CUTLASS: Class Members

<!-- do not remove this div, it is closed by doxygen! -->

| | CUTLASS

CUDA Templates for Linear Algebra Subroutines and Solvers |

<!-- end header part --><!-- Generated by Doxygen 1.8.11 -->

• Main Page
• Modules
• Namespaces
• Classes
• Files

<input type="text" id="MSearchField" value="Search" accesskey="S" onfocus="searchBox.OnSearchFieldFocus(true)" onblur="searchBox.OnSearchFieldFocus(false)" onkeyup="searchBox.OnSearchFieldChange(event)">

• Class List

• Class Index

• Class Hierarchy

• Class Members

• All

• Functions

• Variables

• Typedefs

• Enumerations

• Enumerator

• a

• b

• c

• d

• e

• f

• g

• h

• i

• k

• l

• m

• n

• o

• p

• q

• r

• s

• t

• u

• v

• w

• y

• ~

<!-- top --><!-- window showing the filter options --> <!-- iframe showing the search results (closed by default) -->

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

- i -

• Identity : cutlass::Distribution
• IdentityTensorLayout() : cutlass::IdentityTensorLayout< Rank >
• imag() : cutlass::complex< T > , cutlass::TypeTraits< complex< double > >::integer_type , cutlass::TypeTraits< complex< double > >::unsigned_type
• imag_stride_A : cutlass::library::GemmPlanarComplexBatchedConfiguration , cutlass::library::GemmPlanarComplexConfiguration
• imag_stride_B : cutlass::library::GemmPlanarComplexBatchedConfiguration , cutlass::library::GemmPlanarComplexConfiguration
• imag_stride_C : cutlass::library::GemmPlanarComplexBatchedConfiguration , cutlass::library::GemmPlanarComplexConfiguration
• imag_stride_D : cutlass::library::GemmPlanarComplexBatchedConfiguration , cutlass::library::GemmPlanarComplexConfiguration
• increment_cluster : cutlass::epilogue::threadblock::PredicatedTileIterator< ThreadMap_, Element_ >::Params
• increment_group : cutlass::epilogue::threadblock::PredicatedTileIterator< ThreadMap_, Element_ >::Params
• increment_row : cutlass::epilogue::threadblock::PredicatedTileIterator< ThreadMap_, Element_ >::Params
• Index : cutlass::Coord< Rank_, Index_, LongIndex_ > , cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator< ThreadMap_, Element_, InterleavedK > , cutlass::epilogue::threadblock::PredicatedTileIterator< ThreadMap_, Element_ > , cutlass::epilogue::threadblock::SharedLoadIterator< ThreadMap_, Element_, MaxAlignment > , [cutlass::epilogue::warp::TileIteratorSimt< WarpShape_, Operator_, Element_, layout::RowMajor, MmaSimtPolicy_ >](classcutlass_1_1epilogue_1_1warp_1_1TileIteratorSimt_3_01WarpShape 00_01Operator 00_01Elemenf2bd262ed3e202b25d5802d83965bf3b.html#a05ff07efb8d79a930472de75ea30938a) , [cutlass::epilogue::warp::TileIteratorTensorOp< WarpShape_, OperatorShape_, Element_, layout::RowMajor >](classcutlass_1_1epilogue_1_1warp_1_1TileIteratorTensorOp_3_01WarpShape 00_01OperatorShape 003cbb32beb84b4984cb7853662096d289.html#a551137bff490b3b6acfd2f0685a81da5) , cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor > , cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor > , cutlass::epilogue::warp::TileIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorFragment_, layout::RowMajor > , cutlass::gemm::BatchedGemmCoord , cutlass::gemm::GemmCoord , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajor, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajor, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::ColumnMajor, Policy_ > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::RowMajor, Policy_ > , 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::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::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::TensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, 64 >, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::TensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaVoltaTensorOpAccumulatorTileIterator< Shape_, Element_, Layout_, InstructionShape_, OpDelta_ > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, InstructionShape_, OpDelta_, 32 > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::VoltaTensorOpMultiplicandCongruous< 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::kB, Element_, cutlass::layout::VoltaTensorOpMultiplicandBCongruous< 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::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::VoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, KBlock >, InstructionShape_, OpDelta_, 32 > , cutlass::HostTensor< Element_, Layout_ > , cutlass::IdentityTensorLayout< Rank > , cutlass::layout::ColumnMajor , cutlass::layout::ColumnMajorBlockLinear< BlockRows, BlockColumns > , cutlass::layout::ColumnMajorInterleaved< Interleave > , 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::ContiguousMatrix , cutlass::layout::GeneralMatrix , cutlass::layout::PackedVectorLayout , cutlass::layout::PitchLinear , cutlass::layout::PitchLinearCoord , cutlass::layout::RowMajor , cutlass::layout::RowMajorBlockLinear< BlockRows, BlockColumns > , cutlass::layout::RowMajorInterleaved< Interleave > , 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::TensorCxRSKx< Interleave > , cutlass::layout::TensorNCHW , cutlass::layout::TensorNCxHWx< Interleave > , cutlass::layout::TensorNHWC , cutlass::layout::TensorOpMultiplicand< ElementSize, Crosswise > , cutlass::layout::TensorOpMultiplicandColumnMajorInterleaved< ElementSize, InterleavedK > , cutlass::layout::TensorOpMultiplicandCongruous< ElementSize, Crosswise > , cutlass::layout::TensorOpMultiplicandCongruous< 32, Crosswise > , cutlass::layout::TensorOpMultiplicandCrosswise< ElementSize, Crosswise > , cutlass::layout::TensorOpMultiplicandRowMajorInterleaved< ElementSize, InterleavedK > , cutlass::layout::VoltaTensorOpMultiplicandBCongruous< ElementSize > , cutlass::layout::VoltaTensorOpMultiplicandCongruous< ElementSize > , cutlass::layout::VoltaTensorOpMultiplicandCrosswise< ElementSize, KBlock > , cutlass::MatrixCoord , cutlass::reduction::BatchedReductionTraits< ScalarA_, ScalarC_, ScalarD_, ScalarAlphaBeta_, ScalarAccum_, ReductionSize_, OutputTile_, SubTile_, ThreadShape_, Index_, BlockSwizzle_, maxInReg_, maxOutReg_, Functor_ > , cutlass::Tensor4DCoord , cutlass::TensorRef< Element_, Layout_ > , cutlass::TensorView< Element_, Layout_ > , cutlass::thread::Matrix< Element, Rows, Columns, Layout > , cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ > , cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, Transpose_ > , cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ > , cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, Transpose_ > , cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessSize > , cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessSize > , cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessSize > , cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessSize > , cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::RowMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessSize > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::ColumnMajorTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::ColumnMajorTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::RowMajorTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::RowMajorTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::TensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::TensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileIterator2dThreadTile< Shape_, Element_, layout::ColumnMajorInterleaved< 4 >, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Alignment > , cutlass::transform::threadblock::RegularTileIterator2dThreadTile< Shape_, Element_, layout::RowMajorInterleaved< 4 >, AdvanceRank, ThreadMap_, Alignment > , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_011d3637dbd8bc58bcb020b51bf57fbfc0.html#a236cea40e2359a0b5fe35ff1a3519e10) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::ColumnMajorTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_017982f81d4ef592e19c8427de2ea933a3.html#a16ffd59718fc0840d097581b97d14249) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::ColumnMajorTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_010889a732373c350de9b9a9f6c13cd761.html#a147b0e450c08ac0d819b53a63c7aa99e) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01187f8574e1fe9d7d5e8fbf09bd834bf0.html#a16d6cac906acd65af0137086f8eec3d0) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::ColumnMajorVoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01793f74bfd8f116a827948ab01a37349a.html#aa497c5741e2c1a12525fd100478ec34b) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Shape_::kRow >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01bd31b3810c1fedf2e7e5959ff92b5d3d.html#a1281f6ab20cc0d3823992b2342371d47) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_0184a89653916f5d51ab59d1b386989a17.html#a3a922bd28e511a085e2cd09377c04144) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_0149454d361ea5885cf5166a920b5145df.html#af808b8c3fc0bea942874f61c17bbc4f8) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::RowMajorTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01c20d35180520077a5a09b1e33543c1a5.html#a2284ad3a34f8db161542da80486e9ff1) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::RowMajorTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01a31b454d9c930525c1e9ca406a514f40.html#a309465f4c443c5f54e4772226f54bd3c) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::RowMajorVoltaTensorOpMultiplicandBCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_0104ad31bd559a88cc418ae1cab7492ed5.html#a94e8cc78e38dca1afa16ee123e8c7033) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::RowMajorVoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01f6f6511b5033cad31083644ac69c54d8.html#a78f8a422b799001f2c42659b012b722c) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::RowMajorVoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Shape_::kColumn >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01b3fa5720e807697de61b9f937b269cd0.html#a6f91a8008d60668bc7757654a34efc48) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::TensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01efd5013a2503d6567e2bf6b40c97360c.html#af29174087c689128e79bff5b56efb8a2) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::TensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_0197fef2242a3454a7d1cebe61aee28b43.html#a8cf9ea1e3e4e31ae93de613116ae0f63) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::VoltaTensorOpMultiplicandBCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01a75d2cd74e722d6ad6a3b41aabfd432d.html#acf73851870e141f73aa1c8c5a251714f) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::VoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01f96bbeb63e6d4ce4a2551279de3a9f0e.html#a0adc056cc8ab3d39f8a023085e9ad8c2) , [cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::VoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Shape_::kContiguous >, AdvanceRank, ThreadMap_, Alignment >](classcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape 00_01Element 00_01dbd6b8468d5bd787308d2f615a24d123.html#aed83968f30e942628bbe59a36daaa57e)
• infinity() : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#ab7a40820e64282376a050095d5004b74)
• initial_offset() : cutlass::epilogue::threadblock::InterleavedOutputTileThreadMap< WarpCount_, MmaCount_, Threads, ElementsPerAccess, ElementSize > , cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize >::CompactedThreadMap , cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize > , cutlass::epilogue::threadblock::OutputTileThreadMap< ThreadMap_, Shape_, Iterations_, Delta_, Count_ > , cutlass::transform::PitchLinear2DThreadTileStripminedThreadMap< Shape_, Threads, cutlass::layout::PitchLinearShape< 4, 4 > > , cutlass::transform::PitchLinearStripminedThreadMap< Shape_, Threads, ElementsPerAccess > , cutlass::transform::PitchLinearTilePolicyStripminedThreadContiguous< Shape, Threads, ElementsPerAccess > , cutlass::transform::PitchLinearTilePolicyStripminedThreadStrided< Shape, Threads, ElementsPerAccess > , cutlass::transform::PitchLinearWarpRakedThreadMap< Shape_, Threads, WarpThreadArrangement_, ElementsPerAccess > , cutlass::transform::PitchLinearWarpStripedThreadMap< Shape_, Threads, WarpThreadArrangement_, ElementsPerAccess > , cutlass::transform::TransposePitchLinearThreadMap2DThreadTile< ThreadMap_ > , cutlass::transform::TransposePitchLinearThreadMap< ThreadMap_, WarpThreadArrangement_ > , cutlass::transform::TransposePitchLinearThreadMapSimt< ThreadMap_ >
• initialize() : cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator< ThreadMap_, Element_, InterleavedK >::Params , cutlass::epilogue::threadblock::PredicatedTileIterator< ThreadMap_, Element_ >::Params , 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 >](classcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA 00_01LayoutA 00_01ElementB___00_01Layout4d0960ae6b1d1bf19e6239dbd002249c.html#a7a14474e4238d2fac92ad71c6de087d8) , 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_ >](classcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA 00_01ElementB 00_0c9bb6f4463ab6085e6008b5d5ad6abfd.html#a428d8b1c4ac36040145a59d8e4cff3d2) , 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 >](classcutlass_1_1gemm_1_1device_1_1GemmComplex_3_01ElementA 00_01LayoutA 00_01ElementB___00_07c56401b4df75709ae636675d9980a9a.html#a5c3286631f254746c9eb788b780cdca3) , 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::library::Manifest , cutlass::library::Operation , cutlass::reduction::BatchedReductionTraits< ScalarA_, ScalarC_, ScalarD_, ScalarAlphaBeta_, ScalarAccum_, ReductionSize_, OutputTile_, SubTile_, ThreadShape_, Index_, BlockSwizzle_, maxInReg_, maxOutReg_, Functor_ >::Params
• instruction_shape : cutlass::library::MathInstructionDescription
• InstructionShape : cutlass::epilogue::threadblock::DefaultThreadMapWmmaTensorOp< ThreadblockShape_, WarpShape_, InstructionShape_, PartitionsK, Element_, ElementsPerAccess > , cutlass::epilogue::warp::VoltaTensorOpPolicy< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor > , cutlass::epilogue::warp::VoltaTensorOpPolicy< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor > , 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::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 >](classcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA 00_01LayoutA 00_01ElementB___00_01Layout4d0960ae6b1d1bf19e6239dbd002249c.html#a71b84f983b94b50a48bd0890f1e0ed59) , 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_ >](classcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA 00_01ElementB 00_0c9bb6f4463ab6085e6008b5d5ad6abfd.html#ae073edad6dd4447d7f99c94f4cd0c1c8) , 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 >](classcutlass_1_1gemm_1_1device_1_1GemmComplex_3_01ElementA 00_01LayoutA 