squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
7e370c9637
cutlass/docs/search/all_3.js

181 lines
58 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
['arch',['arch',['../namespacecutlass_1_1arch.html',1,'cutlass']]],
['c',['C',['../structcutlass_1_1library_1_1GemmDescription.html#adb43e15d8d870f6a4fca038a401125e7',1,'cutlass::library::GemmDescription::C()'],['../structcutlass_1_1library_1_1GemmArguments.html#a55d2e1d991fa6cfee6c8a4f3b71cbdd9',1,'cutlass::library::GemmArguments::C()'],['../structcutlass_1_1library_1_1GemmArrayArguments.html#a49928c947bec63af706d31f51fb10fd9',1,'cutlass::library::GemmArrayArguments::C()'],['../structcutlass_1_1Tensor4DCoord.html#ab0f58e5f54b42534fca77a662c78c7ad',1,'cutlass::Tensor4DCoord::c() const '],['../structcutlass_1_1Tensor4DCoord.html#a494c8f38161b2d767f9497e751467699',1,'cutlass::Tensor4DCoord::c()']]],
['can_5fimplement',['can_implement',['../classcutlass_1_1gemm_1_1device_1_1Gemm.html#a40ad889da7ff420fd9f9000cd9f98e32',1,'cutlass::gemm::device::Gemm::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1Gemm_3_01ElementA___00_01LayoutA___00_01ElementB___00_01Layout4d0960ae6b1d1bf19e6239dbd002249c.html#a662bcbcb6164c803ab490c86e69b9ee1',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 >::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1GemmBatched.html#acb4d53fbea4366349574091d68594558',1,'cutlass::gemm::device::GemmBatched::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA___00_01ElementB___00_0c9bb6f4463ab6085e6008b5d5ad6abfd.html#abbd82c0f989a9d07e5e222db96386701',1,'cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ >::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1GemmComplex.html#aa94353c3aa13b38f0e859070edf61c6e',1,'cutlass::gemm::device::GemmComplex::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1GemmComplex_3_01ElementA___00_01LayoutA___00_01ElementB___00_07c56401b4df75709ae636675d9980a9a.html#adb94d2e6dd70b46bea6b5b433e14fea9',1,'cutlass::gemm::device::GemmComplex< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, TransformA, TransformB, SplitKSerial >::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel.html#a114b122602b425909f9be0df461353a4',1,'cutlass::gemm::device::GemmSplitKParallel::can_implement()'],['../classcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_3_01ElementA___00_01LayoutA___00_01ElementBbe7c1f7154ad5b5bf9d4d28301e2b457.html#a465591fbfde2a9aa6330d9adcbf82bd6',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_ >::can_implement()'],['../structcutlass_1_1gemm_1_1kernel_1_1Gemm.html#afa50b807bd445330e9f3a55d664008c9',1,'cutlass::gemm::kernel::Gemm::can_implement()'],['../classcutlass_1_1library_1_1Operation.html#a36bef483ad4a6c1d5bd426e134f16538',1,'cutlass::library::Operation::can_implement()']]],
['capacity',['capacity',['../structcutlass_1_1device__memory_1_1allocation.html#a81d1c8ae7ffc695ae1e6a190ebfe8bb6',1,'cutlass::device_memory::allocation::capacity()'],['../classcutlass_1_1layout_1_1RowMajor.html#a89225f007689acef0e17f6990e32c56e',1,'cutlass::layout::RowMajor::capacity()'],['../classcutlass_1_1layout_1_1ColumnMajor.html#ae0ede39a3011be136c9033327935170d',1,'cutlass::layout::ColumnMajor::capacity()'],['../structcutlass_1_1layout_1_1RowMajorInterleaved.html#a37d81b341052fb816b7a5373efd76c52',1,'cutlass::layout::RowMajorInterleaved::capacity()'],['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html#a8233dbf6ef04491c79780bf27893f3e1',1,'cutlass::layout::ColumnMajorInterleaved::capacity()'],['../structcutlass_1_1layout_1_1ContiguousMatrix.html#af7266ef6f5ba58567103e8792cb0484b',1,'cutlass::layout::ContiguousMatrix::capacity()'],['../structcutlass_1_1layout_1_1ColumnMajorBlockLinear.html#afa68813c9946c24aa27eae56848a52e6',1,'cutlass::layout::ColumnMajorBlockLinear::capacity()'],['../structcutlass_1_1layout_1_1RowMajorBlockLinear.html#a4e39977f24228d8a2776ca1652336c3b',1,'cutlass::layout::RowMajorBlockLinear::capacity()'],['../structcutlass_1_1layout_1_1GeneralMatrix.html#a435e6e78b25296cd7ccaada3dcd4e16b',1,'cutlass::layout::GeneralMatrix::capacity()'],['../classcutlass_1_1layout_1_1PitchLinear.html#a3fb2016836e011e8c77a4b3fbb3e51d5',1,'cutlass::layout::PitchLinear::capacity()'],['../classcutlass_1_1layout_1_1TensorNHWC.html#a3bb3250d891e752789fa02d5c0cc0ede',1,'cutlass::layout::TensorNHWC::capacity()'],['../classcutlass_1_1layout_1_1TensorNCHW.html#a20dd56dacab1558db7253fb737704c51',1,'cutlass::layout::TensorNCHW::capacity()'],['../classcutlass_1_1layout_1_1TensorNCxHWx.html#a915e1193d4f9c1feb973ae1331687bf9',1,'cutlass::layout::TensorNCxHWx::capacity()'],['../classcutlass_1_1layout_1_1TensorCxRSKx.html#a27c2569d09991401630d7842c0c1ba67',1,'cutlass::layout::TensorCxRSKx::capacity()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandCongruous.html#af9149c2f7914f62232dcb3bd8f46384d',1,'cutlass::layout::VoltaTensorOpMultiplicandCongruous::capacity()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html#ae616638f7e2dc315865b3693f71f52cd',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous::capacity()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandCongruous.html#a38fc7f3ffab51a56a76d297ecdc7edf7',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandCongruous::capacity()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandBCongruous.html#aaafaf46f0d3bb10de607e999e28ca87a',1,'cutlass::layout::VoltaTensorOpMultiplicandBCongruous::capacity()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html#a9ac9d347fb65719c8a05295816120fec',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous::capacity()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandBCongruous.html#a2a556452484f1d6958ec57d0a5b68dea',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandBCongruous::capacity()'],['../structcutlass_1_1layout_1_1VoltaTensorOpMultiplicandCrosswise.html#a0c2e65352446d60ea1a917ff840245e8',1,'cutlass::layout::VoltaTensorOpMultiplicandCrosswise::capacity()'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCrosswise.html#a1c709df04e3d4693707dc30b6c1f08f5',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise::capacity()'],['../structcutlass_1_1layout_1_1RowMajorVoltaTensorOpMultiplicandCrosswise.html#a0a6c5b20d5c84ace7d2440c03b42f29e',1,'cutlass::layout::RowMajorVoltaTensorOpMultiplicandCrosswise::capacity()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicand.html#a9ef7a95265d1602eb5d050eb89ad8b6b',1,'cutlass::layout::TensorOpMultiplicand::capacity()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCongruous.html#a016ea88480ec49f60b311b00e06dba54',1,'cutlass::layout::TensorOpMultiplicandCongruous::capacity()'],['../structcutlass_1_1layout_1_1TensorOpMultiplicandCongruous_3_0132_00_01Crosswise_01_4.html#a8580ab6b5c31b815c9ff4d146cbec442',1,'cutlass::
