- o -

• OpDelta : cutlass::gemm::warp::MmaTensorOpAccumulatorTileIterator< Shape_, Element_, cutlass::layout::ColumnMajor, InstructionShape_, OpDelta_ > , cutlass::gemm::warp::MmaTensorOpAccumulatorTileIterator< Shape_, Element_, cutlass::layout::ColumnMajorInterleaved< InterleavedN >, InstructionShape_, OpDelta_ > , cutlass::gemm::warp::MmaTensorOpAccumulatorTileIterator< Shape_, Element_, cutlass::layout::RowMajor, InstructionShape_, OpDelta_ > , cutlass::gemm::warp::MmaTensorOpPolicy< Operator_, OpDelta_ > , cutlass::gemm::warp::MmaVoltaTensorOpAccumulatorTileIterator< Shape_, Element_, Layout_, InstructionShape_, OpDelta_ >
• Operator : cutlass::arch::Mma< gemm::GemmShape< 16, 8, 8 >, 32, half_t, layout::RowMajor, half_t, layout::ColumnMajor, float, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 16, 8, 8 >, 32, half_t, layout::RowMajor, half_t, layout::ColumnMajor, half_t, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 128 >, 32, uint1b_t, layout::RowMajor, uint1b_t, layout::ColumnMajor, int, layout::RowMajor, OpXorPopc > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, int8_t, layout::RowMajor, uint8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, int8_t, layout::RowMajor, uint8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, uint8_t, layout::RowMajor, int8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, uint8_t, layout::RowMajor, int8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, uint8_t, layout::RowMajor, uint8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 16 >, 32, uint8_t, layout::RowMajor, uint8_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, int4b_t, layout::RowMajor, int4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, int4b_t, layout::RowMajor, int4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, int4b_t, layout::RowMajor, uint4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, int4b_t, layout::RowMajor, uint4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, uint4b_t, layout::RowMajor, int4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, uint4b_t, layout::RowMajor, int4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, uint4b_t, layout::RowMajor, uint4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 32 >, 32, uint4b_t, layout::RowMajor, uint4b_t, layout::ColumnMajor, int, layout::RowMajor, OpMultiplyAddSaturate > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::ColumnMajor, float, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::ColumnMajor, half_t, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::RowMajor, float, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::RowMajor, half_t, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::ColumnMajor, float, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::ColumnMajor, half_t, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::RowMajor, float, layout::RowMajor, OpMultiplyAdd > , cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::RowMajor, half_t, layout::RowMajor, OpMultiplyAdd > , cutlass::epilogue::thread::ReductionOpPlus< Element_, Count > , cutlass::epilogue::threadblock::DirectEpilogueTensorOp< Shape_, Operator_, PartitionsK, Element_, OutputOp_, ConvertOp_ > , cutlass::epilogue::warp::FragmentIteratorSimt< WarpShape_, Operator_, layout::RowMajor, MmaSimtPolicy_ > , cutlass::epilogue::warp::SimtPolicy< WarpShape_, Operator_, layout::RowMajor, MmaSimtPolicy_ > , cutlass::epilogue::warp::TileIteratorSimt< WarpShape_, Operator_, Element_, layout::RowMajor, MmaSimtPolicy_ > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassSimt, ArchTag, ElementA, ElementB, ElementC, ElementAccumulator > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassSimt, ArchTag, int8_t, int8_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm70, ElementA, ElementB, ElementC, ElementAccumulator > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, ElementA, ElementB, ElementC, ElementAccumulator > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int4b_t, int4b_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int4b_t, uint4b_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int8_t, int8_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int8_t, uint8_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint4b_t, int4b_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint4b_t, uint4b_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint8_t, int8_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint8_t, uint8_t, ElementC, int32_t > , cutlass::gemm::device::DefaultGemmConfiguration< arch::OpClassWmmaTensorOp, ArchTag, ElementA, ElementB, ElementC, ElementAccumulator > , cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero > , cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero > , cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ > , cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ > , cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ > , cutlass::gemm::thread::Mma< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, arch::OpMultiplyAdd, bool > , cutlass::gemm::thread::Mma< Shape_, half_t, LayoutA, half_t, LayoutB, half_t, LayoutC, arch::OpMultiplyAdd > , cutlass::gemm::thread::Mma< Shape_, half_t, LayoutA_, half_t, LayoutB_, half_t, layout::RowMajor, arch::OpMultiplyAdd, typename platform::enable_if< detail::EnableMma_Crow_SM60< LayoutA_, LayoutB_ >::value >::type > , cutlass::gemm::thread::Mma< Shape_, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, int32_t, LayoutC_, arch::OpMultiplyAdd, int8_t > , cutlass::gemm::thread::Mma< Shape_, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, int32_t, LayoutC_, arch::OpMultiplyAdd, bool > , cutlass::gemm::thread::MmaGeneric< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, Operator_ > , cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::Gemv< Core_ > , cutlass::gemm::threadblock::MmaBase< Shape_, Policy_, Stages, Enable > , cutlass::gemm::threadblock::MmaPipelined< Shape_, IteratorA_, SmemIteratorA_, IteratorB_, SmemIteratorB_, ElementC_, LayoutC_, Policy_, TransformA_, TransformB_, Enable > , cutlass::gemm::threadblock::MmaPolicy< Operator_, SmemPaddingA_, SmemPaddingB_, PartitionsK > , cutlass::gemm::threadblock::MmaSingleStage< Shape_, IteratorA_, SmemIteratorA_, IteratorB_, SmemIteratorB_, ElementC_, LayoutC_, Policy_, Enable > , cutlass::gemm::warp::MmaTensorOpPolicy< Operator_, OpDelta_ >
