mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-04 02:40:06 +00:00
81dca813cc
Continuing the move to use, within libm, public names for libm functions that can be inlined as built-in functions on many architectures, this patch moves calls to __copysign functions to call the corresponding copysign names instead, with asm redirection to __copysign when the calls are not inlined (all cases are inlined except for IBM long double for powerpc soft-float / e500v1). This eliminates the need for an inline function defining __copysign in terms of __builtin_copysign. Tested for x86_64, and with build-many-glibcs.py. * include/math.h [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (MATH_REDIRECT_BINARY_ARGS): New macro. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (copysign): Redirect using MATH_REDIRECT. * sysdeps/alpha/fpu/s_copysign.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/alpha/fpu/s_copysignf.c: Likewise. * sysdeps/ieee754/dbl-64/s_copysign.c: Likewise. * sysdeps/ieee754/float128/s_copysignf128.c: Likewise. * sysdeps/ieee754/flt-32/s_copysignf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_copysignl.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/riscv/rvd/s_copysign.c: Likewise. * sysdeps/riscv/rvf/s_copysignf.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/generic/math_private_calls.h [!__MATH_DECLARING_LONG_DOUBLE || !NO_LONG_DOUBLE] (__copysign): Do not declare and define as an inline function. * math/divtc3.c (__divtc3): Use copysign functions instead of __copysign variants. * math/multc3.c (__multc3): Likewise. * sysdeps/generic/math-type-macros.h (M_COPYSIGN): Likewise. * sysdeps/ieee754/dbl-64/e_atan2.c (signArctan2): Likewise. * sysdeps/ieee754/dbl-64/e_atanh.c (__ieee754_atanh): Likewise. * sysdeps/ieee754/dbl-64/e_gamma_r.c (__ieee754_gamma_r): Likewise. * sysdeps/ieee754/dbl-64/e_jn.c (__ieee754_jn): Likewise. (__ieee754_yn): Likewise. * sysdeps/ieee754/dbl-64/s_asinh.c (__asinh): Likewise. * sysdeps/ieee754/dbl-64/s_atan.c (__signArctan): Likewise. * sysdeps/ieee754/dbl-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/dbl-64/s_sin.c (do_sin): Likewise. (__sin): Likewise. * sysdeps/ieee754/dbl-64/s_sincos.c (__sincos): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_nearbyint.c (__nearbyint): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/flt-32/e_atanhf.c (__ieee754_atanhf): Likewise. * sysdeps/ieee754/flt-32/e_gammaf_r.c (__ieee754_gammaf_r): Likewise. * sysdeps/ieee754/flt-32/e_jnf.c (__ieee754_jnf): Likewise. (__ieee754_ynf): Likewise. * sysdeps/ieee754/flt-32/s_asinhf.c (__asinhf): Likewise. * sysdeps/ieee754/flt-32/s_scalbnf.c (__scalbnf): Likewise. * sysdeps/ieee754/k_standard.c (__kernel_standard): Likewise. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_fmal.c (__fmal): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-96/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl) * sysdeps/ieee754/ldbl-96/s_asinhl.c (__asinhl): Likewise. * sysdeps/ieee754/ldbl-96/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-copysign.c (copysignl): Likewise. * sysdeps/powerpc/power5+/fpu/s_modf.c (__modf): Likewise. * sysdeps/powerpc/power5+/fpu/s_modff.c (__modff): Likewise.
224 lines
6.1 KiB
C
224 lines
6.1 KiB
C
/* Implementation of gamma function according to ISO C.
|
|
Copyright (C) 1997-2018 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1997.
|
|
|
|
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-narrow-eval.h>
|
|
#include <math_private.h>
|
|
#include <fenv_private.h>
|
|
#include <math-underflow.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 double gamma_coeff[] =
|
|
{
|
|
0x1.5555555555555p-4,
|
|
-0xb.60b60b60b60b8p-12,
|
|
0x3.4034034034034p-12,
|
|
-0x2.7027027027028p-12,
|
|
0x3.72a3c5631fe46p-12,
|
|
-0x7.daac36664f1f4p-12,
|
|
};
|
|
|
|
#define NCOEFF (sizeof (gamma_coeff) / sizeof (gamma_coeff[0]))
|
|
|
|
/* Return gamma (X), for positive X less than 184, 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 double
|
|
gamma_positive (double x, int *exp2_adj)
|
|
{
|
|
int local_signgam;
|
|
if (x < 0.5)
|
|
{
|
|
