mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-15 09:30:06 +00:00
d96164c330
Various floating-point functions have code to force underflow exceptions if a tiny result was computed in a way that might not have resulted in such exceptions even though the result is inexact. This typically uses math_force_eval to ensure that the underflowing expression is evaluated, but sometimes uses volatile. This patch refactors such code to use three new macros math_check_force_underflow, math_check_force_underflow_nonneg and math_check_force_underflow_complex (which in turn use math_force_eval). In the limited number of cases not suited to a simple conversion to these macros, existing uses of volatile are changed to use math_force_eval instead. The converted code does not always execute exactly the same sequence of operations as the original code, but the overall effects should be the same. Tested for x86_64, x86, mips64 and powerpc. * sysdeps/generic/math_private.h (fabs_tg): New macro. (min_of_type): Likewise. (math_check_force_underflow): Likewise. (math_check_force_underflow_nonneg): Likewise. (math_check_force_underflow_complex): Likewise. * math/e_exp2l.c (__ieee754_exp2l): Use math_check_force_underflow_nonneg. * math/k_casinh.c (__kernel_casinh): Likewise. * math/k_casinhf.c (__kernel_casinhf): Likewise. * math/k_casinhl.c (__kernel_casinhl): Likewise. * math/s_catan.c (__catan): Use math_check_force_underflow_complex. * math/s_catanf.c (__catanf): Likewise. * math/s_catanh.c (__catanh): Likewise. * math/s_catanhf.c (__catanhf): Likewise. * math/s_catanhl.c (__catanhl): Likewise. * math/s_catanl.c (__catanl): Likewise. * math/s_ccosh.c (__ccosh): Likewise. * math/s_ccoshf.c (__ccoshf): Likewise. * math/s_ccoshl.c (__ccoshl): Likewise. * math/s_cexp.c (__cexp): Likewise. * math/s_cexpf.c (__cexpf): Likewise. * math/s_cexpl.c (__cexpl): Likewise. * math/s_clog.c (__clog): Use math_check_force_underflow_nonneg. * math/s_clog10.c (__clog10): Likewise. * math/s_clog10f.c (__clog10f): Likewise. * math/s_clog10l.c (__clog10l): Likewise. * math/s_clogf.c (__clogf): Likewise. * math/s_clogl.c (__clogl): Likewise. * math/s_csin.c (__csin): Use math_check_force_underflow_complex. * math/s_csinf.c (__csinf): Likewise. * math/s_csinh.c (__csinh): Likewise. * math/s_csinhf.c (__csinhf): Likewise. * math/s_csinhl.c (__csinhl): Likewise. * math/s_csinl.c (__csinl): Likewise. * math/s_csqrt.c (__csqrt): Use math_check_force_underflow. * math/s_csqrtf.c (__csqrtf): Likewise. * math/s_csqrtl.c (__csqrtl): Likewise. * math/s_ctan.c (__ctan): Use math_check_force_underflow_complex. * math/s_ctanf.c (__ctanf): Likewise. * math/s_ctanh.c (__ctanh): Likewise. * math/s_ctanhf.c (__ctanhf): Likewise. * math/s_ctanhl.c (__ctanhl): Likewise. * math/s_ctanl.c (__ctanl): Likewise. * stdlib/strtod_l.c (round_and_return): Use math_force_eval instead of volatile. * sysdeps/ieee754/dbl-64/e_asin.c (__ieee754_asin): Use math_check_force_underflow. * sysdeps/ieee754/dbl-64/e_atanh.c (__ieee754_atanh): Likewise. * sysdeps/ieee754/dbl-64/e_exp.c (__ieee754_exp): Do not use volatile when forcing underflow. * sysdeps/ieee754/dbl-64/e_exp2.c (__ieee754_exp2): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/dbl-64/e_gamma_r.c (__ieee754_gamma_r): Likewise. * sysdeps/ieee754/dbl-64/e_j1.c (__ieee754_j1): Use math_check_force_underflow. * sysdeps/ieee754/dbl-64/e_jn.c (__ieee754_jn): Likewise. * sysdeps/ieee754/dbl-64/e_sinh.c (__ieee754_sinh): Likewise. * sysdeps/ieee754/dbl-64/s_asinh.c (__asinh): Likewise. * sysdeps/ieee754/dbl-64/s_atan.c (atan): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/dbl-64/s_erf.c (__erf): Use math_check_force_underflow. * sysdeps/ieee754/dbl-64/s_expm1.c (__expm1): Likewise. * sysdeps/ieee754/dbl-64/s_fma.c (__fma): Use math_force_eval instead of volatile. * sysdeps/ieee754/dbl-64/s_log1p.c (__log1p): Use math_check_force_underflow. * sysdeps/ieee754/dbl-64/s_sin.c (__sin): Likewise. * sysdeps/ieee754/dbl-64/s_tan.c (tan): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/dbl-64/s_tanh.c (__tanh): Use math_check_force_underflow. * sysdeps/ieee754/flt-32/e_asinf.c (__ieee754_asinf): Likewise. * sysdeps/ieee754/flt-32/e_atanhf.c (__ieee754_atanhf): Likewise. * sysdeps/ieee754/flt-32/e_exp2f.c (__ieee754_exp2f): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/flt-32/e_gammaf_r.c (__ieee754_gammaf_r): Likewise. * sysdeps/ieee754/flt-32/e_j1f.c (__ieee754_j1f): Use math_check_force_underflow. * sysdeps/ieee754/flt-32/e_jnf.c (__ieee754_jnf): Likewise. * sysdeps/ieee754/flt-32/e_sinhf.c (__ieee754_sinhf): Likewise. * sysdeps/ieee754/flt-32/k_sinf.c (__kernel_sinf): Likewise. * sysdeps/ieee754/flt-32/k_tanf.c (__kernel_tanf): Likewise. * sysdeps/ieee754/flt-32/s_asinhf.c (__asinhf): Likewise. * sysdeps/ieee754/flt-32/s_atanf.c (__atanf): Likewise. * sysdeps/ieee754/flt-32/s_erff.c (__erff): Likewise. * sysdeps/ieee754/flt-32/s_expm1f.c (__expm1f): Likewise. * sysdeps/ieee754/flt-32/s_log1pf.c (__log1pf): Likewise. * sysdeps/ieee754/flt-32/s_tanhf.c (__tanhf): Likewise. * sysdeps/ieee754/ldbl-128/e_asinl.c (__ieee754_asinl): Likewise. * sysdeps/ieee754/ldbl-128/e_atanhl.c (__ieee754_atanhl): Likewise. * sysdeps/ieee754/ldbl-128/e_expl.c (__ieee754_expl): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128/e_j1l.c (__ieee754_j1l): Use math_check_force_underflow. * sysdeps/ieee754/ldbl-128/e_jnl.c (__ieee754_jnl): Likewise. * sysdeps/ieee754/ldbl-128/e_sinhl.c (__ieee754_sinhl): Likewise. * sysdeps/ieee754/ldbl-128/k_sincosl.c (__kernel_sincosl): Likewise. * sysdeps/ieee754/ldbl-128/k_sinl.c (__kernel_sinl): Likewise. * sysdeps/ieee754/ldbl-128/k_tanl.c (__kernel_tanl): Likewise. * sysdeps/ieee754/ldbl-128/s_asinhl.c (__asinhl): Likewise. * sysdeps/ieee754/ldbl-128/s_atanl.c (__atanl): Likewise. * sysdeps/ieee754/ldbl-128/s_erfl.c (__erfl): Likewise. * sysdeps/ieee754/ldbl-128/s_expm1l.c (__expm1l): Likewise. * sysdeps/ieee754/ldbl-128/s_fmal.c (__fmal): Use math_force_eval instead of volatile. * sysdeps/ieee754/ldbl-128/s_log1pl.c (__log1pl): Use math_check_force_underflow. * sysdeps/ieee754/ldbl-128/s_tanhl.c (__tanhl): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_asinl.c (__ieee754_asinl): Use math_check_force_underflow. * sysdeps/ieee754/ldbl-128ibm/e_atanhl.c (__ieee754_atanhl): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (__ieee754_gammal_r): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/ldbl-128ibm/e_jnl.c (__ieee754_jnl): Use math_check_force_underflow. * sysdeps/ieee754/ldbl-128ibm/e_sinhl.c (__ieee754_sinhl): Likewise. * sysdeps/ieee754/ldbl-128ibm/k_sincosl.c (__kernel_sincosl): Likewise. * sysdeps/ieee754/ldbl-128ibm/k_sinl.c (__kernel_sinl): Likewise. * sysdeps/ieee754/ldbl-128ibm/k_tanl.c (__kernel_tanl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_asinhl.c (__asinhl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_atanl.c (__atanl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_erfl.c (__erfl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_tanhl.c (__tanhl): Likewise. * sysdeps/ieee754/ldbl-96/e_asinl.c (__ieee754_asinl): Likewise. * sysdeps/ieee754/ldbl-96/e_atanhl.c (__ieee754_atanhl): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (__ieee754_gammal_r): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/ldbl-96/e_j1l.c (__ieee754_j1l): Use math_check_force_underflow. * sysdeps/ieee754/ldbl-96/e_jnl.c (__ieee754_jnl): Likewise. * sysdeps/ieee754/ldbl-96/e_sinhl.c (__ieee754_sinhl): Likewise. * sysdeps/ieee754/ldbl-96/k_sinl.c (__kernel_sinl): Likewise. * sysdeps/ieee754/ldbl-96/k_tanl.c (__kernel_tanl): Use math_check_force_underflow_nonneg. * sysdeps/ieee754/ldbl-96/s_asinhl.c (__asinhl): Use math_check_force_underflow. * sysdeps/ieee754/ldbl-96/s_erfl.c (__erfl): Likewise. * sysdeps/ieee754/ldbl-96/s_fmal.c (__fmal): Use math_force_eval instead of volatile. * sysdeps/ieee754/ldbl-96/s_tanhl.c (__tanhl): Use math_check_force_underflow.
103 lines
2.7 KiB
C
103 lines
2.7 KiB
C
/* s_log1pf.c -- float version of s_log1p.c.
|
|
* Conversion to float by Ian Lance Taylor, Cygnus Support, ian@cygnus.com.
|
|
*/
|
|
|
|
/*
|
|
* ====================================================
|
|
* 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 <float.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
|
|
static const float
|
|
ln2_hi = 6.9313812256e-01, /* 0x3f317180 */
|
|
ln2_lo = 9.0580006145e-06, /* 0x3717f7d1 */
|
|
two25 = 3.355443200e+07, /* 0x4c000000 */
|
|
Lp1 = 6.6666668653e-01, /* 3F2AAAAB */
|
|
Lp2 = 4.0000000596e-01, /* 3ECCCCCD */
|
|
Lp3 = 2.8571429849e-01, /* 3E924925 */
|
|
Lp4 = 2.2222198546e-01, /* 3E638E29 */
|
|
Lp5 = 1.8183572590e-01, /* 3E3A3325 */
|
|
Lp6 = 1.5313838422e-01, /* 3E1CD04F */
|
|
Lp7 = 1.4798198640e-01; /* 3E178897 */
|
|
|
|
static const float zero = 0.0;
|
|
|
|
float
|
|
__log1pf(float x)
|
|
{
|
|
float hfsq,f,c,s,z,R,u;
|
|
int32_t k,hx,hu,ax;
|
|
|
|
GET_FLOAT_WORD(hx,x);
|
|
ax = hx&0x7fffffff;
|
|
|
|
k = 1;
|
|
if (hx < 0x3ed413d7) { /* x < 0.41422 */
|
|
if(ax>=0x3f800000) { /* x <= -1.0 */
|
|
if(x==(float)-1.0) return -two25/zero; /* log1p(-1)=-inf */
|
|
else return (x-x)/(x-x); /* log1p(x<-1)=NaN */
|
|
}
|
|
if(ax<0x31000000) { /* |x| < 2**-29 */
|
|
math_force_eval(two25+x); /* raise inexact */
|
|
if (ax<0x24800000) /* |x| < 2**-54 */
|
|
{
|
|
math_check_force_underflow (x);
|
|
return x;
|
|
}
|
|
else
|
|
return x - x*x*(float)0.5;
|
|
}
|
|
if(hx>0||hx<=((int32_t)0xbe95f61f)) {
|
|
k=0;f=x;hu=1;} /* -0.2929<x<0.41422 */
|
|
}
|
|
if (hx >= 0x7f800000) return x+x;
|
|
if(k!=0) {
|
|
if(hx<0x5a000000) {
|
|
u = (float)1.0+x;
|
|
GET_FLOAT_WORD(hu,u);
|
|
k = (hu>>23)-127;
|
|
/* correction term */
|
|
c = (k>0)? (float)1.0-(u-x):x-(u-(float)1.0);
|
|
c /= u;
|
|
} else {
|
|
u = x;
|
|
GET_FLOAT_WORD(hu,u);
|
|
k = (hu>>23)-127;
|
|
c = 0;
|
|
}
|
|
hu &= 0x007fffff;
|
|
if(hu<0x3504f7) {
|
|
SET_FLOAT_WORD(u,hu|0x3f800000);/* normalize u */
|
|
} else {
|
|
k += 1;
|
|
SET_FLOAT_WORD(u,hu|0x3f000000); /* normalize u/2 */
|
|
hu = (0x00800000-hu)>>2;
|
|
}
|
|
f = u-(float)1.0;
|
|
}
|
|
hfsq=(float)0.5*f*f;
|
|
if(hu==0) { /* |f| < 2**-20 */
|
|
if(f==zero) {
|
|
if(k==0) return zero;
|
|
else {c += k*ln2_lo; return k*ln2_hi+c;}
|
|
}
|
|
R = hfsq*((float)1.0-(float)0.66666666666666666*f);
|
|
if(k==0) return f-R; else
|
|
return k*ln2_hi-((R-(k*ln2_lo+c))-f);
|
|
}
|
|
s = f/((float)2.0+f);
|
|
z = s*s;
|
|
R = z*(Lp1+z*(Lp2+z*(Lp3+z*(Lp4+z*(Lp5+z*(Lp6+z*Lp7))))));
|
|
if(k==0) return f-(hfsq-s*(hfsq+R)); else
|
|
return k*ln2_hi-((hfsq-(s*(hfsq+R)+(k*ln2_lo+c)))-f);
|
|
}
|