Function _mm512_mulhrs_epi16

pub unsafe fn _mm512_mulhrs_epi16(a: __m512i, b: __m512i) -> __m512i

🔬This is a nightly-only experimental API. (stdarch_x86_avx512 #111137)

Available on (x86 or x86-64) and target feature avx512bw and x86 only.

Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst.

Intel’s documentation