gridwise_gemm_xdl_cshuffle_v1.hpp File Reference

gridwise_gemm_xdl_cshuffle_v1.hpp File Reference#

Composable Kernel: gridwise_gemm_xdl_cshuffle_v1.hpp File Reference
Classes | Namespaces | Functions
gridwise_gemm_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_selector.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_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_k0mk1_k0nk1_mn_xdl_cshuffle_v1< ALayout, BLayout, CLayout, FloatA, FloatB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, CGlobalMemoryDataOperation, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeTypeA, ComputeTypeB >
struct  ck::GridwiseGemm_k0mk1_k0nk1_mn_xdl_cshuffle_v1< ALayout, BLayout, CLayout, FloatA, FloatB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, CGlobalMemoryDataOperation, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeTypeA, ComputeTypeB >::Problem
struct  ck::GridwiseGemm_k0mk1_k0nk1_mn_xdl_cshuffle_v1< ALayout, BLayout, CLayout, FloatA, FloatB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, CGlobalMemoryDataOperation, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeTypeA, ComputeTypeB >::Argument

Namespaces

namespace  ck

Functions

template<typename GridwiseGemm, bool HasMainKBlockLoop>
__global__ void ck::kernel_gemm_xdl_cshuffle_v1 (typename GridwiseGemm::Argument karg)
template<typename GridwiseGemm, typename FloatA, typename FloatB, typename FloatC, bool HasMainKBlockLoop>
__global__ void ck::kernel_gemm_xdl_cshuffle_v1 (const FloatA *__restrict__ p_a_grid, const FloatB *__restrict__ p_b_grid, FloatC *__restrict__ p_c_grid, typename GridwiseGemm::Problem problem)