* mingwex/math/s_erf.c: New file.
* mingwex/math/sf_erf.c: New file. * mingwex/Makefile.in (MATH_DISTFILES): Add new files. (MATH_OBJS): Add new objects. * include/math.h (erf[f]): Add prototypes. (erfc[f]): Add prototypes.
This commit is contained in:
Danny Smith
parent
4c49b9a2a5
commit
009bcda6f9
|
|
@ -1,3 +1,12 @@
|
|||
2002-12-08 Danny Smith <dannysmith@users.sourceforge.net>
|
||||
|
||||
* mingwex/math/s_erf.c: New file.
|
||||
* mingwex/math/sf_erf.c: New file.
|
||||
* mingwex/Makefile.in (MATH_DISTFILES): Add new files.
|
||||
(MATH_OBJS): Add new objects.
|
||||
* include/math.h (erf[f]): Add prototypes.
|
||||
(erfc[f]): Add prototypes.
|
||||
|
||||
2002-12-07 Danny Smith <dannysmith@users.sourceforge.net>
|
||||
|
||||
* include/math.h: Add traditional/XOPEN math constants.
|
||||
|
|
|
|||
|
|
@ -518,9 +518,19 @@ extern long double powl (long double, long double);
|
|||
extern float sqrtf (float);
|
||||
extern long double sqrtl (long double);
|
||||
|
||||
/* TODO */
|
||||
/* 7.12.8.1 The erf functions */
|
||||
extern double erf (double);
|
||||
extern float erff (float);
|
||||
/* TODO
|
||||
extern long double erfl (long double);
|
||||
*/
|
||||
|
||||
/* 7.12.8.2 The erfc functions */
|
||||
extern double erfc (double);
|
||||
extern float erfcf (float);
|
||||
/* TODO
|
||||
extern long double erfcl (long double);
|
||||
*/
|
||||
|
||||
/* 7.12.8.3 The lgamma functions */
|
||||
|
||||
|
|
|
|||
|
|
@ -56,10 +56,10 @@ MATH_DISTFILES = \
|
|||
pow.c powf.c powi.c powif.c powil.c powl.c \
|
||||
remainder.S remainderf.S remainderl.S remquo.S \
|
||||
remquof.S remquol.S rint.c rintf.c rintl.c round.c roundf.c \
|
||||
roundl.c scalbn.S scalbnf.S scalbnl.S signbit.c signbitf.c \
|
||||
signbitl.c sinf.S sinhf.c sinhl.c sinl.S sqrtf.c sqrtl.c \
|
||||
tanf.S tanhf.c tanhl.c tanl.S tgamma.c tgammaf.c tgammal.c \
|
||||
trunc.c truncf.c truncl.c
|
||||
roundl.c scalbn.S scalbnf.S scalbnl.S s_erf.c sf_erf.c \
|
||||
signbit.c signbitf.c signbitl.c sinf.S sinhf.c sinhl.c sinl.S \
|
||||
sqrtf.c sqrtl.c tanf.S tanhf.c tanhl.c tanl.S tgamma.c \
|
||||
tgammaf.c tgammal.c trunc.c truncf.c truncl.c
|
||||
|
||||
CC = @CC@
|
||||
# FIXME: Which is it, CC or CC_FOR_TARGET?
|
||||
|
|
@ -127,10 +127,10 @@ MATH_OBJS = \
|
|||
pow.o powf.o powi.o powif.o powil.o powl.o \
|
||||
remainder.o remainderf.o remainderl.o remquo.o \
|
||||
remquof.o remquol.o rint.o rintf.o rintl.o round.o roundf.o \
|
||||
roundl.o scalbn.o scalbnf.o scalbnl.o signbit.o signbitf.o \
|
||||
signbitl.o sinf.o sinhf.o sinhl.o sinl.o sqrtf.o sqrtl.o \
|
||||
tanf.o tanhf.o tanhl.o tanl.o tgamma.o tgammaf.o tgammal.o \
|
||||
trunc.o truncf.o truncl.o
|
||||
roundl.o scalbn.o scalbnf.o scalbnl.o s_erf.o sf_erf.o \
|
||||
signbit.o signbitf.o signbitl.o sinf.o sinhf.o sinhl.o sinl.o \
|
||||
sqrtf.o sqrtl.o tanf.o tanhf.o tanhl.o tanl.o tgamma.o \
|
||||
tgammaf.o tgammal.o trunc.o truncf.o truncl.o
|
||||
FENV_OBJS = fesetround.o fegetround.o \
|
||||
fegetenv.o fesetenv.o feupdateenv.o \
|
||||
feclearexcept.o feholdexcept.o fegetexceptflag.o \
|
||||
|
|
|
|||
|
|
@ -0,0 +1,342 @@
|
|||
|
||||
/* @(#)s_erf.c 1.3 95/01/18 */
|
||||
/*
|
||||
* ====================================================
|
||||
* Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
|
||||
*
|
||||
* Developed at SunSoft, a Sun Microsystems, Inc. business.
