Function _mm256_blend_ps

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

Available on (x86 or x86-64) and target feature avx and x86 only.

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

Intel’s documentation