• OperatorClass : cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero > , cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero > , cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ > , cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ > , cutlass::gemm::device::GemmComplex< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, TransformA, TransformB, SplitKSerial > , cutlass::gemm::device::GemmComplex< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, TransformA, TransformB, SplitKSerial > , cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ > , cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ > , cutlass::gemm::kernel::DefaultGemm< int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementC, LayoutC, ElementAccumulator, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 4 >, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator, false > , cutlass::gemm::threadblock::DefaultMma< int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 4 >, 2, Operator, false > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_, > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ > , cutlass::gemm::warp::MmaComplexTensorOp< Shape_, complex< RealElementA >, LayoutA_, complex< RealElementB >, LayoutB_, complex< RealElementC >, LayoutC_, Policy_, TransformA, TransformB, Enable > , cutlass::gemm::warp::MmaSimt< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, Policy_, PartitionsK, Enable > , cutlass::gemm::warp::MmaTensorOp< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, Policy_, PartitionsK_, AccumulatorsInRowMajor, PartitionsN_, Enable > , cutlass::gemm::warp::MmaVoltaTensorOp< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, Policy_, Enable >
• OperatorCount : cutlass::epilogue::warp::TensorOpPolicy< WarpShape, OperatorShape, layout::ColumnMajorInterleaved< InterleavedK > > , cutlass::epilogue::warp::TensorOpPolicy< WarpShape, OperatorShape, layout::RowMajor >
• OperatorElementC : cutlass::epilogue::warp::FragmentIteratorComplexTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::ColumnMajorInterleaved< InterleavedK > > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor >
• OperatorFragment : cutlass::epilogue::warp::TileIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorFragment_, layout::RowMajor >
• OperatorFragmentC : cutlass::epilogue::warp::FragmentIteratorComplexTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::ColumnMajorInterleaved< InterleavedK > > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor >
• OperatorShape : cutlass::epilogue::warp::FragmentIteratorComplexTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::ColumnMajorInterleaved< InterleavedK > > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::TileIteratorTensorOp< WarpShape_, OperatorShape_, Element_, layout::RowMajor > , cutlass::epilogue::warp::TileIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorFragment_, layout::RowMajor >
• OutputAccessType : cutlass::epilogue::threadblock::Epilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, WarpTileIterator_, SharedLoadIterator_, OutputOp_, Padding_ > , cutlass::epilogue::threadblock::InterleavedEpilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, OutputOp_, InterleavedK, IsBetaZero >
• OutputAccumulatorTile : cutlass::epilogue::warp::FragmentIteratorComplexTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorSimt< WarpShape_, Operator_, layout::RowMajor, MmaSimtPolicy_ > , cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor >
• OutputOp : cutlass::epilogue::threadblock::DefaultEpilogueComplexTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueSimt< Shape_, WarpMmaSimt_, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueVoltaTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueWmmaTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultInterleavedEpilogueTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess, InterleavedK, IsBetaZero, isSplitK > , cutlass::epilogue::threadblock::DirectEpilogueTensorOp< Shape_, Operator_, PartitionsK, Element_, OutputOp_, ConvertOp_ > , cutlass::epilogue::threadblock::Epilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, WarpTileIterator_, SharedLoadIterator_, OutputOp_, Padding_ > , cutlass::epilogue::threadblock::InterleavedEpilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, OutputOp_, InterleavedK, IsBetaZero > , cutlass::gemm::kernel::Gemm< Mma_, Epilogue_, ThreadblockSwizzle_, SplitKSerial > , cutlass::gemm::kernel::GemmBatched< Mma_, Epilogue_, ThreadblockSwizzle_ > , cutlass::gemm::kernel::GemmSplitKParallel< Mma_, Epilogue_, ThreadblockSwizzle_ > , cutlass::reduction::kernel::ReduceSplitK< Shape_, OutputOp_, ReductionOp_, PartitionsPerStage >
• OutputTensorRef : cutlass::reduction::kernel::ReduceSplitK< Shape_, OutputOp_, ReductionOp_, PartitionsPerStage >
• OutputTile : cutlass::reduction::BatchedReductionTraits< ScalarA_, ScalarC_, ScalarD_, ScalarAlphaBeta_, ScalarAccum_, ReductionSize_, OutputTile_, SubTile_, ThreadShape_, Index_, BlockSwizzle_, maxInReg_, maxOutReg_, Functor_ >
• OutputTileIterator : cutlass::epilogue::threadblock::DefaultEpilogueComplexTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueSimt< Shape_, WarpMmaSimt_, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueVoltaTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueWmmaTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultInterleavedEpilogueTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess, InterleavedK, IsBetaZero, isSplitK > , cutlass::epilogue::threadblock::Epilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, WarpTileIterator_, SharedLoadIterator_, OutputOp_, Padding_ > , cutlass::epilogue::threadblock::InterleavedEpilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, OutputOp_, InterleavedK, IsBetaZero >
• OutputTileThreadMap : cutlass::epilogue::threadblock::DefaultEpilogueComplexTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueSimt< Shape_, WarpMmaSimt_, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueVoltaTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultEpilogueWmmaTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess > , cutlass::epilogue::threadblock::DefaultInterleavedEpilogueTensorOp< Shape_, WarpMmaTensorOp_, PartitionsK, OutputOp_, ElementsPerAccess, InterleavedK, IsBetaZero, isSplitK >