# 1.27.0[−][src]Function core::arch::x86_64::_mm_sad_epu8

pub unsafe fn _mm_sad_epu8(a: __m128i, b: __m128i) -> __m128i

This is supported on

**x86-64 and target feature**only.`sse2`

Sum the absolute differences of packed unsigned 8-bit integers.

Computes the absolute differences of packed unsigned 8-bit integers in `a`

and `b`

, then horizontally sum each consecutive 8 differences to produce
two unsigned 16-bit integers, and pack these unsigned 16-bit integers in
the low 16 bits of 64-bit elements returned.