squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
7e370c9637
cutlass/docs/search/functions_2.js

19 lines
6.4 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
['back',['back',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#aa193b8e73b93639f84224d1fea46330d',1,'cutlass::Array< T, N, true >::back()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a6c81a715431cf5a772c2273362df97fd',1,'cutlass::Array< T, N, true >::back() const '],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a693677ee48012a4d013d55741d38764e',1,'cutlass::Array< T, N, false >::back()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a2c1665d0eff4c1788b0a5a3bfa3bc63e',1,'cutlass::Array< T, N, false >::back() const ']]],
['batch',['batch',['../structcutlass_1_1gemm_1_1BatchedGemmCoord.html#a40582b341f6916b17105377a64743682',1,'cutlass::gemm::BatchedGemmCoord::batch() const '],['../structcutlass_1_1gemm_1_1BatchedGemmCoord.html#aac1b2c47cf91faeaaf6aa11e0a657c7b',1,'cutlass::gemm::BatchedGemmCoord::batch()']]],
['batchedgemm',['BatchedGemm',['../namespacecutlass_1_1reference_1_1device.html#aaa524d4e141cc8934eb9a981e1c89fc5',1,'cutlass::reference::device::BatchedGemm(gemm::GemmCoord problem_size, int batch_count, ScalarType alpha, TensorRefCollectionA const &tensor_a, TensorRefCollectionB const &tensor_b, ScalarType beta, TensorRefCollectionC &tensor_c, AccumulatorType initial_accum)'],['../namespacecutlass_1_1reference_1_1device.html#abbb24b1a372b793bf35320443c179875',1,'cutlass::reference::device::BatchedGemm(gemm::GemmCoord problem_size, int batch_count, ScalarType alpha, TensorRefCollectionA const &tensor_a, TensorRefCollectionB const &tensor_b, ScalarType beta, TensorRefCollectionC &tensor_c)'],['../namespacecutlass_1_1reference_1_1device_1_1kernel.html#a013cf9aa1c8f98ec2037f242284def7b',1,'cutlass::reference::device::kernel::BatchedGemm()'],['../namespacecutlass_1_1reference_1_1host.html#a2c1067fa5de91e2f48589120f62125c2',1,'cutlass::reference::host::BatchedGemm(gemm::GemmCoord problem_size, int batch_count, ScalarType alpha, TensorRefCollectionA const &tensor_a, TensorRefCollectionB const &tensor_b, ScalarType beta, TensorRefCollectionC &tensor_c, AccumulatorType initial_accum)'],['../namespacecutlass_1_1reference_1_1host.html#a1d0a79a48353119706ffa09d570c2182',1,'cutlass::reference::host::BatchedGemm(gemm::GemmCoord problem_size, int batch_count, ScalarType alpha, TensorRefCollectionA const &tensor_a, TensorRefCollectionB const &tensor_b, ScalarType beta, TensorRefCollectionC &tensor_c)']]],
['batchedgemmcoord',['BatchedGemmCoord',['../structcutlass_1_1gemm_1_1BatchedGemmCoord.html#accb2951e2bde391b49da9a3b7d46c672',1,'cutlass::gemm::BatchedGemmCoord::BatchedGemmCoord()'],['../structcutlass_1_1gemm_1_1BatchedGemmCoord.html#ae1065cdcd7d6d99f971cba5c2565fe7d',1,'cutlass::gemm::BatchedGemmCoord::BatchedGemmCoord(Base const &coord)'],['../structcutlass_1_1gemm_1_1BatchedGemmCoord.html#a8f943c218bb5681970d30422269f4675',1,'cutlass::gemm::BatchedGemmCoord::BatchedGemmCoord(Index m, Index n, Index k, Index b)']]],
Updating Doxygen docs
2018-10-27 05:54:58 +08:00
['batchedreduction',['BatchedReduction',['../structcutlass_1_1reduction_1_1BatchedReduction.html#a9d76da3dcf4d8ec0cfeb2134f73ea22b',1,'cutlass::reduction::BatchedReduction']]],
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
