Function core::arch::x86_64::_mm_blendv_epi8

pub unsafe fn _mm_blendv_epi8(a: __m128i, b: __m128i, mask: __m128i) -> __m128i

This is supported on x86-64 and target feature sse4.1 only.

Blend packed 8-bit integers from a and b using mask

The high bit of each corresponding mask byte determines the selection. If the high bit is set the element of a is selected. The element of b is selected otherwise.

Intel’s documentation