fb335f6a5f
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.
17 lines
9.5 KiB
JavaScript
17 lines
9.5 KiB
JavaScript
var searchData=
|
|
[
|
|
['element_5foffset',['element_offset',['../classcutlass_1_1ConstSubbyteReference.html#a7ff8cfd6a308811ae197b0eb704bdc24',1,'cutlass::ConstSubbyteReference::element_offset()'],['../classcutlass_1_1SubbyteReference.html#a7183c6e7f6e1da815da827d789d012c6',1,'cutlass::SubbyteReference::element_offset()']]],
|
|
['empty',['empty',['../structcutlass_1_1AlignedBuffer.html#a37921fffef065c4da23ccc328db45f14',1,'cutlass::AlignedBuffer::empty()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a5d1028cb678773f861add6b47f13de78',1,'cutlass::Array< T, N, true >::empty()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a40829269d53d097b5b7bfce32e4afcc4',1,'cutlass::Array< T, N, false >::empty()']]],
|
|
['enable',['enable',['../structcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator_1_1Mask.html#a119c21a58cf4c627c9083412a44b9d2f',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::Mask::enable()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator_1_1Mask.html#acbd971f79b973257f09bacaa265f0520',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::Mask::enable()'],['../structcutlass_1_1PredicateVector.html#adfabd17462a21adf71e37b2dacd1f45f',1,'cutlass::PredicateVector::enable()']]],
|
|
['enable_5fmask',['enable_mask',['../classcutlass_1_1epilogue_1_1threadblock_1_1PredicatedTileIterator.html#a6a5a5722a000c06b769e58de1e1c3903',1,'cutlass::epilogue::threadblock::PredicatedTileIterator::enable_mask()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1InterleavedPredicatedTileIterator.html#a4d9f5f0439afd4f459ed22c2b0db9070',1,'cutlass::epilogue::threadblock::InterleavedPredicatedTileIterator::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen784a0e9da3f55064c47e5613791f51f7.html#af2c85cb702cfa80d347c90032fcb833c',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen89c687c583745a73cb485041911a4c4e.html#a5ca2322fdd7c5c26615d43918fa4549b',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen9838736ad62fae54213fbaf722a989ab.html#ab0a04a52f6575b32d639cc31c9683926',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemenab63a1e105bf37f6371516cb9e2c5a7a.html#ac8df5781301fd131f3d5363a40af1d1d',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator_3_01Shape___00_01Elemen809793e785fb4211888c6b4e5dcfcb39.html#a49e6b47b56849ddbe88e833f3c21ff61',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator< Shape_, Element_, layout::RowMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__1790abaa54a01f277d75766d5882fec8.html#aca915554af4fdd722ef59e0846778782',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__da632779aba661c0f4cfaaa78126b771.html#a712abf81c7e4f3b7ce68060afaa432b6',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileAccessIterator2dThreadTile_3_01Shape__7327fa15996bcb8502cdfcc192350fe1.html#ae3e559443dd5f78da8b73a0b35766f1a',1,'cutlass::transform::threadblock::PredicatedTileAccessIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessType_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00e7c2c404e7aedfe60ad56bb5571306a1.html#a9b108452c6733a2de76de611aab8caf6',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, AccessSize >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0068b3e874b5d93d11f0fa902c7f1d11d9.html#aeaaaa921a3fa27f9a181296c71c671e9',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, AccessSize >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___0041ea81994f8af0d4d071fdb9e66b5ff0.html#afed2a0c5cfb8f89aaf66a7acaa4e6568',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, AccessSize >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00f6b3a9dfab5e7c72d5233f7e5e6e3b9b.html#ae26a5a59ceb0def13f9717340b36a147',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::ColumnMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessSize >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator_3_01Shape___00_01Element___00d670f969180a8d182dffb356ebcc957e.html#ace4da5baffa2dac199449b90dc486414',1,'cutlass::transform::threadblock::PredicatedTileIterator< Shape_, Element_, layout::RowMajorInterleaved< InterleavedK >, AdvanceRank, ThreadMap_, AccessSize >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_017a517f3c73efd795ab05059cc9b111e1.html#aab5504906f1b3e4acf25db2c47869961',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_0165b39a630d10785a3558406f9adb99b9.html#a8f61201ee8e582be64e74c09e87ee36b',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::ColumnMajor, AdvanceRank, ThreadMap_, Transpose_ >::enable_mask()'],['../classcutlass_1_1transform_1_1threadblock_1_1PredicatedTileIterator2dThreadTile_3_01Shape___00_013671177d6219bfeb0e1b4dc4c1b5bf11.html#a7eaef0c562d8a25f5713fc1cffcc1ead',1,'cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::RowMajor, AdvanceRank, ThreadMap_, Transpose_ >::enable_mask()']]],
|
|
['end',['end',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a8e5c83ff2ad6bbfeb5ba0e3c04e3843a',1,'cutlass::Array< T, N, true >::end()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a80258d6b5e43ae529cd726f0d4292619',1,'cutlass::Array< T, N, false >::end()'],['../structcutlass_1_1PredicateVector.html#ad9493fc80fdc33330cc15641779cc275',1,'cutlass::PredicateVector::end()'],['../classcutlass_1_1library_1_1Manifest.html#aef12d421284b669a8fa8822e0c582146',1,'cutlass::library::Manifest::end()']]],
|
|
['epilogue',['epilogue',['../structcutlass_1_1reference_1_1device_1_1thread_1_1Gemm.html#ac5c8d7f3f2ddef533973433bf5c83d73',1,'cutlass::reference::device::thread::Gemm::epilogue()'],['../classcutlass_1_1epilogue_1_1threadblock_1_1Epilogue.html#a3f87787b4dc2c705fd30c4ac98b080cf',1,'cutlass::epilogue::threadblock::Epilogue::Epilogue()']]],
|
|
['epiloguebase',['EpilogueBase',['../classcutlass_1_1epilogue_1_1threadblock_1_1EpilogueBase.html#ac7ce30b261c1d1f9891e05a20850fa6d',1,'cutlass::epilogue::threadblock::EpilogueBase']]],
|
|
['epilogueworkspace',['EpilogueWorkspace',['../classcutlass_1_1epilogue_1_1EpilogueWorkspace.html#aeddb6d40413f06aea489f5d626717298',1,'cutlass::epilogue::EpilogueWorkspace']]],
|
|
['epsilon',['epsilon',['../structstd_1_1numeric__limits_3_01cutlass_1_1half__t_01_4.html#ab9fc3a009eaff0c922307f2780ee3fc0',1,'std::numeric_limits< cutlass::half_t >']]],
|
|
['exp',['exp',['../namespacecutlass.html#a05d95f26c93a6d956d770f140469ac07',1,'cutlass']]],
|
|
['exponent',['exponent',['../structcutlass_1_1half__t.html#a76ce79fa7b4e3e993465a50615eb046f',1,'cutlass::half_t']]],
|
|
['exponent_5fbiased',['exponent_biased',['../structcutlass_1_1half__t.html#aa4cc765866681df569fedd1439cf5477',1,'cutlass::half_t']]],
|
|
['extent',['extent',['../classcutlass_1_1TensorView.html#a7d3914dd5042c9c40be9e21a7b4e9ece',1,'cutlass::TensorView::extent() const '],['../classcutlass_1_1TensorView.html#a1bc72b40e616cbb86a306b8ef0be1575',1,'cutlass::TensorView::extent(int dim) const '],['../classcutlass_1_1thread_1_1Matrix.html#a3b19b3b7ceea1bcefe22155eb28643e8',1,'cutlass::thread::Matrix::extent()'],['../classcutlass_1_1HostTensor.html#af1264450c122c1853231fc64b35a47b8',1,'cutlass::HostTensor::extent() const '],['../classcutlass_1_1HostTensor.html#a8a947176a4ddab5b784c98a0f1896892',1,'cutlass::HostTensor::extent()']]]
|
|
];
|