- b -

• Base : cutlass::epilogue::threadblock::Epilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, WarpTileIterator_, SharedLoadIterator_, OutputOp_, Padding_ > , cutlass::gemm::BatchedGemmCoord , cutlass::gemm::GemmCoord , cutlass::gemm::threadblock::MmaPipelined< Shape_, IteratorA_, SmemIteratorA_, IteratorB_, SmemIteratorB_, ElementC_, LayoutC_, Policy_, TransformA_, TransformB_, Enable > , cutlass::gemm::threadblock::MmaSingleStage< Shape_, IteratorA_, SmemIteratorA_, IteratorB_, SmemIteratorB_, ElementC_, LayoutC_, Policy_, Enable > , cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::ColumnMajorTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::ColumnMajorTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::RowMajorTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::RowMajorTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, InstructionShape_, OpDelta_, 32 > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kB, Element_, cutlass::layout::RowMajorVoltaTensorOpMultiplicandBCongruous< sizeof_bits< Element_ >::value >, InstructionShape_, OpDelta_, 32 > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, KBlock >, InstructionShape_, OpDelta_, 32 > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::RowMajorVoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, KBlock >, InstructionShape_, OpDelta_, 32 > , cutlass::layout::ColumnMajorTensorOpMultiplicandCongruous< ElementSize, Crosswise > , cutlass::layout::ColumnMajorTensorOpMultiplicandCrosswise< ElementSize, Crosswise > , cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous< ElementSize > , cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous< ElementSize > , cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise< ElementSize, KBlock > , cutlass::layout::PitchLinearCoord , cutlass::layout::RowMajorTensorOpMultiplicandCongruous< ElementSize, Crosswise > , cutlass::layout::RowMajorTensorOpMultiplicandCrosswise< ElementSize, Crosswise > , cutlass::layout::RowMajorVoltaTensorOpMultiplicandBCongruous< ElementSize > , cutlass::layout::RowMajorVoltaTensorOpMultiplicandCongruous< ElementSize > , cutlass::layout::RowMajorVoltaTensorOpMultiplicandCrosswise< ElementSize, KBlock > , cutlass::layout::TensorOpMultiplicandCongruous< ElementSize, Crosswise > , cutlass::layout::TensorOpMultiplicandCrosswise< ElementSize, Crosswise > , cutlass::MatrixCoord , cutlass::Tensor4DCoord , cutlass::TensorView< Element_, Layout_ > , cutlass::thread::Matrix< Element, Rows, Columns, Layout >
• BlockSwizzle : cutlass::reduction::BatchedReductionTraits< ScalarA_, ScalarC_, ScalarD_, ScalarAlphaBeta_, ScalarAccum_, ReductionSize_, OutputTile_, SubTile_, ThreadShape_, Index_, BlockSwizzle_, maxInReg_, maxOutReg_, Functor_ >