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.
10 lines
2.4 KiB
JavaScript
10 lines
2.4 KiB
JavaScript
var searchData=
|
|
[
|
|
['warpsize',['WarpSize',['../structcutlass_1_1gemm_1_1warp_1_1WarpSize.html',1,'cutlass::gemm::warp']]],
|
|
['wmma_3c_20shape_5f_2c_20cutlass_3a_3ahalf_5ft_2c_20layouta_5f_2c_20cutlass_3a_3ahalf_5ft_2c_20layoutb_5f_2c_20elementc_5f_2c_20layoutc_5f_2c_20cutlass_3a_3aarch_3a_3aopmultiplyadd_20_3e',['Wmma< Shape_, cutlass::half_t, LayoutA_, cutlass::half_t, LayoutB_, ElementC_, LayoutC_, cutlass::arch::OpMultiplyAdd >',['../structcutlass_1_1arch_1_1Wmma_3_01Shape___00_01cutlass_1_1half__t_00_01LayoutA___00_01cutlass_1_84e30c8cc93eeb7ca02f651bd16d4c38.html',1,'cutlass::arch']]],
|
|
['wmma_3c_20shape_5f_2c_20cutlass_3a_3aint4b_5ft_2c_20layouta_5f_2c_20cutlass_3a_3aint4b_5ft_2c_20layoutb_5f_2c_20int32_5ft_2c_20layoutc_5f_2c_20cutlass_3a_3aarch_3a_3aopmultiplyadd_20_3e',['Wmma< Shape_, cutlass::int4b_t, LayoutA_, cutlass::int4b_t, LayoutB_, int32_t, LayoutC_, cutlass::arch::OpMultiplyAdd >',['../structcutlass_1_1arch_1_1Wmma_3_01Shape___00_01cutlass_1_1int4b__t_00_01LayoutA___00_01cutlass_16fd808a90b3cf9d7cfc99f30888ca3fe.html',1,'cutlass::arch']]],
|
|
['wmma_3c_20shape_5f_2c_20cutlass_3a_3auint1b_5ft_2c_20layouta_5f_2c_20cutlass_3a_3auint1b_5ft_2c_20layoutb_5f_2c_20int32_5ft_2c_20layoutc_5f_2c_20cutlass_3a_3aarch_3a_3aopxorpopc_20_3e',['Wmma< Shape_, cutlass::uint1b_t, LayoutA_, cutlass::uint1b_t, LayoutB_, int32_t, LayoutC_, cutlass::arch::OpXorPopc >',['../structcutlass_1_1arch_1_1Wmma_3_01Shape___00_01cutlass_1_1uint1b__t_00_01LayoutA___00_01cutlass_c80a7ea4d219cd9b13b560b493338028.html',1,'cutlass::arch']]],
|
|
['wmma_3c_20shape_5f_2c_20int8_5ft_2c_20layouta_5f_2c_20int8_5ft_2c_20layoutb_5f_2c_20int32_5ft_2c_20layoutc_5f_2c_20cutlass_3a_3aarch_3a_3aopmultiplyadd_20_3e',['Wmma< Shape_, int8_t, LayoutA_, int8_t, LayoutB_, int32_t, LayoutC_, cutlass::arch::OpMultiplyAdd >',['../structcutlass_1_1arch_1_1Wmma_3_01Shape___00_01int8__t_00_01LayoutA___00_01int8__t_00_01LayoutB_505c57bb6818a941dc16f00cf35a9ec0.html',1,'cutlass::arch']]],
|
|
['wmma_3c_20shape_5f_2c_20uint8_5ft_2c_20layouta_5f_2c_20uint8_5ft_2c_20layoutb_5f_2c_20int32_5ft_2c_20layoutc_5f_2c_20cutlass_3a_3aarch_3a_3aopmultiplyadd_20_3e',['Wmma< Shape_, uint8_t, LayoutA_, uint8_t, LayoutB_, int32_t, LayoutC_, cutlass::arch::OpMultiplyAdd >',['../structcutlass_1_1arch_1_1Wmma_3_01Shape___00_01uint8__t_00_01LayoutA___00_01uint8__t_00_01Layout219a464a1248ebfc37aa29bcb10cb1b0.html',1,'cutlass::arch']]]
|
|
];
|