/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp File Reference

• develop
• include
• ck
• tensor_operation
• gpu
• grid

Classes | Namespaces | Functions

gridwise_gemm_reduce_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/thread/reduction_functions_threadwise.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"

Go to the source code of this file.

Classes
struct	ck::GridwiseGemmReduce_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, FloatReduceAcc, ReducePtrsGlobal, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, CGlobalMemoryDataOperation, ReduceGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, CGridDesc_M_N, ReduceGridDesc_M, 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, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock, LoopSched, PipelineVer >

Namespaces
	ck

Functions
template<typename GridwiseGemm , typename FloatAB , typename FloatC , typename ReducePtrsGlobal , typename AElementwiseOperation , typename BElementwiseOperation , typename CElementwiseOperation , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename AGridDesc_AK0_M_AK1 , typename BGridDesc_BK0_N_BK1 , typename CGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock , typename ReduceGridDescriptor_MBlock_MPerBlock , typename Block2CTileMap , bool HasMainKBlockLoop>
__global__ void	ck::kernel_gemm_reduce_xdl_cshuffle_v1 (const FloatAB *__restrict__ p_a_grid, const FloatAB *__restrict__ p_b_grid, FloatC *__restrict__ p_c_grid, ReducePtrsGlobal p_reduces_grid, const AElementwiseOperation a_element_op, const BElementwiseOperation b_element_op, const CElementwiseOperation c_element_op, const ReduceInElementwiseOperations reduce_in_element_ops, const ReduceAccElementwiseOperations reduce_out_element_ops, const AGridDesc_AK0_M_AK1 a_grid_desc_ak0_m_ak1, const BGridDesc_BK0_N_BK1 b_grid_desc_bk0_n_bk1, const CGridDescriptor_MBlock_MPerBlock_NBlock_NPerBlock c_grid_desc_mblock_mperblock_nblock_nperblock, const ReduceGridDescriptor_MBlock_MPerBlock reduce_grid_desc_mblock_mperblock, const Block2CTileMap block_2_ctile_map)