['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']]],
['cast_5ffrom_5fdouble',['cast_from_double',['../namespacecutlass_1_1library.html#a5f25bb70b92aa865148c22d4cffcaa37',1,'cutlass::library']]],
['cast_5ffrom_5fint64',['cast_from_int64',['../namespacecutlass_1_1library.html#a0b8493aa442c2c23aa57234c4e928660',1,'cutlass::library']]],
['cast_5ffrom_5fuint64',['cast_from_uint64',['../namespacecutlass_1_1library.html#aa997284cf98e50d99e48516f91a96c08',1,'cutlass::library']]],
['cbegin',['cbegin',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a815d434e9da9715a115896b3f6e64608',1,'cutlass::Array< T, N, true >::cbegin()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a86a56cc907c8566068034ef8294cf7c2',1,'cutlass::Array< T, N, false >::cbegin()']]],
['cend',['cend',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a27e663ee5e22d4af436588a500a6cc0c',1,'cutlass::Array< T, N, true >::cend()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#ae6106b72ee9035389afb313801561b16',1,'cutlass::Array< T, N, false >::cend()']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['check',['check',['../structcutlass_1_1platform_1_1is__base__of__helper.html#a5bf08859497e304ca353699ad6ac332b',1,'cutlass::platform::is_base_of_helper::check(DerivedT *, T)'],['../structcutlass_1_1platform_1_1is__base__of__helper.html#ae8896817cabf297437b3a073e693ffd2',1,'cutlass::platform::is_base_of_helper::check(BaseT *, int)']]],
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
['check_5fcmd_5fline_5fflag',['check_cmd_line_flag',['../structcutlass_1_1CommandLine.html#a5a20785501f9ed3d4a57241b08399552',1,'cutlass::CommandLine']]],
['clamp',['clamp',['../structcutlass_1_1Coord.html#a40e145063833155c800b38f82cee7461',1,'cutlass::Coord']]],
['clear',['clear',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#ae67b1d98a446384fc75a1c92474e719d',1,'cutlass::Array< T, N, true >::clear()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a5b84c4dc5257f31108a0598915f03f94',1,'cutlass::Array< T, N, false >::clear()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator_1_1Mask.html#a0fcbcea35583d096e4154209237ba217',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::Mask::clear()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator_1_1Mask.html#aed4717037e76148efbb7bb68d6c4e509',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::Mask::clear()'],['../structcutlass_1_1PredicateVector.html#a51d9239e76ec040819333022fcecdb55',1,'cutlass::PredicateVector::clear()']]],
['clear_5fmask',['clear_mask',['../classcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator.html#a17a6ccbe829782c27e49f47922fce84a',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::clear_mask()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator.html#ab478d83e7b15b9eca8f3f281072cba38',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen784a0e9da3f55064c47e5613791f51f7.html#ac0b90ae65b6bd987bfb0a0fca4912533',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen89c687c583745a73cb485041911a4c4e.html#ae78b23bb3d11b1ad5fe615a4bcb2d15d',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen9838736ad62fae54213fbaf722a989ab.html#ad52c785f2d0e7bfc86633571f5e4a926',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemenab63a1e105bf37f6371516cb9e2c5a7a.html#a2fd2b595bf69e2f4d1c9af852acdd018',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen809793e785fb4211888c6b4e5dcfcb39.html#acd9df23ddc440195ba7a648db3c55f3e',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__1790abaa54a01f277d75766d5882fec8.html#a5ad8047c30a84a55fa1c21c911d148d8',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__da632779aba661c0f4cfaaa78126b771.html#a887454d8c430984ceffd4859903b4898',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__7327fa15996bcb8502cdfcc192350fe1.html#abc85cc801d0e933dfb026a9c266674e2',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00e7c2c404e7aedfe60ad56bb5571306a1.html#afd3e189a510aef0ddceb6f0ceb519d88',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessSize >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0068b3e874b5d93d11f0fa902c7f1d11d9.html#ac31418e71cb8ed71b7ebf51ab7028713',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessSize >::clear_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0041ea81994f8af0d4d071fdb9e66b5ff0.html#a38b1509afcb20c5474ea5998f85c6507',1,'cutlass::transf
Updated doxygen
2018-09-20 05:02:08 +08:00
['clz',['clz',['../namespacecutlass.html#a6bc666acc9f0d7278a788975e226e005',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
['column',['column',['../structcutlass_1_1MatrixCoord.html#afbdcc5ca5b91f11f29046667b0bfde7b',1,'cutlass::MatrixCoord::column() const '],['../structcutlass_1_1MatrixCoord.html#a093f5e568a81c6464dbf4aef996c32ba',1,'cutlass::MatrixCoord::column()']]],
['columnmajor',['ColumnMajor',['../classcutlass_1_1layout_1_1ColumnMajor.html',1,'cutlass::layout']]],
['columnmajor',['ColumnMajor',['../classcutlass_1_1layout_1_1ColumnMajor.html#adc69d6cd2cf938d1ab41c4f2ba0589a4',1,'cutlass::layout::ColumnMajor::ColumnMajor(Index ldm=0)'],['../classcutlass_1_1layout_1_1ColumnMajor.html#a0a9383ad9de01697e2df975c3a3e6ab8',1,'cutlass::layout::ColumnMajor::ColumnMajor(Stride stride)']]],