|
||||
* Permission to use, copy, modify, and distribute this
|
||||
* software is freely granted, provided that this notice
|
||||
* is preserved.
|
||||
* ====================================================
|
||||
*/
|
||||
|
||||
/* double erf(double x)
|
||||
* double erfc(double x)
|
||||
* x
|
||||
* 2 |\
|
||||
* erf(x) = --------- | exp(-t*t)dt
|
||||
* sqrt(pi) \|
|
||||
* 0
|
||||
*
|
||||
* erfc(x) = 1-erf(x)
|
||||
* Note that
|
||||
* erf(-x) = -erf(x)
|
||||
* erfc(-x) = 2 - erfc(x)
|
||||
*
|
||||
* Method:
|
||||
* 1. For |x| in [0, 0.84375]
|
||||
* erf(x) = x + x*R(x^2)
|
||||
* erfc(x) = 1 - erf(x) if x in [-.84375,0.25]
|
||||
* = 0.5 + ((0.5-x)-x*R) if x in [0.25,0.84375]
|
||||
* where R = P/Q where P is an odd poly of degree 8 and
|
||||
* Q is an odd poly of degree 10.
|
||||
* -57.90
|
||||
* | R - (erf(x)-x)/x | <= 2
|
||||
*
|
||||
*
|
||||
* Remark. The formula is derived by noting
|
||||
* erf(x) = (2/sqrt(pi))*(x - x^3/3 + x^5/10 - x^7/42 + ....)
|
||||
* and that
|
||||
* 2/sqrt(pi) = 1.128379167095512573896158903121545171688
|
||||
* is close to one. The interval is chosen because the fix
|
||||
* point of erf(x) is near 0.6174 (i.e., erf(x)=x when x is
|
||||
* near 0.6174), and by some experiment, 0.84375 is chosen to
|
||||
* guarantee the error is less than one ulp for erf.
|
||||
*
|
||||
* 2. For |x| in [0.84375,1.25], let s = |x| - 1, and
|
||||
* c = 0.84506291151 rounded to single (24 bits)
|
||||
* erf(x) = sign(x) * (c + P1(s)/Q1(s))
|
||||
* erfc(x) = (1-c) - P1(s)/Q1(s) if x > 0
|
||||
* 1+(c+P1(s)/Q1(s)) if x < 0
|
||||
* |P1/Q1 - (erf(|x|)-c)| <= 2**-59.06
|
||||
* Remark: here we use the taylor series expansion at x=1.
|
||||
* erf(1+s) = erf(1) + s*Poly(s)
|
||||
* = 0.845.. + P1(s)/Q1(s)
|
||||
* That is, we use rational approximation to approximate
|
||||
* erf(1+s) - (c = (single)0.84506291151)
|
||||
* Note that |P1/Q1|< 0.078 for x in [0.84375,1.25]
|
||||
* where
|
||||
* P1(s) = degree 6 poly in s
|
||||
* Q1(s) = degree 6 poly in s
|
||||
*
|
||||
* 3. For x in [1.25,1/0.35(~2.857143)],
|
||||
* erfc(x) = (1/x)*exp(-x*x-0.5625+R1/S1)
|
||||
* erf(x) = 1 - erfc(x)
|
||||
* where
|
||||
* R1(z) = degree 7 poly in z, (z=1/x^2)
|
||||
* S1(z) = degree 8 poly in z
|
||||
*
|
||||
* 4. For x in [1/0.35,28]
|
||||
* erfc(x) = (1/x)*exp(-x*x-0.5625+R2/S2) if x > 0
|
||||
* = 2.0 - (1/x)*exp(-x*x-0.5625+R2/S2) if -6<x<0
|
||||
* = 2.0 - tiny (if x <= -6)
|
||||
* erf(x) = sign(x)*(1.0 - erfc(x)) if x < 6, else
|
||||
* erf(x) = sign(x)*(1.0 - tiny)
|
||||
* where
|
||||
* R2(z) = degree 6 poly in z, (z=1/x^2)
|
||||
* S2(z) = degree 7 poly in z
|
||||
*
|
||||
* Note1:
|
||||
* To compute exp(-x*x-0.5625+R/S), let s be a single
|
||||
* precision number and s := x; then
|
||||
* -x*x = -s*s + (s-x)*(s+x)
|
||||
* exp(-x*x-0.5626+R/S) =
|
||||
* exp(-s*s-0.5625)*exp((s-x)*(s+x)+R/S);
|
||||
* Note2:
|
||||
* Here 4 and 5 make use of the asymptotic series
|
||||
* exp(-x*x)
|
||||
* erfc(x) ~ ---------- * ( 1 + Poly(1/x^2) )
|
||||
* x*sqrt(pi)
|
||||
* We use rational approximation to approximate
|
||||
* g(s)=f(1/x^2) = log(erfc(x)*x) - x*x + 0.5625
|
||||
* Here is the error bound for R1/S1 and R2/S2
