Class Members

Here is a list of all class members with links to the classes they belong to:

- r -

• r_grid_desc_m_ : ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleDMultipleR_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DELayout, RLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, ConvForwardSpecialization, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument
• rand_val_ptr : ck_tile::FmhaBwdDQDKDVKernel< FmhaPipeline_, KGradEpiloguePipeline_, VGradEpiloguePipeline_ >::FmhaBwdCommonDropoutKargs , ck_tile::FmhaFwdKernel< FmhaPipeline_, EpiloguePipeline_ >::FmhaFwdCommonDropoutKargs
• RandValOutputDataType : ck_tile::BlockFmhaBwdDQDKDVPipelineKRKTRVR< Problem, Policy > , ck_tile::BlockFmhaBwdDQDKDVPipelineKRKTRVRIGLP< Problem, Policy > , ck_tile::BlockFmhaBwdPipelineProblem< QDataType_, KDataType_, VDataType_, GemmDataType_, LSEDataType_, AccDataType_, DDataType_, BiasDataType_, RandValOutputDataType_, ODataType_, OGradDataType_, QGradDataType_, KGradDataType_, VGradDataType_, BiasGradDataType_, BlockFmhaShape_, kIsGroupMode_, kIsDeterministic_, FmhaMask_, FmhaDropout_, Traits_ > , ck_tile::BlockFmhaPipelineProblem< QDataType_, KDataType_, VDataType_, SaccDataType_, SMPLComputeDataType_, BiasDataType_, RandValOutputDataType_, LSEDataType_, PDataType_, OaccDataType_, ODataType_, BlockFmhaShape_, kIsGroupMode_, FmhaMask_, Traits_ > , ck_tile::BlockFmhaPipelineQRKSVS< Problem_, Policy_ > , ck_tile::BlockFmhaPipelineQRKSVSAsync< Problem_, Policy_ > , ck_tile::BlockFmhaPipelineQRKSVSFp8< Problem_, Policy_ > , ck_tile::BlockFmhaPipelineQSKSVS< Problem_, Policy_ > , ck_tile::FmhaBwdDQDKDVKernel< FmhaPipeline_, KGradEpiloguePipeline_, VGradEpiloguePipeline_ > , ck_tile::FmhaFwdKernel< FmhaPipeline_, EpiloguePipeline_ >
• range : ck::BufferResource< T > , ck_tile::buffer_resource
• range0 : ck::sequence_split< Seq, I > , ck_tile::sequence_split< Seq, I >
• range1 : ck::sequence_split< Seq, I > , ck_tile::sequence_split< Seq, I >
• rank : ck_tile::GenericPermuteHostArgs
• raw_lengths_m_n_k_o_ : ck::tensor_operation::device::DeviceBatchedGemmGemm_Xdl_CShuffle< ALayout, BLayout, B1Layout, CLayout, ADataType, BDataType, B1DataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >::Argument , ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemm_Xdl_CShuffle< ALayout, BLayout, B1Layout, CLayout, ADataType, BDataType, B1DataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskOutUpperTriangle, LoopSched >::Argument
• raw_lengths_mz_lz_kz_nz_ : ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Wmma_CShuffle< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::Argument , ck::tensor_operation::device::DeviceGroupedQueryAttentionForward_Wmma< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, QueryGroupNumber, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::Argument , ck::tensor_operation::device::DeviceMultiQueryAttentionForward_Wmma< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::Argument
• raw_lengths_mz_nz_kz_gemm1nz_ : ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, ADataType, BDataType, B1DataType, CDataType, D0sDataType, D1sDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, C0DEElementwiseOperation, B1ElementwiseOperation, C1DEElementwiseOperation, GemmSpec, ASpec, BSpec, B1Spec, CSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, D0sTransferSrcScalarPerVector, LoopSched >::Argument , ck::tensor_operation::device::DeviceGroupedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, ADataType, BDataType, B1DataType, CDataType, Acc0BiasDataType, Acc1BiasDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, BSpec, B1Spec, CSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched >::GroupDeviceArg
• raw_scale : ck_tile::FmhaBwdDQDKDVKernel< FmhaPipeline_, KGradEpiloguePipeline_, VGradEpiloguePipeline_ >::FmhaBwdCommonKargs
• RawArg() : ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Wmma_CShuffle< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::RawArg , ck::tensor_operation::device::DeviceGroupedQueryAttentionForward_Wmma< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, QueryGroupNumber, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::RawArg , ck::tensor_operation::device::DeviceMultiQueryAttentionForward_Wmma< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::RawArg
• Realloc() : ck_tile::DeviceMem , DeviceMem
• Reduce() : ck::PartitionedBlockwiseReduction< AccDataType, BlockSize, ThreadClusterLengths_M_K, ThreadClusterArrangeOrder, OpReduce, PropagateNan, Accumulation > , ck::PartitionedBlockwiseReduction_v2< AccDataType, BlockSize, ThreadClusterLengths_M_K, ThreadClusterDesc, OpReduce, PropagateNan, Accumulation > , ck::PartitionedBlockwiseReductionWithIndex< AccDataType, IndexDataType, BlockSize, ThreadClusterLengths_M_K, ThreadClusterArrangeOrder, OpReduce, PropagateNan, Accumulation > , ck::ThreadwiseReduction< AccDataType, SrcThreadDesc_M_K, DstThreadDesc_M, OpReduce, PropagateNan, Accumulation > , ck::ThreadwiseReductionWithIndex< AccDataType, IndexDataType, SrcThreadDesc_M_K, DstThreadDesc_M, OpReduce, PropagateNan, Accumulation >
• reduce_grid_desc_m_ : 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 >::Argument , 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 >::Argument , 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 >::Argument
• reduce_grid_desc_mblock_mperblock_ : 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 >::Argument , 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 >::Argument , 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 >::Argument
• reduce_in_element_ops_ : 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 >::Argument , 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 >::Argument , 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 >::Argument
• reduce_init : ck_tile::BlockReduce2D< InDistributedTensor_ >
• reduce_length : ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Argument
• reduce_length_ : ck::tensor_operation::device::DeviceBatchNormFwdImpl< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize >::Argument
• reduce_lowest_length : ck::tensor_operation::device::DeviceReduceMultiBlock< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, OutputIndex, HaveIndexInputIfOutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Argument , ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Argument , ck::tensor_operation::device::DeviceReduceThreadWiseMultiD< InDataType, DsDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, OutElementwiseOperation, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, DsVectorSizeSequence >::Argument
• reduce_out_element_ops_ : 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 >::Argument , 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 >::Argument , 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 >::Argument
• reduce_total_length : ck::tensor_operation::device::DeviceMultipleReduceMultiBlock< NumReduction, InDataType, AccDataType, OutDataTypeTuple, Rank, NumReduceDim, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq >::Argument , ck::tensor_operation::device::DeviceMultipleReduceThreadWise< NumReduction, InDataType, AccDataType, OutDataTypeTuple, Rank, NumReduceDim, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq >::Argument , ck::tensor_operation::device::DeviceReduceMultiBlock< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, OutputIndex, HaveIndexInputIfOutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Argument , ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Argument , ck::tensor_operation::device::DeviceReduceThreadWiseMultiD< InDataType, DsDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, OutElementwiseOperation, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, DsVectorSizeSequence >::Argument
• ReduceAdd : ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV3R1< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ReduceDataType, ComputeTypeA, ComputeTypeB >
• reduceAllDim : ck::tensor_operation::device::DeviceMultipleReduceMultiBlock< NumReduction, InDataType, AccDataType, OutDataTypeTuple, Rank, NumReduceDim, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq > , ck::tensor_operation::device::DeviceMultipleReduceThreadWise< NumReduction, InDataType, AccDataType, OutDataTypeTuple, Rank, NumReduceDim, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq > , ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize > , ck::tensor_operation::device::DeviceNormalizationBwdGammaBetaImpl< DYDataType, XDataType, MeanInvStdDataType, ComputeDataType, DGammaDataType, DBetaDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, DGammaDstVectorSize, DBetaDstVectorSize > , ck::tensor_operation::device::DeviceNormalizationFwdImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize, UseWelford > , ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize > , ck::tensor_operation::device::DeviceReduceMultiBlock< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, OutputIndex, HaveIndexInputIfOutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize > , ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize > , ck::tensor_operation::device::DeviceReduceThreadWiseMultiD< InDataType, DsDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, OutElementwiseOperation, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, DsVectorSizeSequence > , ck::tensor_operation::device::DeviceSoftmaxImpl< InDataType, AccDataType, OutDataType, InElementwiseOp, AccElementwiseOp, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >
• ReduceGridDesc_M : 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 > , 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 >
• ReduceGridDescriptor_MBlock_MPerBlock : ck::GridwiseGemmBiasAddReduce_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, FloatC0, FloatC1, FloatReduceAcc, ReducePtrsGlobal, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, C1ElementwiseOperation, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, CGlobalMemoryDataOperation, ReduceGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, CGridDesc_M_N, C0GridDesc_M_N, C1GridDesc_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 > , 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 >
• ReduceOperation : ck::tensor_operation::device::DevicePool2dFwd_NHWC_NHWC< InDataType, OutDataType, IndexDataType, ComputeDataType, ReduceOpId, OutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcOutDstVectorSize > , ck::tensor_operation::device::DevicePool3dFwd_NDHWC_NDHWC< InDataType, OutDataType, IndexDataType, ComputeDataType, ReduceOpId, OutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcOutDstVectorSize >
• reduction_space_offset : ck::GridwiseBatchedGemmMultipleDSoftmaxGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, D0sDataType, AElementwiseOperation, BElementwiseOperation, C0DEElementwiseOperation, B1ElementwiseOperation, C1DEElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, C1GridDesc_M_N, D0sGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PadN, MaskOutUpperTriangle, D0sTransferSrcScalarPerVector, PipelineVer >::SharedMemTrait , 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 , ck::GridwiseBatchedGemmSoftmaxGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, CGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PadN, MaskOutUpperTriangle, PipelineVer >::SharedMemTrait
