mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-25 20:21:07 +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.
131 lines
3.6 KiB
C
131 lines
3.6 KiB
C
/* s_expm1f.c -- float version of s_expm1.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 <errno.h>
|
|
#include <float.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
|
|
static const float huge = 1.0e+30;
|
|
static const float tiny = 1.0e-30;
|
|
|
|
static const float
|
|
one = 1.0,
|
|
o_threshold = 8.8721679688e+01,/* 0x42b17180 */
|
|
ln2_hi = 6.9313812256e-01,/* 0x3f317180 */
|
|
ln2_lo = 9.0580006145e-06,/* 0x3717f7d1 */
|
|
invln2 = 1.4426950216e+00,/* 0x3fb8aa3b */
|
|
/* scaled coefficients related to expm1 */
|
|
Q1 = -3.3333335072e-02, /* 0xbd088889 */
|
|
Q2 = 1.5873016091e-03, /* 0x3ad00d01 */
|
|
Q3 = -7.9365076090e-05, /* 0xb8a670cd */
|
|
Q4 = 4.0082177293e-06, /* 0x36867e54 */
|
|
Q5 = -2.0109921195e-07; /* 0xb457edbb */
|
|
|
|
float
|
|
__expm1f(float x)
|
|
{
|
|
float y,hi,lo,c,t,e,hxs,hfx,r1;
|
|
int32_t k,xsb;
|
|
u_int32_t hx;
|
|
|
|
GET_FLOAT_WORD(hx,x);
|
|
xsb = hx&0x80000000; /* sign bit of x */
|
|
if(xsb==0) y=x; else y= -x; /* y = |x| */
|
|
hx &= 0x7fffffff; /* high word of |x| */
|
|
|
|
/* filter out huge and non-finite argument */
|
|
if(hx >= 0x4195b844) { /* if |x|>=27*ln2 */
|
|
if(hx >= 0x42b17218) { /* if |x|>=88.721... */
|
|
if(hx>0x7f800000)
|
|
return x+x; /* NaN */
|
|
if(hx==0x7f800000)
|
|
return (xsb==0)? x:-1.0;/* exp(+-inf)={inf,-1} */
|
|
if(x > o_threshold) {
|
|
__set_errno (ERANGE);
|
|
return huge*huge; /* overflow */
|
|
}
|
|
}
|
|
if(xsb!=0) { /* x < -27*ln2, return -1.0 with inexact */
|
|
math_force_eval(x+tiny);/* raise inexact */
|
|
return tiny-one; /* return -1 */
|
|
}
|
|
}
|
|
|
|
/* argument reduction */
|
|
if(hx > 0x3eb17218) { /* if |x| > 0.5 ln2 */
|
|
if(hx < 0x3F851592) { /* and |x| < 1.5 ln2 */
|
|
if(xsb==0)
|
|
{hi = x - ln2_hi; lo = ln2_lo; k = 1;}
|
|
else
|
|
{hi = x + ln2_hi; lo = -ln2_lo; k = -1;}
|
|
} else {
|
|
k = invln2*x+((xsb==0)?(float)0.5:(float)-0.5);
|
|
t = k;
|
|
hi = x - t*ln2_hi; /* t*ln2_hi is exact here */
|
|
lo = t*ln2_lo;
|
|
}
|
|
x = hi - lo;
|
|
c = (hi-x)-lo;
|
|
}
|
|
else if(hx < 0x33000000) { /* when |x|<2**-25, return x */
|
|
math_check_force_underflow (x);
|
|
t = huge+x; /* return x with inexact flags when x!=0 */
|
|
return x - (t-(huge+x));
|
|
}
|
|
else k = 0;
|
|
|
|
/* x is now in primary range */
|
|
hfx = (float)0.5*x;
|
|
hxs = x*hfx;
|
|
r1 = one+hxs*(Q1+hxs*(Q2+hxs*(Q3+hxs*(Q4+hxs*Q5))));
|
|
t = (float)3.0-r1*hfx;
|
|
e = hxs*((r1-t)/((float)6.0 - x*t));
|
|
if(k==0) return x - (x*e-hxs); /* c is 0 */
|
|
else {
|
|
e = (x*(e-c)-c);
|
|
e -= hxs;
|
|
if(k== -1) return (float)0.5*(x-e)-(float)0.5;
|
|
if(k==1) {
|
|
if(x < (float)-0.25) return -(float)2.0*(e-(x+(float)0.5));
|
|
else return one+(float)2.0*(x-e);
|
|
}
|
|
if (k <= -2 || k>56) { /* suffice to return exp(x)-1 */
|
|
int32_t i;
|
|
y = one-(e-x);
|
|
GET_FLOAT_WORD(i,y);
|
|
SET_FLOAT_WORD(y,i+(k<<23)); /* add k to y's exponent */
|
|
return y-one;
|
|
}
|
|
t = one;
|
|
if(k<23) {
|
|
int32_t i;
|
|
SET_FLOAT_WORD(t,0x3f800000 - (0x1000000>>k)); /* t=1-2^-k */
|
|
y = t-(e-x);
|
|
GET_FLOAT_WORD(i,y);
|
|
SET_FLOAT_WORD(y,i+(k<<23)); /* add k to y's exponent */
|
|
} else {
|
|
int32_t i;
|
|
SET_FLOAT_WORD(t,((0x7f-k)<<23)); /* 2^-k */
|
|
y = x-(e+t);
|
|
y += one;
|
|
GET_FLOAT_WORD(i,y);
|
|
SET_FLOAT_WORD(y,i+(k<<23)); /* add k to y's exponent */
|
|
}
|
|
}
|
|
return y;
|
|
}
|
|
weak_alias (__expm1f, expm1f)
|