signbitd2

NAME

signbitd2 - return indicators of the signs of double values

SYNOPSIS

Procedure call syntax:

#include <simdmath.h>

vector unsigned long long signbitd2(vector double x);

Link with -lsimdmath

Inline call syntax:

#include <simdmath.h>

#include <signbitd2.h>

vector unsigned long long _signbitd2(vector double x);

Parameters
x	input vector

DESCRIPTION

The signbitd2 function returns a vector in which elements contain all ones or zeros, depending on the sign of the corresponding input vector element.

Note that the signbitd2 function is not logically equivalent to (x < 0.0). IEEE 754 floating point rules include a signed zero, so if the input value is -0.0 signbitd2 will return non-zero even though the naïve implementation will not.

RETURN VALUE

The function signbitd2 returns an unsigned long long vector in which each element is defined as:

ULLONG_MAX	if the sign bit is set for the corresponding element of x.
0	otherwise.

ENVIRONMENT

SPU only

CONFORMING TO

SIMD Math library specification for the Cell Broadband Engine™ Architecture.

NOTES

Basis

ISO9899 (C99) signbit macros.