Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 12/16/2022
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

<span class='option'>_mm256_sad_epu8</span>

Computes sum of absolute differences between extended packed unsigned values of two vectors. The corresponding Intel® AVX2 instruction is VPSADBW.

Syntax

extern __m256i _mm256_sad_epu8(__m256i s1, __m256i s2);

Arguments

s1

integer source vector used for the operation

s2

integer source vector used for the operation

Description

Computes the absolute value of the difference of packed groups of eight unsigned byte integers from the source vectors s1 and s2. Four blocks of eight differences are stored at specific locations in the destination vector. Remaining bits in the destination vector are set to zero.

Returns

Result of the single sum-absolute-difference operation.