/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/docs-6.4.3/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp File Reference

• docs-6.4.3
• include
• ck
• tensor_operation
• gpu
• grid

Classes | Namespaces | Functions

gridwise_gemm_wmma.hpp File Reference

#include "ck/utility/common_header.hpp"
#include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp"
#include "ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp"
#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp"
#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp"
#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"

Go to the source code of this file.

Classes
struct	ck::GridwiseGemm_Wmma< BlockSize, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, CGlobalMemoryDataOperation, AGridDesc, BGridDesc, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, KPerBlock, MPerWmma, NPerWmma, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BEnableLds, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer >
struct	ck::GridwiseGemm_Wmma< BlockSize, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, CGlobalMemoryDataOperation, AGridDesc, BGridDesc, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, KPerBlock, MPerWmma, NPerWmma, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BEnableLds, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer >::SharedMemTrait

Namespaces
	ck

Functions
template<typename GridwiseGemm , typename ADataType , typename BDataType , typename CDataType , typename AGridDesc , typename BGridDesc , typename CGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock , typename AElementwiseOperation , typename BElementwiseOperation , typename CElementwiseOperation , typename Block2CTileMap , bool HasMainKBlockLoop>
__global__ void	ck::kernel_gemm_wmma (const ADataType *__restrict__ p_a_grid, const BDataType *__restrict__ p_b_grid, CDataType *__restrict__ p_c_grid, const AGridDesc a_grid_desc, const BGridDesc b_grid_desc, const CGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock c_grid_desc_mblock_mperblock_nblock_nperblock, const AElementwiseOperation a_element_op, const BElementwiseOperation b_element_op, const CElementwiseOperation c_element_op, const Block2CTileMap block_2_ctile_map)