DLTcollab /sse2neon
从Intel SSE intrinsics到Arm/Aarch 64 NEON实施的翻译器
C++1539
neon-intrinsics 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
从Intel SSE intrinsics到Arm/Aarch 64 NEON实施的翻译器
Actually-sparse dynamic training for PyTorch. CPU-native, Apple Silicon first. Pluggable routers, drop-in SparseLinear.
Optimizing convolution function using ARM's NEON Intrinsics
Extended morphological filters using ARM SIMD instructions for Python on Raspberry Pi (Deep networks for Gaussian denoising and image completion are included.)
exercise in SIMD-coding