|  | CUTLASS
    CUDA Templates for Linear Algebra Subroutines and Solvers | 
Template for a pipelined GEMM kernel. Does not compute batching or support split-K. More...
#include "cutlass/cutlass.h"#include "cutlass/aligned_buffer.h"#include "cutlass/array.h"#include "cutlass/numeric_types.h"#include "cutlass/matrix_shape.h"#include "cutlass/gemm/gemm.h"

Go to the source code of this file.
| Namespaces | |
| cutlass | |
| cutlass::gemm | |
| cutlass::gemm::kernel | |
| Functions | |
| template<typename Mma , typename Epilogue , typename ThreadblockSwizzle > | |
| __global__ void | cutlass::gemm::kernel::GemmPipelined (cutlass::gemm::GemmCoord problem_size, cutlass::gemm::GemmCoord grid_tiled_shape, typename Mma::IteratorA::Params params_A, typename Mma::IteratorA::TensorRef ref_A, typename Mma::IteratorB::Params params_B, typename Mma::IteratorB::TensorRef ref_B, typename Epilogue::Params params_epilogue) | 
 1.8.11
 1.8.11