52 namespace threadblock {
    70     typename InstructionShape_,
    83                       ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_
    98     Shape::kM / WarpShape::kM,
    99     Shape::kN / WarpShape::kN,
   100     Shape::kK / WarpShape::kK
   105     !(Shape::kM % WarpShape::kM) &&
   106     !(Shape::kN % WarpShape::kN),
   107     "Threadblock-scoped GEMM should be divisible by warp-scoped GEMM size."   114   static int const kThreads = WarpCount::kCount * kWarpSize;
   117   static int const kAccessSizeInBits = 128;
   159     layout::PitchLinearShape<8, 4>,
   206     typename InstructionShape_,
   219                       ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_
   234     Shape::kM / WarpShape::kM,
   235     Shape::kN / WarpShape::kN,
   236     Shape::kK / WarpShape::kK
   241     !(Shape::kM % WarpShape::kM) &&
   242     !(Shape::kN % WarpShape::kN),
   243     "Threadblock-scoped GEMM should be divisible by warp-scoped GEMM size."   250   static int const kThreads = WarpCount::kCount * kWarpSize;
   253   static int const kAccessSizeInBits = 128;
   259   static int const kWarpThreadArrangementContiguousA =
   262   static int const kWarpThreadArrangementStridedA =
   263       kWarpSize / kWarpThreadArrangementContiguousA;
   265   static int const kWarpThreadArrangementContiguousB =
   268   static int const kWarpThreadArrangementStridedB =
   269       kWarpSize / kWarpThreadArrangementContiguousB;
   290                                kWarpThreadArrangementStridedA>,
   306                                kWarpThreadArrangementStridedB>,
   352     typename InstructionShape_,
   365                       LayoutC_, arch::OpClassTensorOp, 2, Operator_
   380     Shape::kM / WarpShape::kM,
   381     Shape::kN / WarpShape::kN,
   382     Shape::kK / WarpShape::kK
   387     !(Shape::kM % WarpShape::kM) &&
   388     !(Shape::kN % WarpShape::kN),
   389     "Threadblock-scoped GEMM should be divisible by warp-scoped GEMM size."   396   static int const kThreads = WarpCount::kCount * kWarpSize;
   399   static int const kAccessSizeInBits = 128;
   405   static int const kWarpThreadArrangementContiguousA =
   408   static int const kWarpThreadArrangementStridedA =
   409       kWarpSize / kWarpThreadArrangementContiguousA;
   430                                kWarpThreadArrangementStridedA>,
   493     typename InstructionShape_,
   506                       ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_
   521                               Shape::kN / WarpShape::kN, 
   522                               Shape::kK / WarpShape::kK>;
   526       !(Shape::kM % WarpShape::kM) && !(Shape::kN % WarpShape::kN),
   527       "Threadblock-scoped GEMM should be divisible by warp-scoped GEMM size.");
   533   static int const kThreads = WarpCount::kCount * kWarpSize;
   536   static int const kAccessSizeInBits = 128;
   542   static int const kWarpThreadArrangementContiguousB =
   545   static int const kWarpThreadArrangementStridedB =
   546       kWarpSize / kWarpThreadArrangementContiguousB;
   578                                kWarpThreadArrangementStridedB>,
   615     typename InstructionShape_,
   628     bool AccumulatorsInRowMajor,
   632                       layout::ColumnMajorInterleaved<InterleavedK>, ElementB_,
   634                       LayoutC_, arch::OpClassTensorOp, 2, Operator_,
   635                       AccumulatorsInRowMajor> {
   646   static int const kInterleavedK = InterleavedK;
   650                               Shape::kN / WarpShape::kN, 
   651                               Shape::kK / WarpShape::kK>;
   655       !(Shape::kM % WarpShape::kM) && !(Shape::kN % WarpShape::kN),
   656       "Threadblock-scoped GEMM should be divisible by warp-scoped GEMM size.");
   662   static int const kThreads = WarpCount::kCount * kWarpSize;
   665   static int const kAccessSizeInBits = 128;
   671   static int const kElementsPerAccess =
   674   static int const kWarpThreadArrangementContiguous =
   675       kInterleavedK / kElementsPerAccess;
   677   static int const kWarpThreadArrangementStrided =
   678       kWarpSize / kWarpThreadArrangementContiguous;
   698                                Shape::kK / kInterleavedK>,
   705                                kWarpThreadArrangementStrided>>;
   715                                Shape::kK / kInterleavedK>,
   716       kThreads, layout::PitchLinearShape<32, 1>, kElementsPerAccess>;
   722                                kWarpThreadArrangementStrided>>;
 cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::OperatorClass arch::OpClassTensorOp OperatorClass
Definition: default_mma_core_sm75.h:517
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementA ElementA_ ElementA
Definition: default_mma_core_sm75.h:511
Describes the size of a matrix tile. 