|
||||
* |R1/S1 - f(x)| < 2**(-62.57)
|
||||
* |R2/S2 - f(x)| < 2**(-61.52)
|
||||
*
|
||||
* 5. For inf > x >= 28
|
||||
* erf(x) = sign(x) *(1 - tiny) (raise inexact)
|
||||
* erfc(x) = tiny*tiny (raise underflow) if x > 0
|
||||
* = 2 - tiny if x<0
|
||||
*
|
||||
* 7. Special case:
|
||||
* erf(0) = 0, erf(inf) = 1, erf(-inf) = -1,
|
||||
* erfc(0) = 1, erfc(inf) = 0, erfc(-inf) = 2,
|
||||
* erfc/erf(NaN) is NaN
|
||||
*/
|
||||
|
||||
|
||||
/* #include "fdlibm.h" */
|
||||
|
||||
#include <math.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#define __ieee754_exp exp
|
||||
|
||||
typedef union
|
||||
{
|
||||
double value;
|
||||
struct
|
||||
{
|
||||
uint32_t lsw;
|
||||
uint32_t msw;
|
||||
} parts;
|
||||
} ieee_double_shape_type;
|
||||
|
||||
|
||||
static inline int __get_hi_word(const double x)
|
||||
{
|
||||
ieee_double_shape_type u;
|
||||
u.value = x;
|
||||
return u.parts.msw;
|
||||
}
|
||||
|
||||
static inline void __trunc_lo_word(double *x)
|
||||
{
|
||||
ieee_double_shape_type u;
|
||||
u.value = *x;
|
||||
u.parts.lsw = 0;
|
||||
*x = u.value;
|
||||
}
|
||||
|
||||
|
||||
#ifdef __STDC__
|
||||
static const double
|
||||
#else
|
||||
static double
|
||||
#endif
|
||||
tiny = 1e-300,
|
||||
half= 5.00000000000000000000e-01, /* 0x3FE00000, 0x00000000 */
|
||||
one = 1.00000000000000000000e+00, /* 0x3FF00000, 0x00000000 */
|
||||
two = 2.00000000000000000000e+00, /* 0x40000000, 0x00000000 */
|
||||
/* c = (float)0.84506291151 */
|
||||
erx = 8.45062911510467529297e-01, /* 0x3FEB0AC1, 0x60000000 */
|
||||
/*
|
||||
* Coefficients for approximation to erf on [0,0.84375]
|
||||
*/
|
||||
efx = 1.28379167095512586316e-01, /* 0x3FC06EBA, 0x8214DB69 */
|
||||
efx8= 1.02703333676410069053e+00, /* 0x3FF06EBA, 0x8214DB69 */
|
||||
pp0 = 1.28379167095512558561e-01, /* 0x3FC06EBA, 0x8214DB68 */
|
||||
pp1 = -3.25042107247001499370e-01, /* 0xBFD4CD7D, 0x691CB913 */
|
||||
pp2 = -2.84817495755985104766e-02, /* 0xBF9D2A51, 0xDBD7194F */
|
||||
pp3 = -5.77027029648944159157e-03, /* 0xBF77A291, 0x236668E4 */
|
||||
pp4 = -2.37630166566501626084e-05, /* 0xBEF8EAD6, 0x120016AC */
|
||||
qq1 = 3.97917223959155352819e-01, /* 0x3FD97779, 0xCDDADC09 */
|
||||
qq2 = 6.50222499887672944485e-02, /* 0x3FB0A54C, 0x5536CEBA */
|
||||
qq3 = 5.08130628187576562776e-03, /* 0x3F74D022, 0xC4D36B0F */
|
||||
qq4 = 1.32494738004321644526e-04, /* 0x3F215DC9, 0x221C1A10 */
|
||||
qq5 = -3.96022827877536812320e-06, /* 0xBED09C43, 0x42A26120 */
|
||||
/*
|
||||
* Coefficients for approximation to erf in [0.84375,1.25]
|
||||
*/
|
||||
pa0 = -2.36211856075265944077e-03, /* 0xBF6359B8, 0xBEF77538 */
|
||||
pa1 = 4.14856118683748331666e-01, /* 0x3FDA8D00, 0xAD92B34D */
|
||||
pa2 = -3.72207876035701323847e-01, /* 0xBFD7D240, 0xFBB8C3F1 */
|
||||
pa3 = 3.18346619901161753674e-01, /* 0x3FD45FCA, 0x805120E4 */
|
||||
pa4 = -1.10894694282396677476e-01, /* 0xBFBC6398, 0x3D3E28EC */
|
||||
pa5 = 3.54783043256182359371e-02, /* 0x3FA22A36, 0x599795EB */
|
||||
pa6 = -2.16637559486879084300e-03, /* 0xBF61BF38, 0x0A96073F */
|
||||
qa1 = 1.06420880400844228286e-01, /* 0x3FBB3E66, 0x18EEE323 */
|
||||
qa2 = 5.40397917702171048937e-01, /* 0x3FE14AF0, 0x92EB6F33 */
|
