squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
fb335f6a5f
cutlass/docs/search/all_1.js

77 lines
102 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
['a',['A',['../structcutlass_1_1library_1_1GemmDescription.html#aa821b15ab4f4c51c4890c7cac685fba4',1,'cutlass::library::GemmDescription::A()'],['../structcutlass_1_1library_1_1GemmArguments.html#ab4c9ecf49885b1e2ff88ff9c7a4ffad9',1,'cutlass::library::GemmArguments::A()'],['../structcutlass_1_1library_1_1GemmArrayArguments.html#afcce27cdc91247a9e4e8e610c3a38e63',1,'cutlass::library::GemmArrayArguments::A()']]],
['a_5ftile',['A_tile',['../structcutlass_1_1reference_1_1device_1_1thread_1_1Gemm.html#a2d63fe67429aa6441e6e247563db1a11',1,'cutlass::reference::device::thread::Gemm']]],
['abs',['abs',['../namespacecutlass.html#a512b1ef2b0213d48738cac7bbb87a98e',1,'cutlass::abs(complex< T > const &z)'],['../namespacecutlass.html#a4bd737670cb21ef9871beb716f8ef5ae',1,'cutlass::abs(cutlass::half_t const &h)']]],
['accesscount',['AccessCount',['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandCongruous.html#a01bb7a9d4e19798075935e5a4fdae982',1,'cutlass::layout::VoltaTensorOpMultiplicandCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html#a6c5a1858ade078036ed6659e3b3cce62',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandCongruous.html#a1613a66528cfbbb1d86e566166034b4f',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandBCongruous.html#a05a4f6a3634d44eb7847d1bd944d3af6',1,'cutlass::layout::VoltaTensorOpMultiplicandBCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html#a8262341cde0bddd17a92e0077fbd6e56',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandBCongruous.html#ae6751845741fbf3494391564ba85c1c3',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandBCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicand.html#aca2a06b16d1d4b1b9c0e8b8485e1b02f',1,'cutlass::layout::TensorOpMultiplicand::AccessCount()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCongruous.html#a45607ffb63b8f3e307a2537777c88491',1,'cutlass::layout::TensorOpMultiplicandCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCongruous_3_0132_00_01Crosswise_01_4.html#ac6876a070bf8f7805a70a4b9f41493a7',1,'cutlass::layout::TensorOpMultiplicandCongruous< 32, Crosswise >::AccessCount()'],['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCongruous.html#a41a554dc29e1852fe4cfc21fa250a9ac',1,'cutlass::layout::ColumnMajorTensorOpMultiplicandCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1RowMajorTensorOpMultiplicandCongruous.html#a274f0531c54b7e15243b0460d59e0c3b',1,'cutlass::layout::RowMajorTensorOpMultiplicandCongruous::AccessCount()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCrosswise.html#ae9c97a64123f074907e805d3642d924b',1,'cutlass::layout::TensorOpMultiplicandCrosswise::AccessCount()'],['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCrosswise.html#ab447aac95eab1ad7d24767d4657990a4',1,'cutlass::layout::ColumnMajorTensorOpMultiplicandCrosswise::AccessCount()'],['../structcutlass_1_1layout_1_1RowMajorTensorOpMultiplicandCrosswise.html#ab7adede333905f5e87178fee4c0d530c',1,'cutlass::layout::RowMajorTensorOpMultiplicandCrosswise::AccessCount()']]],
['accesstype',['AccessType',['../structcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_0b878062cc0cd214bf7e17d74ff17e246.html',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >']]],
['accesstype',['AccessType',['../classcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator.html#afde3952d986cff98cf39872192b66a73',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::AccessType()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator.html#a2460e91b9c777313ec5c7295fde7d76f',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::AccessType()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1SharedLoadIterator.html#a813f447702209b6efdb1d4dea64efc2c',1,'cutlass::epilogue::threadblock::SharedLoadIterator::AccessType()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1G16e08718cffa0989cce3fe8dbc4b075b.html#a8d8984d62b6fda3dae79561eb4c96176',1,'cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::AccessType()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1Gdb805a2dc5571ac3b66e0fe6ffdcede2.html#ae2cc318859541f821667086d89ae48f2',1,'cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::AccessType()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmSa0ceeeddc22575876eb977da7f5416a8.html#a54fddd7011b6d199f69ff96dd1bbe806',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::AccessType()