DeviceGemmReduce< NumDTensor, NumReduce > Struct Template Reference#
#include <device_gemm_reduce.hpp>
Public Member Functions | |
| virtual std::unique_ptr< BaseArgument > | MakeArgumentPointer (const void *p_a, const void *p_b, const void *p_bias, std::array< const void *, NumDTensor > p_ds, void *p_c, std::array< void *, NumReduce > p_reduces, ck::index_t M, ck::index_t N, ck::index_t K, ck::index_t StrideA, ck::index_t StrideB, ck::index_t StrideC, std::array< ck::index_t, NumDTensor > StrideDs, std::array< void *, 3 > gemm_element_ops, std::array< void *, NumDTensor > d_element_ops, std::array< void *, NumReduce > reduce_in_element_ops, std::array< void *, NumReduce > reduce_out_element_ops, ck::index_t BatchCount=1)=0 |
| virtual std::unique_ptr< BaseInvoker > | MakeInvokerPointer ()=0 |
| Public Member Functions inherited from ck::tensor_operation::device::BaseOperator | |
| BaseOperator ()=default | |
| BaseOperator (const BaseOperator &)=default | |
| BaseOperator & | operator= (const BaseOperator &)=default |
| virtual bool | IsSupportedArgument (const BaseArgument *) |
| virtual std::string | GetTypeString () const |
| virtual std::string | GetInstanceString () const |
| virtual std::string | GetTypeIdName () const |
| virtual std::optional< std::string > | GetObjectName () const |
| virtual std::optional< std::string > | GetTemplateInfo () const |
| virtual std::string | GetTypeIdHashCode () const |
| virtual size_t | GetWorkSpaceSize (const BaseArgument *) const |
| virtual void | SetWorkSpacePointer (BaseArgument *p_arg, void *p_workspace, const StreamConfig &=StreamConfig{}) const |
| virtual | ~BaseOperator () |
Member Function Documentation
◆ MakeArgumentPointer()
|
pure virtual |
◆ MakeInvokerPointer()
|
pure virtual |
Implemented in ck::tensor_operation::device::DeviceBatchedGemmReduce_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, ReducePtrsGlobal, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock, LoopSched >, ck::tensor_operation::device::DeviceGemmBiasAddReduce_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, BiasDataType, D0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, ReducePtrsGlobal, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, D0ElementwiseOperation, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock, LoopSched >, and ck::tensor_operation::device::DeviceGemmReduce_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, ReducePtrsGlobal, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock, LoopSched >.
The documentation for this struct was generated from the following file: