* Conversion to float by Ian Lance Taylor, Cygnus Support, ian@cygnus.com.
* Optimized by Bruce D. Evans.
*/
* ====================================================
* Copyright 2004 Sun Microsystems, Inc. All Rights Reserved.
*
* Permission to use, copy, modify, and distribute this
* software is freely granted, provided that this notice
* is preserved.
* ====================================================
*/
#include "libm.h"
static const double T[] = {
0x15554d3418c99f.0p-54,
0x1112fd38999f72.0p-55,
0x1b54c91d865afe.0p-57,
0x191df3908c33ce.0p-58,
0x185dadfcecf44e.0p-61,
0x1362b9bf971bcd.0p-59,
};
float __tandf(double x, int odd)
{
double_t z,r,w,s,t,u;
z = x*x;
* Split up the polynomial into small independent terms to give
* opportunities for parallel evaluation. The chosen splitting is
* micro-optimized for Athlons (XP, X64). It costs 2 multiplications
* relative to Horner's method on sequential machines.
*
* We add the small terms from lowest degree up for efficiency on
* non-sequential machines (the lowest degree terms tend to be ready
* earlier). Apart from this, we don't care about order of
* operations, and don't need to to care since we have precision to
* spare. However, the chosen splitting is good for accuracy too,
* and would give results as accurate as Horner's method if the
* small terms were added from highest degree down.
*/
r = T[4] + z*T[5];
t = T[2] + z*T[3];
w = z*z;
s = z*x;
u = T[0] + z*T[1];
r = (x + s*u) + (s*w)*(t + w*r);
return odd ? -1.0/r : r;
}
