Function core::arch::x86_64::_mm256_blend_ps

pub unsafe fn _mm256_blend_ps<const IMM8: i32>(a: __m256, b: __m256) -> __m256

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

Blends packed single-precision (32-bit) floating-point elements from a and b using control mask imm8.

Intel’s documentation