Function core::arch::x86::_mm256_permute2x128_si256

pub unsafe fn _mm256_permute2x128_si256(
    a: __m256i, 
    b: __m256i, 
    imm8: i32
) -> __m256i

This is supported on x86 and target feature avx2 only.

Shuffle 128-bits of integer data selected by imm8 from a and b.

Intel's documentation