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.
This commit is contained in:
@@ -1,13 +1,9 @@
|
||||
var searchData=
|
||||
[
|
||||
['params',['params',['../structcutlass_1_1gemm_1_1Gemm.html#a3c292637ab0ec8e73856d0cf6efb6da2',1,'cutlass::gemm::Gemm::params()'],['../structcutlass_1_1gemm_1_1GemmEpilogue.html#a81b028a18df51d3caa1b0ba0c990e362',1,'cutlass::gemm::GemmEpilogue::params()'],['../structcutlass_1_1gemm_1_1GlobalLoadStream.html#ac8ff1a3e10b25c212cd3cf5ed997fc0e',1,'cutlass::gemm::GlobalLoadStream::params()'],['../structcutlass_1_1gemm_1_1GemmGlobalIteratorAb.html#ab8c79cb1a8157dd00429c93cb4a41322',1,'cutlass::gemm::GemmGlobalIteratorAb::params()'],['../structcutlass_1_1gemm_1_1GemmGlobalIteratorCd.html#ac368b1ea1c5ad2209a6ac6bec597600f',1,'cutlass::gemm::GemmGlobalIteratorCd::params()'],['../structcutlass_1_1gemm_1_1LinearScaling.html#a7bbf90dc0938698a0fa22468f9df315d',1,'cutlass::gemm::LinearScaling::params()'],['../structcutlass_1_1reduction_1_1BatchedReduction.html#a9c9d8378c735597f39927c6ab32519ef',1,'cutlass::reduction::BatchedReduction::params()'],['../structcutlass_1_1TileLoadIterator.html#a5561e676148200c2fc85a603847cc596',1,'cutlass::TileLoadIterator::params()'],['../structcutlass_1_1TileStoreIterator.html#a64e0c9fb1f7d8fcc77bf0a915445ee6d',1,'cutlass::TileStoreIterator::params()']]],
|
||||
['partitionk_5frange',['partitionK_range',['../structcutlass_1_1gemm_1_1GemmTraits_1_1Params.html#a44b9a0d6210561d3b0d538b2c0a38886',1,'cutlass::gemm::GemmTraits::Params']]],
|
||||
['pointer',['pointer',['../structcutlass_1_1FragmentIterator.html#af667793926cdb24d701eb75e0345bbd6',1,'cutlass::FragmentIterator::pointer()'],['../structcutlass_1_1FragmentConstIterator.html#aee37f8ea06127b94a304bb776945509b',1,'cutlass::FragmentConstIterator::pointer()'],['../structcutlass_1_1gemm_1_1GemmGlobalIteratorCd_1_1Params.html#ad764f98e770d4685006e6888214dcd4d',1,'cutlass::gemm::GemmGlobalIteratorCd::Params::pointer()'],['../structcutlass_1_1TileLoadIterator_1_1Params.html#a388d464c35cc1bcd509d22937f38dcf6',1,'cutlass::TileLoadIterator::Params::pointer()'],['../structcutlass_1_1TileStoreIterator_1_1Params.html#a9e50043acd3b851cce169310a04c6827',1,'cutlass::TileStoreIterator::Params::pointer()']]],
|
||||
['pointers',['pointers',['../structcutlass_1_1TensorRefArray.html#ae322501a04b0008e5db4f7fccb6e903e',1,'cutlass::TensorRefArray']]],
|
||||
['predicate_5finc_5fadvance',['predicate_inc_advance',['../structcutlass_1_1gemm_1_1GemmGlobalIteratorCd_1_1Params.html#a2b5d2b02d241e89677c41eb658ace129',1,'cutlass::gemm::GemmGlobalIteratorCd::Params']]],
|
||||
['predicate_5finc_5fh',['predicate_inc_h',['../structcutlass_1_1gemm_1_1GemmGlobalIteratorCd_1_1Params.html#a36afe18f94aacd0746c8946866371d3c',1,'cutlass::gemm::GemmGlobalIteratorCd::Params']]],
|
||||
['predicate_5foffset',['predicate_offset',['../structcutlass_1_1gemm_1_1GemmGlobalIteratorCd_1_1Params.html#a3e8f6cf08d23318f3e3263b55cf3b84a',1,'cutlass::gemm::GemmGlobalIteratorCd::Params']]],
|
||||
['predicates',['predicates',['../structcutlass_1_1gemm_1_1GemmGlobalIteratorAb.html#af323c9db74f0de3376edd35eb377bc9c',1,'cutlass::gemm::GemmGlobalIteratorAb::predicates()'],['../structcutlass_1_1gemm_1_1GemmGlobalIteratorCd.html#ad23e6224e37ec1d13dc237ce8ec6e977',1,'cutlass::gemm::GemmGlobalIteratorCd::predicates()'],['../structcutlass_1_1PredicatedTileLoadStream.html#a8f8c7c54dba8a0c8cd0799b89130564f',1,'cutlass::PredicatedTileLoadStream::predicates()'],['../structcutlass_1_1PredicatedTileStoreStream.html#a2ecdfa152dcf7b3acaf8767f3e69cfbe',1,'cutlass::PredicatedTileStoreStream::predicates()']]],
