function fills the dense values in the area provided in descriptor matB.

integer(4) function cusparseSparseToDense(handle, matA, matB, alg, buffer)
  type(cusparseHandle) :: handle
  type(cusparseSpMatDescr) :: matA
  type(cusparseDnMatDescr) :: matB
  integer(4) :: alg
  integer(4), device :: buffer(*)

5.9.6. cusparseCreateSpVec

This function initializes the sparse vector descriptor used in the generic API. The type, kind, and rank of the input arguments indices and values are actually ignored, and taken from the input arguments idxType and valueType. The vectors are assumed to be contiguous. The idxBase argument is typically CUSPARSE_INDEX_BASE_ONE in Fortran.

integer(4) function cusparseCreateSpVec(descr, size, nnz, indices, values, idxType, idxBase, valueType)
  type(cusparseSpVecDescr) :: descr
  integer(8) :: size, nnz
  integer(4), device :: indices(*)
  real(4), device    :: values(*)
  integer(4) :: idxType, idxBase, valueType

5.9.7. cusparseDestroySpVec

This function releases the host memory associated with the sparse vector descriptor used in the generic API.

integer(4) function cusparseDestroySpVec(descr)
  type(cusparseSpVecDescr) :: descr

5.9.8. cusparseSpVecGet

This function returns the fields within the sparse vector descriptor used in the generic API.

integer(4) function cusparseSpVecGet(descr, size, nnz, indices, values, idxType, idxBase, valueType)
  type(cusparseSpVecDescr) :: descr
  integer(8) :: size, nnz
  type(c_devptr) :: indices
  type(c_devptr) :: values
  integer(4) :: idxType, idxBase, valueType

5.9.9. cusparseSpVecGetIndexBase

This function returns idxBase field within the sparse vector descriptor used in the generic API.

integer(4) function cusparseSpVecGetIndexBase(descr, idxBase)
  type(cusparseSpVecDescr) :: descr
  integer(4) :: idxBase

5.9.10. cusparseSpVecGetValues

This function returns the values field within the sparse vector descriptor used in the generic API.

integer(4) function cusparseSpVecGetValues(descr, values)
  type(cusparseSpVecDescr) :: descr
  type(c_devptr) :: values

5.9.11. cusparseSpVecSetValues

This function sets the values field within the sparse vector descriptor used in the generic API. The type, kind and rank of the values argument is ignored; the type is determined by the valueType field in the descriptor.

integer(4) function cusparseSpVecSetValues(descr, values)
  type(cusparseSpVecDescr) :: descr
  real(4), device :: values(*)

5.9.12. cusparseCreateDnVec

This function initializes the dense vector descriptor used in the generic API. The type, kind, and rank of the values input argument is ignored, and taken from the input argument valueType. The vector is assumed to be contiguous.

integer(4) function cusparseCreateDnVec(descr, size, values, valueType)
  type(cusparseDnVecDescr) :: descr
  integer(8) :: size
  real(4), device    :: values(*)
  integer(4) :: valueType

5.9.13. cusparseDestroyDnVec

This function releases the host memory associated with the dense vector descriptor used in the generic API.

integer(4) function cusparseDestroyDnVec(descr)
  type(cusparseDnVecDescr) :: descr

5.9.14. cusparseDnVecGet

This function returns the fields within the dense vector descriptor used in the generic API.

integer(4) function cusparseDnVecGet(descr, size, values, valueType)
  type(cusparseDnVecDescr) :: descr
  integer(8) :: size
  type(c_devptr) :: values
  integer(4) :: valueType

5.9.15. cusparseDnVecGetValues

This function returns the values field within the dense vector descriptor used in the generic API.

integer(4) function cusparseDnVecGetValues(descr, values)
  type(cusparseDnVecDescr) :: descr
  type(c_devptr) :: values

5.9.16. cusparseDnVecSetValues

This function sets the values field within the dense vector descriptor used in the generic API. The type, kind and rank of the values argument is ignored; the type is determined by the valueType field in the descriptor.

integer(4) function cusparseDnVecSetValues(descr, values)
  type(cusparseDnVecDescr) :: descr
  real(4), device :: values(*)

5.9.17. cusparseCreateCoo

This function initializes the sparse matrix descriptor in COO format used in the generic API. The type, kind, and rank of the input arguments cooRowInd, cooColInd, and cooValues are actually ignored, and taken from the input arguments idxType and valueType. The idxBase argument is typically CUSPARSE_INDEX_BASE_ONE in Fortran.

