mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-23 13:30:06 +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.
648 lines
20 KiB
C
648 lines
20 KiB
C
/*
|
|
* IBM Accurate Mathematical Library
|
|
* written by International Business Machines Corp.
|
|
* Copyright (C) 2001-2015 Free Software Foundation, Inc.
|
|
*
|
|
* This program 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 program 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 program; if not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
/******************************************************************/
|
|
/* MODULE_NAME:uasncs.c */
|
|
/* */
|
|
/* FUNCTIONS: uasin */
|
|
/* uacos */
|
|
/* FILES NEEDED: dla.h endian.h mpa.h mydefs.h usncs.h */
|
|
/* doasin.c sincos32.c dosincos.c mpa.c */
|
|
/* sincos.tbl asincos.tbl powtwo.tbl root.tbl */
|
|
/* */
|
|
/* Ultimate asin/acos routines. Given an IEEE double machine */
|
|
/* number x, compute the correctly rounded value of */
|
|
/* arcsin(x)or arccos(x) according to the function called. */
|
|
/* Assumption: Machine arithmetic operations are performed in */
|
|
/* round to nearest mode of IEEE 754 standard. */
|
|
/* */
|
|
/******************************************************************/
|
|
#include "endian.h"
|
|
#include "mydefs.h"
|
|
#include "asincos.tbl"
|
|
#include "root.tbl"
|
|
#include "powtwo.tbl"
|
|
#include "MathLib.h"
|
|
#include "uasncs.h"
|
|
#include <float.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
|
|
#ifndef SECTION
|
|
# define SECTION
|
|
#endif
|
|
|
|
void __doasin(double x, double dx, double w[]);
|
|
void __dubsin(double x, double dx, double v[]);
|
|
void __dubcos(double x, double dx, double v[]);
|
|
void __docos(double x, double dx, double v[]);
|
|
double __sin32(double x, double res, double res1);
|
|
double __cos32(double x, double res, double res1);
|
|
|
|
/***************************************************************************/
|
|
/* An ultimate asin routine. Given an IEEE double machine number x */
|
|
/* it computes the correctly rounded (to nearest) value of arcsin(x) */
|
|
/***************************************************************************/
|
|
double
|
|
SECTION
|
|
__ieee754_asin(double x){
|
|
double x1,x2,xx,s1,s2,res1,p,t,res,r,cor,cc,y,c,z,w[2];
|
|
mynumber u,v;
|
|
int4 k,m,n;
|
|
|
|
u.x = x;
|
|
m = u.i[HIGH_HALF];
|
|
k = 0x7fffffff&m; /* no sign */
|
|
|
|
if (k < 0x3e500000)
|
|
{
|
|
math_check_force_underflow (x);
|
|
return x; /* for x->0 => sin(x)=x */
|
|
}
|
|
/*----------------------2^-26 <= |x| < 2^ -3 -----------------*/
|
|
else
|
|
if (k < 0x3fc00000) {
|
|
x2 = x*x;
|
|
t = (((((f6*x2 + f5)*x2 + f4)*x2 + f3)*x2 + f2)*x2 + f1)*(x2*x);