00_01ElementB___00_07c56401b4df75709ae636675d9980a9a.html#af691b4304896f601c34eaedf78493ed5) , 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::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::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::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::TensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, 64 >, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::TensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, InstructionShape_, OpDelta_, 32, PartitionsK_ > , cutlass::gemm::warp::MmaVoltaTensorOpAccumulatorTileIterator< Shape_, Element_, Layout_, InstructionShape_, OpDelta_ > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, InstructionShape_, OpDelta_, 32 > , cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::VoltaTensorOpMultiplicandCongruous< 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::kB, Element_, cutlass::layout::VoltaTensorOpMultiplicandBCongruous< 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::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand_, Element_, cutlass::layout::VoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, KBlock >, InstructionShape_, OpDelta_, 32 >
• int_scale : cutlass::Distribution , cutlass::reference::device::detail::RandomGaussianFunc< Element >::Params , cutlass::reference::device::detail::RandomUniformFunc< Element >::Params , cutlass::reference::host::detail::RandomGaussianFunc< Element > , cutlass::reference::host::detail::RandomGaussianFunc< complex< Element > > , cutlass::reference::host::detail::RandomUniformFunc< Element > , cutlass::reference::host::detail::RandomUniformFunc< complex< Element > >
• integer_subbyte() : cutlass::integer_subbyte< Bits, Signed >
• integer_type : cutlass::TypeTraits< complex< float > > , cutlass::TypeTraits< complex< half > > , cutlass::TypeTraits< complex< half_t > > , cutlass::TypeTraits< double > , cutlass::TypeTraits< float > , cutlass::TypeTraits< half_t > , cutlass::TypeTraits< int > , cutlass::TypeTraits< int64_t > , cutlass::TypeTraits< int8_t > , cutlass::TypeTraits< uint64_t > , cutlass::TypeTraits< uint8_t > , cutlass::TypeTraits< unsigned >
• InterleavedEpilogue() : cutlass::epilogue::threadblock::InterleavedEpilogue< Shape_, WarpMmaOperator_, PartitionsK, OutputTileIterator_, AccumulatorFragmentIterator_, OutputOp_, InterleavedK, IsBetaZero >
• InterleavedPredicatedTileIterator() : cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator< ThreadMap_, Element_, InterleavedK >
• InterleavedTile : cutlass::gemm::warp::MmaVoltaTensorOpAccumulatorTileIterator< Shape_, Element_, Layout_, InstructionShape_, OpDelta_ >::Policy
• InterleavedTileShape : cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor > , cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor > , cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor > , cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor > , cutlass::epilogue::warp::VoltaTensorOpPolicy< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor > , cutlass::epilogue::warp::VoltaTensorOpPolicy< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor > , cutlass::gemm::warp::MmaVoltaTensorOp< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, Policy_, Enable >
• IntType : cutlass::reference::device::detail::RandomGaussianFunc< Element > , cutlass::reference::device::detail::RandomUniformFunc< Element >
• Invalid : cutlass::Distribution
• inverse() : cutlass::layout::ColumnMajor , cutlass::layout::ColumnMajorBlockLinear< BlockRows, BlockColumns > , cutlass::layout::ColumnMajorInterleaved< Interleave > , 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::ContiguousMatrix , cutlass::layout::PitchLinear , cutlass::layout::RowMajor , cutlass::layout::RowMajorBlockLinear< BlockRows, BlockColumns > , cutlass::layout::RowMajorInterleaved< Interleave > , 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::TensorNHWC , cutlass::layout::TensorOpMultiplicandCongruous< ElementSize, Crosswise > , cutlass::layout::TensorOpMultiplicandCrosswise< ElementSize, Crosswise >
• is_bounded : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#a59737f49161b87c259683c26737f42c2)
• is_exact : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#a7413e9cd24eb03a86cc5f2d47c49db3e)
• is_iec559 : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#afc86b85a1fe209658a50d8c06e54cb77)
• is_integer : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#a2a2ec168a6f0e9f55dc42d3b3e5fff25)
• is_modulo : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#a640a034527a3577039053113bc1c5e46)
• is_signed : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#ab3a169117baca2e7fae33846caa5dbfd)
• is_source_ever_needed() : cutlass::epilogue::thread::Convert< ElementOutput_, Count, ElementAccumulator_, Round >