['columnmajorblocklinear',['ColumnMajorBlockLinear',['../structcutlass_1_1layout_1_1ColumnMajorBlockLinear.html',1,'cutlass::layout']]],
['columnmajorblocklinear',['ColumnMajorBlockLinear',['../structcutlass_1_1layout_1_1ColumnMajorBlockLinear.html#a740b33237fd49dee4692946811e203ba',1,'cutlass::layout::ColumnMajorBlockLinear']]],
['columnmajorinterleaved',['ColumnMajorInterleaved',['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html',1,'cutlass::layout']]],
['columnmajorinterleaved',['ColumnMajorInterleaved',['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html#acd4d70f17b74ebe3e55ea0027bac5899',1,'cutlass::layout::ColumnMajorInterleaved::ColumnMajorInterleaved(Index ldm=0)'],['../structcutlass_1_1layout_1_1ColumnMajorInterleaved.html#a2d4a85bbfbb919349e6fd2b859a0a461',1,'cutlass::layout::ColumnMajorInterleaved::ColumnMajorInterleaved(Stride stride)']]],
['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']]],
['columnmajortensoropmultiplicandcongruous',['ColumnMajorTensorOpMultiplicandCongruous',['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCongruous.html#a910ff464fc55a153bf3e54cb7b816ccb',1,'cutlass::layout::ColumnMajorTensorOpMultiplicandCongruous::ColumnMajorTensorOpMultiplicandCongruous(Index ldm=0)'],['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCongruous.html#a588582ed7496bb9f6cfbb7f79873affa',1,'cutlass::layout::ColumnMajorTensorOpMultiplicandCongruous::ColumnMajorTensorOpMultiplicandCongruous(Stride stride)']]],
['columnmajortensoropmultiplicandcrosswise',['ColumnMajorTensorOpMultiplicandCrosswise',['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCrosswise.html',1,'cutlass::layout']]],
['columnmajortensoropmultiplicandcrosswise',['ColumnMajorTensorOpMultiplicandCrosswise',['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCrosswise.html#ae9010e219ceb098de21d2673a9112b50',1,'cutlass::layout::ColumnMajorTensorOpMultiplicandCrosswise::ColumnMajorTensorOpMultiplicandCrosswise(Index ldm=0)'],['../structcutlass_1_1layout_1_1ColumnMajorTensorOpMultiplicandCrosswise.html#a77befaca4f7609243842a4e54d50d010',1,'cutlass::layout::ColumnMajorTensorOpMultiplicandCrosswise::ColumnMajorTensorOpMultiplicandCrosswise(Stride stride)']]],
['columnmajorvoltatensoropmultiplicandbcongruous',['ColumnMajorVoltaTensorOpMultiplicandBCongruous',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html',1,'cutlass::layout']]],
['columnmajorvoltatensoropmultiplicandbcongruous',['ColumnMajorVoltaTensorOpMultiplicandBCongruous',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html#ab42f59c4fb58814ce2b5617b12e3faf0',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous::ColumnMajorVoltaTensorOpMultiplicandBCongruous(Index ldm=0)'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandBCongruous.html#a80099cf16729a8b553677fc70bea81bc',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandBCongruous::ColumnMajorVoltaTensorOpMultiplicandBCongruous(Stride stride)']]],
['columnmajorvoltatensoropmultiplicandcongruous',['ColumnMajorVoltaTensorOpMultiplicandCongruous',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html',1,'cutlass::layout']]],
['columnmajorvoltatensoropmultiplicandcongruous',['ColumnMajorVoltaTensorOpMultiplicandCongruous',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html#a9019c397159688cd2bafe55967ee7f36',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous::ColumnMajorVoltaTensorOpMultiplicandCongruous(Index ldm=0)'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCongruous.html#a963c8058ab8ef1a5d21403bd1dc27277',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCongruous::ColumnMajorVoltaTensorOpMultiplicandCongruous(Stride stride)']]],
['columnmajorvoltatensoropmultiplicandcrosswise',['ColumnMajorVoltaTensorOpMultiplicandCrosswise',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCrosswise.html',1,'cutlass::layout']]],
['columnmajorvoltatensoropmultiplicandcrosswise',['ColumnMajorVoltaTensorOpMultiplicandCrosswise',['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCrosswise.html#af2456911e4cfca021d50ec16ca1d7505',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise::ColumnMajorVoltaTensorOpMultiplicandCrosswise(Index ldm=0)'],['../structcutlass_1_1layout_1_1ColumnMajorVoltaTensorOpMultiplicandCrosswise.html#a7c839af8ec4dda7a6114d49daec52728',1,'cutlass::layout::ColumnMajorVoltaTensorOpMultiplicandCrosswise::ColumnMajorVoltaTensorOpMultiplicandCrosswise(Stride stride)']]],
['columnvector',['ColumnVector',['../namespacecutlass_1_1thread.html#a1a7bcc895cfbd560c476b74bd6eb60bc',1,'cutlass::thread']]],
['command_5fline_2eh',['command_line.h',['../command__line_8h.html',1,'']]],
['commandline',['CommandLine',['../structcutlass_1_1CommandLine.html#a7156975dc884e8b58b91c710495fc79d',1,'cutlass::CommandLine']]],
['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#a9050cd0f48c7a7b718ea9223299b3a82',1,'cutlass::complex::complex(T r=T(0))'],['../classcutlass_1_1complex.html#a0eae629b6e4bf0be4a8d259fcc59c842',1,'cutlass::complex::complex(T r, T i)'],['../classcutlass_1_1complex.html#a2a853405a46cc6ed36185a80bd2aae98',1,'cutlass::complex::complex(complex< A > const &z)'],['../classcutlass_1_1complex.html#a8681bee9979b43f21d154e17725cb630',1,'cutlass::complex::complex(cuFloatComplex const &z)'],['../classcutlass_1_1complex.html#ada1e58813aa2d901d44237f5f9fb37db',1,'cutlass::complex::complex(cuDoubleComplex const &z)']]],
['complex',['complex',['../classcutlass_1_1complex.html',1,'cutlass']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['complex_2eh',['complex.h',['../complex_8h.html',1,'']]],
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
['complextransform',['ComplexTransform',['../namespacecutlass.html#a59f08b1b99c4d52257b962d35ba55cde',1,'cutlass::ComplexTransform()'],['../namespacecutlass_1_1library.html#aa2b27589531eec608a86cf43a36c4175',1,'cutlass::library::ComplexTransform()']]],
