I've made minor changes to make it run on apple silicon. for this I've added sse2neon.h which translates x86 intrinsics to arm neon instructions, changes were made with defines so they are only valid for apple silicon and everything else is (hopefully) preserved.
I've made minor changes to make it run on apple silicon. for this I've added sse2neon.h which translates x86 intrinsics to arm neon instructions, changes were made with defines so they are only valid for apple silicon and everything else is (hopefully) preserved.