fminf4

NAME

fminf4 - return smaller values of float elements

SYNOPSIS

Procedure call syntax:

#include <simdmath.h>

vector float fminf4(vector float x, vector float y);

Link with -lsimdmath

Inline call syntax:

#include <simdmath.h>

#include <fminf4.h>

vector float _fminf4(vector float x, vector float y);

Parameters
x.y	input vectors

DESCRIPTION

The fminf4 functions return a vector containing the smaller (less positive) elements of x and y.

RETURN VALUE

The function fminf4 returns a float vector in which each element is defined as:

the smaller (less positive) of the corresponding elements of x and y.
If one element is NaN and the other is numeric, the numeric value is returned.
If both elements are NaN, NaN is returned.

On the SPU single-precision subnormal values are not coerced to zero by this function. Instead, it compares them as normal values even though the floating-point instructions of the SPU do not.

In double precision subnormals¹ equate to zero and so compare as equal. This means that the value returned may be either one of the subnormals, thereby making the following possibly true for two subnormal inputs:

fminf4(a, b) != fminf4(b, a)

ENVIRONMENT

SPU and PPU

CONFORMING TO

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

NOTES

Basis

ISO9899 (C99) fmin functions.