||||
qa3 = 7.18286544141962662868e-02, /* 0x3FB2635C, 0xD99FE9A7 */
|
||||
qa4 = 1.26171219808761642112e-01, /* 0x3FC02660, 0xE763351F */
|
||||
qa5 = 1.36370839120290507362e-02, /* 0x3F8BEDC2, 0x6B51DD1C */
|
||||
qa6 = 1.19844998467991074170e-02, /* 0x3F888B54, 0x5735151D */
|
||||
/*
|
||||
* Coefficients for approximation to erfc in [1.25,1/0.35]
|
||||
*/
|
||||
ra0 = -9.86494403484714822705e-03, /* 0xBF843412, 0x600D6435 */
|
||||
ra1 = -6.93858572707181764372e-01, /* 0xBFE63416, 0xE4BA7360 */
|
||||
ra2 = -1.05586262253232909814e+01, /* 0xC0251E04, 0x41B0E726 */
|
||||
ra3 = -6.23753324503260060396e+01, /* 0xC04F300A, 0xE4CBA38D */
|
||||
ra4 = -1.62396669462573470355e+02, /* 0xC0644CB1, 0x84282266 */
|
||||
ra5 = -1.84605092906711035994e+02, /* 0xC067135C, 0xEBCCABB2 */
|
||||
ra6 = -8.12874355063065934246e+01, /* 0xC0545265, 0x57E4D2F2 */
|
||||
ra7 = -9.81432934416914548592e+00, /* 0xC023A0EF, 0xC69AC25C */
|
||||
sa1 = 1.96512716674392571292e+01, /* 0x4033A6B9, 0xBD707687 */
|
||||
sa2 = 1.37657754143519042600e+02, /* 0x4061350C, 0x526AE721 */
|
||||
sa3 = 4.34565877475229228821e+02, /* 0x407B290D, 0xD58A1A71 */
|
||||
sa4 = 6.45387271733267880336e+02, /* 0x40842B19, 0x21EC2868 */
|
||||
sa5 = 4.29008140027567833386e+02, /* 0x407AD021, 0x57700314 */
|
||||
sa6 = 1.08635005541779435134e+02, /* 0x405B28A3, 0xEE48AE2C */
|
||||
sa7 = 6.57024977031928170135e+00, /* 0x401A47EF, 0x8E484A93 */
|
||||
sa8 = -6.04244152148580987438e-02, /* 0xBFAEEFF2, 0xEE749A62 */
|
||||
/*
|
||||
* Coefficients for approximation to erfc in [1/.35,28]
|
||||
*/
|
||||
rb0 = -9.86494292470009928597e-03, /* 0xBF843412, 0x39E86F4A */
|
||||
rb1 = -7.99283237680523006574e-01, /* 0xBFE993BA, 0x70C285DE */
|
||||
rb2 = -1.77579549177547519889e+01, /* 0xC031C209, 0x555F995A */
|
||||
rb3 = -1.60636384855821916062e+02, /* 0xC064145D, 0x43C5ED98 */
|
||||
rb4 = -6.37566443368389627722e+02, /* 0xC083EC88, 0x1375F228 */
|
||||
rb5 = -1.02509513161107724954e+03, /* 0xC0900461, 0x6A2E5992 */
|
||||
rb6 = -4.83519191608651397019e+02, /* 0xC07E384E, 0x9BDC383F */
|
||||
sb1 = 3.03380607434824582924e+01, /* 0x403E568B, 0x261D5190 */
|
||||
sb2 = 3.25792512996573918826e+02, /* 0x40745CAE, 0x221B9F0A */
|
||||
sb3 = 1.53672958608443695994e+03, /* 0x409802EB, 0x189D5118 */
|
||||
sb4 = 3.19985821950859553908e+03, /* 0x40A8FFB7, 0x688C246A */
|
||||
sb5 = 2.55305040643316442583e+03, /* 0x40A3F219, 0xCEDF3BE6 */
|
||||
sb6 = 4.74528541206955367215e+02, /* 0x407DA874, 0xE79FE763 */
|
||||
sb7 = -2.24409524465858183362e+01; /* 0xC03670E2, 0x42712D62 */
|
||||
|
||||
#ifdef __STDC__
|
||||
double erf(double x)
|
||||
#else
|
||||
double erf(x)
|
||||
double x;
|
||||
#endif
|
||||
{
|
||||
int hx,ix,i;
|
||||
double R,S,P,Q,s,y,z,r;
|
||||
hx = __get_hi_word(x);
|
||||
ix = hx&0x7fffffff;
|
||||
if(ix>=0x7ff00000) { /* erf(nan)=nan */
|
||||
i = ((unsigned)hx>>31)<<1;
|
||||
return (double)(1-i)+one/x; /* erf(+-inf)=+-1 */
|
||||
}
|
||||
|
||||
if(ix < 0x3feb0000) { /* |x|<0.84375 */
|
||||
if(ix < 0x3e300000) { /* |x|<2**-28 */
|
||||
if (ix < 0x00800000)
|
||||
return 0.125*(8.0*x+efx8*x); /*avoid underflow */
|
||||
return x + efx*x;
|
||||
}
|
||||
z = x*x;
|
||||