['begin',['begin',['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#acf5a84cce457d31be7d30c57ab52f64c',1,'cutlass::Array< T, N, true >::begin()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a6e9dbf4a486f07dc72dd5140a7628971',1,'cutlass::Array< T, N, false >::begin()'],['../structcutlass_1_1PredicateVector.html#a649045d8224514a4c28bcaf4b247b4a5',1,'cutlass::PredicateVector::begin()'],['../classcutlass_1_1library_1_1Manifest.html#aa8a131b4258bfda04fdba4449520c587',1,'cutlass::library::Manifest::begin()']]],
['bitcast',['bitcast',['../structcutlass_1_1half__t.html#acb746c82bd4dd496f79b7e611e3653dd',1,'cutlass::half_t']]],
['block_5fshape',['block_shape',['../classcutlass_1_1reduction_1_1kernel_1_1ReduceSplitK.html#af788ae48c72021b8ce49da15dfa72be3',1,'cutlass::reduction::kernel::ReduceSplitK']]],
['blockcompareequal',['BlockCompareEqual',['../namespacecutlass_1_1reference_1_1device_1_1kernel.html#a4595ede72eddace3c973c7f0f74b001d',1,'cutlass::reference::device::kernel::BlockCompareEqual()'],['../namespacecutlass_1_1reference_1_1device.html#aad19927d67f15b89e66560cb77f2a813',1,'cutlass::reference::device::BlockCompareEqual()']]],
['blockcomparerelativelyequal',['BlockCompareRelativelyEqual',['../namespacecutlass_1_1reference_1_1device_1_1kernel.html#a6da13fb683d56d6973af0a97a4023677',1,'cutlass::reference::device::kernel::BlockCompareRelativelyEqual()'],['../namespacecutlass_1_1reference_1_1device.html#a286d24a9faabc0be18f96e1069dca23e',1,'cutlass::reference::device::BlockCompareRelativelyEqual()']]],
['blockfillrandom',['BlockFillRandom',['../namespacecutlass_1_1reference_1_1device.html#af6b21c6d90a1bb3f10dffd0a4adb644a',1,'cutlass::reference::device::BlockFillRandom()'],['../namespacecutlass_1_1reference_1_1host.html#ae6171d78c959aefff277cec4cad8fdb3',1,'cutlass::reference::host::BlockFillRandom()']]],
['blockfillrandomgaussian',['BlockFillRandomGaussian',['../namespacecutlass_1_1reference_1_1device.html#a478e311bfbe901d167090032b6c28732',1,'cutlass::reference::device::BlockFillRandomGaussian()'],['../namespacecutlass_1_1reference_1_1host.html#a121079d5cb24dd0e0339cee552a854de',1,'cutlass::reference::host::BlockFillRandomGaussian()']]],
['blockfillrandomuniform',['BlockFillRandomUniform',['../namespacecutlass_1_1reference_1_1device.html#a6f7f618350cf975e261a4ee758650c66',1,'cutlass::reference::device::BlockFillRandomUniform()'],['../namespacecutlass_1_1reference_1_1host.html#a417152b59865d2ef6995ee2398bcea8d',1,'cutlass::reference::host::BlockFillRandomUniform()']]],
['blockfillsequential',['BlockFillSequential',['../namespacecutlass_1_1reference_1_1device.html#a2cf3ac0ae77e672e2af80f4820434cbe',1,'cutlass::reference::device::BlockFillSequential()'],['../namespacecutlass_1_1reference_1_1host.html#a1808624141976837e298340c9f6c0f6b',1,'cutlass::reference::host::BlockFillSequential()']]],
['blockforeach',['BlockForEach',['../structcutlass_1_1reference_1_1device_1_1BlockForEach.html#a161e212b9b7ddbac36888de97538e106',1,'cutlass::reference::device::BlockForEach::BlockForEach()'],['../structcutlass_1_1reference_1_1host_1_1BlockForEach.html#aa2e578397b5cd68214736c2437f92480',1,'cutlass::reference::host::BlockForEach::BlockForEach()'],['../namespacecutlass_1_1reference_1_1device_1_1kernel.html#a0100d78891f9e00e75453ef8dc24daa6',1,'cutlass::reference::device::kernel::BlockForEach()']]]
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
];
Reference in New Issue Copy Permalink