Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 3/31/2023
Public

A newer version of this document is available.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

Document Table of Contents

_mm_cmp_ps, _mm256_cmp_ps

Compares packed float32 elements of two vectors. The corresponding Intel® AVX instruction is VCMPPS.

Syntax

extern __m128 _mm_cmp_ps(__m128 m1, __m128 m2, const int predicate);

extern __m256 _mm256_cmp_ps(__m256 m1, __m256 m2, const int predicate);

Arguments

m1

float32 vector used for the operation

m2

float32 vector also used for the operation

predicate

an immediate operand that specifies the type of comparison to be performed of the packed values; see immintrin.h file for the values to specify the type of comparison

Description

Performs a SIMD compare of the eight packed single-precision floating-point (float32) values in the first source operand, m1, and the second source operand, m2, and returns the results of the comparison.

The _mm_cmp_ps intrinsic is used for comparing 128-bit float32 values while the _mm256_cmp_ps intrinsic is used for comparing 256-bit float32 values.

The comparison predicate parameter (immediate) specifies the type of comparison performed on each of the pairs of packed values.

Returns

Result of the compare operation.