docs/memory__sm75_8h.html
| | CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers |
Namespaces | Macros | Functions
memory_sm75.h File Reference
Architecture-specific operators on memory added for SM75. More...
#include "cutlass/array.h"
#include "cutlass/layout/matrix.h"
Include dependency graph for memory_sm75.h:
This graph shows which files directly or indirectly include this file:
Go to the source code of this file.
|
| | | cutlass | | | | | cutlass::arch | | |
|
| | #define | CUDA_NVVM_GET_SHARED_POINTER_SUPPORTED 0 | | | | #define | CUDA_NVVM_GET_SHARED_POINTER_ENABLED (CUDA_NVVM_GET_SHARED_POINTER_SUPPORTED) | | | | #define | CUDA_LDMATRIX_SUPPORTED ((__CUDACC_VER_MAJOR__ == 10) && (__CUDACC_VER_MINOR__ >= 2)) | | | | #define | CUDA_LDMATRIX_ENABLED (CUDA_LDMATRIX_SUPPORTED) | | | | #define | CUDA_LDMATRIX_ACTIVATED 0 | | |
|
| | template<typename Layout , int MatrixCount> | | __device__ void | cutlass::arch::ldsm (Array< unsigned, MatrixCount > &D, void const *ptr) | | | | template<> | | __device__ void | cutlass::arch::ldsm< layout::RowMajor, 1 > (Array< unsigned, 1 > &D, void const *ptr) | | | | template<> | | __device__ void | cutlass::arch::ldsm< layout::RowMajor, 2 > (Array< unsigned, 2 > &D, void const *ptr) | | | | template<> | | __device__ void | cutlass::arch::ldsm< layout::RowMajor, 4 > (Array< unsigned, 4 > &D, void const *ptr) | | | | template<> | | __device__ void | cutlass::arch::ldsm< layout::ColumnMajor, 1 > (Array< unsigned, 1 > &D, void const *ptr) | | | | template<> | | __device__ void | cutlass::arch::ldsm< layout::ColumnMajor, 2 > (Array< unsigned, 2 > &D, void const *ptr) | | | | template<> | | __device__ void | cutlass::arch::ldsm< layout::ColumnMajor, 4 > (Array< unsigned, 4 > &D, void const *ptr) | | |
| #define CUDA_LDMATRIX_ACTIVATED 0 |
| #define CUDA_LDMATRIX_ENABLED (CUDA_LDMATRIX_SUPPORTED) |
| #define CUDA_LDMATRIX_SUPPORTED ((__CUDACC_VER_MAJOR__ == 10) && (__CUDACC_VER_MINOR__ >= 2)) |
| #define CUDA_NVVM_GET_SHARED_POINTER_ENABLED (CUDA_NVVM_GET_SHARED_POINTER_SUPPORTED) |
| #define CUDA_NVVM_GET_SHARED_POINTER_SUPPORTED 0 |
Generated by 1.8.11