r = pp0+z*(pp1+z*(pp2+z*(pp3+z*pp4)));
|
||||
s = one+z*(qq1+z*(qq2+z*(qq3+z*(qq4+z*qq5))));
|
||||
y = r/s;
|
||||
return x + x*y;
|
||||
}
|
||||
if(ix < 0x3ff40000) { /* 0.84375 <= |x| < 1.25 */
|
||||
s = fabs(x)-one;
|
||||
P = pa0+s*(pa1+s*(pa2+s*(pa3+s*(pa4+s*(pa5+s*pa6)))));
|
||||
Q = one+s*(qa1+s*(qa2+s*(qa3+s*(qa4+s*(qa5+s*qa6)))));
|
||||
if(hx>=0) return erx + P/Q; else return -erx - P/Q;
|
||||
}
|
||||
if (ix >= 0x40180000) { /* inf>|x|>=6 */
|
||||
if(hx>=0) return one-tiny; else return tiny-one;
|
||||
}
|
||||
x = fabs(x);
|
||||
s = one/(x*x);
|
||||
if(ix< 0x4006DB6E) { /* |x| < 1/0.35 */
|
||||
R=ra0+s*(ra1+s*(ra2+s*(ra3+s*(ra4+s*(
|
||||
ra5+s*(ra6+s*ra7))))));
|
||||
S=one+s*(sa1+s*(sa2+s*(sa3+s*(sa4+s*(
|
||||
sa5+s*(sa6+s*(sa7+s*sa8)))))));
|
||||
} else { /* |x| >= 1/0.35 */
|
||||
R=rb0+s*(rb1+s*(rb2+s*(rb3+s*(rb4+s*(
|
||||
rb5+s*rb6)))));
|
||||
S=one+s*(sb1+s*(sb2+s*(sb3+s*(sb4+s*(
|
||||
sb5+s*(sb6+s*sb7))))));
|
||||
}
|
||||
z = x;
|
||||
__trunc_lo_word(&z);
|
||||
r = __ieee754_exp(-z*z-0.5625)*__ieee754_exp((z-x)*(z+x)+R/S);
|
||||
if(hx>=0) return one-r/x; else return r/x-one;
|
||||
}
|
||||
|
||||
#ifdef __STDC__
|
||||
double erfc(double x)
|
||||
#else
|
||||
double erfc(x)
|
||||
double x;
|
||||
#endif
|
||||
{
|
||||
int hx,ix;
|
||||
double R,S,P,Q,s,y,z,r;
|
||||
hx = __get_hi_word(x);
|
||||
ix = hx&0x7fffffff;
|
||||
if(ix>=0x7ff00000) { /* erfc(nan)=nan */
|
||||
/* erfc(+-inf)=0,2 */
|
||||
return (double)(((unsigned)hx>>31)<<1)+one/x;
|
||||
}
|
||||
|
||||
if(ix < 0x3feb0000) { /* |x|<0.84375 */
|
||||
if(ix < 0x3c700000) /* |x|<2**-56 */
|
||||
return one-x;
|
||||
z = x*x;
|
||||
r = pp0+z*(pp1+z*(pp2+z*(pp3+z*pp4)));
|
||||
s = one+z*(qq1+z*(qq2+z*(qq3+z*(qq4+z*qq5))));
|
||||
y = r/s;
|
||||
if(hx < 0x3fd00000) { /* x<1/4 */
|
||||
return one-(x+x*y);
|
||||
} else {
|
||||
r = x*y;
|
||||
r += (x-half);
|
||||
return half - r ;
|
||||
}
|
||||
}
|
||||
if(ix < 0x3ff40000) { /* 0.84375 <= |x| < 1.25 */
|
||||
s = fabs(x)-one;
|
||||
P = pa0+s*(pa1+s*(pa2+s*(pa3+s*(pa4+s*(pa5+s*pa6)))));
|
||||
Q = one+s*(qa1+s*(qa2+s*(qa3+s*(qa4+s*(qa5+s*qa6)))));
|
||||
if(hx>=0) {
|
||||
z = one-erx; return z - P/Q;
|
||||
} else {
|
||||
z = erx+P/Q; return one+z;
|
||||
}
|
||||
}
|
||||
if (ix < 0x403c0000) { /* |x|<28 */
|
||||
x = fabs(x);
|
||||
s = one/(x*x);
|
||||
if(ix< 0x4006DB6D) { /* |x| < 1/.35 ~ 2.857143*/
|
||||
R=ra0+s*(ra1+s*(ra2+s*(ra3+s*(ra4+s*(
|
||||
ra5+s*(ra6+s*ra7))))));
|
||||
S=one+s*(sa1+s*(sa2+s*(sa3+s*(sa4+s*(
|
||||
sa5+s*(sa6+s*(sa7+s*sa8)))))));
|
||||
} else { /* |x| >= 1/.35 ~ 2.857143 */
|
||||
if(hx<0&&ix>=0x40180000) return two-tiny;/* x < -6 */
|
||||
R=rb0+s*(rb1+s*(rb2+s*(rb3+s*(rb4+s*(
|
||||
rb5+s*rb6)))));
|
||||
S=one+s*(sb1+s*(sb2+s*(sb3+s*(sb4+s*(
|
||||
sb5+s*(sb6+s*sb7))))));
|
||||
}
|
||||
z = x;
|
||||
__trunc_lo_word(&z);
|
||||
r = __ieee754_exp(-z*z-0.5625)*
|
||||
__ieee754_exp((z-x)*(z+x)+R/S);
|
||||
if(hx>0) return r/x; else return two-r/x;
|
||||
} else {
|
||||
if(hx>0) return tiny*tiny; else return two-tiny;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,259 @@
|
|||
/* sf_erf.c -- float version of s_erf.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.
