Function serde::lib::core::arch::x86_64::_mm512_cvtsh_h

pub unsafe fn _mm512_cvtsh_h(a: __m512h) -> f16

🔬This is a nightly-only experimental API. (stdarch_x86_avx512_f16)

Available on x86-64 only.

Copy the lower half-precision (16-bit) floating-point element from a to dst.

Intel’s documentation