integer(4) function cusparseCreateCoo(descr, rows, cols, nnz, cooRowInd, cooColInd, cooValues, idxType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz
  integer(4), device :: cooRowInd(*), cooColInd(*)
  real(4), device    :: cooValues(*)
  integer(4) :: idxType, idxBase, valueType

5.9.18. cusparseCreateCooAoS

This function initializes the sparse matrix descriptor in COO format, with Array of Structures layout, used in the generic API. The type, kind, and rank of the input arguments cooInd and cooValues are actually ignored, and taken from the input arguments idxType and valueType. The idxBase argument is typically CUSPARSE_INDEX_BASE_ONE in Fortran.

integer(4) function cusparseCreateCooAoS(descr, rows, cols, nnz, cooInd, cooValues, idxType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz
  integer(4), device :: cooInd(*)
  real(4), device    :: cooValues(*)
  integer(4) :: idxType, idxBase, valueType

5.9.19. cusparseCreateCsr

This function initializes the sparse matrix descriptor in CSR format used in the generic API. The type, kind, and rank of the input arguments csrRowOffsets, csrColInd, and csrValues are actually ignored, and taken from the input arguments csrRowOffsetsType, csrColIndType, and valueType. The idxBase argument is typically CUSPARSE_INDEX_BASE_ONE in Fortran.

integer(4) function cusparseCreateCsr(descr, rows, cols, nnz, csrRowOffsets, csrColInd, csrValues, &
           csrRowOffsetsType, csrColIndType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz
  integer(4), device :: csrRowOffsets(*), csrColInd(*)
  real(4), device    :: csrValues(*)
  integer(4) :: csrRowOffsetsType, csrColIndType, idxBase, valueType

5.9.20. cusparseCreateBlockedEll

This function initializes the sparse matrix descriptor in Blocked-Ellpack (ELL) format used in the generic API. The type, kind, and rank of the input arguments ellColInd, and ellValues are actually ignored, and taken from the input arguments ellIdxType, and valueType. The idxBase argument is typically CUSPARSE_INDEX_BASE_ONE in Fortran.

integer(4) function cusparseCreateBlockedEll(descr, rows, cols, &
       ellBlockSize, ellCols, ellColInd, ellValues, ellIdxType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, ellBlockSize, ellCols
  integer(4), device :: ellColInd(*)
  real(4), device    :: ellValues(*)
  integer(4) :: ellIdxType, idxBase, valueType

5.9.21. cusparseDestroySpMat

This function releases the host memory associated with the sparse matrix descriptor used in the generic API.

integer(4) function cusparseDestroySpMat(descr)
  type(cusparseSpMatDescr) :: descr

5.9.22. cusparseCooGet

This function returns the fields from the sparse matrix descriptor in COO format used in the generic API.

integer(4) function cusparseCooGet(descr, rows, cols, nnz, cooRowInd, cooColInd, cooValues, idxType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz
  type(c_devptr) :: cooRowInd, cooColInd, cooValues
  integer(4) :: idxType, idxBase, valueType

5.9.23. cusparseCooAoSGet

This function returns the fields from the sparse matrix descriptor in COO format, Array of Structures layout, used in the generic API.

integer(4) function cusparseCooAoSGet(descr, rows, cols, nnz, cooInd, cooValues, idxType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz
  type(c_devptr) :: cooInd, cooValues
  integer(4) :: idxType, idxBase, valueType

5.9.24. cusparseCsrGet

This function returns the fields from the sparse matrix descriptor in CSR format used in the generic API.

integer(4) function cusparseCsrGet(descr, rows, cols, nnz, csrRowOffsets, csrColInd, csrValues, &
           csrRowOffsetsType, crsColIndType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz
  type(c_devptr) :: csrRowOffsets, csrColInd, csrValues
  integer(4) :: csrRowOffsetsType, csrColIndType, idxBase, valueType

5.9.25. cusparseBlockedEllGet

This function returns the fields from the sparse matrix descriptor stored in Blocked-Ellpack (ELL) format.

integer(4) function cusparseBlockedEllGet(descr, rows, cols, &
       ellBlockSize, ellCols, ellColInd, ellValues, ellIdxType, idxBase, valueType)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, ellBlockSize, ellCols
  type(c_devptr) :: ellColInd, ellValues
  integer(4) :: ellIdxType, idxBase, valueType

