output_tile_thread_map.h File Reference

Metaprogram for determining the mapping of output elements to threads for epilogue tiles. More...

#include "cutlass/cutlass.h"
#include "cutlass/numeric_types.h"
#include "cutlass/array.h"
#include "cutlass/layout/matrix.h"
#include "cutlass/matrix_shape.h"
#include "cutlass/tensor_ref.h"
#include "cutlass/fast_math.h"

Include dependency graph for output_tile_thread_map.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::OutputTileShape< Column, Row, Group, Cluster, Tile >
	Tuple defining point in output tile. More...
struct	cutlass::epilogue::threadblock::OutputTileThreadMap< ThreadMap_, Shape_, Iterations_, Delta_, Count_ >
struct	cutlass::epilogue::threadblock::detail::RowArrangement< Shape, WarpsRemaining, ElementsPerAccess, ElementSize, Is2dTile >
	RowArrangement determines how one or more warps cover a region of consecutive rows. More...
struct	cutlass::epilogue::threadblock::detail::RowArrangement< Shape, WarpsRemaining, ElementsPerAccess, ElementSize, false >
	RowArrangement in which each warp's access is a 1D tiled arrangement. More...
struct	cutlass::epilogue::threadblock::detail::RowArrangement< Shape, WarpsRemaining, ElementsPerAccess, ElementSize, true >
	RowArrangement in which each warp's access is a 2D tiled arrangement. More...
struct	cutlass::epilogue::threadblock::detail::RowArrangement< Shape, WarpsRemaining, ElementsPerAccess, ElementSize, true >::Detail
struct	cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize >
struct	cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize >::Detail
struct	cutlass::epilogue::threadblock::OutputTileOptimalThreadMap< Shape_, Count_, Threads, ElementsPerAccess, ElementSize >::CompactedThreadMap
	Compacted thread map in which the 4D region is contiguous. More...
struct	cutlass::epilogue::threadblock::InterleavedOutputTileThreadMap< WarpCount_, MmaCount_, Threads, ElementsPerAccess, ElementSize >
struct	cutlass::epilogue::threadblock::InterleavedOutputTileThreadMap< WarpCount_, MmaCount_, Threads, ElementsPerAccess, ElementSize >::Detail

Namespaces
	cutlass
	cutlass::epilogue
	cutlass::epilogue::threadblock
	cutlass::epilogue::threadblock::detail