• is_source_needed() : cutlass::epilogue::thread::Convert< ElementOutput_, Count, ElementAccumulator_, Round > , cutlass::epilogue::thread::LinearCombination< ElementOutput_, Count, ElementAccumulator_, ElementCompute_, Round > , cutlass::epilogue::thread::LinearCombinationClamp< ElementOutput_, Count, ElementAccumulator_, ElementCompute_, Round > , cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, ElementAccumulator_, ElementCompute_, Round > , cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >
• is_specialized : [std::numeric_limits< cutlass::half_t >](structstd_1_1numeric limits_3_01cutlass_1_1half t_01_4.html#ade4affb586360c5356a7939c1b343a40)
• is_zero() : cutlass::PredicateVector< kPredicates_, kPredicatesPerByte_, kPredicateStart_ >
• Iterations : cutlass::epilogue::threadblock::InterleavedOutputTileThreadMap< WarpCount_, MmaCount_, Threads, ElementsPerAccess, ElementSize > , cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize >::CompactedThreadMap , cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize > , cutlass::epilogue::threadblock::OutputTileThreadMap< ThreadMap_, Shape_, Iterations_, Delta_, Count_ > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajor, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajor, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::ColumnMajor, Policy_ > , cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::RowMajor, Policy_ > , cutlass::transform::PitchLinear2DThreadTileStripminedThreadMap< Shape_, Threads, cutlass::layout::PitchLinearShape< 4, 4 > > , cutlass::transform::PitchLinearStripminedThreadMap< Shape_, Threads, ElementsPerAccess > , cutlass::transform::PitchLinearTilePolicyStripminedThreadContiguous< Shape, Threads, ElementsPerAccess > , cutlass::transform::PitchLinearTilePolicyStripminedThreadStrided< Shape, Threads, ElementsPerAccess > , cutlass::transform::PitchLinearWarpRakedThreadMap< Shape_, Threads, WarpThreadArrangement_, ElementsPerAccess > , cutlass::transform::PitchLinearWarpStripedThreadMap< Shape_, Threads, WarpThreadArrangement_, ElementsPerAccess > , cutlass::transform::TransposePitchLinearThreadMap2DThreadTile< ThreadMap_ > , cutlass::transform::TransposePitchLinearThreadMap< ThreadMap_, WarpThreadArrangement_ > , cutlass::transform::TransposePitchLinearThreadMapSimt< ThreadMap_ >
• iterator() : cutlass::Array< T, N, false >::iterator , cutlass::Array< T, N, true >::iterator
• Iterator() : cutlass::PredicateVector< kPredicates_, kPredicatesPerByte_, kPredicateStart_ >::Iterator
• IteratorA : cutlass::gemm::kernel::DefaultGemv< ThreadBlockShape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementCD_, LayoutCD_, ElementAccumulator_ > , cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ > , cutlass::gemm::threadblock::DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::ColumnMajorInterleaved< InterleavedK >, OperatorClass, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, true > , cutlass::gemm::threadblock::DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false > , cutlass::gemm::threadblock::DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassTensorOp, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, 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::Gemv< Core_ > , 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::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 >
• IteratorB : cutlass::gemm::kernel::DefaultGemv< ThreadBlockShape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementCD_, LayoutCD_, ElementAccumulator_ > , cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ > , cutlass::gemm::threadblock::DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::ColumnMajorInterleaved< InterleavedK >, OperatorClass, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, true > , cutlass::gemm::threadblock::DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false > , cutlass::gemm::threadblock::DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassTensorOp, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, 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::Gemv< Core_ > , 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::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 >
• IteratorC : cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ > , cutlass::gemm::threadblock::Gemv< Core_ > , 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 >
• IteratorCD : cutlass::gemm::kernel::DefaultGemv< ThreadBlockShape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementCD_, LayoutCD_, ElementAccumulator_ >
• IteratorPolicyA : cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ >
• IteratorPolicyB : cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ >
• IteratorPolicyC : cutlass::gemm::threadblock::DefaultGemvCore< Shape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_ >
• IteratorPolicyCD : cutlass::gemm::kernel::DefaultGemv< ThreadBlockShape_, ThreadShape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementCD_, LayoutCD_, ElementAccumulator_ >
