gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp File Reference

• include
• ck
• tensor_operation
• gpu
• grid

Classes | Namespaces

gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.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_v1.hpp"
#include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.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_v7.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::GridwiseBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle< A0B0B1DataType, Acc0DataType, D0sDataType, Acc1DataType, C1ShuffleDataType, D1sDataType, E1DataType, A0ElementwiseOperation, B0ElementwiseOperation, CDE0ElementwiseOperation, B1ElementwiseOperation, CDE1ElementwiseOperation, E1GlobalMemoryDataOperation, A0GridDesc_M_K, B0GridDesc_N_K, D0sGridDesc_M_N, B1GridDesc_N_K, D1sGridDesc_M_N, E1GridDesc_M_N, NumGemm0KPrefetchStage, BlockSize, Gemm0MPerBlock, Gemm0NPerBlock, Gemm0KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, A0K1Value, B0K1Value, B1K1Value, Gemm0MPerXdl, Gemm0NPerXdl, Gemm0MXdlPerWave, Gemm0NXdlPerWave, Gemm1NXdlPerWave, A0BlockTransferThreadClusterLengths_AK0_M_AK1, A0BlockTransferThreadClusterArrangeOrder, A0BlockTransferSrcAccessOrder, A0BlockTransferSrcVectorDim, A0BlockTransferSrcScalarPerVector, A0BlockTransferDstScalarPerVector_AK1, A0ThreadTransferSrcResetCoordinateAfterRun, A0BlockLdsExtraM, B0BlockTransferThreadClusterLengths_BK0_N_BK1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_BK1, B0ThreadTransferSrcResetCoordinateAfterRun, B0BlockLdsExtraN, CDE0BlockTransferSrcVectorDim, CDE0BlockTransferSrcScalarPerVector, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, C1ShuffleGemm0MXdlPerWavePerShuffle, C1ShuffleGemm0NXdlPerWavePerShuffle, CDE1ShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDE1ShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >
struct	ck::GridwiseBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle< A0B0B1DataType, Acc0DataType, D0sDataType, Acc1DataType, C1ShuffleDataType, D1sDataType, E1DataType, A0ElementwiseOperation, B0ElementwiseOperation, CDE0ElementwiseOperation, B1ElementwiseOperation, CDE1ElementwiseOperation, E1GlobalMemoryDataOperation, A0GridDesc_M_K, B0GridDesc_N_K, D0sGridDesc_M_N, B1GridDesc_N_K, D1sGridDesc_M_N, E1GridDesc_M_N, NumGemm0KPrefetchStage, BlockSize, Gemm0MPerBlock, Gemm0NPerBlock, Gemm0KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, A0K1Value, B0K1Value, B1K1Value, Gemm0MPerXdl, Gemm0NPerXdl, Gemm0MXdlPerWave, Gemm0NXdlPerWave, Gemm1NXdlPerWave, A0BlockTransferThreadClusterLengths_AK0_M_AK1, A0BlockTransferThreadClusterArrangeOrder, A0BlockTransferSrcAccessOrder, A0BlockTransferSrcVectorDim, A0BlockTransferSrcScalarPerVector, A0BlockTransferDstScalarPerVector_AK1, A0ThreadTransferSrcResetCoordinateAfterRun, A0BlockLdsExtraM, B0BlockTransferThreadClusterLengths_BK0_N_BK1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_BK1, B0ThreadTransferSrcResetCoordinateAfterRun, B0BlockLdsExtraN, CDE0BlockTransferSrcVectorDim, CDE0BlockTransferSrcScalarPerVector, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, C1ShuffleGemm0MXdlPerWavePerShuffle, C1ShuffleGemm0NXdlPerWavePerShuffle, CDE1ShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDE1ShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >::SharedMemTrait

Namespaces
namespace	ck