|
|
res = x+t; /* res=arcsin(x) according to Taylor series */
|
|
cor = (x-res)+t;
|
|
if (res == res+1.025*cor) return res;
|
|
else {
|
|
x1 = x+big;
|
|
xx = x*x;
|
|
x1 -= big;
|
|
x2 = x - x1;
|
|
p = x1*x1*x1;
|
|
s1 = a1.x*p;
|
|
s2 = ((((((c7*xx + c6)*xx + c5)*xx + c4)*xx + c3)*xx + c2)*xx*xx*x +
|
|
((a1.x+a2.x)*x2*x2+ 0.5*x1*x)*x2) + a2.x*p;
|
|
res1 = x+s1;
|
|
s2 = ((x-res1)+s1)+s2;
|
|
res = res1+s2;
|
|
cor = (res1-res)+s2;
|
|
if (res == res+1.00014*cor) return res;
|
|
else {
|
|
__doasin(x,0,w);
|
|
if (w[0]==(w[0]+1.00000001*w[1])) return w[0];
|
|
else {
|
|
y=fabs(x);
|
|
res=fabs(w[0]);
|
|
res1=fabs(w[0]+1.1*w[1]);
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
/*---------------------0.125 <= |x| < 0.5 -----------------------------*/
|
|
else if (k < 0x3fe00000) {
|
|
if (k<0x3fd00000) n = 11*((k&0x000fffff)>>15);
|
|
else n = 11*((k&0x000fffff)>>14)+352;
|
|
if (m>0) xx = x - asncs.x[n];
|
|
else xx = -x - asncs.x[n];
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+xx*(asncs.x[n+5]
|
|
+xx*asncs.x[n+6]))))+asncs.x[n+7];
|
|
t+=p;
|
|
res =asncs.x[n+8] +t;
|
|
cor = (asncs.x[n+8]-res)+t;
|
|
if (res == res+1.05*cor) return (m>0)?res:-res;
|
|
else {
|
|
r=asncs.x[n+8]+xx*asncs.x[n+9];
|
|
t=((asncs.x[n+8]-r)+xx*asncs.x[n+9])+(p+xx*asncs.x[n+10]);
|
|
res = r+t;
|
|
cor = (r-res)+t;
|
|
if (res == res+1.0005*cor) return (m>0)?res:-res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__dubsin(res,z,w);
|
|
z=(w[0]-fabs(x))+w[1];
|
|
if (z>1.0e-27) return (m>0)?min(res,res1):-min(res,res1);
|
|
else if (z<-1.0e-27) return (m>0)?max(res,res1):-max(res,res1);
|
|
else {
|
|
y=fabs(x);
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fe00000) */
|
|
/*-------------------- 0.5 <= |x| < 0.75 -----------------------------*/
|
|
else
|
|
if (k < 0x3fe80000) {
|
|
n = 1056+((k&0x000fe000)>>11)*3;
|
|
if (m>0) xx = x - asncs.x[n];
|
|
else xx = -x - asncs.x[n];
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+xx*(asncs.x[n+5]
|
|
+xx*(asncs.x[n+6]+xx*asncs.x[n+7])))))+asncs.x[n+8];
|
|
t+=p;
|
|
res =asncs.x[n+9] +t;
|
|
cor = (asncs.x[n+9]-res)+t;
|
|
if (res == res+1.01*cor) return (m>0)?res:-res;
|
|
else {
|
|
r=asncs.x[n+9]+xx*asncs.x[n+10];
|
|
t=((asncs.x[n+9]-r)+xx*asncs.x[n+10])+(p+xx*asncs.x[n+11]);
|
|
res = r+t;
|
|
cor = (r-res)+t;
|
|
if (res == res+1.0005*cor) return (m>0)?res:-res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__dubsin(res,z,w);
|
|
z=(w[0]-fabs(x))+w[1];
|
|
if (z>1.0e-27) return (m>0)?min(res,res1):-min(res,res1);
|
|
else if (z<-1.0e-27) return (m>0)?max(res,res1):-max(res,res1);
|
|
else {
|
|
y=fabs(x);
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fe80000) */
|
|