• reduction_space_size_aligned : ck::GridwiseBatchedGemmMultipleDSoftmaxGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, D0sDataType, AElementwiseOperation, BElementwiseOperation, C0DEElementwiseOperation, B1ElementwiseOperation, C1DEElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, C1GridDesc_M_N, D0sGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PadN, MaskOutUpperTriangle, D0sTransferSrcScalarPerVector, PipelineVer >::SharedMemTrait , 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 , ck::GridwiseBatchedGemmSoftmaxGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, CGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PadN, MaskOutUpperTriangle, PipelineVer >::SharedMemTrait
• reduction_start_block_idx : ck::BlockToCTileMap_GemmStreamK< MPerBlock_, NPerBlock_, KPerBlock_, ReductionStrategy_, TileSwizzleSubM_ > , ck::BlockToCTileMap_GemmStreamK_v2< MPerBlock_, NPerBlock_, KPerBlock_, ReductionStrategy_, TileSwizzleSubM_, GroupNum, M01_ >
• ReductionStrategy : ck::BlockToCTileMap_GemmStreamK< MPerBlock_, NPerBlock_, KPerBlock_, ReductionStrategy_, TileSwizzleSubM_ > , ck::BlockToCTileMap_GemmStreamK_v2< MPerBlock_, NPerBlock_, KPerBlock_, ReductionStrategy_, TileSwizzleSubM_, GroupNum, M01_ >
• reference : ck::span< T > , ck_tile::span< T >
• release() : ck::workgroup_barrier
• relu_ : ck::tensor_operation::element_wise::DynamicUnaryOp
• remaining_slice_sizes : ck_tile::impl::reverse_slice_sequence_impl< sequence< x >, sequence< m >, sequence< id >, SliceSize > , ck_tile::impl::reverse_slice_sequence_impl< sequence< x, xs... >, sequence< m, ms... >, sequence< id, ids... >, SliceSize >
• reorder_new_to_old() : ck_tile::sequence< Is >
• reorder_old_to_new() : ck_tile::sequence< Is >
• reorder_thread_cluster : ck::GridwiseBatchNormBackwardWithBlockwiseWelford< XDataType, DyDataType, DxDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, XYGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize > , ck::GridwiseBatchNormForwardWithBlockwiseWelford< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, XYGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize > , ck::GridwiseElementwiseLayernormWelfordVariance_mk_to_mk< InDataTypePointerTuple, XDataType, GammaDataType, BetaDataType, YDataType, AccDataType, XElementwiseOperation, YElementwiseOperation, InGrid2dDescTuple, GridDesc_M_K, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SweepOnce > , ck::GridwiseMultiblockBatchNormForward< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, XYGridDesc_M_K, MeanVarCountGridDesc_M_G, MeanVarCountGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize > , ck::GridwiseMultiblockWelfordFirstHalf< XDataType, AccDataType, MeanVarDataType, XGridDesc_M_K, MeanVarCountGridDesc_M_G, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcCountSrcVectorDim, XSrcCountSrcVectorSize > , ck::GridwiseMultipleReduction_mk_to_m_multiblock< NumReduction, InDataType, OutDataTypePointerTuple, AccDataType, InGridDesc_M_K, OutGridDesc_M_Tuple, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq > , ck::GridwiseMultipleReduction_mk_to_m_threadwise< NumReduction, InDataType, OutDataTypePointerTuple, AccDataType, InGridDesc_M_K, OutGridDesc_M_Tuple, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq > , ck::GridwiseNormalizationNaiveVariance_mk_to_mk< XDataType, GammaDataType, BetaDataType, YDataType, SaveMeanInvStdDataType, ComputeDataType, YElementwiseOperation, GridDesc_M_K, GridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SaveMeanInvStdDstVectorSize, SweepOnce > , ck::GridwiseNormalizationSplitK1st< XDataType, ComputeDataType, MeanVarDataType, XGridDesc_M_K, MeanVarGridDesc_M_KBlock, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize > , ck::GridwiseNormalizationSplitK2nd< MeanVarDataType, XDataType, GammaDataType, BetaDataType, YDataType, SaveMeanInvStdDataType, ComputeDataType, YElementwiseOperation, MeanVarGridDesc_M_KBlock, CountGridDesc_M_KBlock, XYGammaBetaGridDesc_M_K, SaveMeanInvStdGridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SaveMeanInvStdDstVectorSize > , ck::GridwiseNormalizationWelfordVariance_mk_to_mk< XDataType, GammaDataType, BetaDataType, YDataType, SaveMeanInvStdDataType, ComputeDataType, YElementwiseOperation, GridDesc_M_K, GridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SaveMeanInvStdDstVectorSize, SweepOnce > , ck::GridwiseReduceSecondHalfBatchNormBackwardFinal< XDataType, DyDataType, DxDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, XYGridDesc_M_K, DscaleDbiasGridDesc_M_K, MeanVarGridDesc_M, ScaleBiasGridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize > , ck::GridwiseReduction_mk_to_m_multiblock< InDataType, OutDataType, AccDataType, IndexDataType, InGridDesc_M_K, OutGridDesc_M, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize > , ck::GridwiseSoftmax_mk_to_mk< InDataType, OutDataType, AccDataType, GridDesc_M_K, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, SweepOnce > , ck::GridwiseWelfordSecondHalfBatchNormForwardFinal< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, XYGridDesc_M_K, MeanVarCountGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize > , ck::GridwiseWelfordSecondHalfReduceFirstHalf< XDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, XYGridDesc_M_K, MeanVarGridDesc_M, MeanVarCountGridDesc_M_K, DscaleDbiasGridDesc_M_G, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyVectorDim, XSrcVectorSize, DySrcVectorSize, MeanVarSrcVectorSize >
• ReorderGivenNew2Old() : ck::Sequence< Is >
• ReorderGivenOld2New() : ck::Sequence< Is >
• Repeat_K : ck_tile::Flatmm_32x512x128_1x4x1_16x16x32_Base , ck_tile::FlatmmSn_32x128x512_1x4x1_16x16x32_Base
• Repeat_K0 : ck_tile::FusedMoeGemmShape< BlockTile_0_, WarpPerBlock_0_, WarpTile_0_, BlockTile_1_, WarpPerBlock_1_, WarpTile_1_ >
• Repeat_K1 : ck_tile::FusedMoeGemmShape< BlockTile_0_, WarpPerBlock_0_, WarpTile_0_, BlockTile_1_, WarpPerBlock_1_, WarpTile_1_ >
• Repeat_M : ck_tile::Flatmm_32x512x128_1x4x1_16x16x32_Base , ck_tile::FlatmmSn_32x128x512_1x4x1_16x16x32_Base , ck_tile::Generic2dBlockShape< BlockTile_, WarpPerBlock_, WarpTile_, Vector_ >
• Repeat_M0 : ck_tile::FusedMoeGemmShape< BlockTile_0_, WarpPerBlock_0_, WarpTile_0_, BlockTile_1_, WarpPerBlock_1_, WarpTile_1_ >
• Repeat_M1 : ck_tile::FusedMoeGemmShape< BlockTile_0_, WarpPerBlock_0_, WarpTile_0_, BlockTile_1_, WarpPerBlock_1_, WarpTile_1_ >
• Repeat_N : ck_tile::AddRmsnorm2dRdquantFwd< Pipeline_ > , ck_tile::Flatmm_32x512x128_1x4x1_16x16x32_Base , ck_tile::FlatmmSn_32x128x512_1x4x1_16x16x32_Base , ck_tile::Generic2dBlockShape< BlockTile_, WarpPerBlock_, WarpTile_, Vector_ > , ck_tile::Layernorm2dFwd< Pipeline_, Epilogue_ > , ck_tile::MoeSmoothquant< Pipeline_ > , ck_tile::Rmsnorm2dFwd< Pipeline_, Epilogue_ > , ck_tile::Smoothquant< Pipeline_ >
• Repeat_N0 : ck_tile::FusedMoeGemmShape< BlockTile_0_, WarpPerBlock_0_, WarpTile_0_, BlockTile_1_, WarpPerBlock_1_, WarpTile_1_ >
• Repeat_N1 : ck_tile::FusedMoeGemmShape< BlockTile_0_, WarpPerBlock_0_, WarpTile_0_, BlockTile_1_, WarpPerBlock_1_, WarpTile_1_ >
• replicate() : ck_tile::replicate< UpLengths >
• requantScale_ : ck::tensor_operation::element_wise::Activation_Mul_Clamp< Activation > , ck::tensor_operation::element_wise::Add_Activation_Mul_Clamp< Activation >
• ResetABlockStartWindow() : ck::BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_v1r1< BlockSize, FloatAB, FloatAcc, AK0MK1BlockDesc, BK0K0BN0N1N2N3K1BlockDesc, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack >
• ResetDstSliceWindow() : ck::ThreadGroupTensorSliceTransfer_DirectLoad< ThreadGroup, BlockSliceLengths, ThreadClusterLengths, SrcData, DstData, SrcDesc, DstDesc, SrcVectorDim, DstVectorDim, ScalarPerVector >
• resultRunningMean_ : ck::tensor_operation::device::DeviceBatchNormFwdImpl< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize >::Argument
• resultRunningVariance_ : ck::tensor_operation::device::DeviceBatchNormFwdImpl< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize >::Argument
• resultSaveInvVariance_ : ck::tensor_operation::device::DeviceBatchNormFwdImpl< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize >::Argument
• resultSaveMean_ : ck::tensor_operation::device::DeviceBatchNormFwdImpl< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize >::Argument
• Reverse() : ck::Sequence< Is >
• reverse() : ck_tile::sequence< Is >
• RGridDesc_M : ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched > , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleDMultipleR_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DELayout, RLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, ConvForwardSpecialization, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >
• RGridDescriptor_MBlock_MPerBlock : ck::GridwiseGemmMultipleDMultipleR_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, DsDataType, FloatE, FloatReduceAcc, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, EGlobalMemoryDataOperation, RsGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, EGridDesc_M_N, RGridDesc_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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched, PipelineVer >
• rh_major_minor_to_adaptor_hidden_idss_ : ck_tile::detail::tile_distribution_detail< RhMajorMinor2AdaptorHiddenIdss >
• rhs_lengthss_ : ck_tile::tile_distribution_encoding< RsLengths_, HsLengthss_, Ps2RHssMajor_, Ps2RHssMinor_, Ys2RHsMajor_, Ys2RHsMinor_ >::detail
• rhs_major_minor_to_span_minor_ : ck_tile::tile_distribution_encoding< RsLengths_, HsLengthss_, Ps2RHssMajor_, Ps2RHssMinor_, Ys2RHsMajor_, Ys2RHsMinor_ >::detail
• rhs_major_minor_to_ys_ : ck_tile::tile_distribution_encoding< RsLengths_, HsLengthss_, Ps2RHssMajor_, Ps2RHssMinor_, Ys2RHsMajor_, Ys2RHsMinor_ >::detail
• right_pad() : ck_tile::right_pad< LowLength, RightPadLength, SkipIsValidCheck >
• right_pad_length_ : ck::Pad< LowLength, LeftPadLength, RightPadLength, SkipIsValidCheck > , ck::RightPad< LowLength, RightPadLength, SkipIsValidCheck > , ck_tile::pad< LowLength, LeftPadLength, RightPadLength, SkipIsValidCheck > , ck_tile::right_pad< LowLength, RightPadLength, SkipIsValidCheck >
• right_sort : ck::sequence_sort_impl< Values, Ids, Compare > , ck_tile::sequence_sort_impl< Values, Ids, Compare >
• right_sorted_ids : ck::sequence_sort_impl< Values, Ids, Compare > , ck_tile::sequence_sort_impl< Values, Ids, Compare >
• right_sorted_values : ck::sequence_sort_impl< Values, Ids, Compare > , ck_tile::sequence_sort_impl< Values, Ids, Compare >
• right_type : ck::sequence_split< Seq, I > , ck_tile::sequence_split< Seq, I >
• right_unsorted_ids : ck::sequence_sort_impl< Values, Ids, Compare > , ck_tile::sequence_sort_impl< Values, Ids, Compare >
• right_unsorted_values : ck::sequence_sort_impl< Values, Ids, Compare > , ck_tile::sequence_sort_impl< Values, Ids, Compare >
• RightPad() : ck::RightPad< LowLength, RightPadLength, SkipIsValidCheck >
• rotary_cos_ptr : ck_tile::FmhaFwdAppendKVKernel< FmhaPipeline_ >::RoPEKargs
• rotary_dim : ck_tile::FmhaFwdAppendKVKernel< FmhaPipeline_ >::RoPEKargs
• rotary_sin_ptr : ck_tile::FmhaFwdAppendKVKernel< FmhaPipeline_ >::RoPEKargs
• RotaryEnum : ck_tile::BlockFmhaFwdAppendKVPipeline< Problem_, Policy_ > , ck_tile::BlockFmhaFwdAppendKVPipelineProblem< QDataType_, KDataType_, VDataType_, kM0_, kN0_, kK0_, kN1_, kIsVLayoutRowMajor_, RotaryEnum_, kIsPagedKV_, Traits_ >
• rotating_count : StreamConfig
• RotatingMemWrapper() : ck::utility::RotatingMemWrapper< Argument >
• RotatingMemWrapperMultiD() : ck::utility::RotatingMemWrapperMultiD< Argument, DsDataType >
• round_error() : ck_tile::numeric< T > , ck_tile::numeric< bf8_t > , ck_tile::numeric< bfloat16_t > , ck_tile::numeric< fp8_t > , ck_tile::numeric< half_t > , ck_tile::numeric< int8_t > , ck_tile::numeric< pk_int4_t >