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmS2fe0c60b727c738c622c18fc3dd76644.html#a34b485a73b0d06376d25c2a6e1049579',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::AccessType()'],['../structcutlass_1_1epilogue_1_1warp_1_1VoltaTensorOpPolicy_3_01WarpShape___00_01gemm_1_1GemmShape_1d48185f49e4d066f8e9327bf0856b7f.html#a2015fad226bfcb32ced0435861b268db',1,'cutlass::epilogue::warp::VoltaTensorOpPolicy< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::AccessType()'],['../structcutlass_1_1epilogue_1_1warp_1_1VoltaTensorOpPolicy_3_01WarpShape___00_01gemm_1_1GemmShape_136ce744d4c1c6e8707f5a9785196194.html#ac4b649583277d5a7d314c3cc92929d77',1,'cutlass::epilogue::warp::VoltaTensorOpPolicy< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::AccessType()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaTensorOpAccumulatorTileIterator_3_01Shape___00_01Element___00027dabdc144edd6276f664ca74088510.html#a4046a63c74343751da21c305e51a5cae',1,'cutlass::gemm::warp::MmaTensorOpAccumulatorTileIterator< Shape_, Element_, cutlass::layout::ColumnMajorInterleaved< InterleavedN >, InstructionShape_, OpDelta_ >::AccessType()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen784a0e9da3f55064c47e5613791f51f7.html#a3fb4e41cc8c89e40feba8fe191f3aac3',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::AccessType()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen89c687c583745a73cb485041911a4c4e.html#abbeed260354cc9f12b3ef3c37eadf80b',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::AccessType()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen9838736ad62fae54213fbaf722a989ab.html#ac504e6cfef57426ff95ac2b1b53c21a4',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::AccessType()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemenab63a1e105bf37f6371516cb9e2c5a7a.html#a86394be236262a0c6cdfaa6
['accum',['accum',['../structcutlass_1_1reference_1_1device_1_1thread_1_1Gemm.html#a304c308d4cf13915cf1ba796c506dda6',1,'cutlass::reference::device::thread::Gemm']]],
['accumulatoraccesstype',['AccumulatorAccessType',['../classcutlass_1_1epilogue_1_1threadblock_1_1Epilogue.html#a0cfa64af365e51d50549528edea00692',1,'cutlass::epilogue::threadblock::Epilogue::AccumulatorAccessType()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedEpilogue.html#ac6cd52b624f5b846b219f55ba13f00fc',1,'cutlass::epilogue::threadblock::InterleavedEpilogue::AccumulatorAccessType()']]],
['accumulatorfragmentiterator',['AccumulatorFragmentIterator',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueComplexTensorOp.html#a9c88165210cc6535336db0e5043fa10f',1,'cutlass::epilogue::threadblock::DefaultEpilogueComplexTensorOp::AccumulatorFragmentIterator()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueSimt.html#a10ec4947f79206da93b271e66518c344',1,'cutlass::epilogue::threadblock::DefaultEpilogueSimt::AccumulatorFragmentIterator()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueTensorOp.html#a8d3e9e08ccd955d32168f544b37ccbb6',1,'cutlass::epilogue::threadblock::DefaultEpilogueTensorOp::AccumulatorFragmentIterator()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultInterleavedEpilogueTensorOp.html#ab1ccecd0d03b8b15f7f4d26b0a009281',1,'cutlass::epilogue::threadblock::DefaultInterleavedEpilogueTensorOp::AccumulatorFragmentIterator()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueVoltaTensorOp.html#ad71acdab96fc9406c920ea1173f72480',1,'cutlass::epilogue::threadblock::DefaultEpilogueVoltaTensorOp::AccumulatorFragmentIterator()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueWmmaTensorOp.html#af4ccb442409f47449ce5c064bd780c08',1,'cutlass::epilogue::threadblock::DefaultEpilogueWmmaTensorOp::AccumulatorFragmentIterator()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1Epilogue.html#a0c3840f9e6462afeaa4cff567360912b',1,'cutlass::epilogue::threadblock::Epilogue::AccumulatorFragmentIterator()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1EpilogueBase.html#aa39c8ae2394f8e9514c124e1d16ec106',1,'cutlass::epilogue::threadblock::EpilogueBase::AccumulatorFragmentIterator()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedEpilogue.html#a06ae0cc4aa16a1ed7259bac0b03f5725',1,'cutlass::epilogue::threadblock::InterleavedEpilogue::AccumulatorFragmentIterator()']]],
