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.
19 lines
6.0 KiB
JavaScript
19 lines
6.0 KiB
JavaScript
var searchData=
|
|
[
|
|
['b',['B',['../structcutlass_1_1library_1_1GemmDescription.html#ad6117aecf9e4d22862e621114e95cccf',1,'cutlass::library::GemmDescription::B()'],['../structcutlass_1_1library_1_1GemmArguments.html#ae3b1c625d32bf5cbdbd4d2f520145efc',1,'cutlass::library::GemmArguments::B()'],['../structcutlass_1_1library_1_1GemmArrayArguments.html#a0c3d185b52998f836fbf4c0d27c6e497',1,'cutlass::library::GemmArrayArguments::B()']]],
|
|
['b_5ftile',['B_tile',['../structcutlass_1_1reference_1_1device_1_1thread_1_1Gemm.html#a5329ece817a4d471dfee042a4eb6f7bd',1,'cutlass::reference::device::thread::Gemm']]],
|
|
['batch_5fcount',['batch_count',['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_1_1Arguments.html#ac99ca8f9d8a0053e647a6c99b018bda5',1,'cutlass::gemm::device::GemmBatched::Arguments::batch_count()'],['../structcutlass_1_1gemm_1_1device_1_1GemmBatched_3_01ElementA___00_01LayoutA___00_01ElementB___00_213d78696663f4231cd52c6a277c60e5.html#adb66f3083f56c15578b139b7935452b5',1,'cutlass::gemm::device::GemmBatched< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, layout::ColumnMajor, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ThreadblockSwizzle_, Stages, AlignmentA, AlignmentB, Operator_ >::Arguments::batch_count()'],['../structcutlass_1_1gemm_1_1kernel_1_1GemmBatched_1_1Params.html#a7ed96fc1c9cba288ec807736a3ed96e7',1,'cutlass::gemm::kernel::GemmBatched::Params::batch_count()'],['../structcutlass_1_1library_1_1GemmBatchedConfiguration.html#ae6cc3b877a073bedb8e4d1c91423b0f5',1,'cutlass::library::GemmBatchedConfiguration::batch_count()'],['../structcutlass_1_1library_1_1GemmArrayConfiguration.html#a10fe15d9179998530d3fdd86c78d4a15',1,'cutlass::library::GemmArrayConfiguration::batch_count()']]],
|
|
['batch_5fstride_5fa',['batch_stride_A',['../structcutlass_1_1library_1_1GemmBatchedConfiguration.html#a7bea2035164b174c45a7589d8132f2af',1,'cutlass::library::GemmBatchedConfiguration']]],
|
|
['batch_5fstride_5fb',['batch_stride_B',['../structcutlass_1_1library_1_1GemmBatchedConfiguration.html#ac85cb497652f997f8fa3143be70ac77a',1,'cutlass::library::GemmBatchedConfiguration']]],
|
|
['batch_5fstride_5fc',['batch_stride_C',['../structcutlass_1_1library_1_1GemmBatchedConfiguration.html#a1225f9ce96f9819d6d0cfde7a664b921',1,'cutlass::library::GemmBatchedConfiguration']]],
|
|
['batch_5fstride_5fd',['batch_stride_D',['../structcutlass_1_1library_1_1GemmBatchedConfiguration.html#aa0b8603417007880a9882774f0f5c988',1,'cutlass::library::GemmBatchedConfiguration']]],
|
|
['batched_5fstride_5fa',['batched_stride_A',['../structcutlass_1_1library_1_1GemmPlanarComplexBatchedConfiguration.html#a68643eb068634c6f96719d871363bc09',1,'cutlass::library::GemmPlanarComplexBatchedConfiguration']]],
|
|
['batched_5fstride_5fb',['batched_stride_B',['../structcutlass_1_1library_1_1GemmPlanarComplexBatchedConfiguration.html#a0472cd678eeb71d5ffd42fdcab5af409',1,'cutlass::library::GemmPlanarComplexBatchedConfiguration']]],
|
|
['batched_5fstride_5fc',['batched_stride_C',['../structcutlass_1_1library_1_1GemmPlanarComplexBatchedConfiguration.html#ab3519e652b982d3b3fdf4c788342bda9',1,'cutlass::library::GemmPlanarComplexBatchedConfiguration']]],
|
|
['batched_5fstride_5fd',['batched_stride_D',['../structcutlass_1_1library_1_1GemmPlanarComplexBatchedConfiguration.html#a7245398f9aa9754f6501edf95a8a3ab5',1,'cutlass::library::GemmPlanarComplexBatchedConfiguration']]],
|
|
['beta',['beta',['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#a9677cb04e23e9afa9fcdc3f34074bb56',1,'cutlass::epilogue::thread::LinearCombination::Params::beta()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#a11eb2330d28b470366032dd8f549fe33',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::beta()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#a7f3cb135884b5ef89bdef997159a3844',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::beta()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#af607bd78ed05e98af8dfe0c413e25091',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::beta()'],['../structcutlass_1_1gemm_1_1kernel_1_1detail_1_1GemvBatchedStridedEpilogueScaling.html#abcd99b63173e4330a75558e78a756296',1,'cutlass::gemm::kernel::detail::GemvBatchedStridedEpilogueScaling::beta()'],['../structcutlass_1_1reduction_1_1BatchedReductionTraits_1_1Params.html#a805f78cae27c3305c988f251207d85f7',1,'cutlass::reduction::BatchedReductionTraits::Params::beta()'],['../structcutlass_1_1library_1_1GemmArguments.html#a91f68b30afc142ea697707fa752c9526',1,'cutlass::library::GemmArguments::beta()'],['../structcutlass_1_1library_1_1GemmArrayArguments.html#ac84f31989db6018f465019cf81f83978',1,'cutlass::library::GemmArrayArguments::beta()']]],
|
|
['beta_5fptr',['beta_ptr',['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombination_1_1Params.html#a01f730dac9a4500cb857bf4ca272bc7b',1,'cutlass::epilogue::thread::LinearCombination::Params::beta_ptr()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationClamp_1_1Params.html#adae7ef1a432b24d148df0662954b5bd0',1,'cutlass::epilogue::thread::LinearCombinationClamp::Params::beta_ptr()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_1_1Params.html#a2dfa5dc3c851915d39d27bf6b4cc68e6',1,'cutlass::epilogue::thread::LinearCombinationRelu::Params::beta_ptr()'],['../structcutlass_1_1epilogue_1_1thread_1_1LinearCombinationRelu_3_01ElementOutput___00_01Count_00_00274a94522c46cd041d0b10d484e2ef3.html#a3b26637eb910d79d8ae6a79011ca85e3',1,'cutlass::epilogue::thread::LinearCombinationRelu< ElementOutput_, Count, int, float, Round >::Params::beta_ptr()']]],
|
|
['block',['block',['../structcutlass_1_1KernelLaunchConfiguration.html#a09535026bf08f94c6940c358d95d1edd',1,'cutlass::KernelLaunchConfiguration']]],
|
|
['byte',['byte',['../structcutlass_1_1platform_1_1alignment__of_1_1pad.html#a86f075f91b80918e968951713430f0b4',1,'cutlass::platform::alignment_of::pad']]]
|
|
];
|