5.9.26. cusparseCsrSetPointers

This function sets the pointers in the sparse matrix descriptor in CSR format used in the generic API. Any type for the row offsets, column indices, and values are accepted.

integer(4) function cusparseCsrSetPointers(descr, csrRowOffsets, csrColInd, csrValues)
  type(cusparseSpMatDescr) :: descr
  integer(4), device :: csrRowOffsets(*), csrColInd(*)
  real(4), device :: csrValues(*)

5.9.27. cusparseCscSetPointers

This function sets the pointers in the sparse matrix descriptor in CSC format used in the generic API. Any type for the column offsets, row indices, and values are accepted.

integer(4) function cusparseCscSetPointers(descr, cscColOffsets, cscRowInd, cscValues)
  type(cusparseSpMatDescr) :: descr
  integer(4), device :: cscColOffsets(*), cscRowInd(*)
  real(4), device :: cscValues(*)

5.9.28. cusparseSpMatGetFormat

This function returns the format field within the sparse matrix descriptor used in the generic API. Valid formats for the generic API are CUSPARSE_FORMAT_CSR, CUSPARSE_FORMAT_COO, and CUSPARSE_FORMAT_COO_AOS.

integer(4) function cusparseSpMatGetFormat(descr, format)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: format

5.9.29. cusparseSpMatGetIndexBase

This function returns idxBase field within the sparse matrix descriptor used in the generic API.

integer(4) function cusparseSpMatGetIndexBase(descr, idxBase)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: idxBase

5.9.30. cusparseSpMatGetSize

This function returns the sparse matrix size within the sparse matrix descriptor used in the generic API.

integer(4) function cusparseSpMatGetSize(descr, rows, cols, nnz)
  type(cusparseSpMatDescr) :: descr
  integer(8) :: rows, cols, nnz

5.9.31. cusparseSpMatGetValues

This function returns the values field within the sparse matrix descriptor used in the generic API.

integer(4) function cusparseSpMatGetValues(descr, values)
  type(cusparseSpMatDescr) :: descr
  type(c_devptr) :: values

5.9.32. cusparseSpMatSetValues

This function sets the values field within the sparse matrix descriptor used in the generic API. The type, kind and rank of the values argument is ignored; the type is determined by the valueType field in the descriptor.

integer(4) function cusparseSpMatSetValues(descr, values)
  type(cusparseSpMatDescr) :: descr
  real(4), device :: values(*)

5.9.33. cusparseSpMatGetStridedBatch

This function returns the batchCount field within the sparse matrix descriptor used in the generic API.

integer(4) function cusparseSpMatGetStridedBatch(descr, batchCount)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: batchCount

5.9.34. cusparseSpMatSetStridedBatch

This function sets the batchCount field within the sparse matrix descriptor used in the generic API. It is removed in versions >= CUDA 12.0.

integer(4) function cusparseSpMatSetStridedBatch(descr, batchCount)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: batchCount

5.9.35. cusparseCooSetStridedBatch

This function sets the batchCount and batchStride field within the COO sparse matrix descriptor.

integer(4) function cusparseCooSetStridedBatch(descr, batchCount, &
      batchStride)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: batchCount
  integer(8) :: batchStride

5.9.36. cusparseCsrSetStridedBatch

This function sets the batchCount and batchStride fields within the CSR sparse matrix descriptor.

integer(4) function cusparseCsrSetStridedBatch(descr, batchCount, &
      offsetsBatchStride, columnsValuesBatchStride)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: batchCount
  integer(8) :: offsetsBatchStride, columnsValuesBatchStride

5.9.37. cusparseBsrSetStridedBatch

This function sets the batchCount and batchStride fields within the BSR sparse matrix descriptor.

integer(4) function cusparseBsrSetStridedBatch(descr, batchCount, &
      offsetsBatchStride, columnsBatchStride, valuesBatchStride)
  type(cusparseSpMatDescr) :: descr
  integer(4) :: batchCount
  integer(8) :: offsetsBatchStride, columnsBatchStride
  integer(8) :: valuesBatchStride

5.9.38. cusparseSpMatGetAttribute

This function returns the sparse matrix attribute from the sparse matrix descriptor used in the generic API. Attribute can currently be CUSPARSE_SPMAT_FILL_MODE or CUSPARSE_SPMAT_DIAG_TYPE.

integer(4) function cusparseSpMatGetAttribute(descr, attribute, data, dataSize)
  type(cusparseSpMatDescr), intent(in) :: descr
  integer(4), intent(in)  :: attribute
  integer(4), intent(out) :: data
  integer(8), intent(in)  :: dataSize

