gridwise_batched_gemm_softmax_gemm_wmma_cshuffle.hpp File Reference

• include
• ck
• tensor_operation
• gpu
• grid

Classes | Namespaces

gridwise_batched_gemm_softmax_gemm_wmma_cshuffle.hpp File Reference

#include "ck/utility/env.hpp"
#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"
#include "ck/tensor_operation/gpu/block/blockwise_softmax.hpp"

Go to the source code of this file.

Classes
struct	ck::GridwiseBatchedGemmSoftmaxGemm_Wmma< ADataType, B0DataType, Acc0DataType, B1DataType, Acc1DataType, CShuffleDataType, CDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc, B0GridDesc, B1GridDesc, CGridDesc_M_N, MPerBlock, LPerBlock, KPerBlock, AK1Value, BK1Value, NPerBlock, LTilePerBlock, L1Value, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, BlockSize, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0ThreadTransferSrcResetCoordinateAfterRun, B0EnableLds, B0BlockLdsExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1ThreadTransferSrcResetCoordinateAfterRun, B1EnableLds, B1BlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, PadN, MaskOutUpperTriangle, NumGemmKPrefetchStage, LoopSched, PipelineVer >
struct	ck::GridwiseBatchedGemmSoftmaxGemm_Wmma< ADataType, B0DataType, Acc0DataType, B1DataType, Acc1DataType, CShuffleDataType, CDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc, B0GridDesc, B1GridDesc, CGridDesc_M_N, MPerBlock, LPerBlock, KPerBlock, AK1Value, BK1Value, NPerBlock, LTilePerBlock, L1Value, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, BlockSize, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0ThreadTransferSrcResetCoordinateAfterRun, B0EnableLds, B0BlockLdsExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1ThreadTransferSrcResetCoordinateAfterRun, B1EnableLds, B1BlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, PadN, MaskOutUpperTriangle, NumGemmKPrefetchStage, LoopSched, PipelineVer >::SharedMemTrait

Namespaces
namespace	ck