mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-30 00:31:08 +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.
257 lines
6.5 KiB
C
257 lines
6.5 KiB
C
/* log1pl.c
|
|
*
|
|
* Relative error logarithm
|
|
* Natural logarithm of 1+x, 128-bit long double precision
|
|
*
|
|
*
|
|
*
|
|
* SYNOPSIS:
|
|
*
|
|
* long double x, y, log1pl();
|
|
*
|
|
* y = log1pl( x );
|
|
*
|
|
*
|
|
*
|
|
* DESCRIPTION:
|
|
*
|
|
* Returns the base e (2.718...) logarithm of 1+x.
|
|
*
|
|
* The argument 1+x is separated into its exponent and fractional
|
|
* parts. If the exponent is between -1 and +1, the logarithm
|
|
* of the fraction is approximated by
|
|
*
|
|
* log(1+x) = x - 0.5 x^2 + x^3 P(x)/Q(x).
|
|
*
|
|
* Otherwise, setting z = 2(w-1)/(w+1),
|
|
*
|
|
* log(w) = z + z^3 P(z)/Q(z).
|
|
*
|
|
*
|
|
*
|
|
* ACCURACY:
|
|
*
|
|
* Relative error:
|
|
* arithmetic domain # trials peak rms
|
|
* IEEE -1, 8 100000 1.9e-34 4.3e-35
|
|
*/
|
|
|
|
/* Copyright 2001 by Stephen L. Moshier
|
|
|
|
This library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
This library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with this library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
|
|
#include <float.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
|
|
/* Coefficients for log(1+x) = x - x^2 / 2 + x^3 P(x)/Q(x)
|
|
* 1/sqrt(2) <= 1+x < sqrt(2)
|
|
* Theoretical peak relative error = 5.3e-37,
|
|
* relative peak error spread = 2.3e-14
|
|
*/
|
|
static const long double
|
|
P12 = 1.538612243596254322971797716843006400388E-6L,
|
|
P11 = 4.998469661968096229986658302195402690910E-1L,
|
|
P10 = 2.321125933898420063925789532045674660756E1L,
|
|
P9 = 4.114517881637811823002128927449878962058E2L,
|
|
P8 = 3.824952356185897735160588078446136783779E3L,
|
|
P7 = 2.128857716871515081352991964243375186031E4L,
|
|
P6 = 7.594356839258970405033155585486712125861E4L,
|
|
P5 = 1.797628303815655343403735250238293741397E5L,
|
|
P4 = 2.854829159639697837788887080758954924001E5L,
|
|
P3 = 3.007007295140399532324943111654767187848E5L,
|
|
P2 = 2.014652742082537582487669938141683759923E5L,
|
|
P1 = 7.771154681358524243729929227226708890930E4L,
|
|
P0 = 1.313572404063446165910279910527789794488E4L,
|
|
/* Q12 = 1.000000000000000000000000000000000000000E0L, */
|
|
Q11 = 4.839208193348159620282142911143429644326E1L,
|
|
Q10 = 9.104928120962988414618126155557301584078E2L,
|
|
Q9 = 9.147150349299596453976674231612674085381E3L,
|
|
Q8 = 5.605842085972455027590989944010492125825E4L,
|
|
Q7 = 2.248234257620569139969141618556349415120E5L,
|
|
Q6 = 6.132189329546557743179177159925690841200E5L,
|
|
Q5 = 1.158019977462989115839826904108208787040E6L,
|
|
Q4 = 1.514882452993549494932585972882995548426E6L,
|
|
Q3 = 1.347518538384329112529391120390701166528E6L,
|
|
Q2 = 7.777690340007566932935753241556479363645E5L,
|
|
Q1 = 2.626900195321832660448791748036714883242E5L,
|
|
Q0 = 3.940717212190338497730839731583397586124E4L;
|
|
|
|
/* Coefficients for log(x) = z + z^3 P(z^2)/Q(z^2),
|
|
* where z = 2(x-1)/(x+1)
|
|
* 1/sqrt(2) <= x < sqrt(2)
|
|
* Theoretical peak relative error = 1.1e-35,
|
|
* relative peak error spread 1.1e-9
|
|
*/
|
|
static const long double
|
|
R5 = -8.828896441624934385266096344596648080902E-1L,
|
|
R4 = 8.057002716646055371965756206836056074715E1L,
|
|