/*--------------------- 0.75 <= |x|< 0.921875 ----------------------*/
|
|
else
|
|
if (k < 0x3fed8000) {
|
|
n = 992+((k&0x000fe000)>>13)*13;
|
|
if (m>0) xx = x - asncs.x[n];
|
|
else xx = -x - asncs.x[n];
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+xx*(asncs.x[n+5]
|
|
+xx*(asncs.x[n+6]+xx*(asncs.x[n+7]+xx*asncs.x[n+8]))))))+asncs.x[n+9];
|
|
t+=p;
|
|
res =asncs.x[n+10] +t;
|
|
cor = (asncs.x[n+10]-res)+t;
|
|
if (res == res+1.01*cor) return (m>0)?res:-res;
|
|
else {
|
|
r=asncs.x[n+10]+xx*asncs.x[n+11];
|
|
t=((asncs.x[n+10]-r)+xx*asncs.x[n+11])+(p+xx*asncs.x[n+12]);
|
|
res = r+t;
|
|
cor = (r-res)+t;
|
|
if (res == res+1.0008*cor) return (m>0)?res:-res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
y=hp0.x-res;
|
|
z=((hp0.x-y)-res)+(hp1.x-z);
|
|
__dubcos(y,z,w);
|
|
z=(w[0]-fabs(x))+w[1];
|
|
if (z>1.0e-27) return (m>0)?min(res,res1):-min(res,res1);
|
|
else if (z<-1.0e-27) return (m>0)?max(res,res1):-max(res,res1);
|
|
else {
|
|
y=fabs(x);
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fed8000) */
|
|
/*-------------------0.921875 <= |x| < 0.953125 ------------------------*/
|
|
else
|
|
if (k < 0x3fee8000) {
|
|
n = 884+((k&0x000fe000)>>13)*14;
|
|
if (m>0) xx = x - asncs.x[n];
|
|
else xx = -x - asncs.x[n];
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*(asncs.x[n+6]
|
|
+xx*(asncs.x[n+7]+xx*(asncs.x[n+8]+
|
|
xx*asncs.x[n+9])))))))+asncs.x[n+10];
|
|
t+=p;
|
|
res =asncs.x[n+11] +t;
|
|
cor = (asncs.x[n+11]-res)+t;
|
|
if (res == res+1.01*cor) return (m>0)?res:-res;
|
|
else {
|
|
r=asncs.x[n+11]+xx*asncs.x[n+12];
|
|
t=((asncs.x[n+11]-r)+xx*asncs.x[n+12])+(p+xx*asncs.x[n+13]);
|
|
res = r+t;
|
|
cor = (r-res)+t;
|
|
if (res == res+1.0007*cor) return (m>0)?res:-res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
y=(hp0.x-res)-z;
|
|
z=y+hp1.x;
|
|
y=(y-z)+hp1.x;
|
|
__dubcos(z,y,w);
|
|
z=(w[0]-fabs(x))+w[1];
|
|
if (z>1.0e-27) return (m>0)?min(res,res1):-min(res,res1);
|
|
else if (z<-1.0e-27) return (m>0)?max(res,res1):-max(res,res1);
|
|
else {
|
|
y=fabs(x);
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fee8000) */
|
|
|
|
/*--------------------0.953125 <= |x| < 0.96875 ------------------------*/
|
|
else
|
|
if (k < 0x3fef0000) {
|
|
n = 768+((k&0x000fe000)>>13)*15;
|
|
if (m>0) xx = x - asncs.x[n];
|
|
else xx = -x - asncs.x[n];
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*(asncs.x[n+6]
|
|
+xx*(asncs.x[n+7]+xx*(asncs.x[n+8]+
|
|
xx*(asncs.x[n+9]+xx*asncs.x[n+10]))))))))+asncs.x[n+11];
|
|
t+=p;
|
|
res =asncs.x[n+12] +t;
|
|
cor = (asncs.x[n+12]-res)+t;
|
|
if (res == res+1.01*cor) return (m>0)?res:-res;
|
|
else {
|
|
r=asncs.x[n+12]+xx*asncs.x[n+13];
|
|
t=((asncs.x[n+12]-r)+xx*asncs.x[n+13])+(p+xx*asncs.x[n+14]);
|
|
