e216951f50
When FLT_EVAL_METHOD!=0 (only i386 with x87 fp) the excess
precision of an expression must be removed in an assignment.
(gcc needs -fexcess-precision=standard or -std=c99 for this)
This is done by extra load/store instructions which adds code
bloat when lot of temporaries are used and it makes the result
less precise in many cases.
Using double_t and float_t avoids these issues on i386 and
it makes no difference on other archs.
For now only a few functions are modified where the excess
precision is clearly beneficial (mostly polynomial evaluations
with temporaries).
object size differences on i386, gcc-4.8:
old new
__cosdf.o 123 95
__cos.o 199 169
__sindf.o 131 95
__sin.o 225 203
__tandf.o 207 151
__tan.o 605 499
erff.o 1470 1416
erf.o 1703 1649
j0f.o 1779 1745
j0.o 2308 2274
j1f.o 1602 1568
j1.o 2286 2252
tgamma.o 1431 1424
math/*.o 64164 63635
35 lines
1.1 KiB
C
35 lines
1.1 KiB
C
/* origin: FreeBSD /usr/src/lib/msun/src/k_cosf.c */
|
|
/*
|
|
* Conversion to float by Ian Lance Taylor, Cygnus Support, ian@cygnus.com.
|
|
* Debugged and optimized by Bruce D. Evans.
|
|
*/
|
|
/*
|
|
* ====================================================
|
|
* Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
|
|
*
|
|
* Developed at SunPro, a Sun Microsystems, Inc. business.
|
|
* Permission to use, copy, modify, and distribute this
|
|
* software is freely granted, provided that this notice
|
|
* is preserved.
|
|
* ====================================================
|
|
*/
|
|
|
|
#include "libm.h"
|
|
|
|
/* |cos(x) - c(x)| < 2**-34.1 (~[-5.37e-11, 5.295e-11]). */
|
|
static const double
|
|
C0 = -0x1ffffffd0c5e81.0p-54, /* -0.499999997251031003120 */
|
|
C1 = 0x155553e1053a42.0p-57, /* 0.0416666233237390631894 */
|
|
C2 = -0x16c087e80f1e27.0p-62, /* -0.00138867637746099294692 */
|
|
C3 = 0x199342e0ee5069.0p-68; /* 0.0000243904487962774090654 */
|
|
|
|
float __cosdf(double x)
|
|
{
|
|
double_t r, w, z;
|
|
|
|
/* Try to optimize for parallel evaluation as in __tandf.c. */
|
|
z = x*x;
|
|
w = z*z;
|
|
r = C2+z*C3;
|
|
return ((1.0+z*C0) + w*C1) + (w*z)*r;
|
|
}
|