R3 = -2.024301798136027039250415126250455056397E3L,
|
|
R2 = 2.048819892795278657810231591630928516206E4L,
|
|
R1 = -8.977257995689735303686582344659576526998E4L,
|
|
R0 = 1.418134209872192732479751274970992665513E5L,
|
|
/* S6 = 1.000000000000000000000000000000000000000E0L, */
|
|
S5 = -1.186359407982897997337150403816839480438E2L,
|
|
S4 = 3.998526750980007367835804959888064681098E3L,
|
|
S3 = -5.748542087379434595104154610899551484314E4L,
|
|
S2 = 4.001557694070773974936904547424676279307E5L,
|
|
S1 = -1.332535117259762928288745111081235577029E6L,
|
|
S0 = 1.701761051846631278975701529965589676574E6L;
|
|
|
|
/* C1 + C2 = ln 2 */
|
|
static const long double C1 = 6.93145751953125E-1L;
|
|
static const long double C2 = 1.428606820309417232121458176568075500134E-6L;
|
|
|
|
static const long double sqrth = 0.7071067811865475244008443621048490392848L;
|
|
/* ln (2^16384 * (1 - 2^-113)) */
|
|
static const long double zero = 0.0L;
|
|
|
|
long double
|
|
__log1pl (long double xm1)
|
|
{
|
|
long double x, y, z, r, s;
|
|
ieee854_long_double_shape_type u;
|
|
int32_t hx;
|
|
int e;
|
|
|
|
/* Test for NaN or infinity input. */
|
|
u.value = xm1;
|
|
hx = u.parts32.w0;
|
|
if (hx >= 0x7fff0000)
|
|
return xm1;
|
|
|
|
/* log1p(+- 0) = +- 0. */
|
|
if (((hx & 0x7fffffff) == 0)
|
|
&& (u.parts32.w1 | u.parts32.w2 | u.parts32.w3) == 0)
|
|
return xm1;
|
|
|
|
if ((hx & 0x7fffffff) < 0x3f8e0000)
|
|
{
|
|
math_check_force_underflow (xm1);
|
|
if ((int) xm1 == 0)
|
|
return xm1;
|
|
}
|
|
|
|
if (xm1 >= 0x1p113L)
|
|
x = xm1;
|
|
else
|
|
x = xm1 + 1.0L;
|
|
|
|
/* log1p(-1) = -inf */
|
|
if (x <= 0.0L)
|
|
{
|
|
if (x == 0.0L)
|
|
return (-1.0L / zero); /* log1p(-1) = -inf */
|
|
else
|
|
return (zero / (x - x));
|
|
}
|
|
|
|
/* Separate mantissa from exponent. */
|
|
|
|
/* Use frexp used so that denormal numbers will be handled properly. */
|
|
x = __frexpl (x, &e);
|
|
|
|
/* Logarithm using log(x) = z + z^3 P(z^2)/Q(z^2),
|
|
where z = 2(x-1)/x+1). */
|
|
if ((e > 2) || (e < -2))
|
|
{
|
|
if (x < sqrth)
|
|
{ /* 2( 2x-1 )/( 2x+1 ) */
|
|
e -= 1;
|
|
z = x - 0.5L;
|
|
y = 0.5L * z + 0.5L;
|
|
}
|
|
else
|
|
{ /* 2 (x-1)/(x+1) */
|
|
z = x - 0.5L;
|
|
z -= 0.5L;
|
|
y = 0.5L * x + 0.5L;
|
|
}
|
|
x = z / y;
|
|
z = x * x;
|
|
r = ((((R5 * z
|
|
+ R4) * z
|
|
+ R3) * z
|
|
+ R2) * z
|
|
+ R1) * z
|
|
+ R0;
|
|
s = (((((z
|
|
+ S5) * z
|
|
+ S4) * z
|
|
+ S3) * z
|
|
+ S2) * z
|
|
+ S1) * z
|
|
+ S0;
|
|
z = x * (z * r / s);
|
|
z = z + e * C2;
|
|
z = z + x;
|
|
z = z + e * C1;
|
|
return (z);
|
|
}
|
|
|
|
|
|
/* Logarithm using log(1+x) = x - .5x^2 + x^3 P(x)/Q(x). */
|
|
|
|
if (x < sqrth)
|
|
{
|
|
e -= 1;
|
|
if (e != 0)
|
|
x = 2.0L * x - 1.0L; /* 2x - 1 */
|
|
else
|
|
x = xm1;
|
|
}
|
|
else
|
|
{
|
|
if (e != 0)
|
|
x = x - 1.0L;
|
|
else
|
|
x = xm1;
|
|
}
|
|
z = x * x;
|
|
r = (((((((((((P12 * x
|
|
+ P11) * x
|
|
+ P10) * x
|
|
+ P9) * x
|
|
+ P8) * x
|
|
+ P7) * x
|
|
+ P6) * x
|
|
+ P5) * x
|
|
+ P4) * x
|
|
+ P3) * x
|
|
+ P2) * x
|
|
+ P1) * x
|
|
+ P0;
|
|
s = (((((((((((x
|
|
+ Q11) * x
|
|
+ Q10) * x
|
|
+ Q9) * x
|
|
+ Q8) * x
|
|
+ Q7) * x
|
|
+ Q6) * x
|
|
+ Q5) * x
|
|
+ Q4) * x
|
|
+ Q3) * x
|
|
+ Q2) * x
|
|
+ Q1) * x
|
|
+ Q0;
|
|
y = x * (z * r / s);
|
|
y = y + e * C2;
|
|
z = y - 0.5L * z;
|
|
z = z + x;
|
|
z = z + e * C1;
|
|
return (z);
|
|
}
|