1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54

/* origin: FreeBSD /usr/src/lib/msun/src/k_tanf.c */
/*
* 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"
/* tan(x)/x  t(x) < 2**25.5 (~[2e08, 2e08]). */
static const double T[] = {
0x15554d3418c99f.0p54, /* 0.333331395030791399758 */
0x1112fd38999f72.0p55, /* 0.133392002712976742718 */
0x1b54c91d865afe.0p57, /* 0.0533812378445670393523 */
0x191df3908c33ce.0p58, /* 0.0245283181166547278873 */
0x185dadfcecf44e.0p61, /* 0.00297435743359967304927 */
0x1362b9bf971bcd.0p59, /* 0.00946564784943673166728 */
};
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
* microoptimized 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
* nonsequential 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;
}
