Function core::arch::x86_64::_mm256_cvtepu16_epi32

pub unsafe fn _mm256_cvtepu16_epi32(a: __m128i) -> __m256i

This is supported on x86-64 and target feature avx2 only.

Zeroes extend packed unsigned 16-bit integers in a to packed 32-bit integers, and stores the results in dst.

Intel’s documentation