[][src]Function core::arch::x86_64::_mm_sad_pu8

pub unsafe fn _mm_sad_pu8(a: __m64, b: __m64) -> __m64
🔬 This is a nightly-only experimental API. (stdsimd #48556)
This is supported on x86-64 and target feature sse,mmx only.

Subtracts the corresponding 8-bit unsigned integer values of the two 64-bit vector operands and computes the absolute value for each of the difference. Then sum of the 8 absolute differences is written to the bits [15:0] of the destination; the remaining bits [63:16] are cleared.