CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
|
Internal structure of iterator - made public to enable introspection.
#include <mma_tensor_op_tile_iterator_sm70.h>
Public Types | |
using | LdsShape = layout::PitchLinearShape< 32, 4 > |
using | LdsIterations = layout::PitchLinearShape< InstructionShape::kStrided/LdsShape::kStrided, Shape::kContiguous/LdsShape::kContiguous > |
using cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::VoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, InstructionShape_, OpDelta_, 32 >::Policy::LdsIterations = layout::PitchLinearShape< InstructionShape::kStrided / LdsShape::kStrided, Shape::kContiguous / LdsShape::kContiguous > |
using cutlass::gemm::warp::MmaVoltaTensorOpMultiplicandTileIterator< Shape_, Operand::kA, Element_, cutlass::layout::VoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, InstructionShape_, OpDelta_, 32 >::Policy::LdsShape = layout::PitchLinearShape< 32, 4 > |