Developer Guide and Reference

Contents

_mm256_abs_epi8/16/32

Computes the absolute value of the signed packed integer data elements of a given vector. The corresponding Intel® AVX2 instruction is
VPABSB
,
VPABSW
, or
VPABSD
.

Syntax

extern __m256i _mm256_abs_epi8(__m256i s1);
extern __m256i _mm256_abs_epi16(__m256i s1);
extern __m256i _mm256_abs_epi32(__m256i s1);
Arguments
s1
integer source vector used for the operation
Description
Computes the absolute value of each data element, either signed bytes, 16-bit words, or 32-bit integers, of the source vector and stores the UNSIGNED results in the destination vector.
Returns
Result of the operation.