res = r+t;
|
|
cor = (r-res)+t;
|
|
if (res == res+1.0007*cor) return (m>0)?res:-res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
y=(hp0.x-res)-z;
|
|
z=y+hp1.x;
|
|
y=(y-z)+hp1.x;
|
|
__dubcos(z,y,w);
|
|
z=(w[0]-fabs(x))+w[1];
|
|
if (z>1.0e-27) return (m>0)?min(res,res1):-min(res,res1);
|
|
else if (z<-1.0e-27) return (m>0)?max(res,res1):-max(res,res1);
|
|
else {
|
|
y=fabs(x);
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fef0000) */
|
|
/*--------------------0.96875 <= |x| < 1 --------------------------------*/
|
|
else
|
|
if (k<0x3ff00000) {
|
|
z = 0.5*((m>0)?(1.0-x):(1.0+x));
|
|
v.x=z;
|
|
k=v.i[HIGH_HALF];
|
|
t=inroot[(k&0x001fffff)>>14]*powtwo[511-(k>>21)];
|
|
r=1.0-t*t*z;
|
|
t = t*(rt0+r*(rt1+r*(rt2+r*rt3)));
|
|
c=t*z;
|
|
t=c*(1.5-0.5*t*c);
|
|
y=(c+t24)-t24;
|
|
cc = (z-y*y)/(t+y);
|
|
p=(((((f6*z+f5)*z+f4)*z+f3)*z+f2)*z+f1)*z;
|
|
cor = (hp1.x - 2.0*cc)-2.0*(y+cc)*p;
|
|
res1 = hp0.x - 2.0*y;
|
|
res =res1 + cor;
|
|
if (res == res+1.003*((res1-res)+cor)) return (m>0)?res:-res;
|
|
else {
|
|
c=y+cc;
|
|
cc=(y-c)+cc;
|
|
__doasin(c,cc,w);
|
|
res1=hp0.x-2.0*w[0];
|
|
cor=((hp0.x-res1)-2.0*w[0])+(hp1.x-2.0*w[1]);
|
|
res = res1+cor;
|
|
cor = (res1-res)+cor;
|
|
if (res==(res+1.0000001*cor)) return (m>0)?res:-res;
|
|
else {
|
|
y=fabs(x);
|
|
res1=res+1.1*cor;
|
|
return (m>0)?__sin32(y,res,res1):-__sin32(y,res,res1);
|
|
}
|
|
}
|
|
} /* else if (k < 0x3ff00000) */
|
|
/*---------------------------- |x|>=1 -------------------------------*/
|
|
else if (k==0x3ff00000 && u.i[LOW_HALF]==0) return (m>0)?hp0.x:-hp0.x;
|
|
else
|
|
if (k>0x7ff00000 || (k == 0x7ff00000 && u.i[LOW_HALF] != 0)) return x;
|
|
else {
|
|
u.i[HIGH_HALF]=0x7ff00000;
|
|
v.i[HIGH_HALF]=0x7ff00000;
|
|
u.i[LOW_HALF]=0;
|
|
v.i[LOW_HALF]=0;
|
|
return u.x/v.x; /* NaN */
|
|
}
|
|
}
|
|
#ifndef __ieee754_asin
|
|
strong_alias (__ieee754_asin, __asin_finite)
|
|
#endif
|
|
|
|
/*******************************************************************/
|
|
/* */
|
|
/* End of arcsine, below is arccosine */
|
|
/* */
|
|
/*******************************************************************/
|
|
|
|
double
|
|
SECTION
|
|
__ieee754_acos(double x)
|
|
{
|
|
double x1,x2,xx,s1,s2,res1,p,t,res,r,cor,cc,y,c,z,w[2],eps;
|
|
mynumber u,v;
|
|
int4 k,m,n;
|
|
u.x = x;
|
|
m = u.i[HIGH_HALF];
|
|
k = 0x7fffffff&m;
|
|
/*------------------- |x|<2.77556*10^-17 ----------------------*/
|
|
if (k < 0x3c880000) return hp0.x;
|
|
|
|
/*----------------- 2.77556*10^-17 <= |x| < 2^-3 --------------*/
|
|
else
|
|
if (k < 0x3fc00000) {
|
|
x2 = x*x;
|
|
t = (((((f6*x2 + f5)*x2 + f4)*x2 + f3)*x2 + f2)*x2 + f1)*(x2*x);
|
|
r=hp0.x-x;
|
|
cor=(((hp0.x-r)-x)+hp1.x)-t;
|
|
res = r+cor;
|
|
cor = (r-res)+cor;
