cuBLASDx
0.2.0
Documentation home
User guide:
Requirements and Functionality
Requirements
Supported Compilers
Supported Functionality
Supported GEMM Data Types
Quick Installation Guide
cuBLASDx In Your Project
cuBLASDx In Your CMake Project
Using Custom CUTLASS
Defined Variables
General Matrix Multiply Using cuBLASDx
Defining GEMM Operation
Executing GEMM
Tensor Creation
Copying Tensors
Launching GEMM Kernel
Compilation
Achieving High Performance
General Advice
Matrix Layouts
Memory Management
Advanced
Further Reading
References
API reference
Operators
Description Operators
Size Operator
Type Operator
Precision Operator
Arrangement Operator
TransposeMode Operator
LeadingDimension Operator
Alignment Operator
Function Operator
SM Operator
Execution Operators
Block Operator
Block Configuration Operators
Traits
Description Traits
Size Trait
Type Trait
Precision Trait
Function Trait
Arrangement Trait
Transpose Mode Trait
Alignment Trait
Suggested Alignment Trait
SM Trait
is_blas Trait
is_blas_execution Trait
is_complete_blas Trait
is_complete_blas_execution Trait
Execution Traits
Block Traits
Other Traits
is_supported
suggested_leading_dimension_of
Execution Methods
Block Execute Method
Value Format
Input/Output Data Format
Shared Memory Usage
Other Methods
Shared Memory Slicing
Get Memory Layout
Suggested Shared Memory Layout
Other
Tensor
Tensor Creation
Copying Tensors
Examples
Introduction Examples
Simple GEMM Examples
NVRTC Examples
GEMM Performance
Advanced Examples
Release Notes
0.2.0
New Features
Known Issues
0.1.0
New Features
Known Issues
Software License Agreement
Third Party License Agreements
CUTLASS
cuBLASDx
Search
Please activate JavaScript to enable the search functionality.