mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-30 21:23:52 +08:00
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.
164 lines
4.2 KiB
C
164 lines
4.2 KiB
C
/* Complex square root of float value.
|
|
Copyright (C) 1997-2015 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Based on an algorithm by Stephen L. Moshier <moshier@world.std.com>.
|
|
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 <complex.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
#include <float.h>
|
|
|
|
__complex__ float
|
|
__csqrtf (__complex__ float x)
|
|
{
|
|
__complex__ float res;
|
|
int rcls = fpclassify (__real__ x);
|
|
int icls = fpclassify (__imag__ x);
|
|
|
|
if (__glibc_unlikely (rcls <= FP_INFINITE || icls <= FP_INFINITE))
|
|
{
|
|
if (icls == FP_INFINITE)
|
|
{
|
|
__real__ res = HUGE_VALF;
|
|
__imag__ res = __imag__ x;
|
|
}
|
|
else if (rcls == FP_INFINITE)
|
|
{
|
|
if (__real__ x < 0.0)
|
|
{
|
|
__real__ res = icls == FP_NAN ? __nanf ("") : 0;
|
|
__imag__ res = __copysignf (HUGE_VALF, __imag__ x);
|
|
}
|
|
else
|
|
{
|
|
__real__ res = __real__ x;
|
|
__imag__ res = (icls == FP_NAN
|
|
? __nanf ("") : __copysignf (0.0, __imag__ x));
|
|
}
|
|
}
|
|
else
|
|
{
|
|
__real__ res = __nanf ("");
|
|
__imag__ res = __nanf ("");
|
|
}
|
|
}
|
|
else
|
|
{
|
|
if (__glibc_unlikely (icls == FP_ZERO))
|
|
{
|
|
if (__real__ x < 0.0)
|
|
{
|
|
__real__ res = 0.0;
|
|
__imag__ res = __copysignf (__ieee754_sqrtf (-__real__ x),
|
|
__imag__ x);
|
|
}
|
|
else
|
|
{
|
|
__real__ res = fabsf (__ieee754_sqrtf (__real__ x));
|
|
__imag__ res = __copysignf (0.0, __imag__ x);
|
|
}
|
|
}
|
|
else if (__glibc_unlikely (rcls == FP_ZERO))
|
|
{
|
|
float r;
|
|
if (fabsf (__imag__ x) >= 2.0f * FLT_MIN)
|
|
r = __ieee754_sqrtf (0.5f * fabsf (__imag__ x));
|
|
else
|
|
r = 0.5f * __ieee754_sqrtf (2.0f * fabsf (__imag__ x));
|
|
|
|
__real__ res = r;
|
|
__imag__ res = __copysignf (r, __imag__ x);
|
|
}
|
|
else
|
|
{
|
|
float d, r, s;
|
|
int scale = 0;
|
|
|
|
if (fabsf (__real__ x) > FLT_MAX / 4.0f)
|
|
{
|
|
scale = 1;
|
|
__real__ x = __scalbnf (__real__ x, -2 * scale);
|
|
__imag__ x = __scalbnf (__imag__ x, -2 * scale);
|
|
}
|
|
else if (fabsf (__imag__ x) > FLT_MAX / 4.0f)
|
|
{
|
|
scale = 1;
|
|
if (fabsf (__real__ x) >= 4.0f * FLT_MIN)
|
|
__real__ x = __scalbnf (__real__ x, -2 * scale);
|
|
else
|
|
__real__ x = 0.0f;
|
|
__imag__ x = __scalbnf (__imag__ x, -2 * scale);
|
|
}
|
|
else if (fabsf (__real__ x) < 2.0f * FLT_MIN
|
|
&& fabsf (__imag__ x) < 2.0f * FLT_MIN)
|
|
{
|
|
scale = -((FLT_MANT_DIG + 1) / 2);
|
|
__real__ x = __scalbnf (__real__ x, -2 * scale);
|
|
__imag__ x = __scalbnf (__imag__ x, -2 * scale);
|
|
}
|
|
|
|
d = __ieee754_hypotf (__real__ x, __imag__ x);
|
|
/* Use the identity 2 Re res Im res = Im x
|
|
to avoid cancellation error in d +/- Re x. */
|
|
if (__real__ x > 0)
|
|
{
|
|
r = __ieee754_sqrtf (0.5f * (d + __real__ x));
|
|
if (scale == 1 && fabsf (__imag__ x) < 1.0f)
|
|
{
|
|
/* Avoid possible intermediate underflow. */
|
|
s = __imag__ x / r;
|
|
r = __scalbnf (r, scale);
|
|
scale = 0;
|
|
}
|
|
else
|
|
s = 0.5f * (__imag__ x / r);
|
|
}
|
|
else
|
|
{
|
|
s = __ieee754_sqrtf (0.5f * (d - __real__ x));
|
|
if (scale == 1 && fabsf (__imag__ x) < 1.0f)
|
|
{
|
|
/* Avoid possible intermediate underflow. */
|
|
r = fabsf (__imag__ x / s);
|
|
s = __scalbnf (s, scale);
|
|
scale = 0;
|
|
}
|
|
else
|
|
r = fabsf (0.5f * (__imag__ x / s));
|
|
}
|
|
|
|
if (scale)
|
|
{
|
|
r = __scalbnf (r, scale);
|
|
s = __scalbnf (s, scale);
|
|
}
|
|
|
|
math_check_force_underflow (r);
|
|
math_check_force_underflow (s);
|
|
|
|
__real__ res = r;
|
|
__imag__ res = __copysignf (s, __imag__ x);
|
|
}
|
|
}
|
|
|
|
return res;
|
|
}
|
|
#ifndef __csqrtf
|
|
weak_alias (__csqrtf, csqrtf)
|
|
#endif
|