|
|
if (res == res+1.004*cor) return res;
|
|
else {
|
|
x1 = x+big;
|
|
xx = x*x;
|
|
x1 -= big;
|
|
x2 = x - x1;
|
|
p = x1*x1*x1;
|
|
s1 = a1.x*p;
|
|
s2 = ((((((c7*xx + c6)*xx + c5)*xx + c4)*xx + c3)*xx + c2)*xx*xx*x +
|
|
((a1.x+a2.x)*x2*x2+ 0.5*x1*x)*x2) + a2.x*p;
|
|
res1 = x+s1;
|
|
s2 = ((x-res1)+s1)+s2;
|
|
r=hp0.x-res1;
|
|
cor=(((hp0.x-r)-res1)+hp1.x)-s2;
|
|
res = r+cor;
|
|
cor = (r-res)+cor;
|
|
if (res == res+1.00004*cor) return res;
|
|
else {
|
|
__doasin(x,0,w);
|
|
r=hp0.x-w[0];
|
|
cor=((hp0.x-r)-w[0])+(hp1.x-w[1]);
|
|
res=r+cor;
|
|
cor=(r-res)+cor;
|
|
if (res ==(res +1.00000001*cor)) return res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fc00000) */
|
|
/*---------------------- 0.125 <= |x| < 0.5 --------------------*/
|
|
else
|
|
if (k < 0x3fe00000) {
|
|
if (k<0x3fd00000) n = 11*((k&0x000fffff)>>15);
|
|
else n = 11*((k&0x000fffff)>>14)+352;
|
|
if (m>0) xx = x - asncs.x[n];
|
|
else xx = -x - asncs.x[n];
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*asncs.x[n+6]))))+asncs.x[n+7];
|
|
t+=p;
|
|
y = (m>0)?(hp0.x-asncs.x[n+8]):(hp0.x+asncs.x[n+8]);
|
|
t = (m>0)?(hp1.x-t):(hp1.x+t);
|
|
res = y+t;
|
|
if (res == res+1.02*((y-res)+t)) return res;
|
|
else {
|
|
r=asncs.x[n+8]+xx*asncs.x[n+9];
|
|
t=((asncs.x[n+8]-r)+xx*asncs.x[n+9])+(p+xx*asncs.x[n+10]);
|
|
if (m>0)
|
|
{p = hp0.x-r; t = (((hp0.x-p)-r)-t)+hp1.x; }
|
|
else
|
|
{p = hp0.x+r; t = ((hp0.x-p)+r)+(hp1.x+t); }
|
|
res = p+t;
|
|
cor = (p-res)+t;
|
|
if (res == (res+1.0002*cor)) return res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__docos(res,z,w);
|
|
z=(w[0]-x)+w[1];
|
|
if (z>1.0e-27) return max(res,res1);
|
|
else if (z<-1.0e-27) return min(res,res1);
|
|
else return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fe00000) */
|
|
|
|
/*--------------------------- 0.5 <= |x| < 0.75 ---------------------*/
|
|
else
|
|
if (k < 0x3fe80000) {
|
|
n = 1056+((k&0x000fe000)>>11)*3;
|
|
if (m>0) {xx = x - asncs.x[n]; eps=1.04; }
|
|
else {xx = -x - asncs.x[n]; eps=1.02; }
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*(asncs.x[n+6]+
|
|
xx*asncs.x[n+7])))))+asncs.x[n+8];
|
|
t+=p;
|
|
y = (m>0)?(hp0.x-asncs.x[n+9]):(hp0.x+asncs.x[n+9]);
|
|
t = (m>0)?(hp1.x-t):(hp1.x+t);
|
|
res = y+t;
|
|
if (res == res+eps*((y-res)+t)) return res;
|
|
else {
|
|
r=asncs.x[n+9]+xx*asncs.x[n+10];
|
|
t=((asncs.x[n+9]-r)+xx*asncs.x[n+10])+(p+xx*asncs.x[n+11]);
|
|
if (m>0) {p = hp0.x-r; t = (((hp0.x-p)-r)-t)+hp1.x; eps=1.0004; }
|
|
else {p = hp0.x+r; t = ((hp0.x-p)+r)+(hp1.x+t); eps=1.0002; }
|
|
res = p+t;
|
|
cor = (p-res)+t;
|
|
if (res == (res+eps*cor)) return res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__docos(res,z,w);
|
|
z=(w[0]-x)+w[1];
|
|