Definition: matrix_shape.h:42
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::InstructionShape InstructionShape_ InstructionShape
Definition: default_mma_core_sm75.h:223
Templates implementing storing of tiles from pitch-linear rank=2 tensors. 
Definition: aligned_buffer.h:35
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::LayoutC LayoutC_ LayoutC
Definition: default_mma_core_sm75.h:375
Default warp-level GEMM operators selected by data type, size, and layouts of operands. 
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementB ElementB_ ElementB
Definition: default_mma_core_sm75.h:372
Query the number of threads per warp. 
Definition: gemm/warp/mma.h:43
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::Shape Shape_ Shape
Definition: default_mma_core_sm75.h:636
Definition: tensor_op_multiplicand_sm75.h:734
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementC ElementC_ ElementC
Definition: default_mma_core_sm75.h:515
Definition: default_mma_core.h:90
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Shape Shape_ Shape
Definition: default_mma_core_sm75.h:508
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaTensorOp typename cutlass::gemm::warp::DefaultMmaTensorOp< WarpShape, InstructionShape, ElementA, SmemLayoutA, ElementB, SmemLayoutB, ElementC, LayoutC, Operator, WarpCount::kK >::Type MmaTensorOp
Definition: default_mma_core_sm75.h:325
Templates implementing how threads are mapped to a given tile. 
Partial specialization for m-by-n-by-kgroup. 
Definition: default_mma_tensor_op.h:67
Definition: tensor_op_multiplicand_sm75.h:422
Definition: tensor_op_multiplicand_sm75.h:835
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementB ElementB_ ElementB
Definition: default_mma_core_sm75.h:513
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaTensorOp typename cutlass::gemm::warp::DefaultMmaTensorOp< WarpShape, InstructionShape, ElementA, SmemLayoutA, ElementB, SmemLayoutB, ElementC, LayoutC, Operator, WarpCount::kK >::Type MmaTensorOp
Definition: default_mma_core_sm75.h:593
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::OperatorClass arch::OpClassTensorOp OperatorClass
Definition: default_mma_core_sm75.h:94
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Shape Shape_ Shape
Definition: default_mma_core_sm75.h:85
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Operator Operator_ Operator
Default Operator. 
Definition: default_mma_core_sm75.h:256
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaPolicy MmaPolicy< MmaTensorOp, MatrixShape< 0, 0 >, MatrixShape< 0, 0 >, WarpCount::kK > MmaPolicy
Policy used to define MmaPipelined. 
Definition: default_mma_core_sm75.h:187
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::LayoutC LayoutC_ LayoutC
Definition: default_mma_core_sm75.h:93
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementB ElementB_ ElementB
Definition: default_mma_core_sm75.h:226
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::MmaPolicy MmaPolicy< MmaTensorOp, MatrixShape< 0, 0 >, MatrixShape< 0, 0 >, WarpCount::kK > MmaPolicy
Policy used to define MmaPipelined. 
Definition: default_mma_core_sm75.h:740
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::OperatorClass arch::OpClassTensorOp OperatorClass
Definition: default_mma_core_sm75.h:376
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementA ElementA_ ElementA
Definition: default_mma_core_sm75.h:88
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementA ElementA_ ElementA
Definition: default_mma_core_sm75.h:370
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementA ElementA_ ElementA
Definition: default_mma_core_sm75.h:224
Mapping function for column-major matrices. 
Definition: layout/matrix.h:142
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaPolicy MmaPolicy< MmaTensorOp, MatrixShape< 0, 0 >, MatrixShape< 0, 0 >, WarpCount::kK > MmaPolicy
Policy used to define MmaPipelined. 
Definition: default_mma_core_sm75.h:597
Template defining a shape used by pitch-linear operators. 
Definition: pitch_linear.h:43
Statically sized array of elements that accommodates all CUTLASS-supported numeric types and is safe ...
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementB ElementB_ ElementB
Definition: default_mma_core_sm75.h:90
Defines a Shape template for matrix tiles. 
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::ElementB ElementB_ ElementB
Definition: default_mma_core_sm75.h:641
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementC ElementC_ ElementC
Definition: default_mma_core_sm75.h:374
Defines the size of an element in bits. 