*exp2_adj = 0;
|
|
return __ieee754_exp (__ieee754_lgamma_r (x + 1, &local_signgam)) / x;
|
|
}
|
|
else if (x <= 1.5)
|
|
{
|
|
*exp2_adj = 0;
|
|
return __ieee754_exp (__ieee754_lgamma_r (x, &local_signgam));
|
|
}
|
|
else if (x < 6.5)
|
|
{
|
|
/* Adjust into the range for using exp (lgamma). */
|
|
*exp2_adj = 0;
|
|
double n = ceil (x - 1.5);
|
|
double x_adj = x - n;
|
|
double eps;
|
|
double prod = __gamma_product (x_adj, 0, n, &eps);
|
|
return (__ieee754_exp (__ieee754_lgamma_r (x_adj, &local_signgam))
|
|
* prod * (1.0 + eps));
|
|
}
|
|
else
|
|
{
|
|
double eps = 0;
|
|
double x_eps = 0;
|
|
double x_adj = x;
|
|
double prod = 1;
|
|
if (x < 12.0)
|
|
{
|
|
/* Adjust into the range for applying Stirling's
|
|
approximation. */
|
|
double n = ceil (12.0 - x);
|
|
x_adj = math_narrow_eval (x + n);
|
|
x_eps = (x - (x_adj - n));
|
|
prod = __gamma_product (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. */
|
|
double exp_adj = -eps;
|
|
double x_adj_int = round (x_adj);
|
|
double x_adj_frac = x_adj - x_adj_int;
|
|
int x_adj_log2;
|
|
double x_adj_mant = __frexp (x_adj, &x_adj_log2);
|
|
if (x_adj_mant < M_SQRT1_2)
|
|
{
|
|
x_adj_log2--;
|
|
x_adj_mant *= 2.0;
|
|
}
|
|
*exp2_adj = x_adj_log2 * (int) x_adj_int;
|
|
double ret = (__ieee754_pow (x_adj_mant, x_adj)
|
|
* __ieee754_exp2 (x_adj_log2 * x_adj_frac)
|
|
* __ieee754_exp (-x_adj)
|
|
* sqrt (2 * M_PI / x_adj)
|
|
/ prod);
|
|
exp_adj += x_eps * __ieee754_log (x_adj);
|
|
double bsum = gamma_coeff[NCOEFF - 1];
|
|
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 * __expm1 (exp_adj);
|
|
}
|
|
}
|
|
|
|
double
|
|
__ieee754_gamma_r (double x, int *signgamp)
|
|
{
|
|
int32_t hx;
|
|
uint32_t lx;
|
|
double ret;
|
|
|
|
EXTRACT_WORDS (hx, lx, x);
|
|
|
|
if (__glibc_unlikely (((hx & 0x7fffffff) | lx) == 0))
|
|
{
|
|
/* Return value for x == 0 is Inf with divide by zero exception. */
|
|
*signgamp = 0;
|
|
return 1.0 / x;
|
|
}
|
|
if (__builtin_expect (hx < 0, 0)
|
|
&& (uint32_t) hx < 0xfff00000 && rint (x) == x)
|
|
{
|
|
/* Return value for integer x < 0 is NaN with invalid exception. */
|
|
*signgamp = 0;
|
|
return (x - x) / (x - x);
|
|
}
|
|
if (__glibc_unlikely ((unsigned int) hx == 0xfff00000 && lx == 0))
|
|
{
|
|
/* x == -Inf. According to ISO this is NaN. */
|
|
*signgamp = 0;
|
|
return x - x;
|
|
}
|
|
if (__glibc_unlikely ((hx & 0x7ff00000) == 0x7ff00000))
|
|
{
|
|
/* Positive infinity (return positive infinity) or NaN (return
|
|
NaN). */
|
|
*signgamp = 0;
|
|
return x + x;
|
|
}
|
|
|
|
if (x >= 172.0)
|
|
{
|
|
/* Overflow. */
|
|
*signgamp = 0;
|
|
ret = math_narrow_eval (DBL_MAX * DBL_MAX);
|
|
return ret;
|
|
}
|
|
else
|
|
{
|
|
SET_RESTORE_ROUND (FE_TONEAREST);
|
|
if (x > 0.0)
|
|
{
|
|
*signgamp = 0;
|
|
int exp2_adj;
|
|
double tret = gamma_positive (x, &exp2_adj);
|
|
ret = __scalbn (tret, exp2_adj);
|
|
}
|
|
else if (x >= -DBL_EPSILON / 4.0)
|
|
{
|
|
*signgamp = 0;
|
|
ret = 1.0 / x;
|
|
}
|
|
else
|
|
{
|
|
double tx = trunc (x);
|
|
*signgamp = (tx == 2.0 * trunc (tx / 2.0)) ? -1 : 1;
|
|
if (x <= -184.0)
|
|
/* Underflow. */
|
|
ret = DBL_MIN * DBL_MIN;
|
|
else
|
|
{
|
|
double frac = tx - x;
|
|
if (frac > 0.5)
|
|
frac = 1.0 - frac;
|
|
double sinpix = (frac <= 0.25
|
|
? __sin (M_PI * frac)
|
|
: __cos (M_PI * (0.5 - frac)));
|
|
int exp2_adj;
|
|
double tret = M_PI / (-x * sinpix
|
|
* gamma_positive (-x, &exp2_adj));
|
|
ret = __scalbn (tret, -exp2_adj);
|
|
math_check_force_underflow_nonneg (ret);
|
|
}
|
|
}
|
|
ret = math_narrow_eval (ret);
|
|
}
|
|
if (isinf (ret) && x != 0)
|
|
{
|
|
if (*signgamp < 0)
|
|
{
|
|
ret = math_narrow_eval (-copysign (DBL_MAX, ret) * DBL_MAX);
|
|
ret = -ret;
|
|
}
|
|
else
|
|
ret = math_narrow_eval (copysign (DBL_MAX, ret) * DBL_MAX);
|
|
return ret;
|
|
}
|
|
else if (ret == 0)
|
|
{
|
|
if (*signgamp < 0)
|
|
{
|
|
ret = math_narrow_eval (-copysign (DBL_MIN, ret) * DBL_MIN);
|
|
ret = -ret;
|
|
}
|
|
else
|
|
ret = math_narrow_eval (copysign (DBL_MIN, ret) * DBL_MIN);
|
|
return ret;
|
|
}
|
|
else
|
|
return ret;
|
|
}
|
|
strong_alias (__ieee754_gamma_r, __gamma_r_finite)
|