mirror of
				https://sourceware.org/git/glibc.git
				synced 2025-11-03 20:53:13 +03:00 
			
		
		
		
	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.
		
			
				
	
	
		
			105 lines
		
	
	
		
			3.2 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			105 lines
		
	
	
		
			3.2 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
/* e_asinf.c -- float version of e_asin.c.
 | 
						|
 * Conversion to float by Ian Lance Taylor, Cygnus Support, ian@cygnus.com.
 | 
						|
 */
 | 
						|
 | 
						|
/*
 | 
						|
 * ====================================================
 | 
						|
 * Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
 | 
						|
 *
 | 
						|
 * Developed at SunPro, a Sun Microsystems, Inc. business.
 | 
						|
 * Permission to use, copy, modify, and distribute this
 | 
						|
 * software is freely granted, provided that this notice
 | 
						|
 * is preserved.
 | 
						|
 * ====================================================
 | 
						|
 */
 | 
						|
 | 
						|
/*
 | 
						|
  Modifications for single precision expansion are
 | 
						|
  Copyright (C) 2001 Stephen L. Moshier <moshier@na-net.ornl.gov>
 | 
						|
  and are incorporated herein by permission of the author.  The author
 | 
						|
  reserves the right to distribute this material elsewhere under different
 | 
						|
  copying permissions.  These modifications are distributed here under
 | 
						|
  the following terms:
 | 
						|
 | 
						|
    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/>.  */
 | 
						|
 | 
						|
#if defined(LIBM_SCCS) && !defined(lint)
 | 
						|
static char rcsid[] = "$NetBSD: e_asinf.c,v 1.5 1995/05/12 04:57:25 jtc Exp $";
 | 
						|
#endif
 | 
						|
 | 
						|
#include <float.h>
 | 
						|
#include <math.h>
 | 
						|
#include <math_private.h>
 | 
						|
 | 
						|
static const float
 | 
						|
one =  1.0000000000e+00, /* 0x3F800000 */
 | 
						|
huge =  1.000e+30,
 | 
						|
 | 
						|
pio2_hi = 1.57079637050628662109375f,
 | 
						|
pio2_lo = -4.37113900018624283e-8f,
 | 
						|
pio4_hi = 0.785398185253143310546875f,
 | 
						|
 | 
						|
/* asin x = x + x^3 p(x^2)
 | 
						|
   -0.5 <= x <= 0.5;
 | 
						|
   Peak relative error 4.8e-9 */
 | 
						|
p0 = 1.666675248e-1f,
 | 
						|
p1 = 7.495297643e-2f,
 | 
						|
p2 = 4.547037598e-2f,
 | 
						|
p3 = 2.417951451e-2f,
 | 
						|
p4 = 4.216630880e-2f;
 | 
						|
 | 
						|
float __ieee754_asinf(float x)
 | 
						|
{
 | 
						|
	float t,w,p,q,c,r,s;
 | 
						|
	int32_t hx,ix;
 | 
						|
	GET_FLOAT_WORD(hx,x);
 | 
						|
	ix = hx&0x7fffffff;
 | 
						|
	if(ix==0x3f800000) {
 | 
						|
		/* asin(1)=+-pi/2 with inexact */
 | 
						|
	    return x*pio2_hi+x*pio2_lo;
 | 
						|
	} else if(ix> 0x3f800000) {	/* |x|>= 1 */
 | 
						|
	    return (x-x)/(x-x);		/* asin(|x|>1) is NaN */
 | 
						|
	} else if (ix<0x3f000000) {	/* |x|<0.5 */
 | 
						|
	    if(ix<0x32000000) {		/* if |x| < 2**-27 */
 | 
						|
		math_check_force_underflow (x);
 | 
						|
		if(huge+x>one) return x;/* return x with inexact if x!=0*/
 | 
						|
	    } else {
 | 
						|
		t = x*x;
 | 
						|
		w = t * (p0 + t * (p1 + t * (p2 + t * (p3 + t * p4))));
 | 
						|
		return x+x*w;
 | 
						|
	    }
 | 
						|
	}
 | 
						|
	/* 1> |x|>= 0.5 */
 | 
						|
	w = one-fabsf(x);
 | 
						|
	t = w*0.5f;
 | 
						|
	p = t * (p0 + t * (p1 + t * (p2 + t * (p3 + t * p4))));
 | 
						|
	s = __ieee754_sqrtf(t);
 | 
						|
	if(ix>=0x3F79999A) {	/* if |x| > 0.975 */
 | 
						|
	    t = pio2_hi-(2.0f*(s+s*p)-pio2_lo);
 | 
						|
	} else {
 | 
						|
	    int32_t iw;
 | 
						|
	    w  = s;
 | 
						|
	    GET_FLOAT_WORD(iw,w);
 | 
						|
	    SET_FLOAT_WORD(w,iw&0xfffff000);
 | 
						|
	    c  = (t-w*w)/(s+w);
 | 
						|
	    r  = p;
 | 
						|
	    p  = 2.0f*s*r-(pio2_lo-2.0f*c);
 | 
						|
	    q  = pio4_hi-2.0f*w;
 | 
						|
	    t  = pio4_hi-(p-q);
 | 
						|
	}
 | 
						|
	if(hx>0) return t; else return -t;
 | 
						|
}
 | 
						|
strong_alias (__ieee754_asinf, __asinf_finite)
 |