Member List

• ck
• tensor_operation
• device
• DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
• 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 Member List

This is the complete list of members for 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, including all inherited members.

Argument typedef	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
BaseInvoker()=default	ck::tensor_operation::device::BaseInvoker
BaseInvoker(const BaseInvoker &)=default	ck::tensor_operation::device::BaseInvoker
operator=(const BaseInvoker &)=default	ck::tensor_operation::device::BaseInvoker
Run(const Argument &arg, const StreamConfig &stream_config=StreamConfig{})	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	inline
Run(const BaseArgument *p_arg, const StreamConfig &stream_config=StreamConfig{}) override	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	inlinevirtual
RunImp(const Argument &arg, const StreamConfig &stream_config=StreamConfig{})	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	inline
~BaseInvoker()	ck::tensor_operation::device::BaseInvoker	inlinevirtual