NVIDIA cuDSS (Preview): A high-performance CUDA Library for Direct Sparse Solvers#
NVIDIA cuDSS (Preview) is a library of GPU-accelerated linear solvers with sparse matrices. It provides algorithms for solving linear systems of the following type:
with a sparse matrix \(A\), right-hand side \(B\) and unknown solution \(X\) (could be a matrix or a vector).
The cuDSS functionality allows flexibility in matrix properties and solver configuration, as well as execution parameters like CUDA streams.
Note: Since the library is released as a preview, API is subject to change in later releases.
Download: developer.nvidia.com/cudss-downloads
Provide Feedback: cuDSS-EXTERNAL-Group@nvidia.com
Examples: cuDSS Example 1, cuDSS Example 2, cuDSS Example 3 cuDSS Example 4
Key Features and Properties#
Real/complex general/symmetric/positive-definite sparse matrices
Non-uniform batching (solving multiple different systems of different sizes)
Single and double precision datatype for values and
int
datatype for indicesSingle and multiple right-hand sides
Multi-stage execution with three main phases: reordering & symbolic factorization, numerical factorization and solving
Different algorithms for reordering and factorization phases
Refactorization
Iterative refinement
User-defined device memory handlers and memory pools
Hybrid host/device memory mode/algorithm
Hybrid host/device execution mode
Multi-GPU multi-node (MGMN) execution with a user-definable communication layer
Multi-Threaded (MT) execution with a user-definable threading layer
Multi-threaded reordering for the default reordering algorithm
Synchronous API (asynchronous for factorization and solve when host memory/execution modes are not enabled)
Non-deterministic computations (no bit-wise reproducibility)
Support#
Supported configurations: single GPU, multi-GPU multi-node (MGMN)
Supported SM Architectures: all
SM
starting with Pascal (SM_87
andSM_101
only for aarch64 + Jetson build)Supported OSes:
Linux
,Windows
Supported CPU Architectures:
x86_64
,ARM (SBSA)
,ARM (aarch64/Jetson) for Orin and Thor devices
Supported communication backends (for MGMN mode): pre-built for OpenMPI 4.x and NCCL 2.x + any GPU-aware stream-aware user-defined
Supported threading backends (for MT mode): pre-built for GNU OpenMP (Linux) and VCOMP (Windows) + any user-defined