['accumulatortile',['AccumulatorTile',['../classcutlass_1_1epilogue_1_1threadblock_1_1Epilogue.html#a391a932cd8341c5934cc48ec5fa4c0ab',1,'cutlass::epilogue::threadblock::Epilogue::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1EpilogueBase.html#a1707fb90363342996902b96ccd3bb176',1,'cutlass::epilogue::threadblock::EpilogueBase::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedEpilogue.html#a9de7ab6b6c2dec16edd74f2e8ed1af32',1,'cutlass::epilogue::threadblock::InterleavedEpilogue::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorComplexTensorOp_3_01WarpShape___00_01Operato8cf03c624cf3210c71b7cbd580b080f8.html#a61720e463645c8e4b32021b07fe27a45',1,'cutlass::epilogue::warp::FragmentIteratorComplexTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorSimt_3_01WarpShape___00_01Operator___00_01la3f2abc523201c1b0228df99119ab88e1.html#a0b889a6700c158328616c274a573dd5a',1,'cutlass::epilogue::warp::FragmentIteratorSimt< WarpShape_, Operator_, layout::RowMajor, MmaSimtPolicy_ >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorTensorOp_3_01WarpShape___00_01OperatorShape_5e78dabe303f20d76b00c600aab61eda.html#a2adfa48a2bfefab2cddd5b2185a6d80b',1,'cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorTensorOp_3_01WarpShape___00_01OperatorShape_e459aab140a2ce78336e584f95886726.html#aafb2c78a1f680ddc24f77d87c8edf40f',1,'cutlass::epilogue::warp::FragmentIteratorTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::ColumnMajorInterleaved< InterleavedK > >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1G16e08718cffa0989cce3fe8dbc4b075b.html#a1885e99c86f4e32e9fb5e70a2925a6c7',1,'cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1Gdb805a2dc5571ac3b66e0fe6ffdcede2.html#a5cb7ad40118423ef5d0cdd7cd5e62d79',1,'cutlass::epilogue::warp::FragmentIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorWmmaTensorOp_3_01WarpShape___00_01OperatorShfdb1f120c6797383663f9fd11d0fc599.html#ae5a3dd659afa99bbd53a9bde1cc5ec79',1,'cutlass::epilogue::warp::FragmentIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorElementC_, OperatorFragmentC_, layout::RowMajor >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorSimt_3_01WarpShape___00_01Operator___00_01Elemenf2bd262ed3e202b25d5802d83965bf3b.html#a6c100257da1ab23db35da3c4818a32f3',1,'cutlass::epilogue::warp::TileIteratorSimt< WarpShape_, Operator_, Element_, layout::RowMajor, MmaSimtPolicy_ >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmSa0ceeeddc22575876eb977da7f5416a8.html#a8a79ba0606d52670402e37ee2e8d8a19',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::AccumulatorTile()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmS2fe0c60b727c738c622c18fc3dd76644.html#a30e13f9b73d66049f8233998f29823c4',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::AccumulatorTile()'],['../structcutlass_1_1epilogue_1_1warp_1_1VoltaTensorOpPolicy_3_01WarpShape___00_01gemm_1_1GemmShape_1d48185f49e4d066f8e9327bf0856b7f.html#a21f78a099c4ac53e13fb84757c88c7be',
['add_5fcoord_5foffset',['add_coord_offset',['../classcutlass_1_1TensorRef.html#a4bed879c428963070de8ffbdc5d6e4f9',1,'cutlass::TensorRef']]],
['add_5fpointer_5foffset',['add_pointer_offset',['../classcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator.html#a879f53af759d71280cca8a8932002244',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator.html#a12109679ba6ff108d8b4f633e60b9f5b',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1SharedLoadIterator.html#a1e022ec8d968520bfd0bc7ce51dcaf93',1,'cutlass::epilogue::threadblock::SharedLoadIterator::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorSimt_3_01WarpShape___00_01Operator___00_01Elemenf2bd262ed3e202b25d5802d83965bf3b.html#a59a4695befd919265485918ee935aab1',1,'cutlass::epilogue::warp::TileIteratorSimt< WarpShape_, Operator_, Element_, layout::RowMajor, MmaSimtPolicy_ >::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorTensorOp_3_01WarpShape___00_01OperatorShape___003cbb32beb84b4984cb7853662096d289.html#aeda0dac956a396df42a2d6dedf5da3f5',1,'cutlass::epilogue::warp::TileIteratorTensorOp< WarpShape_, OperatorShape_, Element_, layout::RowMajor >::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmSa0ceeeddc22575876eb977da7f5416a8.html#aa5aec99eff41c3c17177c792bbecb1ca',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmS2fe0c60b727c738c622c18fc3dd76644.html#a565c2563388775804227ccf9c96c4dd4',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::add_pointer_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorWmmaTensorOp_3_01WarpShape___00_01OperatorShape_fd6a91cd8bbd07ecd1344326b830e3a4.html#a2c2595d138f2166285948eb8384149a1',1,'cutlass::epilogue::warp::TileIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorFragment_, layout::RowMajor >::add_pointer_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kA_00_01Element_67ca7e11a38e38f2c51b84767654a90f.html#acdfcb77378bf79c33bb806483f962787',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajor, Policy_, PartitionsK, PartitionGroupSize >::add_pointer_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kB_00_01Element_ea0a4e7ce3cd5d25cabf79383efdf4d9.html#acb381d33987c2851234a63d3c1bb4b84',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajor, Policy_, PartitionsK, PartitionGroupSize >::add_pointer_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kC_00_01Element_4ccafbc821b3a55cd532602442a74031.html#af880fccb3d8dd3587d564a70b3dbf480',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::ColumnMajor, Policy_ >::add_pointer_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kC_00_01Element_8f92ea79e85febb67169c4b2d94b1b20.html#ad1ed9a2d784733057a8c9d0827ed2f42',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::RowMajor, Policy_ >::add_pointer_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kA_00_01Element_f0ce904a9294556f15e1cc9cf7c99a93.html#a07152e70e749553df28cb7e39250809d',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize >::add_pointer_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kB_00_01Element_ada156b62fcbdce47009c5bf1321c92c.html#aa5ce9379e65e2ed6269c6c
['add_5ftile_5foffset',['add_tile_offset',['../classcutlass_1_1epilogue_1_1threadblock_1_1SharedLoadIterator.html#a4706618cd7b040c01d23440574696417',1,'cutlass::epilogue::threadblock::SharedLoadIterator::add_tile_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorSimt_3_01WarpShape___00_01Operator___00_01Elemenf2bd262ed3e202b25d5802d83965bf3b.html#ae9f188af3f314fb898e7ad842cba98df',1,'cutlass::epilogue::warp::TileIteratorSimt< WarpShape_, Operator_, Element_, layout::RowMajor, MmaSimtPolicy_ >::add_tile_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorTensorOp_3_01WarpShape___00_01OperatorShape___003cbb32beb84b4984cb7853662096d289.html#aa54bfe6b9c53d0e79cfbae74c0e52fe4',1,'cutlass::epilogue::warp::TileIteratorTensorOp< WarpShape_, OperatorShape_, Element_, layout::RowMajor >::add_tile_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmSa0ceeeddc22575876eb977da7f5416a8.html#ab9627099133cc3fad152ea9984458147',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >::add_tile_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1GemmS2fe0c60b727c738c622c18fc3dd76644.html#a13ef705330675c5360e4430a9a002c07',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >::add_tile_offset()'],['../classcutlass_1_1epilogue_1_1warp_1_1TileIteratorWmmaTensorOp_3_01WarpShape___00_01OperatorShape_fd6a91cd8bbd07ecd1344326b830e3a4.html#aef2b622345c91bc99f1baec9cefc8392',1,'cutlass::epilogue::warp::TileIteratorWmmaTensorOp< WarpShape_, OperatorShape_, OperatorFragment_, layout::RowMajor >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kA_00_01Element_67ca7e11a38e38f2c51b84767654a90f.html#ad640be3cb5eaa3eabf94d3ad2d065e60',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajor, Policy_, PartitionsK, PartitionGroupSize >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kB_00_01Element_ea0a4e7ce3cd5d25cabf79383efdf4d9.html#a8118c7b8864ff0d164b826952d18ebb5',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajor, Policy_, PartitionsK, PartitionGroupSize >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kC_00_01Element_4ccafbc821b3a55cd532602442a74031.html#a53acfb33cbaec4476b1417247701c520',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::ColumnMajor, Policy_ >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kC_00_01Element_8f92ea79e85febb67169c4b2d94b1b20.html#af9c46433b6f8797445edee097b672ca0',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::RowMajor, Policy_ >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kA_00_01Element_f0ce904a9294556f15e1cc9cf7c99a93.html#a8b999378652ae624760df7740b0ad0f6',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kA, Element_, layout::ColumnMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kB_00_01Element_ada156b62fcbdce47009c5bf1321c92c.html#a1eb491d56ae62c73dfafd9ad6b4c938d',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kB, Element_, layout::RowMajorInterleaved< 4 >, Policy_, PartitionsK, PartitionGroupSize >::add_tile_offset()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaTensorOpMultiplicandTileIterator_3_01Shape___00_01Operand___0ed7daaeba1c095e77f68533d4d2c475c.html#aa061b3786066f1fbde3e6c993e2dec6c',1,'cutlass::gemm::warp::MmaTensorOpMultiplicandTileIterator< Shape_, Ope
['advance_5fcluster',['advance_cluster',['../structcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator_1_1Params.html#a38a6dcfddaf9078334107eb8a38595fb',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::Params']]],
