mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-28 15:51:07 +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.
219 lines
6.3 KiB
C
219 lines
6.3 KiB
C
/* Implementation of gamma function according to ISO C.
|
|
Copyright (C) 1997-2015 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1997 and
|
|
Jakub Jelinek <jj@ultra.linux.cz, 1999.
|
|
|
|
The GNU C 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.
|
|
|
|
The GNU C 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 the GNU C Library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
#include <float.h>
|
|
|
|
/* Coefficients B_2k / 2k(2k-1) of x^-(2k-1) inside exp in Stirling's
|
|
approximation to gamma function. */
|
|
|
|
static const long double gamma_coeff[] =
|
|
{
|
|
0x1.555555555555555555555555558p-4L,
|
|
-0xb.60b60b60b60b60b60b60b60b6p-12L,
|
|
0x3.4034034034034034034034034p-12L,
|
|
-0x2.7027027027027027027027027p-12L,
|
|
0x3.72a3c5631fe46ae1d4e700dca9p-12L,
|
|
-0x7.daac36664f1f207daac36664f2p-12L,
|
|
0x1.a41a41a41a41a41a41a41a41a4p-8L,
|
|
-0x7.90a1b2c3d4e5f708192a3b4c5ep-8L,
|
|
0x2.dfd2c703c0cfff430edfd2c704p-4L,
|
|
-0x1.6476701181f39edbdb9ce625988p+0L,
|
|
0xd.672219167002d3a7a9c886459cp+0L,
|
|
-0x9.cd9292e6660d55b3f712eb9e08p+4L,
|
|
0x8.911a740da740da740da740da74p+8L,
|
|
};
|
|
|
|
#define NCOEFF (sizeof (gamma_coeff) / sizeof (gamma_coeff[0]))
|
|
|
|
/* Return gamma (X), for positive X less than 191, in the form R *
|
|
2^(*EXP2_ADJ), where R is the return value and *EXP2_ADJ is set to
|
|
avoid overflow or underflow in intermediate calculations. */
|
|
|
|
static long double
|
|
gammal_positive (long double x, int *exp2_adj)
|
|
{
|
|
int local_signgam;
|
|
if (x < 0.5L)
|
|
{
|
|
*exp2_adj = 0;
|
|
return __ieee754_expl (__ieee754_lgammal_r (x + 1, &local_signgam)) / x;
|
|
}
|
|
else if (x <= 1.5L)
|
|
{
|
|
*exp2_adj = 0;
|
|
return __ieee754_expl (__ieee754_lgammal_r (x, &local_signgam));
|
|
}
|
|
else if (x < 11.5L)
|
|
{
|
|
/* Adjust into the range for using exp (lgamma). */
|
|
*exp2_adj = 0;
|
|
long double n = __ceill (x - 1.5L);
|
|
long double x_adj = x - n;
|
|
long double eps;
|
|
long double prod = __gamma_productl (x_adj, 0, n, &eps);
|
|
return (__ieee754_expl (__ieee754_lgammal_r (x_adj, &local_signgam))
|
|
* prod * (1.0L + eps));
|
|
}
|
|
else
|
|
{
|
|
long double eps = 0;
|
|
long double x_eps = 0;
|
|
long double x_adj = x;
|
|
long double prod = 1;
|
|
if (x < 23.0L)
|
|
{
|
|
/* Adjust into the range for applying Stirling's
|
|
approximation. */
|
|
long double n = __ceill (23.0L - x);
|
|
x_adj = x + n;
|
|
x_eps = (x - (x_adj - n));
|
|
prod = __gamma_productl (x_adj - n, x_eps, n, &eps);
|
|
}
|
|
/* The result is now gamma (X_ADJ + X_EPS) / (PROD * (1 + EPS)).