|
||||
['problem_5fsize',['problem_size',['../structcutlass_1_1gemm_1_1SplitkPIGemmTraits_1_1Params.html#a542a371bf39a9e58889d78e782af3aae',1,'cutlass::gemm::SplitkPIGemmTraits::Params::problem_size()'],['../structcutlass_1_1gemm_1_1GemmDesc.html#a52a5538b1b5208090417cf98d8735e3f',1,'cutlass::gemm::GemmDesc::problem_size()'],['../structcutlass_1_1gemm_1_1GemmEpilogue.html#a6bea57249e3645a4b08a11619cb1687e',1,'cutlass::gemm::GemmEpilogue::problem_size()'],['../structcutlass_1_1gemm_1_1GemmTraits_1_1Params.html#af2233a6ebf39788e27f051f8c614ab90',1,'cutlass::gemm::GemmTraits::Params::problem_size()'],['../structcutlass_1_1reduction_1_1BatchedReductionTraits_1_1Params.html#adbd0cf20c4f7033016d1b8fdaca6aeae',1,'cutlass::reduction::BatchedReductionTraits::Params::problem_size()']]],
|
||||
['problem_5fsize_5finitialized',['problem_size_initialized',['../structcutlass_1_1gemm_1_1SplitkPIGemmTraits_1_1Params.html#a966f73ad90754f53eed5faf68fc77d87',1,'cutlass::gemm::SplitkPIGemmTraits::Params']]]
|
||||
['opcode_5fclass',['opcode_class',['../structcutlass_1_1library_1_1MathInstructionDescription.html#a71a323433c2c1df305e5597097b882c7',1,'cutlass::library::MathInstructionDescription']]],
|
||||
['operand_5fa',['operand_A',['../classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_1_1SharedStorage.html#a5533d8fe7815988b669237fad934f1ff',1,'cutlass::gemm::threadblock::MmaBase::SharedStorage']]],
|
||||
['operand_5fb',['operand_B',['../classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_1_1SharedStorage.html#a09be4dd0e90ad9e14ec284842e772cd5',1,'cutlass::gemm::threadblock::MmaBase::SharedStorage']]],
|
||||
['other',['other',['../structcutlass_1_1reference_1_1device_1_1detail_1_1TensorFillDiagonalFunc_1_1Params.html#a4b44e8cc5d91ef6e388a17a741ca130a',1,'cutlass::reference::device::detail::TensorFillDiagonalFunc::Params::other()'],['../structcutlass_1_1reference_1_1device_1_1detail_1_1TensorUpdateOffDiagonalFunc_1_1Params.html#a38c69fb4480004c98d1df6386b2200ce',1,'cutlass::reference::device::detail::TensorUpdateOffDiagonalFunc::Params::other()'],['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorFillDiagonalFunc.html#ab5fdecc2fd8df736bf4efe884a8e873e',1,'cutlass::reference::host::detail::TensorFillDiagonalFunc::other()'],['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorUpdateOffDiagonalFunc.html#a05cc631b27ee842d78b48a4a1a16b943',1,'cutlass::reference::host::detail::TensorUpdateOffDiagonalFunc::other()']]],
|
||||
['output',['output',['../structcutlass_1_1reduction_1_1kernel_1_1ReduceSplitK_1_1Params.html#ac4dbbbd4c98f1be716d5d1d739953e17',1,'cutlass::reduction::kernel::ReduceSplitK::Params']]],
|
||||
['output_5fop',['output_op',['../structcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp_1_1Params.html#a0c230d7407585f6cd6221ebcd5966a0d',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp::Params::output_op()'],['../structcutlass_1_1gemm_1_1kernel_1_1Gemm_1_1Params.html#a9f492a3d44ce667cb807fe6b97c33ab9',1,'cutlass::gemm::kernel::Gemm::Params::output_op()'],['../structcutlass_1_1gemm_1_1kernel_1_1GemmSplitKParallel_1_1Params.html#a5ee295472b6ada3e57fa0442b8cffd72',1,'cutlass::gemm::kernel::GemmSplitKParallel::Params::output_op()']]]
|
||||
];
|
||||
|
||||
Reference in New Issue
Block a user