['advance_5fcolumn',['advance_column',['../structcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator_1_1Params.html#a5593ba3ee47ba8bb6dc2b0b001b38824',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::Params']]],
['advance_5fgroup',['advance_group',['../structcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator_1_1Params.html#a010385e2b1e39fb0a42ce65c68e07e8e',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::Params']]],
['advance_5frow',['advance_row',['../structcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator_1_1Params.html#a4ceaade8da07a3951a30c6d24b79f557',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::Params::advance_row()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator_1_1Params.html#a31c6472b5e890a37657d573646114156',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::Params::advance_row()']]],
['advance_5ftile',['advance_tile',['../structcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator_1_1Params.html#a93f34cf9a98ab9bf6b2f7156848c9efd',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::Params']]],
['aligned_5fbuffer_2eh',['aligned_buffer.h',['../aligned__buffer_8h.html',1,'']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['aligned_5fchunk',['aligned_chunk',['../structcutlass_1_1platform_1_1aligned__chunk.html',1,'cutlass::platform']]],
['aligned_5fstorage',['aligned_storage',['../structcutlass_1_1platform_1_1aligned__storage.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
['alignedarray',['AlignedArray',['../classcutlass_1_1AlignedArray.html',1,'cutlass']]],
['alignedbuffer',['AlignedBuffer',['../structcutlass_1_1AlignedBuffer.html',1,'cutlass']]],
['alignedbuffer_3c_20element_2c_20cutlass_3a_3amatrixshape_3a_3akcount_20_3e',['AlignedBuffer< Element, cutlass::MatrixShape::kCount >',['../structcutlass_1_1AlignedBuffer.html',1,'cutlass']]],
['alignedbuffer_3c_20typename_20operator_3a_3aelementa_2c_20cutlass_3a_3amatrixshape_3a_3akcount_20_3e',['AlignedBuffer< typename Operator::ElementA, cutlass::MatrixShape::kCount >',['../structcutlass_1_1AlignedBuffer.html',1,'cutlass']]],
['alignedbuffer_3c_20typename_20operator_3a_3aelementb_2c_20cutlass_3a_3amatrixshape_3a_3akcount_20_3e',['AlignedBuffer< typename Operator::ElementB, cutlass::MatrixShape::kCount >',['../structcutlass_1_1AlignedBuffer.html',1,'cutlass']]],
['alignment',['alignment',['../structcutlass_1_1library_1_1TensorDescription.html#a9fed369aad059bda36c528e72f8bb8fd',1,'cutlass::library::TensorDescription']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['alignment_5fof',['alignment_of',['../structcutlass_1_1platform_1_1alignment__of.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20const_20value_5ft_20_3e',['alignment_of< const value_t >',['../structcutlass_1_1platform_1_1alignment__of_3_01const_01value__t_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20const_20volatile_20value_5ft_20_3e',['alignment_of< const volatile value_t >',['../structcutlass_1_1platform_1_1alignment__of_3_01const_01volatile_01value__t_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20double2_20_3e',['alignment_of< double2 >',['../structcutlass_1_1platform_1_1alignment__of_3_01double2_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20double4_20_3e',['alignment_of< double4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01double4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20float4_20_3e',['alignment_of< float4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01float4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20int4_20_3e',['alignment_of< int4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01int4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20long4_20_3e',['alignment_of< long4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01long4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20longlong2_20_3e',['alignment_of< longlong2 >',['../structcutlass_1_1platform_1_1alignment__of_3_01longlong2_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20longlong4_20_3e',['alignment_of< longlong4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01longlong4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20uint4_20_3e',['alignment_of< uint4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01uint4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20ulong4_20_3e',['alignment_of< ulong4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01ulong4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20ulonglong2_20_3e',['alignment_of< ulonglong2 >',['../structcutlass_1_1platform_1_1alignment__of_3_01ulonglong2_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20ulonglong4_20_3e',['alignment_of< ulonglong4 >',['../structcutlass_1_1platform_1_1alignment__of_3_01ulonglong4_01_4.html',1,'cutlass::platform']]],
