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

18 lines
45 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
['packed',['packed',['../classcutlass_1_1layout_1_1RowMajor.html#a770edcc93145fc3dfa4dfdf37a7c515e',1,'cutlass::layout::RowMajor::packed()'],['../classcutlass_1_1layout_1_1ColumnMajor.html#afd7374b993fd41d55a8c02691b02ead7',1,'cutlass::layout::ColumnMajor::packed()'],['../structcutlass_1_1layout_1_1RowMajorInterleaved.html#a4c012aaca002750d6dda744388f6cd30',1,'cutlass::layout::RowMajorInterleaved::packed()'],['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html#ab690e548a771a3e35357f454f3c924a5',1,'cutlass::layout::ColumnMajorInterleaved::packed()'],['../structcutlass_1_1layout_1_1ContiguousMatrix.html#a4c5f7cb47727b7ca7fdce09984c8669d',1,'cutlass::layout::ContiguousMatrix::packed()'],['../structcutlass_1_1layout_1_1ColumnMajorBlockLinear.html#a17c4a1e21d92742ca725379a963a3fc7',1,'cutlass::layout::ColumnMajorBlockLinear::packed()'],['../structcutlass_1_1layout_1_1RowMajorBlockLinear.html#a21b674f37ee92e3ef1413ece1e2f6d49',1,'cutlass::layout::RowMajorBlockLinear::packed()'],['../structcutlass_1_1layout_1_1GeneralMatrix.html#a41dac2461e2f7b652fd06df7631df259',1,'cutlass::layout::GeneralMatrix::packed()'],['../classcutlass_1_1layout_1_1PitchLinear.html#a3c76f195505f55b26d17c136a13c5f32',1,'cutlass::layout::PitchLinear::packed()'],['../classcutlass_1_1layout_1_1TensorNHWC.html#ab38ea68b38cf635ea661360967edb8d2',1,'cutlass::layout::TensorNHWC::packed()'],['../classcutlass_1_1layout_1_1TensorNCHW.html#a3096dbd7c7243eaa54c139d137b7e2b5',1,'cutlass::layout::TensorNCHW::packed()'],['../classcutlass_1_1layout_1_1TensorNCxHWx.html#af6a8593026ce08ec962f43db36c84496',1,'cutlass::layout::TensorNCxHWx::packed()'],['../classcutlass_1_1layout_1_1TensorCxRSKx.html#a48194ca13de771a824c37d48bf3885d7',1,'cutlass::layout::TensorCxRSKx::packed()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandCongruous.html#a0f6dfb913a9f6d1dd6a6e4d83e3c87ec',1,'cutlass::layout::VoltaTensorOpMultiplicandCongruous::packed()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html#af4efe777f1d9ec8c62d870e3ced85114',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous::packed()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandCongruous.html#a0930c8e2ba61cdfd454817c841ef5135',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandCongruous::packed()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandBCongruous.html#a9e54d47e637060ba318d04416d35f4f4',1,'cutlass::layout::VoltaTensorOpMultiplicandBCongruous::packed()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html#a61d5ba91f20217170458cb0affbe3e02',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous::packed()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandBCongruous.html#a860c3a44cff442eada17a765b5744049',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandBCongruous::packed()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandCrosswise.html#aa27ee17b10d393e8578afdbdedaa190e',1,'cutlass::layout::VoltaTensorOpMultiplicandCrosswise::packed()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCrosswise.html#ac0c8aea5f38628ce078dd1562e44ff06',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise::packed()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandCrosswise.html#a6ccf0dc730b1b68b5f842c10d4fb710c',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandCrosswise::packed()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicand.html#aae09584d5e60d401d73484d579722007',1,'cutlass::layout::TensorOpMultiplicand::packed()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCongruous.html#a9307437b4b93a3dd450244bb54aa50d4',1,'cutlass::layout::TensorOpMultiplicandCongruous::packed()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCongruous_3_0132_00_01Crosswise_01_4.html#aafa9812d3c82b30b2d416738c586bfe0',1,'cutlass::layout::TensorOpMultiplicandCongruous< 32, Crosswise >::packed()'],['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCongruous.html#ae068c7ff740e38ea4c06a35a57416595',1,'cutlas
['packedvectorlayout',['PackedVectorLayout',['../classcutlass_1_1layout_1_1PackedVectorLayout.html#a8a6ead8c5b4b2a9e22d1e6ae779ff038',1,'cutlass::layout::PackedVectorLayout']]],
