squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
7e370c9637
cutlass/docs/search/classes_2.js

42 lines
5.6 KiB
JavaScript
Raw Normal View History

CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
var searchData=
[
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['cast',['Cast',['../structcutlass_1_1reference_1_1detail_1_1Cast.html',1,'cutlass::reference::detail']]],
['cast_3c_20float_2c_20int8_5ft_20_3e',['Cast< float, int8_t >',['../structcutlass_1_1reference_1_1detail_1_1Cast_3_01float_00_01int8__t_01_4.html',1,'cutlass::reference::detail']]],
['cast_3c_20float_2c_20uint8_5ft_20_3e',['Cast< float, uint8_t >',['../structcutlass_1_1reference_1_1detail_1_1Cast_3_01float_00_01uint8__t_01_4.html',1,'cutlass::reference::detail']]],
['columnmajor',['ColumnMajor',['../classcutlass_1_1layout_1_1ColumnMajor.html',1,'cutlass::layout']]],
['columnmajorblocklinear',['ColumnMajorBlockLinear',['../structcutlass_1_1layout_1_1ColumnMajorBlockLinear.html',1,'cutlass::layout']]],
['columnmajorinterleaved',['ColumnMajorInterleaved',['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html',1,'cutlass::layout']]],
['columnmajorinterleaved_3c_204_20_3e',['ColumnMajorInterleaved< 4 >',['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html',1,'cutlass::layout']]],
['columnmajortensoropmultiplicandcongruous',['ColumnMajorTensorOpMultiplicandCongruous',['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCongruous.html',1,'cutlass::layout']]],
['columnmajortensoropmultiplicandcrosswise',['ColumnMajorTensorOpMultiplicandCrosswise',['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCrosswise.html',1,'cutlass::layout']]],
['columnmajorvoltatensoropmultiplicandbcongruous',['ColumnMajorVoltaTensorOpMultiplicandBCongruous',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html',1,'cutlass::layout']]],
['columnmajorvoltatensoropmultiplicandcongruous',['ColumnMajorVoltaTensorOpMultiplicandCongruous',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html',1,'cutlass::layout']]],
['columnmajorvoltatensoropmultiplicandcrosswise',['ColumnMajorVoltaTensorOpMultiplicandCrosswise',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCrosswise.html',1,'cutlass::layout']]],
['commandline',['CommandLine',['../structcutlass_1_1CommandLine.html',1,'cutlass']]],
['compactedthreadmap',['CompactedThreadMap',['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileOptimalThreadMap_1_1CompactedThreadMap.html',1,'cutlass::epilogue::threadblock::OutputTileOptimalThreadMap']]],
['complex',['complex',['../classcutlass_1_1complex.html',1,'cutlass']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['conditional',['conditional',['../structcutlass_1_1platform_1_1conditional.html',1,'cutlass::platform']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['conditional_3c_20_28_28ksizebits_2532_29_21_3d0_29_2c_20typename_20platform_3a_3aconditional_3c_20_28_28ksizebits_2516_29_21_3d0_29_2c_20uint8_5ft_2c_20uint16_5ft_20_3e_3a_3atype_2c_20uint32_5ft_20_3e',['conditional< ((kSizeBits%32)!=0), typename platform::conditional< ((kSizeBits%16)!=0), uint8_t, uint16_t >::type, uint32_t >',['../structcutlass_1_1platform_1_1conditional.html',1,'cutlass::platform']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['conditional_3c_20false_2c_20t_2c_20f_20_3e',['conditional< false, T, F >',['../structcutlass_1_1platform_1_1conditional_3_01false_00_01T_00_01F_01_4.html',1,'cutlass::platform']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['const_5fiterator',['const_iterator',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4_1_1const__iterator.html',1,'cutlass::Array< T, N, true >']]],
['const_5fiterator',['const_iterator',['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__iterator.html',1,'cutlass::Array< T, N, false >']]],
['const_5freference',['const_reference',['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__reference.html',1,'cutlass::Array< T, N, false >']]],
['const_5freverse_5fiterator',['const_reverse_iterator',['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__reverse__iterator.html',1,'cutlass::Array< T, N, false >']]],
['const_5freverse_5fiterator',['const_reverse_iterator',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4_1_1const__reverse__iterator.html',1,'cutlass::Array< T, N, true >']]],
['constiterator',['ConstIterator',['../classcutlass_1_1PredicateVector_1_1ConstIterator.html',1,'cutlass::PredicateVector']]],
['constsubbytereference',['ConstSubbyteReference',['../classcutlass_1_1ConstSubbyteReference.html',1,'cutlass']]],
['contiguousmatrix',['ContiguousMatrix',['../structcutlass_1_1layout_1_1ContiguousMatrix.html',1,'cutlass::layout']]],
['convert',['Convert',['../classcutlass_1_1epilogue_1_1thread_1_1Convert.html',1,'cutlass::epilogue::thread']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['coord',['Coord',['../structcutlass_1_1Coord.html',1,'cutlass']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['coord_3c_202_2c_20int_20_3e',['Coord< 2, int >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
['coord_3c_203_20_3e',['Coord< 3 >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['coord_3c_203_2c_20int_20_3e',['Coord< 3, int >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['coord_3c_204_20_3e',['Coord< 4 >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['coord_3c_204_2c_20int_20_3e',['Coord< 4, int >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['coord_3c_20kstriderank_20_3e',['Coord< kStrideRank >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
['coord_3c_20kstriderank_2c_20index_20_3e',['Coord< kStrideRank, Index >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
['coord_3c_20kstriderank_2c_20index_2c_20longindex_20_3e',['Coord< kStrideRank, Index, LongIndex >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
['coord_3c_20layout_3a_3akrank_20_3e',['Coord< Layout::kRank >',['../structcutlass_1_1Coord.html',1,'cutlass']]],
['cuda_5fexception',['cuda_exception',['../classcutlass_1_1cuda__exception.html',1,'cutlass']]]
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
];
Reference in New Issue Copy Permalink