Definition: numeric_types.h:42
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementC ElementC_ ElementC
Definition: default_mma_core_sm75.h:228
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::OperatorClass arch::OpClassTensorOp OperatorClass
Definition: default_mma_core_sm75.h:230
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::InstructionShape InstructionShape_ InstructionShape
Definition: default_mma_core_sm75.h:87
Defines basic properties needed by CTA-level GEMMs assuming expectations about data layout of the glo...
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::LayoutC LayoutC_ LayoutC
Definition: default_mma_core_sm75.h:229
Top-level include for all CUTLASS numeric types. 
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::InstructionShape InstructionShape_ InstructionShape
Definition: default_mma_core_sm75.h:510
Shape of a matrix multiply-add operation. 
Definition: include/cutlass/gemm/gemm.h:57
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::WarpShape WarpShape_ WarpShape
Definition: default_mma_core_sm75.h:509
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::ElementA ElementA_ ElementA
Definition: default_mma_core_sm75.h:639
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Operator Operator_ Operator
Default Operator. 
Definition: default_mma_core_sm75.h:402
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::WarpShape WarpShape_ WarpShape
Definition: default_mma_core_sm75.h:86
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Operator Operator_ Operator
Default Operator. 
Definition: default_mma_core_sm75.h:539
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaPolicy MmaPolicy< MmaTensorOp, MatrixShape< 0, 0 >, MatrixShape< 0, 0 >, WarpCount::kK > MmaPolicy
Policy used to define MmaPipelined. 
Definition: default_mma_core_sm75.h:474
Mapping function for row-major matrices. 
Definition: layout/matrix.h:50
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaTensorOp typename cutlass::gemm::warp::DefaultMmaTensorOp< WarpShape, InstructionShape, ElementA, SmemLayoutA, ElementB, SmemLayoutB, ElementC, LayoutC, Operator, WarpCount::kK >::Type MmaTensorOp
Definition: default_mma_core_sm75.h:179
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::InstructionShape InstructionShape_ InstructionShape
Definition: default_mma_core_sm75.h:638
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::ElementC ElementC_ ElementC
Definition: default_mma_core_sm75.h:643
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Operator Operator_ Operator
Default Operator. 
Definition: default_mma_core_sm75.h:120
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaTensorOp typename cutlass::gemm::warp::DefaultMmaTensorOp< WarpShape, InstructionShape, ElementA, SmemLayoutA, ElementB, SmemLayoutB, ElementC, LayoutC, Operator, WarpCount::kK >::Type MmaTensorOp
Definition: default_mma_core_sm75.h:466
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::ElementC ElementC_ ElementC
Definition: default_mma_core_sm75.h:92
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::InstructionShape InstructionShape_ InstructionShape
Definition: default_mma_core_sm75.h:369
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Shape Shape_ Shape
Definition: default_mma_core_sm75.h:221
Definition: layout/matrix.h:343
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::WarpShape WarpShape_ WarpShape
Definition: default_mma_core_sm75.h:222
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::OperatorClass arch::OpClassTensorOp OperatorClass
Definition: default_mma_core_sm75.h:645
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::MmaTensorOp typename cutlass::gemm::warp::DefaultMmaTensorOp< WarpShape, InstructionShape, ElementA, SmemLayoutA, ElementB, SmemLayoutB, ElementC, LayoutC, Operator, WarpCount::kK, AccumulatorsInRowMajor >::Type MmaTensorOp
Definition: default_mma_core_sm75.h:736
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::WarpShape WarpShape_ WarpShape
Definition: default_mma_core_sm75.h:637
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::Shape Shape_ Shape
Definition: default_mma_core_sm75.h:367
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::WarpShape WarpShape_ WarpShape
Definition: default_mma_core_sm75.h:368
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::LayoutC LayoutC_ LayoutC
Definition: default_mma_core_sm75.h:644
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::MmaPolicy MmaPolicy< MmaTensorOp, MatrixShape< 0, 0 >, MatrixShape< 0, 0 >, WarpCount::kK > MmaPolicy
Policy used to define MmaPipelined. 
Definition: default_mma_core_sm75.h:333
Basic include for CUTLASS. 
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >::Operator Operator_ Operator
Default Operator. 
Definition: default_mma_core_sm75.h:668
cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >::LayoutC LayoutC_ LayoutC
Definition: default_mma_core_sm75.h:516
Definition: layout/matrix.h:237
Definition: tensor_op_multiplicand_sm75.h:527