• row_stride_o : ck_tile::FmhaFwdSplitKVCombineKernel< FmhaPipeline_, EpiloguePipeline_ >::CommonKargs
• row_stride_o_acc : ck_tile::FmhaFwdSplitKVCombineKernel< FmhaPipeline_, EpiloguePipeline_ >::CommonKargs
• RowPerSubBlock : ck::GridwiseSparseEmbeddingsForwardLayernorm< EmbType, IndexType, GammaDataType, BetaDataType, AccDataType, OutType, OutGridDesc, EmbElementwiseOperation, BlockSize, DimClusterSize, RowClusterSize, DimPerBlock, RowPerBlock, DimThreadSize, RowVectorSize, NumEmbeddings >
• RowsPerBlock : ck_tile::TopkSoftmaxWarpPerRowProblem< InputType_, WeightType_, IndexType_, Experts_, IssuesPerCol_, BytesPerIssue_, LaunchType_, BlockSize_ >
• RowsPerWarp : ck_tile::TopkSoftmaxWarpPerRowProblem< InputType_, WeightType_, IndexType_, Experts_, IssuesPerCol_, BytesPerIssue_, LaunchType_, BlockSize_ >
• RowsPerWarpPerColIssue : ck_tile::TopkSoftmaxWarpPerRowProblem< InputType_, WeightType_, IndexType_, Experts_, IssuesPerCol_, BytesPerIssue_, LaunchType_, BlockSize_ >
• RowSubBlocks : ck::GridwiseSparseEmbeddingsForwardLayernorm< EmbType, IndexType, GammaDataType, BetaDataType, AccDataType, OutType, OutGridDesc, EmbElementwiseOperation, BlockSize, DimClusterSize, RowClusterSize, DimPerBlock, RowPerBlock, DimThreadSize, RowVectorSize, NumEmbeddings >
• rp_undrop : ck_tile::BlockDropout , ck_tile::BlockDropoutBwd< true, IsWG32_, IsStoreRandval_ > , ck_tile::FmhaBwdDQDKDVKernel< FmhaPipeline_, KGradEpiloguePipeline_, VGradEpiloguePipeline_ >::FmhaBwdCommonDropoutKargs , ck_tile::FmhaFwdKernel< FmhaPipeline_, EpiloguePipeline_ >::FmhaFwdCommonDropoutKargs
• rs_element_op_ : ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleDMultipleR_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DELayout, RLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, ConvForwardSpecialization, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument
• rs_grid_desc_mblock_mperblock_ : ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleDMultipleR_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DELayout, RLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, ConvForwardSpecialization, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument
• rs_lengths_ : ck_tile::tile_distribution_encoding< RsLengths_, HsLengthss_, Ps2RHssMajor_, Ps2RHssMinor_, Ys2RHsMajor_, Ys2RHsMinor_ >
• RsGridPointer : ck::GridwiseGemmMultipleDMultipleR_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, DsDataType, FloatE, FloatReduceAcc, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, EGlobalMemoryDataOperation, RsGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, EGridDesc_M_N, RGridDesc_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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched, PipelineVer >
• RsLengths : ck_tile::tile_distribution_encoding< RsLengths_, HsLengthss_, Ps2RHssMajor_, Ps2RHssMinor_, Ys2RHsMajor_, Ys2RHsMinor_ >
• Run() : ck::BlockwiseGemmDl_A_BK0_BM_BK1_B_BK0_BN_BK1_C_BM0_BM1_BN0_BN1_pipeline_BM0_2_BN0_2< BlockSize, FloatA, FloatB, FloatC, ABlockDesc_BK0_BM_BK1, BBlockDesc_BK0_BN_BK1, BM1PerThreadBM11, BN1PerThreadBN11, BK0PerThread, BM10BN10ThreadClusterBM10Xs, BM10BN10ThreadClusterBN10Xs, AThreadCopyScalarPerVector_BM11, BThreadCopyScalarPerVector_BN11, type > , ck::BlockwiseGemmDlops_km_kn_m0m1n0n1_v2r2_pipeline_2x2< BlockSize, FloatA, FloatB, FloatC, AKMBlockDesc, BKNBlockDesc, M1PerThreadM11, N1PerThreadN11, KPerThread, M1N1ThreadClusterM100, M1N1ThreadClusterN100, M1N1ThreadClusterM101, M1N1ThreadClusterN101, AThreadCopyScalarPerVector_M11, BThreadCopyScalarPerVector_N11, type > , ck::BlockwiseGemmDlops_km_kn_m0m1n0n1_v3< BlockSize, FloatA, FloatB, FloatC, ABlockDesc_E1_K1_E2, BBlockDesc_E1_N_Ho_Wo_E2, CThreadDesc_K_N_Ho_Wo, EPerThreadLoop, KPerThreadLoop > , ck::BlockwiseGemmDpp_ak0mak1_bk0nbk1_m0n0m1n1m2n2< BlockSize, ABDataType, AccDataType, AK0MK1BlockDesc, BK0NK1BlockDesc, MPerDpp, NPerDpp, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmWMMA< BlockSize, FloatA, FloatB, FloatAcc, ABlockDesc, BBlockDesc, MPerBlock, NPerBlock, KPerBlock, MPerWMMA, NPerWMMA, MRepeat, NRepeat, KPack, AEnableLds, BEnableLds, TransposeC > , ck::BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_v1< BlockSize, FloatA, FloatB, FloatAcc, AK0MK1BlockDesc, BK0NK1BlockDesc, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack, ComputeTypeA, ComputeTypeB > , ck::BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_v1r1< BlockSize, FloatAB, FloatAcc, AK0MK1BlockDesc, BK0K0BN0N1N2N3K1BlockDesc, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v1< BlockGemmPipelineScheduler::Interwave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v1< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v1_ab_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v1_b_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v2< BlockGemmPipelineScheduler::Interwave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v2< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v2_ab_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v2_b_scale< BlockGemmPipelineScheduler::Interwave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v2_b_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v3< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v3_ab_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v3_b_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v4< BlockSize, FloatAB, FloatAcc, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack, TransposeC, AMmaKStride, BMmaKStride > , ck::BlockwiseGemmXdlops_pipeline_v4< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v4_b_scale< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_pipeline_v5< BlockGemmPipelineScheduler::Intrawave, BlockSize, ADataType, BDataType, ComputeDataType, AccDataType, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, ABlockTransferSrcScalarPerVector, BBlockTransferSrcScalarPerVector, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack > , ck::BlockwiseGemmXdlops_v2< BlockSize, FloatAB, FloatAcc, ATileDesc, BTileDesc, AMmaTileDesc, BMmaTileDesc, MPerBlock, NPerBlock, KPerBlock, MPerXDL, NPerXDL, MRepeat, NRepeat, KPack, TransposeC, AMmaKStride, BMmaKStride > , ck::BlockwiseSoftmax< BlockSize, AccDataType, ThreadMap_M_K, ThreadClusterDesc_M_K, ThreadSliceDesc_M_K, IgnoreNaN > , ck::BlockwiseWelford< T, BlockSize, ThreadClusterLengths_M_K, ThreadClusterArrangeOrder, GetActualVariance > , ck::dpp8::DppLanegroupGemm< MPerThread, NPerThread, KPerThread, BaseInputType, AVecDataType, BVecDataType, CVecDataType, ShareA >
• run() : ck::dpp_type< DppInstr::dpp8_f16_16x16x2 > , ck::dpp_type< DppInstr::dpp8_f16_1x32x2 > , ck::dpp_type< DppInstr::dpp8_f16_2x16x2 > , ck::dpp_type< DppInstr::dpp8_f16_2x32x2 > , ck::dpp_type< DppInstr::dpp8_f16_32x8x2 > , ck::dpp_type< DppInstr::dpp8_f16_4x16x2 > , ck::dpp_type< DppInstr::dpp8_f16_4x32x2 > , ck::dpp_type< DppInstr::dpp8_f16_8x16x2 > , ck::dpp_type< DppInstr::dpp8_f16_8x32x2 >
• Run() : ck::DppGemm< BaseType, MPerDpp, NPerDpp, KPack > , ck::GridwiseBatchedGemmGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, CGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer > , ck::GridwiseBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle< A0B0B1DataType, Acc0DataType, D0sDataType, Acc1DataType, C1ShuffleDataType, D1sDataType, E1DataType, A0ElementwiseOperation, B0ElementwiseOperation, CDE0ElementwiseOperation, B1ElementwiseOperation, CDE1ElementwiseOperation, E1GlobalMemoryDataOperation, A0GridDesc_M_K, B0GridDesc_N_K, D0sGridDesc_M_N, B1GridDesc_N_K, D1sGridDesc_M_N, E1GridDesc_M_N, NumGemm0KPrefetchStage, BlockSize, Gemm0MPerBlock, Gemm0NPerBlock, Gemm0KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, A0K1Value, B0K1Value, B1K1Value, Gemm0MPerXdl, Gemm0NPerXdl, Gemm0MXdlPerWave, Gemm0NXdlPerWave, Gemm1NXdlPerWave, A0BlockTransferThreadClusterLengths_AK0_M_AK1, A0BlockTransferThreadClusterArrangeOrder, A0BlockTransferSrcAccessOrder, A0BlockTransferSrcVectorDim, A0BlockTransferSrcScalarPerVector, A0BlockTransferDstScalarPerVector_AK1, A0ThreadTransferSrcResetCoordinateAfterRun, A0BlockLdsExtraM, B0BlockTransferThreadClusterLengths_BK0_N_BK1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_BK1, B0ThreadTransferSrcResetCoordinateAfterRun, B0BlockLdsExtraN, CDE0BlockTransferSrcVectorDim, CDE0BlockTransferSrcScalarPerVector, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, C1ShuffleGemm0MXdlPerWavePerShuffle, C1ShuffleGemm0NXdlPerWavePerShuffle, CDE1ShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDE1ShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched > , ck::GridwiseBatchedGemmMultipleDSoftmaxGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, D0sDataType, AElementwiseOperation, BElementwiseOperation, C0DEElementwiseOperation, B1ElementwiseOperation, C1DEElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, C1GridDesc_M_N, D0sGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PadN, MaskOutUpperTriangle, D0sTransferSrcScalarPerVector, PipelineVer > , 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 > , ck::GridwiseBatchedGemmSoftmaxGemm_Xdl_CShuffle< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, B1GridDesc_BK0_N_BK1, CGridDesc_M_N, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1Value, BK1Value, B1K1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1ThreadTransferSrcResetCoordinateAfterRun, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PadN, MaskOutUpperTriangle, PipelineVer > , ck::GridwiseBatchNormBackwardWithBlockwiseWelford< XDataType, DyDataType, DxDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, XYGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize > , ck::GridwiseBatchNormForwardWithBlockwiseWelford< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, XYGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize > , ck::GridwiseElementwise< InGridDescTuple, OutGridDescTuple, InDataTypePointerTuple, OutDataTypePointerTuple, Block2TileMap, ElementwiseOperation, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq, SrcVectorDim, DstVectorDim > , ck::GridwiseElementwise_1D< InGrid1dDescTuple, OutGrid1dDescTuple, InDataTypePointerTuple, OutDataTypePointerTuple, ElementwiseOperation, UnaryOperation, Scale, MPerThread, InScalarPerVectorSeq, OutScalarPerVectorSeq > , ck::GridwiseElementwiseLayernormWelfordVariance_mk_to_mk< InDataTypePointerTuple, XDataType, GammaDataType, BetaDataType, YDataType, AccDataType, XElementwiseOperation, YElementwiseOperation, InGrid2dDescTuple, GridDesc_M_K, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SweepOnce > , ck::GridwiseFpAintBGemm_Wmma< BlockSize, ADataType, BDataType, ScaleDataType, AccDataType, CShuffleDataType, CDataType, CGlobalMemoryDataOperation, AGridDesc, BGridDesc, ScaleGridDesc, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, KPerBlock, MPerWmma, NPerWmma, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BEnableLds, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer > , ck::GridwiseGemm_ak0mak1_bk0nbk1_mn_dpp< BlockSize, ABDataType, AccDataType, CDataType, CGlobalMemoryDataOperation, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, MPerBlock, NPerBlock, KPerBlock, MPerDpp, NPerDpp, AK1Value, BK1Value, MDppPerWave, NDppPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumGemmKPrefetchStage, PipelineVer > , ck::GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_bwd_weight< BlockSize, FloatA, FloatB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_B_K0_M_K1, BGridDesc_B_K0_N_K1, CMNGridDesc, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, ABlockLdsM1PerBlock, ABlockLdsM0PerBlock, ABlockLdsM1Padding, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, BBlockLdsN1PerBlock, BBlockLdsN0PerBlock, BBlockLdsN1Padding, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferScalarPerVector_NWaveNPerXDL, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, ABlockLdsExtraM1Wrw, BBlockLdsExtraN1Wrw, NumGemmKPrefetchStage, PipelineVer, ComputeTypeA, ComputeTypeB > , ck::GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_streamk< BlockSize, Block2CTileMap_, FloatAB_, FloatAcc_, FloatC_, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferScalarPerVector_NWaveNPerXDL, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock > , ck::GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_v2r4< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, ABK0MK1GridDesc, BBK0NK1GridDesc, CMNGridDesc, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > , ck::GridwiseGemm_bk0mk1_bk0nk1_mn_xdlops_v2r4r2< BlockSize, FloatA, FloatB, FloatAcc, FloatC, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferScalarPerVector_NWaveNPerXDL, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, LoopSched, PipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB > , 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 > , ck::GridwiseGemm_k0mk1_k0nk1_mn_xdl_waveletmodel_cshuffle< ABDataType, FloatGemmAcc, EDataTypeShuffle, EDataType, AElementwiseOperation, BElementwiseOperation, EElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, EGridDesc_M_N, NumGemmKPrefetchStage, TileLoadThreadGroupSize, TileMathThreadGroupSize, 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 > , ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > , ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v2r3< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumGemmKPrefetchStage, LoopSched, PipelineVer > , ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r1< BlockSize, FloatAB, FloatAcc, FloatCShuffle, FloatC, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl, CBlockTransferScalarPerVector_NWaveNPerXdl, NumGemmKPrefetchStage, PipelineVer > , ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r2< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, C0GridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl, CBlockTransferScalarPerVector_NWaveNPerXdl, NumGemmKPrefetchStage, PipelineVer > , ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r3< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, C0GridDesc_M_N, C1GridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl, CBlockTransferScalarPerVector_NWaveNPerXdl, NumGemmKPrefetchStage, PipelineVer > , ck::GridwiseGemm_Wmma< BlockSize, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, CGlobalMemoryDataOperation, AGridDesc, BGridDesc, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, KPerBlock, MPerWmma, NPerWmma, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BEnableLds, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer > , ck::GridwiseGemm_xdl_cshuffle_streamk_v3< ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB > , ck::GridwiseGemm_xdl_cshuffle_v2< 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 > , ck::GridwiseGemm_xdl_cshuffle_v3< ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB > , ck::GridwiseGemm_xdlops_splitk_lds_direct_load< BlockSize, FloatA, FloatB, FloatAcc, FloatC, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, MPerBlock, NPerBlock, K0PerBlock, MPerXDL, NPerXDL, K1Value, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferScalarPerVector_NWaveNPerXDL, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, LoopSched, PipelineVer, ComputeType > , ck::GridwiseGemmBiasAddReduce_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, FloatC0, FloatC1, FloatReduceAcc, ReducePtrsGlobal, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, C1ElementwiseOperation, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, CGlobalMemoryDataOperation, ReduceGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, CGridDesc_M_N, C0GridDesc_M_N, C1GridDesc_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 > , ck::GridwiseGemmDl_bkm_bkn_mn_v1r3< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_B_K0_M_K1, BGridDesc_B_K0_N_K1, CGridDesc_M_N, MPerBlock, NPerBlock, K0PerBlock, K1Value, M1PerThreadM111, N1PerThreadN111, KPerThread, M11N11ThreadClusterM110Xs, M11N11ThreadClusterN110Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > , ck::GridwiseGemmDl_km_kn_mn_v1r3< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, MPerBlock, NPerBlock, K0PerBlock, K1Value, M1PerThreadM111, N1PerThreadN111, KPerThread, M11N11ThreadClusterM110Xs, M11N11ThreadClusterN110Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > , ck::GridwiseGemmDlMultipleD_km_kn_mn< BlockSize, FloatAB, FloatAcc, DsDataType, FloatC, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, MPerBlock, NPerBlock, K0PerBlock, K1Value, M1PerThreadM111, N1PerThreadN111, KPerThread, M11N11ThreadClusterM110Xs, M11N11ThreadClusterN110Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > , ck::GridwiseGemmLayernorm_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, FloatC, FloatC0, FloatReduceAcc, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, CElementwiseOperation, CGlobalMemoryDataOperation, AGridDesc_AK0_M_AK1, BGridDesc_BK0_N_BK1, CGridDesc_M_N, C0GridDesc_N, 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, CReduceThreadCopySrcDstScalarPerVector_NPerBlock, LoopSched, PipelineVer > , ck::GridwiseGemmMultiD_ABScale_xdl_cshuffle_v3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, 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, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB > , ck::GridwiseGemmMultiD_xdl_cshuffle_v3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB > , ck::GridwiseGemmMultipleABD_xdl_cshuffle< AsDataType, BsDataType, AComputeDataType_, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, BComputeDataType_ > , ck::GridwiseGemmMultipleD_Wmma< ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AGridDesc, BGridDesc, DsGridDesc_M_N, EGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, MPerBlock, NPerBlock, KPerBlock, MPerWmma, NPerWmma, K1Value, MRepeat, NRepeat, BlockSize, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, AEnableLds, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BThreadTransferSrcResetCoordinateAfterRun, BEnableLds, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer > , ck::GridwiseGemmMultipleD_xdl_cshuffle< ADataType, BDataType, AComputeDataType_, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, BComputeDataType_ > , ck::GridwiseGemmMultipleD_Xdl_CShuffle_LdsDirectLoad< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AComputeDataType_, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferScalarPerVector, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferScalarPerVector, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, BComputeDataType > , ck::GridwiseGemmMultipleD_xdl_splitk_cshuffle< ADataType, BDataType, AComputeType, BComputeType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_KBatch_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_KBatch_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ALDSType, BLDSType > , ck::GridwiseGemmMultipleDMultipleR_k0mk1_k0nk1_mn_xdl_cshuffle_v1< FloatAB, FloatGemmAcc, FloatCShuffle, DsDataType, FloatE, FloatReduceAcc, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, EGlobalMemoryDataOperation, RsGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, EGridDesc_M_N, RGridDesc_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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched, PipelineVer > , ck::GridwiseGemmMultipleDWelfordFirstHalf_xdl_cshuffle< ABDataType, AccDataType, CShuffleDataType, DsDataType, EMeanVarDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, DsGridDesc_M_N, EGridDesc_M_N, MeanVarGridDesc_M_NBlock, CountGridDesc_M_NBlock, 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, PostShuffleThreadClusterSize_M_N, PostShuffleScalarPerVector, LoopSched, PipelineVer > , ck::GridwiseGemmPipeline_v1< 1, false, false > , ck::GridwiseGemmPipeline_v1< 1, false, true > , ck::GridwiseGemmPipeline_v1< 1, true, false > , ck::GridwiseGemmPipeline_v1< 1, true, true > , ck::GridwiseGemmPipeline_v1< 2, true, true > , ck::GridwiseGemmPipeline_v1_WeightOnly< 1, true, true > , ck::GridwiseGemmPipeline_v2 , ck::GridwiseGemmPipeline_v3 , ck::GridwiseGemmPipeline_v4< 1 > , ck::GridwiseGemmPipeline_v4< 2 > , ck::GridwiseGemmPipelineInterwave_v1< 1 > , 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 > , ck::GridwiseGemmSplitKMultipleD_xdl_cshuffle< ABDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, DsGridDesc_M_N, EGridDesc_M_N, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched > , ck::GridwiseMultiblockBatchNormForward< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, XYGridDesc_M_K, MeanVarCountGridDesc_M_G, MeanVarCountGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize > , ck::GridwiseMultiblockWelfordFirstHalf< XDataType, AccDataType, MeanVarDataType, XGridDesc_M_K, MeanVarCountGridDesc_M_G, GetReduceCountPerThreadFunctor, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcCountSrcVectorDim, XSrcCountSrcVectorSize > , ck::GridwiseMultipleReduction_mk_to_m_multiblock< NumReduction, InDataType, OutDataTypePointerTuple, AccDataType, InGridDesc_M_K, OutGridDesc_M_Tuple, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq > , ck::GridwiseMultipleReduction_mk_to_m_threadwise< NumReduction, InDataType, OutDataTypePointerTuple, AccDataType, InGridDesc_M_K, OutGridDesc_M_Tuple, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq > , ck::GridwiseNormalizationBwdData_mk_to_mk< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, GridDesc_M_K, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, DYSrcVectorDim, DYSrcVectorSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, MeanInvStdSrcVectorDim, MeanInvStdSrcVectorSize, DXDstVectorDim, DXDstVectorSize, SweepOnce > , ck::GridwiseNormalizationBwdGammaBeta_mk_to_k< DYDataType, XDataType, MeanInvStdDataType, ComputeDataType, DGammaDataType, DBetaDataType, GridDesc_M_K, GridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, DYSrcVectorDim, DYSrcVectorSize, XSrcVectorDim, XSrcVectorSize, MeanInvStdSrcVectorDim, MeanInvStdSrcVectorSize, DGammaDstVectorSize, DBetaDstVectorSize > , ck::GridwiseNormalizationNaiveVariance_mk_to_mk< XDataType, GammaDataType, BetaDataType, YDataType, SaveMeanInvStdDataType, ComputeDataType, YElementwiseOperation, GridDesc_M_K, GridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SaveMeanInvStdDstVectorSize, SweepOnce > , ck::GridwiseNormalizationSplitK1st< XDataType, ComputeDataType, MeanVarDataType, XGridDesc_M_K, MeanVarGridDesc_M_KBlock, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize > , ck::GridwiseNormalizationSplitK2nd< MeanVarDataType, XDataType, GammaDataType, BetaDataType, YDataType, SaveMeanInvStdDataType, ComputeDataType, YElementwiseOperation, MeanVarGridDesc_M_KBlock, CountGridDesc_M_KBlock, XYGammaBetaGridDesc_M_K, SaveMeanInvStdGridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SaveMeanInvStdDstVectorSize > , ck::GridwiseNormalizationWelfordVariance_mk_to_mk< XDataType, GammaDataType, BetaDataType, YDataType, SaveMeanInvStdDataType, ComputeDataType, YElementwiseOperation, GridDesc_M_K, GridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorDim, YDstVectorSize, SaveMeanInvStdDstVectorSize, SweepOnce > , ck::GridwisePermute< InGridDesc, OutGridDesc, InDataType, OutDataType, ElementwiseOperation, BlockSize, NPerBlock, HPerBlock, WPerBlock, InBlockLdsExtraW, InBlockTransferThreadClusterLengths, InBlockTransferThreadClusterArrangeOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector > , ck::GridwisePutElement_1D< InGrid1dDesc, InDataType, IndexDataType, OutDataType, ElementwiseOperation, MemOp, InVectorSize > , ck::GridwiseReduceSecondHalfBatchNormBackwardFinal< XDataType, DyDataType, DxDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, XYGridDesc_M_K, DscaleDbiasGridDesc_M_K, MeanVarGridDesc_M, ScaleBiasGridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize > , ck::GridwiseReduction_mk_to_m_multiblock< InDataType, OutDataType, AccDataType, IndexDataType, InGridDesc_M_K, OutGridDesc_M, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize > , ck::GridwiseReduction_mk_to_m_threadwise< InDataType, OutDataType, AccDataType, IndexDataType, InGridDesc_M_K, OutGridDesc_M, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize > , ck::GridwiseReduction_mk_to_m_threadwise_multi_d< InDataType, DsDataType, OutDataType, AccDataType, InGridDesc_M_K, DsGridDesc_M, OutGridDesc_M, ReduceOperation, InElementwiseOperation, OutElementwiseOperation, OutMemoryDataOperation, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, DsVectorSize > , ck::GridwiseSoftmax_mk_to_mk< InDataType, OutDataType, AccDataType, GridDesc_M_K, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, SweepOnce > , ck::GridwiseSparseEmbeddingsForwardLayernorm< EmbType, IndexType, GammaDataType, BetaDataType, AccDataType, OutType, OutGridDesc, EmbElementwiseOperation, BlockSize, DimClusterSize, RowClusterSize, DimPerBlock, RowPerBlock, DimThreadSize, RowVectorSize, NumEmbeddings > , ck::GridwiseTensorRearrange< InputGridDesc, InputDataType, OutputGridDesc, OutputDataType, BlockSize, MPerBlock, KPerBlock, ThreadClusterLengths, ScalarPerVector, DstInMemOp, Block2ETileMap, ComputePtrOffsetOfStridedBatch > , ck::GridwiseWelfordSecondHalfBatchNormForwardFinal< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, XYGridDesc_M_K, MeanVarCountGridDesc_M_K, ScaleBiasGridDesc_M, MeanVarGridDesc_M, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize > , ck::GridwiseWelfordSecondHalfLayernorm2d< EMeanVarDataType, HDataType, GammaDataType, BetaDataType, ComputeDataType, EHGridDesc_M_N, MeanVarGridDesc_M_NBlock, CountGridDesc_M_NBlock, GammaBetaGridDesc_N, HElementwiseOperation, BlockSize, MThreadClusterSize, NThreadClusterSize, MThreadSliceSize, NThreadSliceSize, ESrcVectorSize, HDstVectorSize, GammaSrcVectorSize, BetaSrcVectorSize > , ck::GridwiseWelfordSecondHalfReduceFirstHalf< XDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, XYGridDesc_M_K, MeanVarGridDesc_M, MeanVarCountGridDesc_M_K, DscaleDbiasGridDesc_M_G, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyVectorDim, XSrcVectorSize, DySrcVectorSize, MeanVarSrcVectorSize > , ck::intrin_mfma_f32_16x16x128f8f6f4< 16, 16 > , ck::intrin_mfma_f32_16x16x16bf16_1k< 16, 16 > , ck::intrin_mfma_f32_16x16x16f16< 16, 16 > , ck::intrin_mfma_f32_16x16x1f32< 16, 64 > , ck::intrin_mfma_f32_16x16x32bf16< 16, 16 > , ck::intrin_mfma_f32_16x16x32bf8bf8< 16, 16 > , ck::intrin_mfma_f32_16x16x32bf8f8< 16, 16 > , ck::intrin_mfma_f32_16x16x32f16< 16, 16 > , ck::intrin_mfma_f32_16x16x32f8bf8< 16, 16 > , ck::intrin_mfma_f32_16x16x32f8f8< 16, 16 > , ck::intrin_mfma_f32_16x16x4f16< 16, 64 > , ck::intrin_mfma_f32_16x16x4f32< 16, 16 > , ck::intrin_mfma_f32_16x16x8bf16< 16, 16 > , ck::intrin_mfma_f32_32x32x16bf16< 32, 32 > , ck::intrin_mfma_f32_32x32x16bf8bf8< 32, 32 > , ck::intrin_mfma_f32_32x32x16bf8f8< 32, 32 > , ck::intrin_mfma_f32_32x32x16f16< 32, 32 > , ck::intrin_mfma_f32_32x32x16f8bf8< 32, 32 > , ck::intrin_mfma_f32_32x32x16f8f8< 32, 32 > , ck::intrin_mfma_f32_32x32x1f32< 32, 64 > , ck::intrin_mfma_f32_32x32x1f32< 64, 64 > , ck::intrin_mfma_f32_32x32x2f32< 32, 32 > , ck::intrin_mfma_f32_32x32x4bf16< 32, 32 > , ck::intrin_mfma_f32_32x32x4f16< 32, 64 > , ck::intrin_mfma_f32_32x32x4f16< 64, 64 > , ck::intrin_mfma_f32_32x32x64f8f6f4< 32, 32 > , ck::intrin_mfma_f32_32x32x8bf16_1k< 32, 32 > , ck::intrin_mfma_f32_32x32x8f16< 32, 32 > , ck::intrin_mfma_f32_4x4x1f32< 4, 64 > , ck::intrin_mfma_f32_4x4x1f32< 8, 64 > , ck::intrin_mfma_f32_4x4x4f16< 4, 64 > , ck::intrin_mfma_f32_4x4x4f16< 8, 64 > , ck::intrin_mfma_f64_16x16x4f64< 16, 16 > , ck::intrin_mfma_i32_16x16x16i8< 16, 16 > , ck::intrin_mfma_i32_16x16x32i8< 16, 16 > , ck::intrin_mfma_i32_16x16x64i8< 16, 16 > , ck::intrin_mfma_i32_32x32x16i8< 32, 32 > , ck::intrin_mfma_i32_32x32x32i8< 32, 32 > , ck::intrin_mfma_i32_32x32x8i8< 32, 32 > , ck::intrin_mfma_scale_f32_16x16x128f8f6f4< 16, 16 > , ck::intrin_mfma_scale_f32_32x32x64f8f6f4< 32, 32 > , ck::intrin_smfmac_f32_16x16x32bf16< 16, 16 > , ck::intrin_smfmac_f32_16x16x32f16< 16, 16 > , ck::intrin_smfmac_f32_32x32x16bf16< 32, 32 > , ck::intrin_smfmac_f32_32x32x16f16< 32, 32 > , ck::intrin_wmma_bf16_16x16x16_bf16_w32< 16, 16, Opsel > , ck::intrin_wmma_bf16_16x16x16_bf16_w64< 16, 16, Opsel > , ck::intrin_wmma_f16_16x16x16_f16_w32< 16, 16, Opsel > , ck::intrin_wmma_f16_16x16x16_f16_w64< 16, 16, Opsel > , ck::intrin_wmma_f32_16x16x16_bf16_w32< 16, 16 > , ck::intrin_wmma_f32_16x16x16_bf16_w32_gfx12< 16, 16 > , ck::intrin_wmma_f32_16x16x16_bf16_w64< 16, 16 > , ck::intrin_wmma_f32_16x16x16_f16_w32< 16, 16 > , ck::intrin_wmma_f32_16x16x16_f16_w32_gfx12< 16, 16 > , ck::intrin_wmma_f32_16x16x16_f16_w64< 16, 16 > , ck::intrin_wmma_i32_16x16x16_iu8_w32< 16, 16, neg_a, neg_b, clamp > , ck::intrin_wmma_i32_16x16x16_iu8_w32_gfx12< 16, 16, neg_a, neg_b, clamp > , ck::intrin_wmma_i32_16x16x16_iu8_w64< 16, 16, neg_a, neg_b, clamp >
• run() : ck::mfma_type< MfmaInstr::mfma_f32_16x16x128f8f6f4 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x16bf16_1k > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x16f16 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x1xf32 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x32bf16 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x32bf8bf8 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x32bf8f8 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x32f16 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x32f8bf8 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x32f8f8 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x4f16 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x4xf32 > , ck::mfma_type< MfmaInstr::mfma_f32_16x16x8bf16 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x16bf16 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x16bf8bf8 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x16bf8f8 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x16f16 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x16f8bf8 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x16f8f8 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x1xf32 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x2xf32 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x4bf16 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x4f16 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x64f8f6f4 > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x8bf16_1k > , ck::mfma_type< MfmaInstr::mfma_f32_32x32x8f16 > , ck::mfma_type< MfmaInstr::mfma_f32_4x4x1xf32 > , ck::mfma_type< MfmaInstr::mfma_f32_4x4x4f16 > , ck::mfma_type< MfmaInstr::mfma_f64_16x16x4f64 > , ck::mfma_type< MfmaInstr::mfma_i32_16x16x16i8 > , ck::mfma_type< MfmaInstr::mfma_i32_16x16x32i8 > , ck::mfma_type< MfmaInstr::mfma_i32_16x16x64i8 > , ck::mfma_type< MfmaInstr::mfma_i32_32x32x16i8 > , ck::mfma_type< MfmaInstr::mfma_i32_32x32x32i8 > , ck::mfma_type< MfmaInstr::mfma_i32_32x32x8i8 > , ck::mfma_type< MfmaInstr::mfma_scale_f32_16x16x128f8f6f4 > , ck::mfma_type< MfmaInstr::mfma_scale_f32_32x32x64f8f6f4 > , ck::smfmac< SmfmacInstr::smfmac_f32_16x16x32bf16 > , ck::smfmac< SmfmacInstr::smfmac_f32_16x16x32f16 > , ck::smfmac< SmfmacInstr::smfmac_f32_32x32x16bf16 > , ck::smfmac< SmfmacInstr::smfmac_f32_32x32x16f16 >
• Run() : ck::SparseXdlopsGemm< base_type, MPerXdlops, NPerXdlops, KPack, additional_type > , ck::tensor_operation::device::BaseInvoker , ck::tensor_operation::device::DeviceAvgPool2dBwd_NHWC_NHWC< DOutDataType, DInDataType, ComputeDataType, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcOutDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceAvgPool3dBwd_NDHWC_NDHWC< DOutDataType, DInDataType, ComputeDataType, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcOutDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Wmma_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmEPermuteXdl< ALayout, BLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmGemm_Xdl_CShuffle< ALayout, BLayout, B1Layout, CLayout, ADataType, BDataType, B1DataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmMultiD_Xdl< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmMultiD_Xdl_CShuffle_V3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmMultipleD_Dl< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle< A0Layout, B0Layout, D0sLayout, B1Layout, D1sLayout, E1Layout, A0DataType, B0DataType, Acc0DataType, D0sDataType, B1DataType, Acc1DataType, C1ShuffleDataType, D1sDataType, E1DataType, A0ElementwiseOperation, B0ElementwiseOperation, CDE0ElementwiseOperation, B1ElementwiseOperation, CDE1ElementwiseOperation, PadGemm0M, PadGemm0N, PadGemm0K, PadGemm1N, PadGemm1K, NumGemm0KPrefetchStage, BlockSize, Gemm0MPerBlock, Gemm0NPerBlock, Gemm0KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, A0K1, B0K1, B1K1, Gemm0MPerXdl, Gemm0NPerXdl, Gemm0MXdlPerWave, Gemm0NXdlPerWave, Gemm1NXdlPerWave, A0BlockTransferThreadClusterLengths_AK0_M_AK1, A0BlockTransferThreadClusterArrangeOrder, A0BlockTransferSrcAccessOrder, A0BlockTransferSrcVectorDim, A0BlockTransferSrcScalarPerVector, A0BlockTransferDstScalarPerVector_AK1, A0BlockLdsExtraM, B0BlockTransferThreadClusterLengths_BK0_N_BK1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_BK1, B0BlockLdsExtraN, CDE0BlockTransferSrcVectorDim, CDE0BlockTransferSrcScalaerPerVector, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, C1ShuffleMXdlPerWavePerShuffle, C1ShuffleGemm0NXdlPerWavePerShuffle, CDE1ShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDE1ShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , 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 >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemm_Xdl_CShuffle< ALayout, BLayout, B1Layout, CLayout, ADataType, BDataType, B1DataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskOutUpperTriangle, LoopSched >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Wmma_CShuffle< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::CrossAttnInvoker , ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Wmma_CShuffle< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Wmma_CShuffle< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::SelfAttnInvoker , ck::tensor_operation::device::DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, ADataType, BDataType, B1DataType, CDataType, D0sDataType, D1sDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, C0DEElementwiseOperation, B1ElementwiseOperation, C1DEElementwiseOperation, GemmSpec, ASpec, BSpec, B1Spec, CSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, D0sTransferSrcScalarPerVector, LoopSched >::Invoker , ck::tensor_operation::device::DeviceBatchedGemmXdl< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumGemmKPrefetchStage, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker , ck::tensor_operation::device::DeviceBatchNormFwdImpl< XDataType, YDataType, AccDataType, ScaleDataType, BiasDataType, MeanVarDataType, YElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XSrcYDstVectorDim, XSrcVectorSize, YDstVectorSize, ScaleSrcVectorSize, BiasSrcVectorSize, MeanVarSrcDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceCGemm_4Gemm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, 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, LoopSched, >::Invoker , ck::tensor_operation::device::DeviceColumnToImageImpl< NDimSpatial, ImageLayout, InputDataType, OutputDataType, BlockSize, MPerBlock, KPerBlock, ThreadClusterLengths, ScalarPerVector,, bool, type >::Invoker , ck::tensor_operation::device::DeviceContractionMultipleABD_Xdl_CShuffle< NumDimM, NumDimN, NumDimK, AsDataType, BsDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceContractionMultipleD_Xdl_CShuffle< NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, ComputeDataType, LoopSched >::Invoker , ck::tensor_operation::device::DeviceConv2dBwdDataXdl_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardDataSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceConv2dBwdWeightXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXdl >::Invoker , ck::tensor_operation::device::DeviceConv2dFwdXdl_C_Shuffle_Bias_Activation_Add_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvForwardSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl, CBlockTransferScalarPerVector_NWaveNPerXdl >::Invoker , ck::tensor_operation::device::DeviceConv2dFwdXdl_C_Shuffle_Bias_Activation_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, OutGlobalMemoryDataOperation, ConvForwardSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl, CBlockTransferScalarPerVector_NWaveNPerXdl >::Invoker , ck::tensor_operation::device::DeviceConv2dFwdXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvForwardSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MXdlPerWave_MWaveMPerXdl_NBlock_NXdlPerWave_NWaveNPerXdl, CBlockTransferScalarPerVector_NWaveNPerXdl >::Invoker , ck::tensor_operation::device::DeviceConv2dFwdXdl_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvForwardSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceConv3dFwdNaive_Input_N_Di_Hi_Wi_C_Weight_K_Z_Y_X_C_Output_N_Do_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation >::Invoker , ck::tensor_operation::device::DeviceConv3dFwdXdl_Input_N_Di_Hi_Wi_C_Weight_K_Z_Y_X_C_Output_N_Do_Ho_Wo_K< InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvForwardSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceConvNdBwdDataNwcKxcNwk_Dl< NDimSpatial, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardDataSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceConvNdBwdDataNwcKxcNwk_Xdl< NDimSpatial, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardDataSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker , ck::tensor_operation::device::DeviceElementwiseNormalizationImpl< InDataTypeTuple, GammaDataType, BetaDataType, AccDataType, YDataType, XElementwiseOperation, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceFpAintBGemm_Wmma_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, ScaleDataType, CDataType, AccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, 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, LoopSched, PipelineVer, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle_LdsDirectLoad< ALayout, BLayout, ELayout, ADataType, BDataType, EDataType, AccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferScalarPerVector, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferScalarPerVector, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeDataType >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle_Streamk_V3< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV2< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, 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, LoopSched, PipelineVer, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV3< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, PermuteA, PermuteB >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV3R1< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ReduceDataType, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGemm_Xdl_WaveletModel_CShuffle< ALayout, BLayout, ELayout, ADataType, BDataType, GemmAcEDataType, CShuffleDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, TileLoadThreadGroupSize, TileMathThreadGroupSize, 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 >::Invoker , 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 >::Invoker , ck::tensor_operation::device::DeviceGemmDl< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, >::Invoker , ck::tensor_operation::device::DeviceGemmDpp< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerDpp, NPerDpp, MDppPerWave, NDppPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumPrefetch, PipelineVer >::Invoker , 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 >::Invoker , ck::tensor_operation::device::DeviceGemmMultiD_ABScale_Xdl_CShuffle_V3< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, 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, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::Invoker , ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleABD_Xdl_CShuffle< AsLayout, BsLayout, DsLayout, CLayout, AsDataType, BsDataType, GemmAccDataType, CShuffleDataType, DsDataType, CDataType, AElementwiseOperation, BElementwiseOperation, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleD_Dl< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleD_Wmma_CShuffle< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleD_Xdl_CShuffle< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeDataType >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleD_Xdl_CShuffle< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeDataType > , ck::tensor_operation::device::DeviceGemmMultipleD_Xdl_CShuffle_LdsDirectLoad< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferScalarPerVector, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferScalarPerVector, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ComputeDataType >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleDLayernorm_Xdl_CShuffle< ALayout, BLayout, DsLayout, HLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EMeanVarDataType, GammaDataType, BetaDataType, HDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, HElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, GemmMPerBlock, GemmNPerBlock, GemmKPerBlock, 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, PostShuffleThreadClusterSize_M_N, PostShuffleScalarPerVector, LayernormThreadClusterSize_M_N, LayernormThreadSliceSize_M, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Invoker , 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 >::Invoker , ck::tensor_operation::device::DeviceGemmWmma_CShuffle< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGemmXdl< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumPrefetch, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGemmXdlSkipBLds< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferSrcScalarPerVector, BBlockBufferSize, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceGemmXdlSplitKCShuffle< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXDL, ComputeType, PipelineVer, LoopSched, LDSTypeA, LDSTypeB >::Invoker , ck::tensor_operation::device::DeviceGemmXdlSplitKCShuffle_LdsDirectLoad< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferScalarPerVector, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferScalarPerVector, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXDL, ComputeType, PipelineVer, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGemmXdlStreamK< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXDL >::Invoker , ck::tensor_operation::device::DeviceGroupedContractionMultipleD_Xdl_CShuffle< NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOp, BElementwiseOp, CDEElementwiseOp, ConvBackwardDataSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerWMMA, NPerWMMA, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOp, BElementwiseOp, CDEElementwiseOp, ConvBackwardDataSpecialization, DoPadGemmM, DoPadGemmN, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched, AComputeType, BComputeType >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Dl< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerWMMA, NPerWMMA, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Xdl_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXdl, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdWeightMultipleD_Xdl_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, DsLayout, InDataType, WeiDataType, OutDataType, AccDataType, DsDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXdl, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXdl, BlkGemmPipeSched, BlkGemmPipelineVer, NumGroupsToMerge, ComputeTypeA, ComputeTypeB, TransposeTransferSrcScalarPerVector, TransposeTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdDl_NHWC_KYXC_NHWK< NDimSpatial, ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, ConvForwardSpecialization, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdDlMultipleD_NHWC_KYXC_NHWK< NDimSpatial, ADataType, BDataType, DsDataType, EDataType, AccDataType, ALayout, BLayout, DsLayout, ELayout, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, AComputeDataType, BComputeDataType, LoopSched, NumGroupsToMerge >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, GemmSpec, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, BlkGemmPipeSched, BlkGemmPipelineVer, AComputeDataType, BComputeDataType >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleD_Wmma_CShuffle< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, AComputeDataType, BComputeDataType, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleDMultipleR_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DELayout, RLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, ConvForwardSpecialization, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGroupedGemm_Xdl< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGroupedGemm_Xdl_Fixed_NK< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, PipelineVer, LoopSched, ComputeType, ALDSType, BLDSType >::Invoker , ck::tensor_operation::device::DeviceGroupedGemm_Xdl_Multi_ABD_Fixed_NK< AsLayout, BsLayout, DsLayout, ELayout, AsDataType, BsDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, ComputeType, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGroupedGemmMultipleD_Dl< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, M1PerThread, N1PerThread, KPerThread, M1N1ThreadClusterM1Xs, M1N1ThreadClusterN1Xs, ABlockTransferThreadSliceLengths_K0_M0_M1_K1, ABlockTransferThreadClusterLengths_K0_M0_M1_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorTensorLengths_K0_M0_M1_K1, ABlockTransferSrcVectorTensorContiguousDimOrder, ABlockTransferDstVectorTensorLengths_K0_M0_M1_K1, BBlockTransferThreadSliceLengths_K0_N0_N1_K1, BBlockTransferThreadClusterLengths_K0_N0_N1_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorTensorLengths_K0_N0_N1_K1, BBlockTransferSrcVectorTensorContiguousDimOrder, BBlockTransferDstVectorTensorLengths_K0_N0_N1_K1, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, >::Invoker , ck::tensor_operation::device::DeviceGroupedGemmMultipleDSplitKXdlCShuffleTwoStage< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_KBatch_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_KBatch_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, PipelineVer, LoopSched, ComputeDataType, >::Invoker , ck::tensor_operation::device::DeviceGroupedGemmMultipleDXdlCShuffleTileLoop< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB >::Invoker , ck::tensor_operation::device::DeviceGroupedGemmSoftmaxGemmPermute_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, NumDimO, ADataType, BDataType, B1DataType, CDataType, Acc0BiasDataType, Acc1BiasDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, BSpec, B1Spec, CSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, Gemm1NPerBlock, Gemm1KPerBlock, AK1, BK1, B1K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, Gemm1NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, B1BlockTransferThreadClusterLengths_BK0_N_BK1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_BK1, B1BlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched >::Invoker , ck::tensor_operation::device::DeviceGroupedGemmXdlSplitKCShuffle< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, PipelineVer, LoopSched, >::Invoker , ck::tensor_operation::device::DeviceGroupedQueryAttentionForward_Wmma< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, QueryGroupNumber, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceImageToColumnImpl< NDimSpatial, ImageLayout, InputDataType, OutputDataType, BlockSize, MPerBlock, KPerBlock, ThreadClusterLengths, ScalarPerVector,, bool, type >::Invoker , ck::tensor_operation::device::DeviceMaxPoolBwdImpl< DOutDataType, IndexDataType, DInDataType, InOutVectorSize >::Invoker , ck::tensor_operation::device::DeviceMultipleReduceMultiBlock< NumReduction, InDataType, AccDataType, OutDataTypeTuple, Rank, NumReduceDim, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq >::Invoker , ck::tensor_operation::device::DeviceMultipleReduceThreadWise< NumReduction, InDataType, AccDataType, OutDataTypeTuple, Rank, NumReduceDim, ReduceOperation, InElementwiseOperationTuple, AccElementwiseOperationTuple, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSizeSeq >::Invoker , ck::tensor_operation::device::DeviceMultiQueryAttentionForward_Wmma< NumDimG, NumDimM, NumDimL, NumDimK, NumDimN, ADataType, B0DataType, B1DataType, CDataType, Acc0BiasDataType, Acc0DataType, Acc1BiasDataType, Acc1DataType, CShuffleDataType, AElementwiseOperation, B0ElementwiseOperation, AccElementwiseOperation, B1ElementwiseOperation, CElementwiseOperation, GemmSpec, ASpec, B0Spec, B1Spec, CSpec, NumPrefetch, BlockSize, MPerBlock, LPerBlock, KPerBlock, AK1, BK1, NPerBlock, LTilePerBlock, L1, MPerWmma, LPerWmma, NPerWmma, MRepeat, LRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, B0BlockTransferThreadClusterLengths_K0_L_K1, B0BlockTransferThreadClusterArrangeOrder, B0BlockTransferSrcAccessOrder, B0BlockTransferSrcVectorDim, B0BlockTransferSrcScalarPerVector, B0BlockTransferDstScalarPerVector_K1, B0BlockLdsAddExtraL, B1BlockTransferThreadClusterLengths_L0_N_L1, B1BlockTransferThreadClusterArrangeOrder, B1BlockTransferSrcAccessOrder, B1BlockTransferSrcVectorDim, B1BlockTransferSrcScalarPerVector, B1BlockTransferDstScalarPerVector_L1, B1BlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, MaskingSpec, LoopSched, PipelineVer >::Invoker , ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceNormalizationBwdGammaBetaImpl< DYDataType, XDataType, MeanInvStdDataType, ComputeDataType, DGammaDataType, DBetaDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, DGammaDstVectorSize, DBetaDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceNormalizationFwdImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYSrcVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize, UseWelford >::Invoker , ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::Invoker , ck::tensor_operation::device::DevicePermuteImpl< NumDim, InDataType, OutDataType, ElementwiseOperation, BlockSize, NPerBlock, HPerBlock, WPerBlock, InBlockLdsExtraW, InBlockTransferThreadClusterLengths, InBlockTransferThreadClusterArrangeOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector >::Invoker , ck::tensor_operation::device::DevicePool2dFwd_NHWC_NHWC< InDataType, OutDataType, IndexDataType, ComputeDataType, ReduceOpId, OutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcOutDstVectorSize >::Invoker , ck::tensor_operation::device::DevicePool3dFwd_NDHWC_NDHWC< InDataType, OutDataType, IndexDataType, ComputeDataType, ReduceOpId, OutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcOutDstVectorSize >::Invoker , ck::tensor_operation::device::DevicePutElementImpl< InDataType, IndexDataType, OutDataType, ElementwiseOperation, MemOp, InVectorSize >::Invoker , ck::tensor_operation::device::DeviceReduceMultiBlock< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, OutputIndex, HaveIndexInputIfOutputIndex, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceReduceThreadWiseMultiD< InDataType, DsDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, OutElementwiseOperation, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize, DsVectorSizeSequence >::Invoker , ck::tensor_operation::device::DeviceSoftmaxImpl< InDataType, AccDataType, OutDataType, InElementwiseOp, AccElementwiseOp, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker , ck::tensor_operation::device::DeviceSparseEmbeddingsForwardLayernorm< EmbType, IndexType, GammaDataType, BetaDataType, AccDataType, OutType, EmbElementwiseOperation, BlockSize, DimClusterSize, RowClusterSize, DimPerBlock, RowPerBlock, DimThreadSize, RowVectorSize, NumEmbeddings >::Invoker , ck::tensor_operation::device::DeviceSplitKContractionMultipleD_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >::Invoker , ck::ThreadGroupTensorSliceTransfer_DirectLoad< ThreadGroup, BlockSliceLengths, ThreadClusterLengths, SrcData, DstData, SrcDesc, DstDesc, SrcVectorDim, DstVectorDim, ScalarPerVector > , ck::ThreadGroupTensorSliceTransfer_v4r1< ThreadGroup, SrcElementwiseOperation, DstElementwiseOperation, DstInMemOp, BlockSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, DstScalarStrideInVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v4r2< ThreadGroup, ElementwiseOperation, DstInMemOps, BlockSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDatas, DstDatas, SrcDescs, DstDescs, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcsScalarPerVector, DstsScalarPerVector, SrcsScalarStrideInVector, DstsScalarStrideInVector, ThreadTransferSrcsResetCoordinateAfterRun, ThreadTransferDstsResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v6r1< ThreadGroup, ElementwiseOperation, DstInMemOp, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, DimAccessOrder, VectorDim, ScalarPerVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun > , ck::ThreadGroupTensorSliceTransfer_v6r1r2< ThreadGroup, ElementwiseOperation, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, DimAccessOrder, VectorDim, ScalarPerVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun > , ck::ThreadGroupTensorSliceTransfer_v6r2< ThreadGroup, ElementwiseOperation, DstInMemOp, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, Src0Data, Src1Data, DstData, Src0Desc, Src1Desc, DstDesc, DimAccessOrder, VectorDim, ScalarPerVector, ThreadTransferSrc0ResetCoordinateAfterRun, ThreadTransferSrc1ResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun > , ck::ThreadGroupTensorSliceTransfer_v6r3< ThreadGroup, ElementwiseOperation, DstInMemOp, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, Src0Data, Src1Data, Src2Data, DstData, Src0Desc, Src1Desc, Src2Desc, DstDesc, DimAccessOrder, VectorDim, ScalarPerVector, ThreadTransferSrc0ResetCoordinateAfterRun, ThreadTransferSrc1ResetCoordinateAfterRun, ThreadTransferSrc2ResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun > , ck::ThreadGroupTensorSliceTransfer_v7< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, DimAccessOrder, VectorDim, ScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags > , ck::ThreadGroupTensorSliceTransfer_v7r2< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v7r3< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVectors, DstScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseContractionDl_A_TK0_TM0_TM1_TK1_B_TK0_TN0_TN1_TK1_C_TM0_TM1_TN0_TN1< FloatA, FloatB, FloatC, AThreadDesc_TK0_TM0_TM1_TK1, BThreadDesc_TK0_TN0_TN1_TK1, CThreadDesc_TM0_TM1_TN0_TN1, TKLengths, TMLengths, TNLengths, type > , ck::ThreadwiseGemmDl_km0m1_kn0n1_m0m1n0n1< FloatA, FloatB, FloatC, AThreadDesc_TK0_TM0_TM1_TK1, BThreadDesc_TK0_TN0_TN1_TK1, CThreadDesc_TM0_TM1_TN0_TN1, TKLengths, TMLengths, TNLengths, type > , ck::ThreadwiseGemmDlops_km_kn_mn_v3< FloatA, FloatB, FloatC, AThreadDesc_E1_K_E2, BThreadDesc_E1_N_Ho_Wo_E2, CThreadDesc_K_N_Ho_Wo, type > , ck::ThreadwiseTensorSliceSet_v1< Data, Desc, SliceLengths, type > , ck::ThreadwiseTensorSliceTransfer_StaticToStatic< SrcData, DstData, SrcDesc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, DstVectorDim, DstScalarPerVector, type > , ck::ThreadwiseTensorSliceTransfer_StaticToStatic_InterRow< SrcData, DstData, SrcDesc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, DstVectorDim, DstScalarPerVector, LowEightRowlaneIdx, HighEightRowLaneIdx, IntraRowSwizzlePerm, type > , ck::ThreadwiseTensorSliceTransfer_StaticToStatic_IntraRow< SrcData, DstData, SrcDesc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, DstVectorDim, DstScalarPerVector, IntraRowSwizzlePerm, type > , ck::ThreadwiseTensorSliceTransfer_v1r3< SrcData, DstData, SrcDesc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, DstVectorDim, DstScalarPerVector, DstInMemOp, DstScalarStrideInVector, DstResetCoordinateAfterRun, type > , ck::ThreadwiseTensorSliceTransfer_v2< SrcData, DstData, SrcDesc, DstDesc, SliceLengths, DimAccessOrder, SrcVectorDim, SrcScalarPerVector, SrcScalarStrideInVector, SrcResetCoordinateAfterRun, InvalidElementAsNaN, type > , ck::ThreadwiseTensorSliceTransfer_v4< SrcData, DstData, SrcDesc, DstDesc, SliceLengths, DimAccessOrder, SrcVectorDim, SrcScalarPerVector, SrcScalarStrideInVector, type > , ck::ThreadwiseTensorSliceTransfer_v4r1< SrcData, DstData, SrcDesc, DstDesc, SliceLengths, DimAccessOrder, SrcVectorTensorLengths, SrcVectorTensorContiguousDimOrder, type > , ck::ThreadwiseTensorSliceTransfer_v6r1< SrcData, DstData, SrcDesc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, VectorDim, ScalarPerVector, DstInMemOp, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v6r1r2< SrcData, DstData, SrcDesc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, VectorDim, ScalarPerVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v6r2< Src0Data, Src1Data, DstData, Src0Desc, Src1Desc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, VectorDim, ScalarPerVector, DstInMemOp, Src0ResetCoordinateAfterRun, Src1ResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v6r3< Src0Data, Src1Data, Src2Data, DstData, Src0Desc, Src1Desc, Src2Desc, DstDesc, ElementwiseOperation, SliceLengths, DimAccessOrder, VectorDim, ScalarPerVector, DstInMemOp, Src0ResetCoordinateAfterRun, Src1ResetCoordinateAfterRun, Src2ResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v7< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, DimAccessOrder, VectorDim, ScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags > , ck::ThreadwiseTensorSliceTransfer_v7r2< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v7r3< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVectors, DstScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseWelford< T, XThreadDesc_M_K, MeanVarThreadDesc_M > , ck::ThreadwiseWelfordMerge< T, SrcMeanVarCountThreadDesc_M_K, DstMeanVarThreadDesc_M, GetActualVariance >