['params',['Params',['../structcutlass_1_1epilogue_1_1thread_1_1Convert_1_1Params.html#a5a6c0959f8481505164e6f4748a77dbe',1,'cutlass::epilogue::thread::Convert::Params::Params()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#ad7ac223e67928ea2aa44b64602089e81',1,'cutlass::epilogue::thread::LinearCombination::Params::Params()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#af4d2e889198f2e325cb4f0e3a3832f49',1,'cutlass::epilogue::thread::LinearCombination::Params::Params(ElementCompute alpha, ElementCompute beta)'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#aa6f2fb0b8fb92a28b4b534c3db7e9430',1,'cutlass::epilogue::thread::LinearCombination::Params::Params(ElementCompute const *alpha_ptr, ElementCompute const *beta_ptr)'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#ab19de8ec29f12815e5d558ad3a32ba66',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::Params()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#ac1f07947c5ab483d00d479624dbcecf2',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::Params(ElementCompute alpha, ElementCompute beta)'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#ac8a5fb23021e36af70e41e93e019f83b',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::Params(ElementCompute const *alpha_ptr, ElementCompute const *beta_ptr)'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#aab0a1bf972d12ad08acec38f10702bf0',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::Params()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#afcaa9ef1be508e3dd08a530266cb346f',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::Params(ElementCompute alpha, ElementCompute beta, ElementCompute threshold=ElementCompute(0))'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#a1f25f8df366d33bc4b256c92869ec20e',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::Params(ElementCompute const *alpha_ptr, ElementCompute const *beta_ptr, ElementCompute threshold=ElementCompute(0))'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#ab4301431271a1a57a51904b8c00584b2',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::Params()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#abd772185bd19b9d2ed08aa0d1344581c',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::Params(ElementCompute alpha, ElementCompute beta, ElementCompute threshold=ElementCompute(0))'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#abe3bc8635de57a97da921f89eb224368',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::Params(ElementCompute const *alpha_ptr, ElementCompute const *beta_ptr, ElementCompute threshold=ElementCompute(0))'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp_1_1Params.html#a7890b7910f0b680ff5b9230d91efc2ef',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp::Params::Params(TensorRef destination_ref_, TensorRef source_ref_, typename OutputOp::Params output_op_, typename ConvertOp::Params convert_op_)'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp_1_1Params.html#ae9578b799d3eb7d566112abb51146ec2',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp::Params::Params(TensorRef destination_ref_, TensorRef source_ref_, typename OutputOp::Params output_op_)'],['../structcutlass_1_1epilogue_1_1EpilogueWorkspace_1_1Params.html#a1d05c8ac7337fa0437a7870e024b58e3',1,'cutlass::epilogue::EpilogueWorkspace::Pa
['parsed_5fargc',['parsed_argc',['../structcutlass_1_1CommandLine.html#a228e1a273d223eec4b2f6d73135d3c1e',1,'cutlass::CommandLine']]],
['pitchlinear',['PitchLinear',['../classcutlass_1_1layout_1_1PitchLinear.html#a2c8c3651e1cf3282e623451a8d60f42b',1,'cutlass::layout::PitchLinear::PitchLinear(Index ldm=0)'],['../classcutlass_1_1layout_1_1PitchLinear.html#a827c1a15b7175bd5189a652011245302',1,'cutlass::layout::PitchLinear::PitchLinear(Stride _stride)']]],
['pitchlinearcoord',['PitchLinearCoord',['../structcutlass_1_1layout_1_1PitchLinearCoord.html#ada179709a13a11ca3e60b21b2fc69ed9',1,'cutlass::layout::PitchLinearCoord::PitchLinearCoord()'],['../structcutlass_1_1layout_1_1PitchLinearCoord.html#a224149b37de99bf9aaa2ceca08d019df',1,'cutlass::layout::PitchLinearCoord::PitchLinearCoord(Coord< 2, Index > const &coord)'],['../structcutlass_1_1layout_1_1PitchLinearCoord.html#a632057f0693badf11d9dc5c0140835fb',1,'cutlass::layout::PitchLinearCoord::PitchLinearCoord(Index contiguous_, Index strided_)']]],
['polar',['polar',['../namespacecutlass.html#a7bd7a35ae6ef9c350ae342b8c75958c5',1,'cutlass']]],
['predicatedtileaccessiterator',['PredicatedTileAccessIterator',['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen784a0e9da3f55064c47e5613791f51f7.html#a01973ed26ee44cc778e3913b8b64df1b',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen784a0e9da3f55064c47e5613791f51f7.html#a53537adcbf6bd8db4679009ad77fae77',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen89c687c583745a73cb485041911a4c4e.html#af0d24b5f67377109966b009a95c1f9fb',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen89c687c583745a73cb485041911a4c4e.html#ad3f7e1362d06e1bc10c9215a15c8755c',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen9838736ad62fae54213fbaf722a989ab.html#a89ea0762a8628807ffd46b18d9ea4f91',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen9838736ad62fae54213fbaf722a989ab.html#a7ef4172187d2bfd0e8e558a0877375b0',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemenab63a1e105bf37f6371516cb9e2c5a7a.html#a5bdef21a5f1017340ac6403cde5a2132',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemenab63a1e105bf37f6371516cb9e2c5a7a.html#a28ef2a11ff8aa22e6e3091cf47fdfc04',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen809793e785fb4211888c6b4e5dcfcb39.html#a8af4e1b2338f22dea60c857e13377e6c',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajorInterleaved< InterleavedK >, AdvanceRank,