|
||||
* ====================================================
|
||||
*/
|
||||
|
||||
/*
|
||||
#include "fdlibm.h"
|
||||
*/
|
||||
#include <stdint.h>
|
||||
#define __ieee754_expf expf
|
||||
|
||||
#include <math.h>
|
||||
|
||||
typedef union
|
||||
{
|
||||
float value;
|
||||
uint32_t word;
|
||||
} ieee_float_shape_type;
|
||||
|
||||
/* Get a 32 bit int from a float. */
|
||||
|
||||
static inline int
|
||||
__get_float_word(float d)
|
||||
{
|
||||
ieee_float_shape_type u;
|
||||
u.value = d;
|
||||
return u.word;
|
||||
}
|
||||
|
||||
/* Set a float from a 32 bit int. */
|
||||
|
||||
#define SET_FLOAT_WORD(d,i) \
|
||||
do { \
|
||||
ieee_float_shape_type sf_u; \
|
||||
sf_u.word = (i); \
|
||||
(d) = sf_u.value; \
|
||||
} while (0)
|
||||
|
||||
static inline void __trunc_float_word(float * x)
|
||||
{
|
||||
ieee_float_shape_type u;
|
||||
u.value = * x;
|
||||
u.word &= 0xfffff000;
|
||||
}
|
||||
|
||||
#ifdef __v810__
|
||||
#define const
|
||||
#endif
|
||||
|
||||
#ifdef __STDC__
|
||||
static const float
|
||||
#else
|
||||
static float
|
||||
#endif
|
||||
tiny = 1e-30,
|
||||
half= 5.0000000000e-01, /* 0x3F000000 */
|
||||
one = 1.0000000000e+00, /* 0x3F800000 */
|
||||
two = 2.0000000000e+00, /* 0x40000000 */
|
||||
/* c = (subfloat)0.84506291151 */
|
||||
erx = 8.4506291151e-01, /* 0x3f58560b */
|
||||
/*
|
||||
* Coefficients for approximation to erf on [0,0.84375]
|
||||
*/
|
||||
efx = 1.2837916613e-01, /* 0x3e0375d4 */
|
||||
efx8= 1.0270333290e+00, /* 0x3f8375d4 */
|
||||
pp0 = 1.2837916613e-01, /* 0x3e0375d4 */
|
||||
pp1 = -3.2504209876e-01, /* 0xbea66beb */
|
||||
pp2 = -2.8481749818e-02, /* 0xbce9528f */
|
||||
pp3 = -5.7702702470e-03, /* 0xbbbd1489 */
|
||||
pp4 = -2.3763017452e-05, /* 0xb7c756b1 */
|
||||
qq1 = 3.9791721106e-01, /* 0x3ecbbbce */
|
||||
qq2 = 6.5022252500e-02, /* 0x3d852a63 */
|
||||
qq3 = 5.0813062117e-03, /* 0x3ba68116 */
|
||||
qq4 = 1.3249473704e-04, /* 0x390aee49 */
|
||||
qq5 = -3.9602282413e-06, /* 0xb684e21a */
|
||||
/*
|
||||
* Coefficients for approximation to erf in [0.84375,1.25]
|
||||
*/
|
||||
pa0 = -2.3621185683e-03, /* 0xbb1acdc6 */
|
||||
pa1 = 4.1485610604e-01, /* 0x3ed46805 */
|
||||
pa2 = -3.7220788002e-01, /* 0xbebe9208 */
|
||||
pa3 = 3.1834661961e-01, /* 0x3ea2fe54 */
|
||||
pa4 = -1.1089469492e-01, /* 0xbde31cc2 */
|
||||
pa5 = 3.5478305072e-02, /* 0x3d1151b3 */
|
||||
pa6 = -2.1663755178e-03, /* 0xbb0df9c0 */
|
||||
qa1 = 1.0642088205e-01, /* 0x3dd9f331 */
|
||||
qa2 = 5.4039794207e-01, /* 0x3f0a5785 */
|
||||
qa3 = 7.1828655899e-02, /* 0x3d931ae7 */
|
||||
qa4 = 1.2617121637e-01, /* 0x3e013307 */
|
||||
qa5 = 1.3637083583e-02, /* 0x3c5f6e13 */
|
||||
qa6 = 1.1984500103e-02, /* 0x3c445aa3 */
