| A0GridDesc_AK0_M_AK1 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 > | |
| A0GridDesc_M_K 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 > | |
| B0GridDesc_BK0_N_BK1 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 > | |
| B0GridDesc_N_K 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 > | |
| B1GridDesc_BK0_N_BK1 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 > | |
| B1GridDesc_N_K 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 > | |
| BaseOperator()=default | ck::tensor_operation::device::BaseOperator | |
| BaseOperator(const BaseOperator &)=default | ck::tensor_operation::device::BaseOperator | |
| CheckDLayout() | 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 > | inlinestatic |
| D0sGridDesc_M_N 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 > | |
| D1sGridDesc_M_N 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 > | |
| DeviceOp 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 > | |
| E1GridDesc_M_N 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 > | |
| gemm0_padder | 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 > | static |
| Gemm0MXdlPerWave32 | 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 > | static |
| Gemm0MXdlPerWave64 | 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 > | static |
| gemm1_padder | 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 > | static |
| GetInstanceString() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetObjectName() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTemplateInfo() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTypeIdHashCode() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTypeIdName() const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GetTypeString() const override | ck::tensor_operation::device::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 > | inlinevirtual |
| GetWorkSpaceSize(const BaseArgument *) const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| GridwiseGemm32 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 > | |
| GridwiseGemm64 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 > | |
| GridwiseGemmBase 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 > | |
| I0 | 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 > | static |
| I1 | 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 > | static |
| I2 | 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 > | static |
| I3 | 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 > | static |
| I4 | 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 > | static |
| I5 | 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 > | static |
| I6 | 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 > | static |
| I7 | 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 > | static |
| I8 | 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 > | static |
| I9 | 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 > | static |
| IsSupportedArgument(const Argument &arg) | 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 > | inlinestatic |
| IsSupportedArgument(const BaseArgument *p_arg) 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 > | inlinevirtual |
| IsValidCompilationParameter() | 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 > | inlinestatic |
| MakeA0GridDescriptor_M_K(index_t MRaw, index_t KRaw, index_t StrideA0) | 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 > | inlinestatic |
| MakeArgument(const A0DataType *p_a0, const B0DataType *p_b0, std::array< const void *, NumD0Tensor > p_d0s, const B1DataType *p_b1, std::array< const void *, NumD1Tensor > p_d1s, E1DataType *p_e1, index_t MRaw, index_t NRaw, index_t KRaw, index_t Gemm1NRaw, index_t Batch, index_t StrideA0, index_t StrideB0, std::array< index_t, NumD0Tensor > StrideD0s, index_t StrideB1, std::array< index_t, NumD1Tensor > StrideD1s, index_t StrideE1, index_t BatchStrideA0, index_t BatchStrideB0, std::array< index_t, NumD0Tensor > BatchStrideD0s, index_t BatchStrideB1, std::array< index_t, NumD1Tensor > BatchStrideD1s, index_t BatchStrideE1, A0ElementwiseOperation a0_element_op, B0ElementwiseOperation b0_element_op, CDE0ElementwiseOperation cde0_element_op, B1ElementwiseOperation b1_element_op, CDE1ElementwiseOperation cde1_element_op) | 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 > | inlinestatic |
| MakeArgumentPointer(const void *p_a0, const void *p_b0, std::array< const void *, NumD0Tensor > p_d0s, const void *p_b1, std::array< const void *, NumD1Tensor > p_d1s, void *p_e1, index_t MRaw, index_t NRaw, index_t KRaw, index_t Gemm1NRaw, index_t Batch, index_t StrideA0, index_t StrideB0, std::array< ck::index_t, NumD0Tensor > StrideD0s, index_t StrideB1, std::array< ck::index_t, NumD1Tensor > StrideD1s, index_t StrideE1, index_t BatchStrideA0, index_t BatchStrideB0, std::array< ck::index_t, NumD0Tensor > BatchStrideD0s, index_t BatchStrideB1, std::array< ck::index_t, NumD1Tensor > BatchStrideD1s, index_t BatchStrideE1, A0ElementwiseOperation a0_element_op, B0ElementwiseOperation b0_element_op, CDE0ElementwiseOperation cde0_element_op, B1ElementwiseOperation b1_element_op, CDE1ElementwiseOperation cde1_element_op) 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 > | inlinevirtual |
| MakeB0GridDescriptor_N_K(index_t KRaw, index_t NRaw, index_t StrideB) | 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 > | inlinestatic |
| MakeB1GridDescriptor_N_K(index_t KRaw, index_t NRaw, index_t StrideB) | 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 > | inlinestatic |
| MakeD0GridDescriptor_M_N(index_t MRaw, index_t NRaw, index_t StrideD0) | 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 > | inlinestatic |
| MakeD0sGridDescriptor_M_N(const std::array< index_t, NumD1Tensor > &MRaws, const std::array< index_t, NumD1Tensor > &NRaws, const std::array< index_t, NumD1Tensor > &DsStride) | 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 > | inlinestatic |
| MakeD1sGridDescriptor_M_N(const std::array< index_t, NumD1Tensor > &MRaws, const std::array< index_t, NumD1Tensor > &NRaws, const std::array< index_t, NumD1Tensor > &DsStride) | 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 > | inlinestatic |
| MakeE1GridDescriptor_M_N(index_t MRaw, index_t NRaw, index_t StrideE1) | 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 > | inlinestatic |
| MakeInvoker() | 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 > | inlinestatic |
| MakeInvokerPointer() 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 > | inlinevirtual |
| NumD0Tensor | 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 > | static |
| NumD1Tensor | 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 > | static |
| operator=(const BaseOperator &)=default | ck::tensor_operation::device::BaseOperator | |
| SetWorkSpacePointer(BaseArgument *p_arg, void *p_workspace, const StreamConfig &=StreamConfig{}) const | ck::tensor_operation::device::BaseOperator | inlinevirtual |
| ~BaseOperator() | ck::tensor_operation::device::BaseOperator | inlinevirtual |