Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 7/13/2023
Public
Document Table of Contents

_mm256_permute_ps, _mm_permute_ps

Permutes 256-bit or 128-bit float32 values into a 256-bit or 128-bit destination vector. The corresponding Intel® AVX instruction is VPERMILPS.

Syntax

extern __m256 _mm256_permute_ps(__m256 m1, int control);

extern __m128 _mm_permute_ps(__m128 m1, int control);

Arguments

m1

a 256-bit or 128-bit float32 vector

control

an integer specified as an 8-bit immediate;

  • for the 256-bit m1 vector this integer contains four 2-bit control fields in the low 8 bits of the immediate
  • for the 128-bit m1 vector this integer contains two 2-bit control fields in the low 4 bits of the immediate

Description

The _mm256_permute_ps intrinsic permutes single-precision floating point elements (float32 elements) in the 256-bit source vector m1, according to a specified 2-bit control field, control, and stores the result in a destination vector.

The _mm_permute_ps intrinsic permutes single-precision floating point elements (float32 elements) in the 128-bit source vector m1, according to a specified 2-bit control field, control, and stores the result in a destination vector.

Returns

A 256-bit or 128-bit float32 vector with permuted values.