['compute_5fgemm',['compute_gemm',['../namespacecutlass_1_1reference_1_1device.html#a4b872e5b16985b2cf31530a9090a8423',1,'cutlass::reference::device::compute_gemm(gemm::GemmCoord problem_size, ScalarType alpha, TensorRef< ElementA, LayoutA > tensor_a, TensorRef< ElementB, LayoutB > tensor_b, ScalarType beta, TensorRef< ElementC, LayoutC > tensor_c, TensorRef< ElementC, LayoutC > tensor_d, AccumulatorType initial_accum)'],['../namespacecutlass_1_1reference_1_1device.html#aa1b04f721cb13fb3f110acf6b29dc53b',1,'cutlass::reference::device::compute_gemm(gemm::GemmCoord problem_size, ScalarType alpha, TensorRef< ElementA, LayoutA > tensor_a, TensorRef< ElementB, LayoutB > tensor_b, ScalarType beta, TensorRef< ElementC, LayoutC > tensor_c, AccumulatorType initial_accum)'],['../namespacecutlass_1_1reference_1_1host.html#a300d68abd082150020768c0a94044a34',1,'cutlass::reference::host::compute_gemm(gemm::GemmCoord problem_size, ScalarType alpha, TensorRef< ElementA, LayoutA > tensor_a, TensorRef< ElementB, LayoutB > tensor_b, ScalarType beta, TensorRef< ElementC, LayoutC > tensor_c, TensorRef< ElementC, LayoutC > tensor_d, ComputeType initial_accum)'],['../namespacecutlass_1_1reference_1_1host.html#aa75c5933390f3960666e97b37c854877',1,'cutlass::reference::host::compute_gemm(gemm::GemmCoord problem_size, ScalarType alpha, TensorRef< ElementA, LayoutA > tensor_a, TensorRef< ElementB, LayoutB > tensor_b, ScalarType beta, TensorRef< ElementC, LayoutC > tensor_c, ComputeType initial_accum)']]],
['computefragment',['ComputeFragment',['../classcutlass_1_1epilogue_1_1thread_1_1Convert.html#a1f6d13cc82035c3427f0a9367f35f18b',1,'cutlass::epilogue::thread::Convert::ComputeFragment()'],['../classcutlass_1_1epilogue_1_1thread_1_1LinearCombination.html#ad024cd3ca657233883219177fc2f50af',1,'cutlass::epilogue::thread::LinearCombination::ComputeFragment()'],['../classcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp.html#a212e93f8d2c9793d77ec4b679b6c81e6',1,'cutlass::epilogue::thread::LinearCombinationClamp::ComputeFragment()'],['../classcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu.html#a54909b2fb614bf006572ceb79a264d05',1,'cutlass::epilogue::thread::LinearCombinationRelu::ComputeFragment()'],['../classcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_01int_00_01float_00_01Round_01_4.html#a2690ec31dbbcb0b647a4c1846d171ef6',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::ComputeFragment()']]],
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
['conj',['conj',['../namespacecutlass.html#adba9348e32642fa40c186b5ca6e5ba4e',1,'cutlass']]],
['const_5fbegin',['const_begin',['../structcutlass_1_1PredicateVector.html#a505db4b5fba1671ee8362c18e2ccce1b',1,'cutlass::PredicateVector']]],
['const_5fend',['const_end',['../structcutlass_1_1PredicateVector.html#a8017a90ffe8a8039fff56b6956739045',1,'cutlass::PredicateVector']]],
['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_5fiterator',['const_iterator',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4_1_1const__iterator.html#a40f18ab5962efa95ac4ae4f5140c5d7b',1,'cutlass::Array< T, N, true >::const_iterator::const_iterator()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4_1_1const__iterator.html#a56cb84bfcb97eeeae472f03fc203d759',1,'cutlass::Array< T, N, true >::const_iterator::const_iterator(T const *_ptr)'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__iterator.html#a2baacc6de7180213621a2d6b2328ca7d',1,'cutlass::Array< T, N, false >::const_iterator::const_iterator()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__iterator.html#a273a0ea9cf66fac0787e90339fd49371',1,'cutlass::Array< T, N, false >::const_iterator::const_iterator(Storage const *ptr, int idx=0)']]],
['const_5fmax',['const_max',['../namespacecutlass.html#a072919006084ca52479a69cd10694448',1,'cutlass']]],
['const_5fmin',['const_min',['../namespacecutlass.html#a1676e17a7fea0ac40d9d239cbd3ce872',1,'cutlass']]],
['const_5fpointer',['const_pointer',['../structcutlass_1_1AlignedBuffer.html#a9ea058b3d86ad689240836e2d89686c4',1,'cutlass::AlignedBuffer::const_pointer()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a319dba33ebc8556e58f699f32c6a391b',1,'cutlass::Array< T, N, true >::const_pointer()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a8a90423fc5483b3ee1d31f377321e9e0',1,'cutlass::Array< T, N, false >::const_pointer()']]],
['const_5fref',['const_ref',['../classcutlass_1_1TensorRef.html#a5c5c66a59e9759f11f832fb71f4234c2',1,'cutlass::TensorRef::const_ref()'],['../classcutlass_1_1TensorView.html#aef27ab5348a53539286057a0da8720fc',1,'cutlass::TensorView::const_ref()'],['../classcutlass_1_1thread_1_1Matrix.html#a850e9e43797c386ffbdec398d1c1b559',1,'cutlass::thread::Matrix::const_ref()']]],
['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_5freference',['const_reference',['../structcutlass_1_1AlignedBuffer.html#a878e461a9368a2e9639464caf78ac718',1,'cutlass::AlignedBuffer::const_reference()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#ad64094119b89bb538cd1c1ea979c7954',1,'cutlass::Array< T, N, true >::const_reference()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__reference.html#abf1841f0ac863891efcf23bd5ac57847',1,'cutlass::Array< T, N, false >::const_reference::const_reference()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__reference.html#ac9e3b9e2f5797efbc47e3415aa204079',1,'cutlass::Array< T, N, false >::const_reference::const_reference(Storage const *ptr, int idx=0)']]],
['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 >']]],
['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#aa839335a821fad9841eb31560d7520a2',1,'cutlass::Array< T, N, true >::const_reverse_iterator::const_reverse_iterator()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4_1_1const__reverse__iterator.html#a6e2a9b7f836704d9d39ad42c74502a07',1,'cutlass::Array< T, N, true >::const_reverse_iterator::const_reverse_iterator(T const *_ptr)'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__reverse__iterator.html#aae7705a26ea52ebd18d5f5809d816ee2',1,'cutlass::Array< T, N, false >::const_reverse_iterator::const_reverse_iterator()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4_1_1const__reverse__iterator.html#a4bef88847b70f6bca81dd46bd883373b',1,'cutlass::Array< T, N, false >::const_reverse_iterator::const_reverse_iterator(Storage const *ptr, int idx=0)']]],