|
||||
/*
|
||||
* Coefficients for approximation to erfc in [1.25,1/0.35]
|
||||
*/
|
||||
ra0 = -9.8649440333e-03, /* 0xbc21a093 */
|
||||
ra1 = -6.9385856390e-01, /* 0xbf31a0b7 */
|
||||
ra2 = -1.0558626175e+01, /* 0xc128f022 */
|
||||
ra3 = -6.2375331879e+01, /* 0xc2798057 */
|
||||
ra4 = -1.6239666748e+02, /* 0xc322658c */
|
||||
ra5 = -1.8460508728e+02, /* 0xc3389ae7 */
|
||||
ra6 = -8.1287437439e+01, /* 0xc2a2932b */
|
||||
ra7 = -9.8143291473e+00, /* 0xc11d077e */
|
||||
sa1 = 1.9651271820e+01, /* 0x419d35ce */
|
||||
sa2 = 1.3765776062e+02, /* 0x4309a863 */
|
||||
sa3 = 4.3456588745e+02, /* 0x43d9486f */
|
||||
sa4 = 6.4538726807e+02, /* 0x442158c9 */
|
||||
sa5 = 4.2900814819e+02, /* 0x43d6810b */
|
||||
sa6 = 1.0863500214e+02, /* 0x42d9451f */
|
||||
sa7 = 6.5702495575e+00, /* 0x40d23f7c */
|
||||
sa8 = -6.0424413532e-02, /* 0xbd777f97 */
|
||||
/*
|
||||
* Coefficients for approximation to erfc in [1/.35,28]
|
||||
*/
|
||||
rb0 = -9.8649431020e-03, /* 0xbc21a092 */
|
||||
rb1 = -7.9928326607e-01, /* 0xbf4c9dd4 */
|
||||
rb2 = -1.7757955551e+01, /* 0xc18e104b */
|
||||
rb3 = -1.6063638306e+02, /* 0xc320a2ea */
|
||||
rb4 = -6.3756646729e+02, /* 0xc41f6441 */
|
||||
rb5 = -1.0250950928e+03, /* 0xc480230b */
|
||||
rb6 = -4.8351919556e+02, /* 0xc3f1c275 */
|
||||
sb1 = 3.0338060379e+01, /* 0x41f2b459 */
|
||||
sb2 = 3.2579251099e+02, /* 0x43a2e571 */
|
||||
sb3 = 1.5367296143e+03, /* 0x44c01759 */
|
||||
sb4 = 3.1998581543e+03, /* 0x4547fdbb */
|
||||
sb5 = 2.5530502930e+03, /* 0x451f90ce */
|
||||
sb6 = 4.7452853394e+02, /* 0x43ed43a7 */
|
||||
sb7 = -2.2440952301e+01; /* 0xc1b38712 */
|
||||
|
||||
#ifdef __STDC__
|
||||
float erff(float x)
|
||||
#else
|
||||
float erff(x)
|
||||
float x;
|
||||
#endif
|
||||
{
|
||||
int32_t hx,ix,i;
|
||||
float R,S,P,Q,s,y,z,r;
|
||||
hx = __get_float_word(x);
|
||||
ix = hx&0x7fffffff;
|
||||
if(!(ix<0x7f800000L)) { /* erf(nan)=nan */
|
||||
i = ((uint32_t)hx>>31)<<1;
|
||||
return (float)(1-i)+one/x; /* erf(+-inf)=+-1 */
|
||||
}
|
||||
|
||||
if(ix < 0x3f580000) { /* |x|<0.84375 */
|
||||
if(ix < 0x31800000) { /* |x|<2**-28 */
|
||||
if (ix < 0x04000000)
|
||||
/*avoid underflow */
|
||||
return (float)0.125*((float)8.0*x+efx8*x);
|
||||
return x + efx*x;
|
||||
}
|
||||
z = x*x;
|
||||
r = pp0+z*(pp1+z*(pp2+z*(pp3+z*pp4)));
|
||||
s = one+z*(qq1+z*(qq2+z*(qq3+z*(qq4+z*qq5))));
|
||||
y = r/s;
|
||||
return x + x*y;
|
||||
}
|
||||
if(ix < 0x3fa00000) { /* 0.84375 <= |x| < 1.25 */
|
||||
s = fabsf(x)-one;
|
||||
P = pa0+s*(pa1+s*(pa2+s*(pa3+s*(pa4+s*(pa5+s*pa6)))));
|
||||
Q = one+s*(qa1+s*(qa2+s*(qa3+s*(qa4+s*(qa5+s*qa6)))));
|
||||
if(hx>=0) return erx + P/Q; else return -erx - P/Q;
|
||||
}
|
||||
