Function core::arch::x86_64::_mm256_permute2f128_si256

pub unsafe fn _mm256_permute2f128_si256(
    a: __m256i, 
    b: __m256i, 
    imm8: i32
) -> __m256i

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

Shuffle 258-bits (composed of integer data) selected by imm8 from a and b.

Intel's documentation