5.9.39. cusparseSpMatSetAttribute

This function sets the sparse matrix attribute for the sparse matrix descriptor used in the generic API. Attribute can currently be CUSPARSE_SPMAT_FILL_MODE or CUSPARSE_SPMAT_DIAG_TYPE.

integer(4) function cusparseSpMatSetAttribute(descr, attribute, data, dataSize)
  type(cusparseSpMatDescr), intent(out) :: descr
  integer(4), intent(in) :: attribute
  integer(4), intent(in) :: data
  integer(8), intent(in) :: dataSize

5.9.40. cusparseCreateDnMat

This function initializes the dense matrix descriptor used in the generic API. The type, kind, and rank of the values input argument is ignored, and taken from the input argument valueType. The order argument in Fortran should normally be CUSPARSE_ORDER_COL.

integer(4) function cusparseCreateDnMat(descr, rows, cols, ld, values, valueType, order)
  type(cusparseDnMatDescr) :: descr
  integer(8) :: rows, cols, ld
  real(4), device    :: values(*)
  integer(4), value  :: valueType, order

5.9.41. cusparseDestroyDnMat

This function releases the host memory associated with the dense matrix descriptor used in the generic API.

integer(4) function cusparseDestroyDnMat(descr)
  type(cusparseDnMatDescr) :: descr

5.9.42. cusparseDnMatGet

This function returns the fields from the dense matrix descriptor used in the generic API.

integer(4) function cusparseDnMatGet(descr, rows, cols, ld, values, valueType, order)
  type(cusparseDnMatDescr) :: descr
  integer(8) :: rows, cols, ld
  type(c_devptr) :: values
  integer(4) :: valueType, order

5.9.43. cusparseDnMatGetValues

This function returns the values field within the dense matrix descriptor used in the generic API.

integer(4) function cusparseDnMatGetValues(descr, values)
  type(cusparseDnMatDescr) :: descr
  type(c_devptr) :: values

5.9.44. cusparseDnMatSetValues

This function sets the values field within the dense matrix descriptor used in the generic API. The type, kind and rank of the values argument is ignored; the type is determined by the valueType field in the descriptor.

integer(4) function cusparseDnMatSetValues(descr, values)
  type(cusparseDnMatDescr) :: descr
  real(4), device :: values(*)

5.9.45. cusparseDnMatGetStridedBatch

This function returns the batchCount field within the dense matrix descriptor used in the generic API.

integer(4) function cusparseDnMatGetStridedBatch(descr, batchCount)
  type(cusparseDnMatDescr) :: descr
  integer(4) :: batchCount

5.9.46. cusparseDnMatSetStridedBatch

This function sets the batchCount field within the dense matrix descriptor used in the generic API.

integer(4) function cusparseDnMatSetStridedBatch(descr, batchCount)
  type(cusparseDnMatDescr) :: descr
  integer(4) :: batchCount

5.9.47. cusparseSpVV_bufferSize

This function returns the size of the workspace needed by cusparseSpVV(). The value returned is in bytes.

integer(4) function cusparseSpVV_bufferSize(handle, opX, vecX, vecY, result, computeType, bufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: opX
  type(cusparseSpVecDescr) :: vecX
  type(cusparseDnVecDescr) :: vecY
  real(4), device    :: result ! device or host variable
  integer(4) :: computeType
  integer(8), intent(out) :: bufferSize

5.9.48. cusparseSpVV

This function forms the dot product of a sparse vector vecX and a dense vector vecY. The buffer argument can be any type, but the size should be greater than or equal to the size returned from cusparseSpVV_buffersize(). See the cuSPARSE Library documentation for datatype and computetype combinations supported in each release.

integer(4) function cusparseSpVV(handle, opX, vecX, vecY, result, computeType, buffer)
  type(cusparseHandle) :: handle
  integer(4) :: opX
  type(cusparseSpVecDescr) :: vecX
  type(cusparseDnVecDescr) :: vecY
  real(4), device    :: result ! device or host variable
  integer(4) :: computeType
  integer(4), device :: buffer(*)

5.9.49. cusparseSpMV_bufferSize

This function returns the size of the workspace needed by cusparseSpMV(). The value returned is in bytes.

