| AGridDesc_AK0_M_AK1 typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| BaseOperator()=default | ck::tensor_operation::device::BaseOperator | |
| BaseOperator(const BaseOperator &)=default | ck::tensor_operation::device::BaseOperator | |
| BGridDesc_BK0_N_BK1 typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| Block2CTileMap typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| C0GridDesc_N typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| CGridDesc_M_N typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| DeviceOp typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| GetInstanceString() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetObjectName() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTemplateInfo() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTypeIdHashCode() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTypeIdName() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTypeString() const override | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinevirtual |
| GetWorkSpaceSize(const BaseArgument *) const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GridwiseGemm32 typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| GridwiseGemm64 typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| GridwiseGemmBase typedef | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | |
| I0 | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | static |
| I1 | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | static |
| I2 | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | static |
| IsSupportedArgument(const Argument &arg) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| IsSupportedArgument(const BaseArgument *p_arg) override | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinevirtual |
| IsValidCompilationParameter() | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeAGridDescriptor_AK0_M_AK1(index_t MRaw, index_t KRaw, index_t StrideA) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeArgument(const ADataType *p_a, const BDataType *p_b, CDataType *p_c, const C0DataType *p_c0_bias, const C0DataType *p_c0_add, const C0DataType *p_c0_gamma, const C0DataType *p_c0_beta, index_t MRaw, index_t NRaw, index_t KRaw, index_t StrideA, index_t StrideB, index_t StrideC, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, AccElementwiseOperation acc_element_op, CElementwiseOperation c_element_op) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeArgumentPointer(const void *p_a, const void *p_b, void *p_c, const void *p_c0_bias, const void *p_c0_add, const void *p_c0_gamma, const void *p_c0_beta, index_t MRaw, index_t NRaw, index_t KRaw, index_t StrideA, index_t StrideB, index_t StrideC, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, AccElementwiseOperation acc_element_op, CElementwiseOperation c_element_op, index_t=1) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inline |
| MakeBGridDescriptor_BK0_N_BK1(index_t KRaw, index_t NRaw, index_t StrideB) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeCGridDescriptor_M_N(index_t MRaw, index_t NRaw, index_t StrideC) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeGridDescriptor_N(index_t NRaw) | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeInvoker() | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inlinestatic |
| MakeInvokerPointer() | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | inline |
| NXdlPerWave32 | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | static |
| NXdlPerWave64 | ck::tensor_operation::device::DeviceGemmLayerNorm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, C0DataType, GemmAccDataType, CShuffleDataType, ReduceAccDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched > | static |
| operator=(const BaseOperator &)=default | ck::tensor_operation::device::BaseOperator | |
| SetWorkSpacePointer(BaseArgument *p_arg, void *p_workspace, const StreamConfig &=StreamConfig{}) const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| ~BaseOperator() | ck::tensor_operation::device::BaseOperator | inlinevirtual |