['const_5fview',['const_view',['../classcutlass_1_1TensorView.html#ab7794e21b87340f8b73aeb4dca2cb80c',1,'cutlass::TensorView::const_view()'],['../classcutlass_1_1thread_1_1Matrix.html#a65a4c5ff99fd0a7dbee722c9e04fac35',1,'cutlass::thread::Matrix::const_view()']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['constexpr',['constexpr',['../platform_8h.html#a72f0657181cca64b44eb186b707eb380',1,'platform.h']]],
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
['constiterator',['ConstIterator',['../classcutlass_1_1PredicateVector_1_1ConstIterator.html',1,'cutlass::PredicateVector']]],
['constiterator',['ConstIterator',['../classcutlass_1_1PredicateVector_1_1ConstIterator.html#a1216aab9c567ec0d4232019008ef3ea7',1,'cutlass::PredicateVector::ConstIterator::ConstIterator(ConstIterator const &it)'],['../classcutlass_1_1PredicateVector_1_1ConstIterator.html#abb6749fd0f66f9442fa18fabbb3588e4',1,'cutlass::PredicateVector::ConstIterator::ConstIterator(PredicateVector const &vec, int _start=0)']]],
['constreference',['ConstReference',['../classcutlass_1_1HostTensor.html#a4c6d967596e266ceab3d36f6c8d05152',1,'cutlass::HostTensor']]],
['constsubbytereference',['ConstSubbyteReference',['../classcutlass_1_1ConstSubbyteReference.html',1,'cutlass']]],
['constsubbytereference',['ConstSubbyteReference',['../classcutlass_1_1ConstSubbyteReference.html#aa00016fe6dafa323e9875be4287fbfe5',1,'cutlass::ConstSubbyteReference::ConstSubbyteReference()'],['../classcutlass_1_1ConstSubbyteReference.html#a158ae5a484751f274c083807b4a37868',1,'cutlass::ConstSubbyteReference::ConstSubbyteReference(Element const *ptr, int64_t offset)'],['../classcutlass_1_1ConstSubbyteReference.html#adfefff5e63632fcdc4f59e21dccea16d',1,'cutlass::ConstSubbyteReference::ConstSubbyteReference(Element *ptr=nullptr)']]],
['consttensorref',['ConstTensorRef',['../classcutlass_1_1epilogue_1_1threadblock_1_1Epilogue.html#a92587dbbf9e08f1db3fab5443ae870e8',1,'cutlass::epilogue::threadblock::Epilogue::ConstTensorRef()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedEpilogue.html#ac88c09516fa86c8b66690a26a73c4a99',1,'cutlass::epilogue::threadblock::InterleavedEpilogue::ConstTensorRef()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator.html#a53cca23a482d1e55ca3e21011a54ae79',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::ConstTensorRef()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator.html#a5531982973996f04fb344d11e4e9d015',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::ConstTensorRef()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1SharedLoadIterator.html#a5208835793dcd89f36ea65a8fcadf7e7',1,'cutlass::epilogue::threadblock::SharedLoadIterator::ConstTensorRef()'],['../classcutlass_1_1TensorRef.html#ad3c5c9466713f62a5191e720827f34da',1,'cutlass::TensorRef::ConstTensorRef()'],['../classcutlass_1_1TensorView.html#a48c934ddac84fa964fb9b1364ec44164',1,'cutlass::TensorView::ConstTensorRef()'],['../classcutlass_1_1thread_1_1Matrix.html#a5cae9543ffd1f2e722943b53fa5486b9',1,'cutlass::thread::Matrix::ConstTensorRef()'],['../classcutlass_1_1HostTensor.html#ae76a55dd7f4d827f042f9c9018567271',1,'cutlass::HostTensor::ConstTensorRef()']]],
['consttensorview',['ConstTensorView',['../classcutlass_1_1TensorView.html#a71def6d54ed28dfe3b17fde3e6461578',1,'cutlass::TensorView::ConstTensorView()'],['../classcutlass_1_1thread_1_1Matrix.html#a24979d95b579648b9871db63ba9f7c6b',1,'cutlass::thread::Matrix::ConstTensorView()'],['../classcutlass_1_1HostTensor.html#ac4445444c8f092dd1be47f1530affbaf',1,'cutlass::HostTensor::ConstTensorView()']]],
['contains',['contains',['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorContainsFunc.html#a36f817e5b6e993ac3c9aaf78186a1ffb',1,'cutlass::reference::host::detail::TensorContainsFunc::contains()'],['../classcutlass_1_1TensorView.html#a6a6a1f99d06abd8fb3f5a8e4e0fea25e',1,'cutlass::TensorView::contains()']]],
['contiguous',['contiguous',['../structcutlass_1_1layout_1_1PitchLinearCoord.html#adb31bc9b8cf49dfff64245b70a850834',1,'cutlass::layout::PitchLinearCoord::contiguous() const '],['../structcutlass_1_1layout_1_1PitchLinearCoord.html#a3d3c19009c7cf8991cb33f1ff8c8d494',1,'cutlass::layout::PitchLinearCoord::contiguous()']]],
['contiguousmatrix',['ContiguousMatrix',['../structcutlass_1_1layout_1_1ContiguousMatrix.html',1,'cutlass::layout']]],
['contiguousmatrix',['ContiguousMatrix',['../structcutlass_1_1layout_1_1ContiguousMatrix.html#a4515c6a78dadf99bf491137e6bb52451',1,'cutlass::layout::ContiguousMatrix']]],
['conversion_5fop_2eh',['conversion_op.h',['../conversion__op_8h.html',1,'']]],
['convert',['Convert',['../classcutlass_1_1epilogue_1_1thread_1_1Convert.html',1,'cutlass::epilogue::thread']]],
['convert',['Convert',['../classcutlass_1_1epilogue_1_1thread_1_1Convert.html#ac7ec0a00e5863dc06f4d99477fd5c056',1,'cutlass::epilogue::thread::Convert::Convert()'],['../structcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_1_1Arguments.html#aabbedd03888a6090f049f53f53bf4e45',1,'cutlass::gemm::device::GemmSplitKParallel::Arguments::convert()'],['../structcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_3_01ElementA___00_01LayoutA___00_01Elementafcb1aeaf2035a7ac769d7acc233423b.html#a48ced96adaf371f03c1c9a50db9f50f2',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::convert()'],['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorCopyIf.html#ad9e5902883076ca684487d276a79c47e',1,'cutlass::reference::host::detail::TensorCopyIf::convert()'],['../structcutlass_1_1half__t.html#a4c472ad52970df8b6f5c05beff66ff9f',1,'cutlass::half_t::convert(float const &flt)'],['../structcutlass_1_1half__t.html#a1cddd98cc0650a0fcc5ff1ea0cb08fcf',1,'cutlass::half_t::convert(int