integer(4) function cusparseSpMV_bufferSize(handle, opA, alpha, matA, vecX, beta, vecY, computeType, alg, bufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: opA
  real(4) :: alpha, beta ! device or host variable
  type(cusparseSpMatDescr) :: matA
  type(cusparseDnVecDescr) :: vecX, vecY
  integer(4) :: computeType, alg
  integer(8), intent(out) :: bufferSize

5.9.50. cusparseSpMV

This function forms the multiplication of a sparse matrix matA and a dense vector vecX to produce dense vector vecY. The buffer argument can be any type, but the size should be greater than or equal to the size returned from cusparseSpMV_buffersize(). The type of arguments alpha and beta should match the computeType argument. See the cuSPARSE Library documentation for the datatype, computeType, sparse format, and alg combinations supported in each release.

integer(4) function cusparseSpMV(handle, opA, alpha, matA, vecX, beta, vecY, computeType, alg, buffer)
  type(cusparseHandle) :: handle
  integer(4) :: opA
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseSpMatDescr) :: matA
  type(cusparseDnVecDescr) :: vecX, vecY
  integer(4) :: computeType, alg
  integer(4), device :: buffer(*)

5.9.51. cusparseSpSV_CreateDescr

This function initializes the sparse matrix descriptor used in solving a sparse triangular system.

integer(4) function cusparseSpSV_CreateDescr(descr)
  type(cusparseSpSVDescr) :: descr

5.9.52. cusparseSpSV_DestroyDescr

This function frees and destroys the sparse matrix descriptor used in solving a sparse triangular system.

integer(4) function cusparseSpSV_DestroyDescr(descr)
  type(cusparseSpSVDescr) :: descr

5.9.53. cusparseSpSV_bufferSize

This function returns the size of the workspace needed by cusparseSpSV(). The value returned is in bytes.

integer(4) function cusparseSpSV_bufferSize(handle, opA, alpha, matA, vecX, vecY, &
  computeType, alg, spsvDescr, bufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: opA
  real(4) :: alpha ! device or host variable
  type(cusparseSpMatDescr) :: matA
  type(cusparseDnVecDescr) :: vecX, vecY
  integer(4) :: computeType, alg
  type(cusparseSpSVDescr) :: spsvDescr
  integer(8), intent(out) :: bufferSize

5.9.54. cusparseSpSV_analysis

This function performs the analysis phase needed by cusparseSpSV().

integer(4) function cusparseSpSV_analysis(handle, opA, alpha, matA, vecX, vecY, &
  computeType, alg, spsvDescr, buffer)
  type(cusparseHandle) :: handle
  integer(4) :: opA
  real(4) :: alpha ! device or host variable
  type(cusparseSpMatDescr) :: matA
  type(cusparseDnVecDescr) :: vecX, vecY
  integer(4) :: computeType, alg
  type(cusparseSpSVDescr) :: spsvDescr
  integer(4), device :: buffer(*)

5.9.55. cusparseSpSV_solve

This function executes the solve phase for the sparse triangular linear system.

integer(4) function cusparseSpSV_analysis(handle, opA, alpha, matA, vecX, vecY, &
  computeType, alg, spsvDescr)
  type(cusparseHandle) :: handle
  integer(4) :: opA
  real(4) :: alpha ! device or host variable
  type(cusparseSpMatDescr) :: matA
  type(cusparseDnVecDescr) :: vecX, vecY
  integer(4) :: computeType, alg
  type(cusparseSpSVDescr) :: spsvDescr

5.9.56. cusparseSpSV_updateMatrix

This function updates the values in the sparse matrix used by cusparseSpSV(). The value type should match the sparse matrix type. The updates can be to the entire matrix, CUSPARSE_SPSV_UPDATE_GENERAL, or to the diagonal, CUSPARSE_SPSV_UPDATE_DIAGONAL.

integer(4) function cusparseSpSV_updateMatrix(handle, spsvDescr, &
      newValues, updatePart)
  type(cusparseHandle) :: handle
  type(cusparseSpSVDescr) :: spsvDescr
  real(4), device :: newValues(*)  ! Any type, same as the Matrix
  integer(4) :: updatePart  ! General or Diagonal

5.9.57. cusparseSpMM_bufferSize

This function returns the size of the workspace needed by cusparseSpMM(). The value returned is in bytes.

integer(4) function cusparseSpMM_bufferSize(handle, opA, opB, alpha, matA, matB, beta, matC, computeType, alg, bufferSize)
  type(cusparseHandle) :: handle
  integer(4) :: opA, opB
  real(4), device :: alpha, beta ! device or host variable
  type(cusparseSpMatDescr