• run() : ck::wmma_type< WmmaInstr::wmma_bf16_16x16x16_bf16, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_f16_16x16x16_f16, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_f32_16x16x16_bf16, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_f32_16x16x16_bf16_gfx12, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_f32_16x16x16_f16, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_f32_16x16x16_f16_gfx12, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_i32_16x16x16_iu8, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > > , ck::wmma_type< WmmaInstr::wmma_i32_16x16x16_iu8_gfx12, WaveSize, typename std::enable_if_t< WaveSize==32||WaveSize==64 > >
• Run() : ck::WmmaGemm< src_type_a, src_type_b, dst_type, MPerWmma, NPerWmma, KPack, TransposeC, AssemblyBackend > , ck::XdlopsGemm< base_type, MPerXdlops, NPerXdlops, KPack, additional_type, TransposeC > , ck_tile::BlockDropout , ck_tile::BlockDropoutBwd< true, IsWG32_, IsStoreRandval_ > , ck_tile::GroupedGemmKernel< TilePartitioner_, GemmPipeline_, EpiloguePipeline_ >
• Run0() : ck::GridwiseGemmSplitKMultipleD_xdl_cshuffle< ABDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, DsGridDesc_M_N, EGridDesc_M_N, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >
• Run1() : ck::GridwiseGemmSplitKMultipleD_xdl_cshuffle< ABDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, EGlobalMemoryDataOperation, AGridDesc_M_K, BGridDesc_N_K, DsGridDesc_M_N, EGridDesc_M_N, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched >
• Run_2Lds() : ck::GridwiseGemm_xdl_cshuffle_streamk_v3< ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB > , ck::GridwiseGemm_xdl_cshuffle_v3< ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB > , ck::GridwiseGemmMultiD_xdl_cshuffle_v3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >
• RunGemm() : ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, AComputeDataType, BComputeDataType, LoopSched, NumGroupsToMerge >::Invoker , ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3< NDimSpatial, ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, ConvForwardSpecialization, GemmSpec, 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, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, BlkGemmPipeSched, BlkGemmPipelineVer, AComputeDataType, BComputeDataType >::Invoker , ck_tile::GemmKernel< TilePartitioner_, GemmPipeline_, EpiloguePipeline_ >
• RunGemmV3() : ck::tensor_operation::device::DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CBlockTransferScalarPerVector_NWaveNPerXdl, BlkGemmPipeSched, BlkGemmPipelineVer, NumGroupsToMerge, ComputeTypeA, ComputeTypeB, TransposeTransferSrcScalarPerVector, TransposeTransferDstScalarPerVector >::Invoker
• RunLoadWavePipeline() : ck::GridwiseGemmLoadWave< TileLoadThreadGroup, 1 >
• RunMathWavePipeline() : ck::GridwiseGemmMathWave< TileMathThreadGroup, 1 >
• RunRead() : ck::BlockwiseTensorSliceTransfer_v5r1< BlockSize, DstInMemOp, BlockSliceLengths, ThreadSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorTensorLengths, DstVectorTensorLengths, SrcVectorTensorContiguousDimOrder, DstVectorTensorContiguousDimOrder, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun > , ck::ThreadGroupTensorSliceTransfer_v4r1< ThreadGroup, SrcElementwiseOperation, DstElementwiseOperation, DstInMemOp, BlockSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, DstScalarStrideInVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v4r1_dequant< ThreadGroup, SrcElementwiseOperation, ScaleElementwiseOperation, DstElementwiseOperation, DstInMemOp, BlockSliceLengths, BlockScaleSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, ScaleData, DstData, SrcDesc, ScaleDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, ScaleScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, ScaleScalarStrideInVector, DstScalarStrideInVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v4r2< ThreadGroup, ElementwiseOperation, DstInMemOps, BlockSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDatas, DstDatas, SrcDescs, DstDescs, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcsScalarPerVector, DstsScalarPerVector, SrcsScalarStrideInVector, DstsScalarStrideInVector, ThreadTransferSrcsResetCoordinateAfterRun, ThreadTransferDstsResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v7r2< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v7r3< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVectors, DstScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3< SliceLengths, DstInMemOp, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v3r1< SliceLengths, SrcElementwiseOperation, DstElementwiseOperation, DstInMemOp, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector_, DstScalarPerVector_, SrcScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3r1_dequant< SliceLengths, ScaleSliceLengths, SrcElementwiseOperation, ScaleElementwiseOperation, DstElementwiseOperation, DstInMemOp, SrcData, ScaleData, DstData, SrcDesc, ScaleDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, ScaleScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, ScaleScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3r2< SliceLengths, ElementwiseOperation, DstInMemOps, SrcDatas, DstDatas, SrcDescs, DstDescs, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcsScalarPerVector, DstsScalarPerVector, SrcsScalarStrideInVector, DstsScalarStrideInVector, SrcsResetCoordinateAfterRun, DstsResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v5r1< SliceLengths, DstInMemOp, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorTensorLengths, DstVectorTensorLengths, SrcVectorTensorContiguousDimOrder, DstVectorTensorContiguousDimOrder, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v7r2< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v7r3< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVectors, DstScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags, NumThreadScratch >
• RunReduce() : ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV3R1< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, BlkGemmPipeSched, BlkGemmPipelineVer, ReduceDataType, ComputeTypeA, ComputeTypeB >::Invoker
• RunScaleRead() : ck::ThreadGroupTensorSliceTransfer_v4r1_dequant< ThreadGroup, SrcElementwiseOperation, ScaleElementwiseOperation, DstElementwiseOperation, DstInMemOp, BlockSliceLengths, BlockScaleSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, ScaleData, DstData, SrcDesc, ScaleDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, ScaleScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, ScaleScalarStrideInVector, DstScalarStrideInVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3r1_dequant< SliceLengths, ScaleSliceLengths, SrcElementwiseOperation, ScaleElementwiseOperation, DstElementwiseOperation, DstInMemOp, SrcData, ScaleData, DstData, SrcDesc, ScaleDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, ScaleScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, ScaleScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun, NumThreadScratch >
• RunWithIndex() : ck::GridwiseReduction_mk_to_m_multiblock< InDataType, OutDataType, AccDataType, IndexDataType, InGridDesc_M_K, OutGridDesc_M, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize > , ck::GridwiseReduction_mk_to_m_threadwise< InDataType, OutDataType, AccDataType, IndexDataType, InGridDesc_M_K, OutGridDesc_M, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, OutMemoryDataOperation, PropagateNan, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >
• RunWithZeroing() : ck::GridwiseGemmMultipleD_xdl_splitk_cshuffle< ADataType, BDataType, AComputeType, BComputeType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1Value, BK1Value, MPerXdl, NPerXdl, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_KBatch_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_KBatch_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BThreadTransferSrcResetCoordinateAfterRun, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer, ALDSType, BLDSType >
• RunWrite() : ck::BlockwiseTensorSliceTransfer_v5r1< BlockSize, DstInMemOp, BlockSliceLengths, ThreadSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorTensorLengths, DstVectorTensorLengths, SrcVectorTensorContiguousDimOrder, DstVectorTensorContiguousDimOrder, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun > , ck::ThreadGroupTensorSliceTransfer_v4r1< ThreadGroup, SrcElementwiseOperation, DstElementwiseOperation, DstInMemOp, BlockSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, DstScalarStrideInVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v4r1_dequant< ThreadGroup, SrcElementwiseOperation, ScaleElementwiseOperation, DstElementwiseOperation, DstInMemOp, BlockSliceLengths, BlockScaleSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcData, ScaleData, DstData, SrcDesc, ScaleDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, ScaleScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, ScaleScalarStrideInVector, DstScalarStrideInVector, ThreadTransferSrcResetCoordinateAfterRun, ThreadTransferDstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v4r2< ThreadGroup, ElementwiseOperation, DstInMemOps, BlockSliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDatas, DstDatas, SrcDescs, DstDescs, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcsScalarPerVector, DstsScalarPerVector, SrcsScalarStrideInVector, DstsScalarStrideInVector, ThreadTransferSrcsResetCoordinateAfterRun, ThreadTransferDstsResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v7r2< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadGroupTensorSliceTransfer_v7r3< ThreadGroup, SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, ThreadClusterLengths, ThreadClusterArrangeOrder, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVectors, DstScalarPerVector, ThreadTransferSrcResetCoordinateAfterRunFlags, ThreadTransferDstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3< SliceLengths, DstInMemOp, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v3r1< SliceLengths, SrcElementwiseOperation, DstElementwiseOperation, DstInMemOp, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector_, DstScalarPerVector_, SrcScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3r1_dequant< SliceLengths, ScaleSliceLengths, SrcElementwiseOperation, ScaleElementwiseOperation, DstElementwiseOperation, DstInMemOp, SrcData, ScaleData, DstData, SrcDesc, ScaleDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, ScaleScalarPerVector, DstScalarPerVector, SrcScalarStrideInVector, ScaleScalarStrideInVector, DstScalarStrideInVector, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v3r2< SliceLengths, ElementwiseOperation, DstInMemOps, SrcDatas, DstDatas, SrcDescs, DstDescs, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcsScalarPerVector, DstsScalarPerVector, SrcsScalarStrideInVector, DstsScalarStrideInVector, SrcsResetCoordinateAfterRun, DstsResetCoordinateAfterRun, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v5r1< SliceLengths, DstInMemOp, SrcData, DstData, SrcDesc, DstDesc, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorTensorLengths, DstVectorTensorLengths, SrcVectorTensorContiguousDimOrder, DstVectorTensorContiguousDimOrder, SrcResetCoordinateAfterRun, DstResetCoordinateAfterRun > , ck::ThreadwiseTensorSliceTransfer_v7r2< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVector, DstScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags, NumThreadScratch > , ck::ThreadwiseTensorSliceTransfer_v7r3< SrcDatas, DstDatas, SrcDescs, DstDescs, ElementwiseOperation, DstInMemOps, SliceLengths, SrcDimAccessOrder, DstDimAccessOrder, SrcVectorDim, DstVectorDim, SrcScalarPerVectors, DstScalarPerVector, SrcResetCoordinateAfterRunFlags, DstResetCoordinateAfterRunFlags, NumThreadScratch >