if (z>1.0e-27) return max(res,res1);
|
|
else if (z<-1.0e-27) return min(res,res1);
|
|
else return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fe80000) */
|
|
|
|
/*------------------------- 0.75 <= |x| < 0.921875 -------------*/
|
|
else
|
|
if (k < 0x3fed8000) {
|
|
n = 992+((k&0x000fe000)>>13)*13;
|
|
if (m>0) {xx = x - asncs.x[n]; eps = 1.04; }
|
|
else {xx = -x - asncs.x[n]; eps = 1.01; }
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*(asncs.x[n+6]+xx*(asncs.x[n+7]+
|
|
xx*asncs.x[n+8]))))))+asncs.x[n+9];
|
|
t+=p;
|
|
y = (m>0)?(hp0.x-asncs.x[n+10]):(hp0.x+asncs.x[n+10]);
|
|
t = (m>0)?(hp1.x-t):(hp1.x+t);
|
|
res = y+t;
|
|
if (res == res+eps*((y-res)+t)) return res;
|
|
else {
|
|
r=asncs.x[n+10]+xx*asncs.x[n+11];
|
|
t=((asncs.x[n+10]-r)+xx*asncs.x[n+11])+(p+xx*asncs.x[n+12]);
|
|
if (m>0) {p = hp0.x-r; t = (((hp0.x-p)-r)-t)+hp1.x; eps=1.0032; }
|
|
else {p = hp0.x+r; t = ((hp0.x-p)+r)+(hp1.x+t); eps=1.0008; }
|
|
res = p+t;
|
|
cor = (p-res)+t;
|
|
if (res == (res+eps*cor)) return res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__docos(res,z,w);
|
|
z=(w[0]-x)+w[1];
|
|
if (z>1.0e-27) return max(res,res1);
|
|
else if (z<-1.0e-27) return min(res,res1);
|
|
else return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fed8000) */
|
|
|
|
/*-------------------0.921875 <= |x| < 0.953125 ------------------*/
|
|
else
|
|
if (k < 0x3fee8000) {
|
|
n = 884+((k&0x000fe000)>>13)*14;
|
|
if (m>0) {xx = x - asncs.x[n]; eps=1.04; }
|
|
else {xx = -x - asncs.x[n]; eps =1.005; }
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*(asncs.x[n+6]
|
|
+xx*(asncs.x[n+7]+xx*(asncs.x[n+8]+
|
|
xx*asncs.x[n+9])))))))+asncs.x[n+10];
|
|
t+=p;
|
|
y = (m>0)?(hp0.x-asncs.x[n+11]):(hp0.x+asncs.x[n+11]);
|
|
t = (m>0)?(hp1.x-t):(hp1.x+t);
|
|
res = y+t;
|
|
if (res == res+eps*((y-res)+t)) return res;
|
|
else {
|
|
r=asncs.x[n+11]+xx*asncs.x[n+12];
|
|
t=((asncs.x[n+11]-r)+xx*asncs.x[n+12])+(p+xx*asncs.x[n+13]);
|
|
if (m>0) {p = hp0.x-r; t = (((hp0.x-p)-r)-t)+hp1.x; eps=1.0030; }
|
|
else {p = hp0.x+r; t = ((hp0.x-p)+r)+(hp1.x+t); eps=1.0005; }
|
|
res = p+t;
|
|
cor = (p-res)+t;
|
|
if (res == (res+eps*cor)) return res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__docos(res,z,w);
|
|
z=(w[0]-x)+w[1];
|
|
if (z>1.0e-27) return max(res,res1);
|
|
else if (z<-1.0e-27) return min(res,res1);
|
|
else return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fee8000) */
|
|
|
|
/*--------------------0.953125 <= |x| < 0.96875 ----------------*/
|
|
else
|
|
if (k < 0x3fef0000) {
|
|
n = 768+((k&0x000fe000)>>13)*15;
|
|
if (m>0) {xx = x - asncs.x[n]; eps=1.04; }
|
|
else {xx = -x - asncs.x[n]; eps=1.005;}
|
|
t = asncs.x[n+1]*xx;
|
|
