Function core::arch::x86_64::_mm_blend_ps

pub unsafe fn _mm_blend_ps<const IMM4: i32>(a: __m128, b: __m128) -> __m128

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

Blend packed single-precision (32-bit) floating-point elements from a and b using mask IMM4

Intel’s documentation