const &n)'],['../structcutlass_1_1half__t.html#a6af4af16ddbbfcefde206c29cac5c1ec',1,'cutlass::half_t::convert(unsigned const &n)'],['../structcutlass_1_1half__t.html#a5ef78c3a7ccd316fc4fe52b7c230f87b',1,'cutlass::half_t::convert(half_t const &x)'],['../structcutlass_1_1NumericConverter.html#a4d1a347bd8c92f3dc5b6e919005d34d2',1,'cutlass::NumericConverter::convert()'],['../structcutlass_1_1NumericConverter_3_01int8__t_00_01float_00_01Round_01_4.html#ab90d4ee00677c3129962501a148cdaf7',1,'cutlass::NumericConverter< int8_t, float, Round >::convert()'],['../structcutlass_1_1NumericConverter_3_01T_00_01T_00_01Round_01_4.html#aa61325e20130b528104b990fc8ec3bb8',1,'cutlass::NumericConverter< T, T, Round >::convert()'],['../structcutlass_1_1NumericConverter_3_01float_00_01half__t_00_01Round_01_4.html#af7d7dec76e968b489efa25be32a4cf04',1,'cutlass::NumericConverter< float, half_t, Round >::convert()'],['../structcutlass_1_1NumericConverter_3_01half__t_00_01float_00_01FloatRoundStyle_1_1round__to__nearest_01_4.html#aaf16c1dd3bb1fc0566c819146dfd5ab8',1,'cutlass::NumericConverter< half_t, float, FloatRoundStyle::round_to_nearest >::convert()'],['../structcutlass_1_1NumericConverter_3_01half__t_00_01float_00_01FloatRoundStyle_1_1round__toward__zero_01_4.html#a43ab30e5283f39b1defe46b13da9ac1b',1,'cutlass::NumericConverter< half_t, float, FloatRoundStyle::round_toward_zero >::convert()'],['../structcutlass_1_1NumericConverterClamp.html#aefadbac80ed0f5be1abc6f6704631fe2',1,'cutlass::NumericConverterClamp::convert()'],['../structcutlass_1_1NumericArrayConverter.html#a157bacb3ab7d03032c83ff75d0a0d090',1,'cutlass::NumericArrayConverter::convert()'],['../structcutlass_1_1NumericArrayConverter_3_01half__t_00_01float_00_012_00_01FloatRoundStyle_1_1round__to__nearest_01_4.html#a3cc4d59f083555f24288e15490eeb41d',1,'cutlass::NumericArrayConverter< half_t, float, 2, FloatRoundStyle::round_to_nearest >::convert()'],['../structcutlass_1_1NumericArrayConverter_3_01float_00_01half__t_00_012_00_01Round_01_4.html#a16ac842664840d5db0ba823303c9ec4e',1,'cutlass::NumericArrayConverter< float, half_t, 2, Round >::convert()'],['../structcutlass_1_1NumericArrayConverter_3_01half__t_00_01float_00_01N_00_01Round_01_4.html#af8e268c03414c218485ed80e158725e8',1,'cutlass::NumericArrayConverter< half_t, float, N, Round >::convert()'],['../structcutlass_1_1NumericArrayConverter_3_01float_00_01half__t_00_01N_00_01Round_01_4.html#a4602966344dcf217c4dbd97deb358c6f',1,'cutlass::NumericArrayConverter< float, half_t, N, Round >::convert()']]],
['convert_5fop',['convert_op',['../structcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp_1_1Params.html#a97f1044e7b7cec1ddd1f120b8b7539f2',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp::Params']]],
['convertop',['ConvertOp',['../classcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp.html#a71707c91f25720e027e9e3b9f7a8a113',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp']]],
['convertscaledop',['ConvertScaledOp',['../classcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel.html#affb7a5c96c9e8b04eb94a464e5fdc48b',1,'cutlass::gemm::device::GemmSplitKParallel::ConvertScaledOp()'],['../classcutlass_1_1gemm_1_1device_1_1GemmSplitKParallel_3_01ElementA___00_01LayoutA___00_01ElementBbe7c1f7154ad5b5bf9d4d28301e2b457.html#aa69d9364cc5247ea353608d5c0600fe7',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_ >::ConvertScaledOp()']]],
['coord',['Coord',['../structcutlass_1_1Coord.html',1,'cutlass']]],
['coord',['Coord',['../structcutlass_1_1Coord.html#a5281db2419b5567db4265dead7ac02cc',1,'cutlass::Coord::Coord(Index value=Index(0))'],['../structcutlass_1_1Coord.html#ab7094975a4b7471315ca083ae575030a',1,'cutlass::Coord::Coord(Index const (&_idx)[kRank])'],['../structcutlass_1_1Coord.html#a42aefbb547e39b8cc7267c58a610c147',1,'cutlass::Coord::Coord(Coord< kRank, Index, LongIndex > const &coord)']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['coord_2eh',['coord.h',['../coord_8h.html',1,'']]],
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']]],
['copy',['copy',['../namespacecutlass_1_1device__memory.html#a117e201964852b2b3e228d81eaf73f93',1,'cutlass::device_memory']]],
['copy_5fdevice_5fto_5fdevice',['copy_device_to_device',['../namespacecutlass_1_1device__memory.html#a8ff6151b081442db9af7421110c0242b',1,'cutlass::device_memory']]],
['copy_5fhost_5fto_5fhost',['copy_host_to_host',['../namespacecutlass_1_1device__memory.html#a0a3ab26e6c9a8aae6b09bfb3e4eb24e8',1,'cutlass::device_memory']]],
['copy_5fin_5fdevice_5fto_5fdevice',['copy_in_device_to_device',['../classcutlass_1_1HostTensor.html#a5686ea068c8f3e820ccff015e95bc474',1,'cutlass::HostTensor']]],
['copy_5fin_5fdevice_5fto_5fhost',['copy_in_device_to_host',['../classcutlass_1_1HostTensor.html#a2b4858efb0356a6fc01bb9f55f0ad3b2',1,'cutlass::HostTensor']]],
['copy_5fin_5fhost_5fto_5fdevice',['copy_in_host_to_device',['../classcutlass_1_1HostTensor.html#ad385330c69ecd7bd0b6c3660815253fa',1,'cutlass::HostTensor']]],
['copy_5fin_5fhost_5fto_5fhost',['copy_in_host_to_host',['../classcutlass_1_1HostTensor.html#ae11229ea69460ca174c5e6f9815eb97f',1,'cutlass::HostTensor']]],
['copy_5fout_5fdevice_5fto_5fdevice',['copy_out_device_to_device',['../classcutlass_1_1HostTensor.html#ab7179440d39b0445113b30b7a460a1ec',1,'cutlass::HostTensor']]],
['copy_5fout_5fdevice_5fto_5fhost',['copy_out_device_to_host',['../classcutlass_1_1HostTensor.html#ab3051d2842b3aa3815e2ea5f53abfc2a',1,'cutlass::HostTensor']]],
['copy_5fout_5fhost_5fto_5fdevice',['copy_out_host_to_device',['../classcutlass_1_1HostTensor.html#abeefdb8bccb2d8d751fdb22fa7e8ef0c',1,'cutlass::HostTensor']]],
['copy_5fout_5fhost_5fto_5fhost',['copy_out_host_to_host',['../classcutlass_1_1HostTensor.html#a40da221db96cfda76ba5623856c66bf1',1,'cutlass::HostTensor']]],
['copy_5fto_5fdevice',['copy_to_device',['../namespacecutlass_1_1device__memory.html#adce1a75429c0eae9d34dc18944777325',1,'cutlass::device_memory']]],
