[−][src]Function safe_arch::sub_saturating_i8_m256i

#[must_use]pub fn sub_saturating_i8_m256i(a: m256i, b: m256i) -> m256i
This is supported with target feature avx2 only.

Lanewise saturating a - b with lanes as i8.

let a = m256i::from([126_i8; 32]);
let b = m256i::from([125_i8; 32]);
let c: [i8; 32] = sub_saturating_i8_m256i(a, b).into();
assert_eq!(c, [1_i8; 32]);