Function core::arch::x86_64::_mm256_permute2f128_ps

pub unsafe fn _mm256_permute2f128_ps(
    a: __m256, 
    b: __m256, 
    const IMM8: i32
) -> __m256

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

Shuffles 256 bits (composed of 8 packed single-precision (32-bit) floating-point elements) selected by imm8 from a and b.

Intel’s documentation