['copy_5fto_5fhost',['copy_to_host',['../namespacecutlass_1_1device__memory.html#a5333f291105136d2e8e4c31329d93c31',1,'cutlass::device_memory']]],
['copysign',['copysign',['../namespacecutlass.html#ac42c217e2600fb741312b535c633bb76',1,'cutlass']]],
['core',['Core',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemv.html#a4a5d78877329cd922780fc31a6448ef0',1,'cutlass::gemm::kernel::DefaultGemv']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['core_5fio_2eh',['core_io.h',['../core__io_8h.html',1,'']]],
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
['cos',['cos',['../namespacecutlass.html#a2337866060023f87d4d821850738541f',1,'cutlass']]],
['count',['Count',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp_3_01ThreadblockShape__4433cc988100e98097a748d2670fb0fc.html#a037e7c6716020fa2297eee14ba9704b0',1,'cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, half_t >::Detail::Count()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp_3_01ThreadblockShape__52116c60c62f0fd520071558e42b814f.html#a26f942339b9c6844886b8d5967e07914',1,'cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, float >::Detail::Count()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileThreadMap.html#a0bd9c4b005f277eb40b9d2bdccdcb9e0',1,'cutlass::epilogue::threadblock::OutputTileThreadMap::Count()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileOptimalThreadMap.html#a94a7c6cfdb44e3c8d15b1f948dbebaaf',1,'cutlass::epilogue::threadblock::OutputTileOptimalThreadMap::Count()']]],
['crbegin',['crbegin',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#ab1813941489bef9563cc0bc3f647b2ca',1,'cutlass::Array< T, N, true >::crbegin()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a01b9f76c6052dc2467095b91c1ebe34e',1,'cutlass::Array< T, N, false >::crbegin()']]],
['crend',['crend',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a76e1b5d728b155f9d967a43c0cc3b0dd',1,'cutlass::Array< T, N, true >::crend()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#abbc436f18649c1578ef95eb501872094',1,'cutlass::Array< T, N, false >::crend()']]],
['cublas_5ftype',['cublas_type',['../structcutlass_1_1TypeTraits_3_01int8__t_01_4.html#ac801fb97ec8a1a8cce0dbab46a614eff',1,'cutlass::TypeTraits< int8_t >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01uint8__t_01_4.html#ae5edc866e5de8527b6ddf06c3844684b',1,'cutlass::TypeTraits< uint8_t >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01int_01_4.html#abe5b201de5b1ef7a4e23f5ab6ed06f4a',1,'cutlass::TypeTraits< int >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01unsigned_01_4.html#aeafbc657f1a9020e36bbe523a33990b5',1,'cutlass::TypeTraits< unsigned >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01int64__t_01_4.html#a24cf2f6d484f30a1b329c3f8c1fb573d',1,'cutlass::TypeTraits< int64_t >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01uint64__t_01_4.html#a9ef28cd1f430f25cdda594f060f4e718',1,'cutlass::TypeTraits< uint64_t >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01half__t_01_4.html#a0491882d302a1038f1bb3c3d09374bb4',1,'cutlass::TypeTraits< half_t >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01float_01_4.html#aa835af229fbe3c00ccc6ea164bb1eb62',1,'cutlass::TypeTraits< float >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01double_01_4.html#ae0e23f7459fa1586160ae47e151428ae',1,'cutlass::TypeTraits< double >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01half_01_4_01_4.html#afe1a23ad5e158fc64fac88bd6095602e',1,'cutlass::TypeTraits< complex< half > >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01half__t_01_4_01_4.html#a5ca73eeea32d33e33e8a98890a78593d',1,'cutlass::TypeTraits< complex< half_t > >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01float_01_4_01_4.html#a6885f2871ac12091946d8f9a833efc0e',1,'cutlass::TypeTraits< complex< float > >::cublas_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01double_01_4_01_4.html#a474db90f9990e15f86a822e6a226eeb7',1,'cutlass::TypeTraits< complex< double > >::cublas_type()']]],
['cuda_5fexception',['cuda_exception',['../classcutlass_1_1cuda__exception.html#acbfb99c9979ce7d24fe774459c66cfa5',1,'cutlass::cuda_exception']]],
['cuda_5fexception',['cuda_exception',['../classcutlass_1_1cuda__exception.html',1,'cutlass']]],
['cuda_5fldmatrix_5factivated',['CUDA_LDMATRIX_ACTIVATED',['../memory__sm75_8h.html#a29d596a2e497f5f641e9fbacb3965a7a',1,'memory_sm75.h']]],
['cuda_5fldmatrix_5fenabled',['CUDA_LDMATRIX_ENABLED',['../memory__sm75_8h.html#a95ee2a0203757d1d2fb1ea2d2bb05292',1,'memory_sm75.h']]],
['cuda_5fldmatrix_5fsupported',['CUDA_LDMATRIX_SUPPORTED',['../memory__sm75_8h.html#abac6d4ac2f9ce3fff90851a5156836ce',1,'memory_sm75.h']]],
['cuda_5flog',['CUDA_LOG',['../include_2cutlass_2util_2debug_8h.html#a27e3466bcf1ec7fda4f6f95aa0a51177',1,'CUDA_LOG(): debug.h'],['../tools_2util_2include_2cutlass_2util_2debug_8h.html#a27e3466bcf1ec7fda4f6f95aa0a51177',1,'CUDA_LOG(): debug.h']]],
['cuda_5flog_5fdebug',['CUDA_LOG_DEBUG',['../include_2cutlass_2util_2debug_8h.html#a8d6986db819719ada8b29d53dfc104a6',1,'CUDA_LOG_DEBUG(): debug.h'],['../tools_2util_2include_2cutlass_2util_2debug_8h.html#a8d6986db819719ada8b29d53dfc104a6',1,'CUDA_LOG_DEBUG(): debug.h']]],
['cuda_5fnvvm_5fget_5fshared_5fpointer_5fenabled',['CUDA_NVVM_GET_SHARED_POINTER_ENABLED',['../memory__sm75_8h.html#a4eee9c4995d720384992aabe5c6d6bc7',1,'memory_sm75.h']]],
['cuda_5fnvvm_5fget_5fshared_5fpointer_5fsupported',['CUDA_NVVM_GET_SHARED_POINTER_SUPPORTED',['../memory__sm75_8h.html#a46f2866d35a895ba34326282b8acfaa6',1,'memory_sm75.h']]],
['cuda_5fperror',['CUDA_PERROR',['../include_2cutlass_2util_2debug_8h.html#aed8337b88d71895f95f8980ef0b3a50b',1,'CUDA_PERROR(): debug.h'],['../tools_2util_2include_2cutlass_2util_2debug_8h.html#aed8337b88d71895f95f8980ef0b3a50b',1,'CUDA_PERROR(): debug.h']]],
['cuda_5fperror_5fdebug',['CUDA_PERROR_DEBUG',['../include_2cutlass_2util_2debug_8h.html#a36436f5408940a47ac5cdfc9b31648db',1,'CUDA_PERROR_DEBUG(): debug.h'],['../tools_2util_2include_2cutlass_2util_2debug_8h.html#a36436f5408940a47ac5cdfc9b31648db',1,'CUDA_PERROR_DEBUG(): debug.h']]],
