Developer Guide and Reference

Contents

_mm_cmp_pd, _mm256_cmp_pd

Compares packed 128-bit and 256-bit float64 vector elements. The corresponding Intel® AVX instruction is
VCMPPD
.

Syntax

extern __m128d _mm_cmp_pd(__m128d m1, __m128d m2, const int predicate);
extern __m256d _mm256_cmp_pd(__m256d m1, __m256d m2, const int predicate);
Arguments
m1
float64 vector used for the operation
m2
float64 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 four packed double-precision floating-point (float64) values in the first source operand,
m1
, and the second source operand,
m2
, and returns the results of the comparison.
The
_mm_cmp_pd
intrinsic is used for comparing 128-bit float64 values while the
_m256_cmp_pd
intrinsic is used for comparing 256-bit float64 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.