['alignment_5fof_3c_20volatile_20value_5ft_20_3e',['alignment_of< volatile value_t >',['../structcutlass_1_1platform_1_1alignment__of_3_01volatile_01value__t_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
['allocate',['allocate',['../namespacecutlass_1_1device__memory.html#a345678796dcc23b33b4288e26c9b029f',1,'cutlass::device_memory']]],
['allocation',['allocation',['../structcutlass_1_1device__memory_1_1allocation.html',1,'cutlass::device_memory']]],
['allocation',['allocation',['../structcutlass_1_1device__memory_1_1allocation.html#a49b392100679f307f116fc0f854bad0a',1,'cutlass::device_memory::allocation::allocation()'],['../structcutlass_1_1device__memory_1_1allocation.html#a87b81eac219bdc38af93cad71beab87a',1,'cutlass::device_memory::allocation::allocation(size_t _capacity)'],['../structcutlass_1_1device__memory_1_1allocation.html#a73138c905fb54cfb1556914cb6d106c7',1,'cutlass::device_memory::allocation::allocation(allocation const &p)']]],
['allocation_3c_20element_20_3e',['allocation< Element >',['../structcutlass_1_1device__memory_1_1allocation.html',1,'cutlass::device_memory']]],
['alpha',['alpha',['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#aebf79db277fc69c1fafae975538f8c57',1,'cutlass::epilogue::thread::LinearCombination::Params::alpha()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#a92b42f2498efb637ba4e2eb2bc7710c8',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::alpha()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#a48d23248d58b6f7b5aa6aae7cd66afa0',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::alpha()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#a4a225cb1f8a09c643a8016024ccbf6cb',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::alpha()'],['../structcutlass_1_1gemm_1_1kernel_1_1detail_1_1GemvBatchedStridedEpilogueScaling.html#afd6c2151dbdd056d214d5ccee685c676',1,'cutlass::gemm::kernel::detail::GemvBatchedStridedEpilogueScaling::alpha()'],['../structcutlass_1_1reduction_1_1BatchedReductionTraits_1_1Params.html#afada1cbad87636228fb58d8577bb8470',1,'cutlass::reduction::BatchedReductionTraits::Params::alpha()'],['../structcutlass_1_1library_1_1GemmArguments.html#a94a7760d5bbee524c2381adf7a2fd683',1,'cutlass::library::GemmArguments::alpha()'],['../structcutlass_1_1library_1_1GemmArrayArguments.html#a2de0ca18e82590a98ac2ffea6a741840',1,'cutlass::library::GemmArrayArguments::alpha()']]],
['alpha_5fptr',['alpha_ptr',['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#aabd9260f2a8a1b809864fe20dc3c7553',1,'cutlass::epilogue::thread::LinearCombination::Params::alpha_ptr()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#a0ddbb24a81370a342d05509bb78f122c',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::alpha_ptr()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#a6c266e54081c08d25f4d6832ca24e673',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::alpha_ptr()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#aa4d227d5db2999f4738a207183fc4fc3',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::alpha_ptr()']]],
['append',['append',['../classcutlass_1_1library_1_1Manifest.html#a4ac48eea96c01c493136c94b794cbdd4',1,'cutlass::library::Manifest']]],
['apply',['apply',['../structcutlass_1_1reference_1_1detail_1_1Cast.html#a4f708d02a945435beaf9e3f4e35eaf58',1,'cutlass::reference::detail::Cast::apply()'],['../structcutlass_1_1reference_1_1detail_1_1Cast_3_01float_00_01int8__t_01_4.html#a6f14ff7b5626a9251957732e602177a4',1,'cutlass::reference::detail::Cast< float, int8_t >::apply()'],['../structcutlass_1_1reference_1_1detail_1_1Cast_3_01float_00_01uint8__t_01_4.html#a7651ff6200842b6ab786e6d720339b3b',1,'cutlass::reference::detail::Cast< float, uint8_t >::apply()']]],
['arch_2eh',['arch.h',['../arch_8h.html',1,'']]],