['cuda_5fperror_5fexit',['CUDA_PERROR_EXIT',['../include_2cutlass_2util_2debug_8h.html#a002632ff687c83cff0484476be401f05',1,'CUDA_PERROR_EXIT(): debug.h'],['../tools_2util_2include_2cutlass_2util_2debug_8h.html#a002632ff687c83cff0484476be401f05',1,'CUDA_PERROR_EXIT(): debug.h']]],
['cuda_5fperror_5fimpl',['cuda_perror_impl',['../namespacecutlass.html#a6d3dfeb642a2ce3d5f52243fe48f89cc',1,'cutlass::cuda_perror_impl()'],['../tools_2util_2include_2cutlass_2util_2debug_8h.html#aed67644b6ffaa6d88a2efa09fcaafdce',1,'cuda_perror_impl(): debug.h']]],
['cudaerror',['cudaError',['../classcutlass_1_1cuda__exception.html#a5e2363c04ed0a43e244b274cb21aebf1',1,'cutlass::cuda_exception']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['cutlass',['cutlass',['../namespacecutlass.html',1,'']]],
['cutlass_2eh',['cutlass.h',['../cutlass_8h.html',1,'']]],
['cutlass_5fassert',['CUTLASS_ASSERT',['../cutlass_8h.html#a0159b8e4cd578881a1ccfd0921516af7',1,'cutlass.h']]],
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
['cutlass_5fenable_5ff16c',['CUTLASS_ENABLE_F16C',['../half_8h.html#a57f123df3fd68693c04e71072f870c3a',1,'half.h']]],
['cutlass_5fenable_5ftensor_5fcore_5fmma',['CUTLASS_ENABLE_TENSOR_CORE_MMA',['../cutlass_8h.html#a60467e248cf2879c0531d122a3e2a32d',1,'cutlass.h']]],
['cutlass_5fgemm_5floop',['CUTLASS_GEMM_LOOP',['../cutlass_8h.html#a8e18ced39c05ab3304bb4fcdc0cc9f71',1,'cutlass.h']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['cutlass_5fhost_5fdevice',['CUTLASS_HOST_DEVICE',['../cutlass_8h.html#a28c2443a142676d3d71effdae1a986b1',1,'cutlass.h']]],
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
['cutlass_5fpragma_5fno_5funroll',['CUTLASS_PRAGMA_NO_UNROLL',['../cutlass_8h.html#adb3bc73d74b4a4bf13099d5696db3352',1,'cutlass.h']]],
['cutlass_5fpragma_5funroll',['CUTLASS_PRAGMA_UNROLL',['../cutlass_8h.html#a4b1c9f25ab6eaa25e1f2258dd63e6ce4',1,'cutlass.h']]],
['cutlass_5fsimt_5fepilogue_5fuse_5fscalar_5fstores',['CUTLASS_SIMT_EPILOGUE_USE_SCALAR_STORES',['../tile__iterator__simt_8h.html#af5392199c6e71a31335abd0bb1d9ba36',1,'tile_iterator_simt.h']]],
['debug',['debug',['../namespacecutlass_1_1debug.html',1,'cutlass']]],
['detail',['detail',['../namespacecutlass_1_1gemm_1_1threadblock_1_1detail.html',1,'cutlass::gemm::threadblock']]],
['detail',['detail',['../namespacecutlass_1_1reference_1_1device_1_1kernel_1_1detail.html',1,'cutlass::reference::device::kernel']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['detail',['detail',['../namespacecutlass_1_1detail.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
['detail',['detail',['../namespacecutlass_1_1reference_1_1device_1_1detail.html',1,'cutlass::reference::device']]],
['detail',['detail',['../namespacecutlass_1_1reference_1_1detail.html',1,'cutlass::reference']]],
['detail',['detail',['../namespacecutlass_1_1reference_1_1host_1_1detail.html',1,'cutlass::reference::host']]],
['detail',['detail',['../namespacecutlass_1_1gemm_1_1kernel_1_1detail.html',1,'cutlass::gemm::kernel']]],
['detail',['detail',['../namespacecutlass_1_1gemm_1_1thread_1_1detail.html',1,'cutlass::gemm::thread']]],
['detail',['detail',['../namespacecutlass_1_1epilogue_1_1threadblock_1_1detail.html',1,'cutlass::epilogue::threadblock']]],
['device',['device',['../namespacecutlass_1_1gemm_1_1device.html',1,'cutlass::gemm']]],
['device',['device',['../namespacecutlass_1_1reference_1_1device.html',1,'cutlass::reference']]],
['device_5fmemory',['device_memory',['../namespacecutlass_1_1device__memory.html',1,'cutlass']]],
['epilogue',['epilogue',['../namespacecutlass_1_1epilogue.html',1,'cutlass']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['gemm',['gemm',['../namespacecutlass_1_1gemm.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
['host',['host',['../namespacecutlass_1_1reference_1_1host.html',1,'cutlass::reference']]],
['kernel',['kernel',['../namespacecutlass_1_1reduction_1_1kernel.html',1,'cutlass::reduction']]],
['kernel',['kernel',['../namespacecutlass_1_1gemm_1_1kernel.html',1,'cutlass::gemm']]],
['kernel',['kernel',['../namespacecutlass_1_1reference_1_1device_1_1kernel.html',1,'cutlass::reference::device']]],
['layout',['layout',['../namespacecutlass_1_1layout.html',1,'cutlass']]],
['library',['library',['../namespacecutlass_1_1library.html',1,'cutlass']]],
Updating Doxygen docs
2018-10-27 05:54:58 +08:00
['platform',['platform',['../namespacecutlass_1_1platform.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
['reduction',['reduction',['../namespacecutlass_1_1reduction.html',1,'cutlass']]],
['reference',['reference',['../namespacecutlass_1_1reference.html',1,'cutlass']]],
['thread',['thread',['../namespacecutlass_1_1gemm_1_1thread.html',1,'cutlass::gemm']]],
['thread',['thread',['../namespacecutlass_1_1epilogue_1_1thread.html',1,'cutlass::epilogue']]],
['thread',['thread',['../namespacecutlass_1_1reduction_1_1thread.html',1,'cutlass::reduction']]],
['thread',['thread',['../namespacecutlass_1_1transform_1_1thread.html',1,'cutlass::transform']]],
['thread',['thread',['../namespacecutlass_1_1reference_1_1device_1_1thread.html',1,'cutlass::reference::device']]],
['thread',['thread',['../namespacecutlass_1_1thread.html',1,'cutlass']]],
['threadblock',['threadblock',['../namespacecutlass_1_1epilogue_1_1threadblock.html',1,'cutlass::epilogue']]],
['threadblock',['threadblock',['../namespacecutlass_1_1transform_1_1threadblock.html',1,'cutlass::transform']]],
['threadblock',['threadblock',['../namespacecutlass_1_1gemm_1_1threadblock.html',1,'cutlass::gemm']]],
['transform',['transform',['../namespacecutlass_1_1transform.html',1,'cutlass']]],
['warp',['warp',['../namespacecutlass_1_1gemm_1_1warp.html',1,'cutlass::gemm']]],
['warp',['warp',['../namespacecutlass_1_1epilogue_1_1warp.html',1,'cutlass::epilogue']]]
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
];
Reference in New Issue Copy Permalink