CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
Classes | Namespaces
default_thread_map_volta_tensor_op.h File Reference
#include "predicated_tile_iterator.h"
#include "cutlass/gemm/gemm.h"
Include dependency graph for default_thread_map_volta_tensor_op.h:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes

struct  cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape, WarpShape, PartitionsK, ElementOutput, ElementsPerAccess, ElementAccumulator >
 Defines the optimal thread map for TensorOp accumulator layouts. More...
 
struct  cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, half_t >
 Defines the optimal thread map for TensorOp accumulator layouts. More...
 
struct  cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, half_t >::Detail
 
struct  cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, float >
 Defines the optimal thread map for TensorOp accumulator layouts. More...
 
struct  cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, float >::Detail
 

Namespaces

 cutlass
 
 cutlass::epilogue
 
 cutlass::epilogue::threadblock