[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl
Like NVIDIA/thrust, 0 likes 0 Bookmark NVIDIA/thrust, 0 bookmarks 0 This is a set of simple programs that can be used to explore the features of a parallel platform.
Like ParRes/Kernels, 0 likes 0 Bookmark ParRes/Kernels, 0 bookmarks 0 Playing around "Less Slow" coding practices in C++ 20, C, CUDA, PTX, & Assembly, from numerics & SIMD to coroutines, ranges, exception handling, networking and user-space IO
Like ashvardanian/less_slow.cpp, 0 likes 0 Bookmark ashvardanian/less_slow.cpp, 0 bookmarks 0 Mixed-precision numerics benchmarks in Rust and Python - covering GEMMs, SYRKs, DOTs, and higher-level BLAS and LAPACK-style functionality
Like ashvardanian/NumWars, 0 likes 0 Bookmark ashvardanian/NumWars, 0 bookmarks 0 A curated list of awesome SIMD frameworks, libraries and software
Like awesome-simd/awesome-simd, 0 likes 0 Bookmark awesome-simd/awesome-simd, 0 bookmarks 0 Fastest kernels written from scratch
Like pranjalssh/fast.cu, 0 likes 0 Bookmark pranjalssh/fast.cu, 0 bookmarks 0 CUDA Core Compute Libraries
Like NVIDIA/cccl, 0 likes 0 Bookmark NVIDIA/cccl, 0 bookmarks 0 We aim to redefine Data Parallel libraries portabiliy, performance, programability and maintainability, by using C++ standard features, instead of creating new compilers.
Like Libraries-Openly-Fused/FusedKernelLibrary, 0 likes 0 Bookmark Libraries-Openly-Fused/FusedKernelLibrary, 0 bookmarks 0 