|
|
Compute gamma (X_ADJ + X_EPS) using Stirling's approximation,
|
|
starting by computing pow (X_ADJ, X_ADJ) with a power of 2
|
|
factored out. */
|
|
long double exp_adj = -eps;
|
|
long double x_adj_int = __roundl (x_adj);
|
|
long double x_adj_frac = x_adj - x_adj_int;
|
|
int x_adj_log2;
|
|
long double x_adj_mant = __frexpl (x_adj, &x_adj_log2);
|
|
if (x_adj_mant < M_SQRT1_2l)
|
|
{
|
|
x_adj_log2--;
|
|
x_adj_mant *= 2.0L;
|
|
}
|
|
*exp2_adj = x_adj_log2 * (int) x_adj_int;
|
|
long double ret = (__ieee754_powl (x_adj_mant, x_adj)
|
|
* __ieee754_exp2l (x_adj_log2 * x_adj_frac)
|
|
* __ieee754_expl (-x_adj)
|
|
* __ieee754_sqrtl (2 * M_PIl / x_adj)
|
|
/ prod);
|
|
exp_adj += x_eps * __ieee754_logl (x_adj);
|
|
long double bsum = gamma_coeff[NCOEFF - 1];
|
|
long double x_adj2 = x_adj * x_adj;
|
|
for (size_t i = 1; i <= NCOEFF - 1; i++)
|
|
bsum = bsum / x_adj2 + gamma_coeff[NCOEFF - 1 - i];
|
|
exp_adj += bsum / x_adj;
|
|
return ret + ret * __expm1l (exp_adj);
|
|
}
|
|
}
|
|
|
|
long double
|
|
__ieee754_gammal_r (long double x, int *signgamp)
|
|
{
|
|
int64_t hx;
|
|
double xhi;
|
|
long double ret;
|
|
|
|
xhi = ldbl_high (x);
|
|
EXTRACT_WORDS64 (hx, xhi);
|
|
|
|
if ((hx & 0x7fffffffffffffffLL) == 0)
|
|
{
|
|
/* Return value for x == 0 is Inf with divide by zero exception. */
|
|
*signgamp = 0;
|
|
return 1.0 / x;
|
|
}
|
|
if (hx < 0 && (u_int64_t) hx < 0xfff0000000000000ULL && __rintl (x) == x)
|
|
{
|
|
/* Return value for integer x < 0 is NaN with invalid exception. */
|
|
*signgamp = 0;
|
|
return (x - x) / (x - x);
|
|
}
|
|
if (hx == 0xfff0000000000000ULL)
|
|
{
|
|
/* x == -Inf. According to ISO this is NaN. */
|
|
*signgamp = 0;
|
|
return x - x;
|
|
}
|
|
if ((hx & 0x7ff0000000000000ULL) == 0x7ff0000000000000ULL)
|
|
{
|
|
/* Positive infinity (return positive infinity) or NaN (return
|
|
NaN). */
|
|
*signgamp = 0;
|
|
return x + x;
|
|
}
|
|
|
|
if (x >= 172.0L)
|
|
{
|
|
/* Overflow. */
|
|
*signgamp = 0;
|
|
return LDBL_MAX * LDBL_MAX;
|
|
}
|
|
else
|
|
{
|
|
SET_RESTORE_ROUNDL (FE_TONEAREST);
|
|
if (x > 0.0L)
|
|
{
|
|
*signgamp = 0;
|
|
int exp2_adj;
|
|
ret = gammal_positive (x, &exp2_adj);
|
|
ret = __scalbnl (ret, exp2_adj);
|
|
}
|
|
else if (x >= -0x1p-110L)
|
|
{
|
|
*signgamp = 0;
|
|
ret = 1.0L / x;
|
|
}
|
|
else
|
|
{
|
|
long double tx = __truncl (x);
|
|
*signgamp = (tx == 2.0L * __truncl (tx / 2.0L)) ? -1 : 1;
|
|
if (x <= -191.0L)
|
|
/* Underflow. */
|
|
ret = LDBL_MIN * LDBL_MIN;
|
|
else
|
|
{
|
|
long double frac = tx - x;
|
|
if (frac > 0.5L)
|
|
frac = 1.0L - frac;
|
|
long double sinpix = (frac <= 0.25L
|
|
? __sinl (M_PIl * frac)
|
|
: __cosl (M_PIl * (0.5L - frac)));
|
|
int exp2_adj;
|
|
ret = M_PIl / (-x * sinpix
|
|
* gammal_positive (-x, &exp2_adj));
|
|
ret = __scalbnl (ret, -exp2_adj);
|
|
math_check_force_underflow_nonneg (ret);
|
|
}
|
|
}
|
|
}
|
|
if (isinf (ret) && x != 0)
|
|
{
|
|
if (*signgamp < 0)
|
|
return -(-__copysignl (LDBL_MAX, ret) * LDBL_MAX);
|
|
else
|
|
return __copysignl (LDBL_MAX, ret) * LDBL_MAX;
|
|
}
|
|
else if (ret == 0)
|
|
{
|
|
if (*signgamp < 0)
|
|
return -(-__copysignl (LDBL_MIN, ret) * LDBL_MIN);
|
|
else
|
|
return __copysignl (LDBL_MIN, ret) * LDBL_MIN;
|
|
}
|
|
else
|
|
return ret;
|
|
}
|
|
strong_alias (__ieee754_gammal_r, __gammal_r_finite)
|