• IteratorThreadMapA : [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShab94a11a77dd0565102710907089acee0.html#a0f450843b1adf93a82d8fc2e3c58f769) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShafafd5c61db86cbfe90863578ddd11092.html#a26456fb7a61b7ace3225fc91e9b1f68c) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_, >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha46446d1e3871e31d2e728f710d78c8c1.html#ac80eca77d0a29a9178b266a4a5deaae9) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha8da7a0cfbbe859b701fdd9f2b8566aa7.html#aa2ba14171d7b2cef99a3db1419ea41fb) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha84e9f8afb6a4ca9f5dcd219b182d16e7.html#a269432cb8385f4cdc6783d122990410f) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha2c0d0b7cdb5c4bcb11e83c058eb65345.html#a368fe0ace8f4cfcfd886af813344a225) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha34a52cc7b2942e8c290f0032b6779b52.html#a6034c733de72b0f3060f92102298c9d6) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaaf312aafe9da92ea9d417bcc12a8e7dc.html#a11b7dc567a5f7bb381827b8409530f6a) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha863d4139ccaa713bc4bde32c425f4067.html#ab265cae212878b47d8eb4050e5e63474) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaf03a122202ad10acdc96f280106d678b.html#ac7be3a6fb81e9c39bc3d4cabd68922d0) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha69bef08ea63dd930f99d9788105873dd.html#a051a850ff5e96734a936a05b8247e69f) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha3adf608332a8c9ee7014fced0da8a9ca.html#ab71d03458d9f47b2d40bfb6bc52016b5) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShab7edfba3cdf43a07e3c4d719d87565a4.html#a5d3406fa412d5c96e6d16f95048c150e) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc803d38bc1e4618c07c47f54c87ae2678.html#a7bac08ac303fafc399f88bf74af2b55d) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instrucf60fe02fcdd80d28b7fd419133465dcc.html#a9f433583080cc1b8a5dd35c0d932f02e) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc2bf00737f4ad0a9da9a8be6d3e66c152.html#a507e4ab53b7c31ce1de65d588c74e3ff) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc24092ddc01fc83dabb7db4c14880fe60.html#a1ba5e5bc951f24bccc0db30b532ddb62) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc4fee9f2965b8468bfb42b94a74527d22.html#ac6b64933f9b6628ebc1324fd13689143)
• IteratorThreadMapB : [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShab94a11a77dd0565102710907089acee0.html#a89581e14b7ce8bc081a6a6a1ee9857d7) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShafafd5c61db86cbfe90863578ddd11092.html#a09be4f20512d02f18452dab77298b4da) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_, >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha46446d1e3871e31d2e728f710d78c8c1.html#a4143b289655ce6b6484be69cf746600b) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha8da7a0cfbbe859b701fdd9f2b8566aa7.html#ae7c43ed31d0702528c90f170bf772293) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha84e9f8afb6a4ca9f5dcd219b182d16e7.html#ad6be000724ac447ecd66dd0720f05162) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha2c0d0b7cdb5c4bcb11e83c058eb65345.html#a50e3846c0e25e25e81bdbfbacd44106c) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha34a52cc7b2942e8c290f0032b6779b52.html#a81b77d546a00570e7941b5e08b37269c) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaaf312aafe9da92ea9d417bcc12a8e7dc.html#aede8b6f434f8bc14a337820d7c79abf2) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha863d4139ccaa713bc4bde32c425f4067.html#abd3a92eaa779a0148b42921ef1e6b82c) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShaf03a122202ad10acdc96f280106d678b.html#a30b09ef8128d5e6ad601ffba66af08c5) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha69bef08ea63dd930f99d9788105873dd.html#ab1a8a43bc393cdc8b9c690d3f1f4b2cb) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmSha3adf608332a8c9ee7014fced0da8a9ca.html#a84468e2419e1bc35fd1dec28329bf6ca) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01GemmShab7edfba3cdf43a07e3c4d719d87565a4.html#a4fbba145ad9d05c141f26636dfeacbd7) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc803d38bc1e4618c07c47f54c87ae2678.html#a1d752a45cea363b3b957ce23da1af694) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instrucf60fe02fcdd80d28b7fd419133465dcc.html#a7d3f221de20d5cbf0a0a31fc8b99a272) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc2bf00737f4ad0a9da9a8be6d3e66c152.html#a2465d25ece980d3652cc02acf0874c11) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc24092ddc01fc83dabb7db4c14880fe60.html#ad4ebd07d52c77fbc01844e197c6d6a09) , [cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >](structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape 00_01WarpShape 00_01Instruc4fee9f2965b8468bfb42b94a74527d22.html#a8e981771cd56b2be97ead8f1ef585b1b)

<!-- contents --><!-- start footer part -->

---

<address class="footer"><small> Generated by 1.8.11 </small></address>