if (ix >= 0x40c00000) { /* inf>|x|>=6 */
|
||||
if(hx>=0) return one-tiny; else return tiny-one;
|
||||
}
|
||||
x = fabsf(x);
|
||||
s = one/(x*x);
|
||||
if(ix< 0x4036DB6E) { /* |x| < 1/0.35 */
|
||||
R=ra0+s*(ra1+s*(ra2+s*(ra3+s*(ra4+s*(
|
||||
ra5+s*(ra6+s*ra7))))));
|
||||
S=one+s*(sa1+s*(sa2+s*(sa3+s*(sa4+s*(
|
||||
sa5+s*(sa6+s*(sa7+s*sa8)))))));
|
||||
} else { /* |x| >= 1/0.35 */
|
||||
R=rb0+s*(rb1+s*(rb2+s*(rb3+s*(rb4+s*(
|
||||
rb5+s*rb6)))));
|
||||
S=one+s*(sb1+s*(sb2+s*(sb3+s*(sb4+s*(
|
||||
sb5+s*(sb6+s*sb7))))));
|
||||
}
|
||||
__trunc_float_word (&z);
|
||||
r = __ieee754_expf(-z*z-(float)0.5625)*__ieee754_expf((z-x)*(z+x)+R/S);
|
||||
if(hx>=0) return one-r/x; else return r/x-one;
|
||||
}
|
||||
|
||||
#ifdef __STDC__
|
||||
float erfcf(float x)
|
||||
#else
|
||||
float erfcf(x)
|
||||
float x;
|
||||
#endif
|
||||
{
|
||||
int32_t hx,ix;
|
||||
float R,S,P,Q,s,y,z,r;
|
||||
hx = __get_float_word(x);
|
||||
ix = hx&0x7fffffff;
|
||||
if(!(ix<0x7f800000L)) { /* erfc(nan)=nan */
|
||||
/* erfc(+-inf)=0,2 */
|
||||
return (float)(((uint32_t)hx>>31)<<1)+one/x;
|
||||
}
|
||||
|
||||
if(ix < 0x3f580000) { /* |x|<0.84375 */
|
||||
if(ix < 0x23800000) /* |x|<2**-56 */
|
||||
return one-x;
|
||||
z = x*x;
|
||||
r = pp0+z*(pp1+z*(pp2+z*(pp3+z*pp4)));
|
||||
s = one+z*(qq1+z*(qq2+z*(qq3+z*(qq4+z*qq5))));
|
||||
y = r/s;
|
||||
if(hx < 0x3e800000) { /* x<1/4 */
|
||||
return one-(x+x*y);
|
||||
} else {
|
||||
r = x*y;
|
||||
r += (x-half);
|
||||
return half - r ;
|
||||
}
|
||||
}
|
||||
if(ix < 0x3fa00000) { /* 0.84375 <= |x| < 1.25 */
|
||||
s = fabsf(x)-one;
|
||||
P = pa0+s*(pa1+s*(pa2+s*(pa3+s*(pa4+s*(pa5+s*pa6)))));
|
||||
Q = one+s*(qa1+s*(qa2+s*(qa3+s*(qa4+s*(qa5+s*qa6)))));
|
||||
if(hx>=0) {
|
||||
z = one-erx; return z - P/Q;
|
||||
} else {
|
||||
z = erx+P/Q; return one+z;
|
||||
}
|
||||
}
|
||||
|
||||
if (ix < 0x41e00000) { /* |x|<28 */
|
||||
x = fabsf(x);
|
||||
s = one/(x*x);
|
||||
if(ix< 0x4036DB6D) { /* |x| < 1/.35 ~ 2.857143*/
|
||||
R=ra0+s*(ra1+s*(ra2+s*(ra3+s*(ra4+s*(
|
||||
ra5+s*(ra6+s*ra7))))));
|
||||
S=one+s*(sa1+s*(sa2+s*(sa3+s*(sa4+s*(
|
||||
sa5+s*(sa6+s*(sa7+s*sa8)))))));
|
||||
} else { /* |x| >= 1/.35 ~ 2.857143 */
|
||||
if(hx<0&&ix>=0x40c00000) return two-tiny;/* x < -6 */
|
||||
R=rb0+s*(rb1+s*(rb2+s*(rb3+s*(rb4+s*(
|
||||
rb5+s*rb6)))));
|
||||
S=one+s*(sb1+s*(sb2+s*(sb3+s*(sb4+s*(
|
||||
sb5+s*(sb6+s*sb7))))));
|
||||
}
|
||||
__trunc_float_word (&z);
|
||||
r = __ieee754_expf(-z*z-(float)0.5625)*
|
||||
__ieee754_expf((z-x)*(z+x)+R/S);
|
||||
if(hx>0) return r/x; else return two-r/x;
|
||||
} else {
|
||||
if(hx>0) return tiny*tiny; else return two-tiny;
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue