glibc/sysdeps/ieee754/ldbl-96/e_gammal_r.c
Joseph Myers 70e2ba332f Do not include fenv_private.h in math_private.h.
Continuing the clean-up related to the catch-all math_private.h
header, this patch stops math_private.h from including fenv_private.h.
Instead, fenv_private.h is included directly from those users of
math_private.h that also used interfaces from fenv_private.h.  No
attempt is made to remove unused includes of math_private.h, but that
is a natural followup.

(However, since math_private.h sometimes defines optimized versions of
math.h interfaces or __* variants thereof, as well as defining its own
interfaces, I think it might make sense to get all those optimized
versions included from include/math.h, not requiring a separate header
at all, before eliminating unused math_private.h includes - that
avoids a file quietly becoming less-optimized if someone adds a call
to one of those interfaces without restoring a math_private.h include
to that file.)

There is still a pitfall that if code uses plain fe* and __fe*
interfaces, but only includes fenv.h and not fenv_private.h or (before
this patch) math_private.h, it will compile on platforms with
exceptions and rounding modes but not get the optimized versions (and
possibly not compile) on platforms without exception and rounding mode
support, so making it easy to break the build for such platforms
accidentally.

I think it would be most natural to move the inlines / macros for fe*
and __fe* in the case of no exceptions and rounding modes into
include/fenv.h, so that all code including fenv.h with _ISOMAC not
defined automatically gets them.  Then fenv_private.h would be purely
the header for the libc_fe*, SET_RESTORE_ROUND etc. internal
interfaces and the risk of breaking the build on other platforms than
the one you tested on because of a missing fenv_private.h include
would be much reduced (and there would be some unused fenv_private.h
includes to remove along with unused math_private.h includes).

Tested for x86_64 and x86, and tested with build-many-glibcs.py that
installed stripped shared libraries are unchanged by this patch.

	* sysdeps/generic/math_private.h: Do not include <fenv_private.h>.
	* math/fromfp.h: Include <fenv_private.h>.
	* math/math-narrow.h: Likewise.
	* math/s_cexp_template.c: Likewise.
	* math/s_csin_template.c: Likewise.
	* math/s_csinh_template.c: Likewise.
	* math/s_ctan_template.c: Likewise.
	* math/s_ctanh_template.c: Likewise.
	* math/s_iseqsig_template.c: Likewise.
	* math/w_acos_compat.c: Likewise.
	* math/w_acosf_compat.c: Likewise.
	* math/w_acosl_compat.c: Likewise.
	* math/w_asin_compat.c: Likewise.
	* math/w_asinf_compat.c: Likewise.
	* math/w_asinl_compat.c: Likewise.
	* math/w_ilogb_template.c: Likewise.
	* math/w_j0_compat.c: Likewise.
	* math/w_j0f_compat.c: Likewise.
	* math/w_j0l_compat.c: Likewise.
	* math/w_j1_compat.c: Likewise.
	* math/w_j1f_compat.c: Likewise.
	* math/w_j1l_compat.c: Likewise.
	* math/w_jn_compat.c: Likewise.
	* math/w_jnf_compat.c: Likewise.
	* math/w_llogb_template.c: Likewise.
	* math/w_log10_compat.c: Likewise.
	* math/w_log10f_compat.c: Likewise.
	* math/w_log10l_compat.c: Likewise.
	* math/w_log2_compat.c: Likewise.
	* math/w_log2f_compat.c: Likewise.
	* math/w_log2l_compat.c: Likewise.
	* math/w_log_compat.c: Likewise.
	* math/w_logf_compat.c: Likewise.
	* math/w_logl_compat.c: Likewise.
	* sysdeps/aarch64/fpu/feholdexcpt.c: Likewise.
	* sysdeps/aarch64/fpu/fesetround.c: Likewise.
	* sysdeps/aarch64/fpu/fgetexcptflg.c: Likewise.
	* sysdeps/aarch64/fpu/ftestexcept.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_atan2.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_exp.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_exp2.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_gamma_r.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_jn.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_pow.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_remainder.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_sqrt.c: Likewise.
	* sysdeps/ieee754/dbl-64/gamma_product.c: Likewise.
	* sysdeps/ieee754/dbl-64/lgamma_neg.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_atan.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_fma.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_fmaf.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_llrint.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_llround.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_lrint.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_lround.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_nearbyint.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_sin.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_sincos.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_tan.c: Likewise.
	* sysdeps/ieee754/dbl-64/wordsize-64/s_lround.c: Likewise.
	* sysdeps/ieee754/dbl-64/wordsize-64/s_nearbyint.c: Likewise.
	* sysdeps/ieee754/dbl-64/x2y2m1.c: Likewise.
	* sysdeps/ieee754/float128/float128_private.h: Likewise.
	* sysdeps/ieee754/flt-32/e_gammaf_r.c: Likewise.
	* sysdeps/ieee754/flt-32/e_j1f.c: Likewise.
	* sysdeps/ieee754/flt-32/e_jnf.c: Likewise.
	* sysdeps/ieee754/flt-32/lgamma_negf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_llrintf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_llroundf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_lrintf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_lroundf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_nearbyintf.c: Likewise.
	* sysdeps/ieee754/k_standardl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_expl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_gammal_r.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_j1l.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_jnl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/gamma_productl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/lgamma_negl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_fmal.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_llrintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_llroundl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_lrintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_lroundl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_nearbyintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/x2y2m1l.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_expl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_j1l.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_jnl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/lgamma_negl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_fmal.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_llrintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_llroundl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_lrintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_lroundl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_rintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/x2y2m1l.c: Likewise.
	* sysdeps/ieee754/ldbl-96/e_gammal_r.c: Likewise.
	* sysdeps/ieee754/ldbl-96/e_jnl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/gamma_productl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/lgamma_negl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_fma.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_fmal.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_llrintl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_llroundl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_lrintl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_lroundl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/x2y2m1l.c: Likewise.
	* sysdeps/powerpc/fpu/e_sqrt.c: Likewise.
	* sysdeps/powerpc/fpu/e_sqrtf.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_ceil.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_floor.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_nearbyint.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_round.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_roundeven.c: Likewise.
	* sysdeps/riscv/rv64/rvd/s_trunc.c: Likewise.
	* sysdeps/riscv/rvd/s_finite.c: Likewise.
	* sysdeps/riscv/rvd/s_fmax.c: Likewise.
	* sysdeps/riscv/rvd/s_fmin.c: Likewise.
	* sysdeps/riscv/rvd/s_fpclassify.c: Likewise.
	* sysdeps/riscv/rvd/s_isinf.c: Likewise.
	* sysdeps/riscv/rvd/s_isnan.c: Likewise.
	* sysdeps/riscv/rvd/s_issignaling.c: Likewise.
	* sysdeps/riscv/rvf/fegetround.c: Likewise.
	* sysdeps/riscv/rvf/feholdexcpt.c: Likewise.
	* sysdeps/riscv/rvf/fesetenv.c: Likewise.
	* sysdeps/riscv/rvf/fesetround.c: Likewise.
	* sysdeps/riscv/rvf/feupdateenv.c: Likewise.
	* sysdeps/riscv/rvf/fgetexcptflg.c: Likewise.
	* sysdeps/riscv/rvf/ftestexcept.c: Likewise.
	* sysdeps/riscv/rvf/s_ceilf.c: Likewise.
	* sysdeps/riscv/rvf/s_finitef.c: Likewise.
	* sysdeps/riscv/rvf/s_floorf.c: Likewise.
	* sysdeps/riscv/rvf/s_fmaxf.c: Likewise.
	* sysdeps/riscv/rvf/s_fminf.c: Likewise.
	* sysdeps/riscv/rvf/s_fpclassifyf.c: Likewise.
	* sysdeps/riscv/rvf/s_isinff.c: Likewise.
	* sysdeps/riscv/rvf/s_isnanf.c: Likewise.
	* sysdeps/riscv/rvf/s_issignalingf.c: Likewise.
	* sysdeps/riscv/rvf/s_nearbyintf.c: Likewise.
	* sysdeps/riscv/rvf/s_roundevenf.c: Likewise.
	* sysdeps/riscv/rvf/s_roundf.c: Likewise.
	* sysdeps/riscv/rvf/s_truncf.c: Likewise.
2018-09-03 21:09:04 +00:00

213 lines
6.0 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_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 long double gamma_coeff[] =
{
0x1.5555555555555556p-4L,
-0xb.60b60b60b60b60bp-12L,
0x3.4034034034034034p-12L,
-0x2.7027027027027028p-12L,
0x3.72a3c5631fe46aep-12L,
-0x7.daac36664f1f208p-12L,
0x1.a41a41a41a41a41ap-8L,
-0x7.90a1b2c3d4e5f708p-8L,
};
#define NCOEFF (sizeof (gamma_coeff) / sizeof (gamma_coeff[0]))
/* Return gamma (X), for positive X less than 1766, 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 < 7.5L)
{
/* 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 < 13.0L)
{
/* Adjust into the range for applying Stirling's
approximation. */
long double n = __ceill (13.0L - 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)
* 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)
{
uint32_t es, hx, lx;
long double ret;
GET_LDOUBLE_WORDS (es, hx, lx, x);
if (__glibc_unlikely (((es & 0x7fff) | hx | lx) == 0))
{
/* Return value for x == 0 is Inf with divide by zero exception. */
*signgamp = 0;
return 1.0 / x;
}
if (__glibc_unlikely (es == 0xffffffff && ((hx & 0x7fffffff) | lx) == 0))
{
/* x == -Inf. According to ISO this is NaN. */
*signgamp = 0;
return x - x;
}
if (__glibc_unlikely ((es & 0x7fff) == 0x7fff))
{
/* Positive infinity (return positive infinity) or NaN (return
NaN). */
*signgamp = 0;
return x + x;
}
if (__builtin_expect ((es & 0x8000) != 0, 0) && __rintl (x) == x)
{
/* Return value for integer x < 0 is NaN with invalid exception. */
*signgamp = 0;
return (x - x) / (x - x);
}
if (x >= 1756.0L)
{
/* 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 >= -LDBL_EPSILON / 4.0L)
{
*signgamp = 0;
ret = 1.0L / x;
}
else
{
long double tx = __truncl (x);
*signgamp = (tx == 2.0L * __truncl (tx / 2.0L)) ? -1 : 1;
if (x <= -1766.0L)
/* 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)