mirror of
https://mirror.skon.top/https://github.com/FFmpeg/FFmpeg
synced 2026-04-22 05:40:27 +08:00
~4x faster than the C version. The shuffles in the 15pt dim1 are seriously expensive. Not happy with it, but I'm contempt. Can be easily converted to pure AVX by removing all vpermpd/vpermps instructions.