47 namespace threadblock {
    59     typename InstructionShape,
    73     typename OperatorClass,
    77     typename Operator = 
typename platform::conditional<
    78         (platform::is_same<OperatorClass,
    79                            cutlass::arch::OpClassTensorOp>::value) &&
    84         cutlass::arch::OpMultiplyAddSaturate,
    85         cutlass::arch::OpMultiplyAdd>::type,
    88     bool AccumulatorsInRowMajor = 
false 
Definition: aligned_buffer.h:35
Template for a double-buffered threadblock-scoped GEMM kernel. 
Definition: default_mma_core.h:90
Statically sized array of elements that accommodates all CUTLASS-supported numeric types and is safe ...
Templates exposing architecture support for warp-level multiply-add operations. 
Defines a Shape template for matrix tiles. 
Template for a double-buffered threadblock-scoped GEMM kernel. 
Top-level include for all CUTLASS numeric types. 
Basic include for CUTLASS.