p=xx*xx*(asncs.x[n+2]+xx*(asncs.x[n+3]+xx*(asncs.x[n+4]+
|
|
xx*(asncs.x[n+5]+xx*(asncs.x[n+6]
|
|
+xx*(asncs.x[n+7]+xx*(asncs.x[n+8]+xx*(asncs.x[n+9]+
|
|
xx*asncs.x[n+10]))))))))+asncs.x[n+11];
|
|
t+=p;
|
|
y = (m>0)?(hp0.x-asncs.x[n+12]):(hp0.x+asncs.x[n+12]);
|
|
t = (m>0)?(hp1.x-t):(hp1.x+t);
|
|
res = y+t;
|
|
if (res == res+eps*((y-res)+t)) return res;
|
|
else {
|
|
r=asncs.x[n+12]+xx*asncs.x[n+13];
|
|
t=((asncs.x[n+12]-r)+xx*asncs.x[n+13])+(p+xx*asncs.x[n+14]);
|
|
if (m>0) {p = hp0.x-r; t = (((hp0.x-p)-r)-t)+hp1.x; eps=1.0030; }
|
|
else {p = hp0.x+r; t = ((hp0.x-p)+r)+(hp1.x+t); eps=1.0005; }
|
|
res = p+t;
|
|
cor = (p-res)+t;
|
|
if (res == (res+eps*cor)) return res;
|
|
else {
|
|
res1=res+1.1*cor;
|
|
z=0.5*(res1-res);
|
|
__docos(res,z,w);
|
|
z=(w[0]-x)+w[1];
|
|
if (z>1.0e-27) return max(res,res1);
|
|
else if (z<-1.0e-27) return min(res,res1);
|
|
else return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
} /* else if (k < 0x3fef0000) */
|
|
/*-----------------0.96875 <= |x| < 1 ---------------------------*/
|
|
|
|
else
|
|
if (k<0x3ff00000) {
|
|
z = 0.5*((m>0)?(1.0-x):(1.0+x));
|
|
v.x=z;
|
|
k=v.i[HIGH_HALF];
|
|
t=inroot[(k&0x001fffff)>>14]*powtwo[511-(k>>21)];
|
|
r=1.0-t*t*z;
|
|
t = t*(rt0+r*(rt1+r*(rt2+r*rt3)));
|
|
c=t*z;
|
|
t=c*(1.5-0.5*t*c);
|
|
y = (t27*c+c)-t27*c;
|
|
cc = (z-y*y)/(t+y);
|
|
p=(((((f6*z+f5)*z+f4)*z+f3)*z+f2)*z+f1)*z;
|
|
if (m<0) {
|
|
cor = (hp1.x - cc)-(y+cc)*p;
|
|
res1 = hp0.x - y;
|
|
res =res1 + cor;
|
|
if (res == res+1.002*((res1-res)+cor)) return (res+res);
|
|
else {
|
|
c=y+cc;
|
|
cc=(y-c)+cc;
|
|
__doasin(c,cc,w);
|
|
res1=hp0.x-w[0];
|
|
cor=((hp0.x-res1)-w[0])+(hp1.x-w[1]);
|
|
res = res1+cor;
|
|
cor = (res1-res)+cor;
|
|
if (res==(res+1.000001*cor)) return (res+res);
|
|
else {
|
|
res=res+res;
|
|
res1=res+1.2*cor;
|
|
return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
}
|
|
else {
|
|
cor = cc+p*(y+cc);
|
|
res = y + cor;
|
|
if (res == res+1.03*((y-res)+cor)) return (res+res);
|
|
else {
|
|
c=y+cc;
|
|
cc=(y-c)+cc;
|
|
__doasin(c,cc,w);
|
|
res = w[0];
|
|
cor=w[1];
|
|
if (res==(res+1.000001*cor)) return (res+res);
|
|
else {
|
|
res=res+res;
|
|
res1=res+1.2*cor;
|
|
return __cos32(x,res,res1);
|
|
}
|
|
}
|
|
}
|
|
} /* else if (k < 0x3ff00000) */
|
|
|
|
/*---------------------------- |x|>=1 -----------------------*/
|
|
else
|
|
if (k==0x3ff00000 && u.i[LOW_HALF]==0) return (m>0)?0:2.0*hp0.x;
|
|
else
|
|
if (k>0x7ff00000 || (k == 0x7ff00000 && u.i[LOW_HALF] != 0)) return x;
|
|
else {
|
|
u.i[HIGH_HALF]=0x7ff00000;
|
|
v.i[HIGH_HALF]=0x7ff00000;
|
|
u.i[LOW_HALF]=0;
|
|
v.i[LOW_HALF]=0;
|
|
return u.x/v.x;
|
|
}
|
|
}
|
|
#ifndef __ieee754_acos
|
|
strong_alias (__ieee754_acos, __acos_finite)
|
|
#endif
|