['predicatedtileaccessiterator2dthreadtile',['PredicatedTileAccessIterator2dThreadTile',['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__1790abaa54a01f277d75766d5882fec8.html#a9394782d0f53ab741dbbabfa2ece2b25',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__1790abaa54a01f277d75766d5882fec8.html#a10500645804b2cb6a0e537f03b57f384',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__da632779aba661c0f4cfaaa78126b771.html#af1b744fd89da7f5c305ad26fc042c17b',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__da632779aba661c0f4cfaaa78126b771.html#a16c11af90a353e0bb703f879050b6e04',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__7327fa15996bcb8502cdfcc192350fe1.html#ae2cf64f40d954803ad851128c785dc07',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__7327fa15996bcb8502cdfcc192350fe1.html#a6735ad678e1efcd3949e36e65a50f9eb',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::PredicatedTileAccessIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)']]],
['predicatedtileiterator',['PredicatedTileIterator',['../classcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator.html#a0b73a5e03549ccf747bf5bf3c07f6f27',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::PredicatedTileIterator()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00e7c2c404e7aedfe60ad56bb5571306a1.html#a562259e56e4981326c16c96b00b67987',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00e7c2c404e7aedfe60ad56bb5571306a1.html#a36c915019a92458f22a40fbd0bad8363',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0068b3e874b5d93d11f0fa902c7f1d11d9.html#a80cdbe77271741f7f60da8af629149f2',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0068b3e874b5d93d11f0fa902c7f1d11d9.html#a79a6680479608730781b18d8f9ef86fb',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0041ea81994f8af0d4d071fdb9e66b5ff0.html#aa496890ca772ec1ee9ed7afe0651ba07',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0041ea81994f8af0d4d071fdb9e66b5ff0.html#ab77e9c9d9d7337dea6c27ee24f09ea86',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00f6b3a9dfab5e7c72d5233f7e5e6e3b9b.html#a9bf65422579611ecaf4275516b6d9e1f',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00f6b3a9dfab5e7c72d5233f7e5e6e3b9b.html#a52c7377c5a2457b3b652e90f2f3a1a53',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessSize >::PredicatedTileIterator(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00d670f969180a8d182dffb356ebcc957e.html#a699675b64057208e8ae82f700c7adb6b',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_,
['predicatedtileiterator2dthreadtile',['PredicatedTileIterator2dThreadTile',['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_017a517f3c73efd795ab05059cc9b111e1.html#aef7f87f11e85c20cfedb2c15c1bcdc1b',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::PredicatedTileIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_017a517f3c73efd795ab05059cc9b111e1.html#a344627cd2525bf07e4c631d2cc3ca1d9',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::PredicatedTileIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_0165b39a630d10785a3558406f9adb99b9.html#a691ce7629fc7d52146086dffae11c7e4',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, Transpose_ >::PredicatedTileIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_0165b39a630d10785a3558406f9adb99b9.html#a26211dc2b48ab669363e9af8738f1e13',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, Transpose_ >::PredicatedTileIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_013671177d6219bfeb0e1b4dc4c1b5bf11.html#a206d1ee28d98522f4e6577c41cce5ddb',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, Transpose_ >::PredicatedTileIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id, TensorCoord const &threadblock_offset)'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_013671177d6219bfeb0e1b4dc4c1b5bf11.html#a5b351404fe3d7bd3af79cba4118f04b8',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, Transpose_ >::PredicatedTileIterator2dThreadTile(Params const &params, Pointer pointer, TensorCoord extent, int thread_id)']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['predicatevector',['PredicateVector',['../structcutlass_1_1PredicateVector.html#aec1201df19c0ed0516810a3f19353c21',1,'cutlass::PredicateVector']]],
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
['product',['product',['../structcutlass_1_1Coord.html#ad5a2fb5b6b57e0726624c2b6e7c6545c',1,'cutlass::Coord']]],
['proj',['proj',['../namespacecutlass.html#a325f724545a11d64c5353664a1494ab2',1,'cutlass']]]
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
];
Reference in New Issue Copy Permalink