['archtag',['ArchTag',['../classcutlass_1_1gemm_1_1device_1_1Gemm.html#afe7ab8c15e83c6cd59b6bcf3fe6e48c0',1,'cutlass::gemm::device::Gemm::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA___00_01LayoutA___00_01ElementB___00_01Layout4d0960ae6b1d1bf19e6239dbd002249c.html#a1b502a4097e745c12d0d628d080ba447',1,'cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero >::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1GemmBatched.html#add5d679e0acf0813a52c209d2448e81b',1,'cutlass::gemm::device::GemmBatched::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA___00_01ElementB___00_0c9bb6f4463ab6085e6008b5d5ad6abfd.html#a681b145a9701109f9d72059bb874895b',1,'cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ >::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1GemmComplex.html#a630a9bb98fd95ab9d5a2520e10573974',1,'cutlass::gemm::device::GemmComplex::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1GemmComplex_3_01ElementA___00_01LayoutA___00_01ElementB___00_07c56401b4df75709ae636675d9980a9a.html#a15200a21650efa7f582747dbbad044ca',1,'cutlass::gemm::device::GemmComplex< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, TransformA, TransformB, SplitKSerial >::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel.html#a2a48eb6e51e2315e945882d5e70ebb2f',1,'cutlass::gemm::device::GemmSplitKParallel::ArchTag()'],['../classcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_3_01ElementA___00_01LayoutA___00_01ElementBbe7c1f7154ad5b5bf9d4d28301e2b457.html#ab83912e2e116c176d3f733ccdee06a1b',1,'cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ >::ArchTag()']]],
['arg',['arg',['../namespacecutlass.html#a2d34a68d49bf2a35de81b6600425b645',1,'cutlass']]],
['args',['args',['../structcutlass_1_1CommandLine.html#a6a338671a8d323882f9d9463863eb1c1',1,'cutlass::CommandLine']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1GemmComplex_3_01ElementA___00_01LayoutA___00_01ElementB___00_a3923967cafb5cb9774c320dc24baa77.html',1,'cutlass::gemm::device::GemmComplex< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, TransformA, TransformB, SplitKSerial >']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_1_1Arguments.html',1,'cutlass::gemm::device::GemmSplitKParallel']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_1_1Arguments.html',1,'cutlass::gemm::device::GemmBatched']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1Gemm_1_1Arguments.html',1,'cutlass::gemm::device::Gemm']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_3_01ElementA___00_01LayoutA___00_01Elementafcb1aeaf2035a7ac769d7acc233423b.html',1,'cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ >']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1Gemm_1_1Arguments.html#a4b5c3e7a0f2307ca90632fa476aac1aa',1,'cutlass::gemm::device::Gemm::Arguments::Arguments()'],['../structcutlass_1_1gemm_1_1device_1_1Gemm_1_1Arguments.html#a975d1d55ab7d42eb02eb226e2bbb5812',1,'cutlass::gemm::device::Gemm::Arguments::Arguments(GemmCoord problem_size_, TensorRef< ElementA const, LayoutA > ref_A_, TensorRef< ElementB const, LayoutB > ref_B_, TensorRef< ElementC const, LayoutC > ref_C_, TensorRef< ElementC, LayoutC > ref_D_, typename EpilogueOutputOp::Params epilogue_=typename EpilogueOutputOp::Params(), int split_k_slices=1)'],['../structcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA___00_01LayoutA___00_01ElementB___00_01Layou1b211cc9c97c022d8fe10f2dd32c8709.html#ac6c397a181a52c0dbb39bf3710ee4658',1,'cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero >::Arguments::Arguments()'],['../structcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA___00_01LayoutA___00_01ElementB___00_01Layou1b211cc9c97c022d8fe10f2dd32c8709.html#a331de1adfdcbea6d0137afe64a4f6f4c',1,'cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero >::Arguments::Arguments(GemmCoord problem_size_, TensorRef< ElementA const, LayoutA > ref_A_, TensorRef< ElementB const, LayoutB > ref_B_, TensorRef< ElementC const, LayoutC > ref_C_, TensorRef< ElementC, LayoutC > ref_D_, typename EpilogueOutputOp::Params epilogue_=typename EpilogueOutputOp::Params(), int split_k_slices=1)'],['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_1_1Arguments.html#a72bd469f15b44e492cf84658b5f09ad5',1,'cutlass::gemm::device::GemmBatched::Arguments::Arguments()'],['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_1_1Arguments.html#a0befb9945aadcba460f4d1ad73020e9c',1,'cutlass::gemm::device::GemmBatched::Arguments::Arguments(GemmCoord problem_size_, TensorRef< ElementA const, LayoutA > ref_A_, int64_t stride_A_, TensorRef< ElementB const, LayoutB > ref_B_, int64_t stride_B_, TensorRef< ElementC const, LayoutC > ref_C_, int64_t stride_C_, TensorRef< ElementC, LayoutC > ref_D_, int64_t stride_D_, typename EpilogueOutputOp::Params epilogue_, int batch_count_)'],['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA___00_01ElementB___00_213d78696663f4231cd52c6a277c60e5.html#ae86daa985279c77e57e682b64a68d330',1,'cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ >::Arguments::Arguments()'],['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA___00_01ElementB___00_213d78696663f4231cd52c6a277c60e5.html#a2129a4dccbd73f8c0f26b08ce5a5cb28',1,'cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ >::Arguments::Arguments(GemmCoord problem_size_, TensorRef< ElementA const, LayoutA > ref_A_, int64_t stride_A_, TensorRef< ElementB const, LayoutB > ref_B_, int64_t stride_B_, TensorRef< ElementC const, LayoutC > ref_C_, int64_t stride_C_, TensorRef< ElementC, LayoutC > ref_D_, int64_t stride_D_, typename EpilogueOutputOp::Params epilogue_, int batch_count_)'],['../structcu
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA___00_01LayoutA___00_01ElementB___00_01Layou1b211cc9c97c022d8fe10f2dd32c8709.html',1,'cutlass::gemm::device::Gemm< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, SplitKSerial, Operator_, IsBetaZero >']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1GemmComplex_1_1Arguments.html',1,'cutlass::gemm::device::GemmComplex']]],
['arguments',['Arguments',['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA___00_01ElementB___00_213d78696663f4231cd52c6a277c60e5.html',1,'cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ >']]],
['array',['Array',['../structcutlass_1_1AlignedBuffer.html#a6083193cadb42a445442da9be737d934',1,'cutlass::AlignedBuffer::Array()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a168315948a76d6ae9d7491ad0e1ca302',1,'cutlass::Array< T, N, true >::Array()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a22af701f6f542b29198c759b653d3fb0',1,'cutlass::Array< T, N, true >::Array(Array const &x)'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#ac37d0c85dd6246ff7e08d12903f49c4d',1,'cutlass::Array< T, N, false >::Array()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a5d4667c3c9ebf3322ba94d43421e2577',1,'cutlass::Array< T, N, false >::Array(Array const &x)']]],
['array_2eh',['array.h',['../array_8h.html',1,'']]],
['array_3c_20t_2c_20n_2c_20false_20_3e',['Array< T, N, false >',['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html',1,'cutlass']]],
['array_3c_20t_2c_20n_2c_20true_20_3e',['Array< T, N, true >',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html',1,'cutlass']]],
['array_5fsubbyte_2eh',['array_subbyte.h',['../array__subbyte_8h.html',1,'']]],
['at',['at',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#aedd3e189bcbbb69ecd98978bcbbc3f1f',1,'cutlass::Array< T, N, true >::at(size_type pos)'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#ab504833fe30934eeb6e71e235e7942f1',1,'cutlass::Array< T, N, true >::at(size_type pos) const '],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a6268f2bbbdfc671cf7066ea0ee1bb46f',1,'cutlass::Array< T, N, false >::at(size_type pos)'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a0443a4af7c9594492bfb8a84bbd12a52',1,'cutlass::Array< T, N, false >::at(size_type pos) const '],['../structcutlass_1_1Coord.html#a8a65128c86b236cd2bea875b85a34bc1',1,'cutlass::Coord::at()'],['../structcutlass_1_1Coord.html#a358dde78a1c2105a9aeb4adee8bb3d2d',1,'cutlass::Coord::at(int dim)'],['../structcutlass_1_1Coord.html#ac7379275d7431ead927af7966b6fa0ec',1,'cutlass::Coord::at() const '],['../structcutlass_1_1Coord.html#a06046c22b877abfb277d3f0fe4f8578a',1,'cutlass::Coord::at(int dim) const '],['../classcutlass_1_1PredicateVector_1_1Iterator.html#a36d28f662e1ab2f8b0b9da9e6863c1de',1,'cutlass::PredicateVector::Iterator::at()'],['../classcutlass_1_1PredicateVector_1_1ConstIterator.html#a691a6b129b56af221741b3825d58d2ac',1,'cutlass::PredicateVector::ConstIterator::at()'],['../structcutlass_1_1PredicateVector.html#af14b5caa5b8722f06726681a1a985031',1,'cutlass::PredicateVector::at()'],['../classcutlass_1_1TensorRef.html#a8758907a1c9b1fcd00e7ece626d03b76',1,'cutlass::TensorRef::at()'],['../classcutlass_1_1thread_1_1Matrix.html#a2756a0c0eb2efcce5033fb175855755e',1,'cutlass::thread::Matrix::at()'],['../classcutlass_1_1HostTensor.html#ab1253b57fd95f16b2dec9e36e84051d4',1,'cutlass::HostTensor::at(TensorCoord const &coord)'],['../classcutlass_1_1HostTensor.html#ae261f1b7ef78cc52dcb77f1a2fd05b69',1,'cutlass::HostTensor::at(TensorCoord const &coord) const ']]],
['mma_2eh',['mma.h',['../arch_2mma_8h.html',1,'']]],
['mma_5fsm50_2eh',['mma_sm50.h',['../arch_2mma__sm50_8h.html',1,'']]],
['mma_5fsm60_2eh',['mma_sm60.h',['../arch_2mma__sm60_8h.html',1,'']]],
['mma_5fsm61_2eh',['mma_sm61.h',['../arch_2mma__sm61_8h.html',1,'']]]
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
];
Reference in New Issue Copy Permalink