erf.c revision ddc0e0b53c661f6e439e3b7072b3ef353eadb4af
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
*/
/*
* Copyright 2006 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
/* INDENT OFF */
/*
* 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
* 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)
* 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)],
* 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]
* = 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
*
* 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,
*/
/* INDENT ON */
#include "libm_macros.h"
#include <math.h>
static const double xxx[] = {
/* tiny */ 1e-300,
/* half */ 5.00000000000000000000e-01, /* 3FE00000, 00000000 */
/* one */ 1.00000000000000000000e+00, /* 3FF00000, 00000000 */
/* two */ 2.00000000000000000000e+00, /* 40000000, 00000000 */
/* erx */ 8.45062911510467529297e-01, /* 3FEB0AC1, 60000000 */
/*
* Coefficients for approximation to erf on [0,0.84375]
*/
/* efx */ 1.28379167095512586316e-01, /* 3FC06EBA, 8214DB69 */
/* efx8 */ 1.02703333676410069053e+00, /* 3FF06EBA, 8214DB69 */
/* pp0 */ 1.28379167095512558561e-01, /* 3FC06EBA, 8214DB68 */
/* pp1 */ -3.25042107247001499370e-01, /* BFD4CD7D, 691CB913 */
/* pp2 */ -2.84817495755985104766e-02, /* BF9D2A51, DBD7194F */
/* pp3 */ -5.77027029648944159157e-03, /* BF77A291, 236668E4 */
/* pp4 */ -2.37630166566501626084e-05, /* BEF8EAD6, 120016AC */
/* qq1 */ 3.97917223959155352819e-01, /* 3FD97779, CDDADC09 */
/* qq2 */ 6.50222499887672944485e-02, /* 3FB0A54C, 5536CEBA */
/* qq3 */ 5.08130628187576562776e-03, /* 3F74D022, C4D36B0F */
/* qq4 */ 1.32494738004321644526e-04, /* 3F215DC9, 221C1A10 */
/* qq5 */ -3.96022827877536812320e-06, /* BED09C43, 42A26120 */
/*
* Coefficients for approximation to erf in [0.84375,1.25]
*/
/* pa0 */ -2.36211856075265944077e-03, /* BF6359B8, BEF77538 */
/* pa1 */ 4.14856118683748331666e-01, /* 3FDA8D00, AD92B34D */
/* pa2 */ -3.72207876035701323847e-01, /* BFD7D240, FBB8C3F1 */
/* pa3 */ 3.18346619901161753674e-01, /* 3FD45FCA, 805120E4 */
/* pa4 */ -1.10894694282396677476e-01, /* BFBC6398, 3D3E28EC */
/* pa5 */ 3.54783043256182359371e-02, /* 3FA22A36, 599795EB */
/* pa6 */ -2.16637559486879084300e-03, /* BF61BF38, 0A96073F */
/* qa1 */ 1.06420880400844228286e-01, /* 3FBB3E66, 18EEE323 */
/* qa2 */ 5.40397917702171048937e-01, /* 3FE14AF0, 92EB6F33 */
/* qa3 */ 7.18286544141962662868e-02, /* 3FB2635C, D99FE9A7 */
/* qa4 */ 1.26171219808761642112e-01, /* 3FC02660, E763351F */
/* qa5 */ 1.36370839120290507362e-02, /* 3F8BEDC2, 6B51DD1C */
/* qa6 */ 1.19844998467991074170e-02, /* 3F888B54, 5735151D */
/*
* Coefficients for approximation to erfc in [1.25,1/0.35]
*/
/* ra0 */ -9.86494403484714822705e-03, /* BF843412, 600D6435 */
/* ra1 */ -6.93858572707181764372e-01, /* BFE63416, E4BA7360 */
/* ra2 */ -1.05586262253232909814e+01, /* C0251E04, 41B0E726 */
/* ra3 */ -6.23753324503260060396e+01, /* C04F300A, E4CBA38D */
/* ra4 */ -1.62396669462573470355e+02, /* C0644CB1, 84282266 */
/* ra5 */ -1.84605092906711035994e+02, /* C067135C, EBCCABB2 */
/* ra6 */ -8.12874355063065934246e+01, /* C0545265, 57E4D2F2 */
/* ra7 */ -9.81432934416914548592e+00, /* C023A0EF, C69AC25C */
/* sa1 */ 1.96512716674392571292e+01, /* 4033A6B9, BD707687 */
/* sa2 */ 1.37657754143519042600e+02, /* 4061350C, 526AE721 */
/* sa3 */ 4.34565877475229228821e+02, /* 407B290D, D58A1A71 */
/* sa4 */ 6.45387271733267880336e+02, /* 40842B19, 21EC2868 */
/* sa5 */ 4.29008140027567833386e+02, /* 407AD021, 57700314 */
/* sa6 */ 1.08635005541779435134e+02, /* 405B28A3, EE48AE2C */
/* sa7 */ 6.57024977031928170135e+00, /* 401A47EF, 8E484A93 */
/* sa8 */ -6.04244152148580987438e-02, /* BFAEEFF2, EE749A62 */
/*
* Coefficients for approximation to erfc in [1/.35,28]
*/
/* rb0 */ -9.86494292470009928597e-03, /* BF843412, 39E86F4A */
/* rb1 */ -7.99283237680523006574e-01, /* BFE993BA, 70C285DE */
/* rb2 */ -1.77579549177547519889e+01, /* C031C209, 555F995A */
/* rb3 */ -1.60636384855821916062e+02, /* C064145D, 43C5ED98 */
/* rb4 */ -6.37566443368389627722e+02, /* C083EC88, 1375F228 */
/* rb5 */ -1.02509513161107724954e+03, /* C0900461, 6A2E5992 */
/* rb6 */ -4.83519191608651397019e+02, /* C07E384E, 9BDC383F */
/* sb1 */ 3.03380607434824582924e+01, /* 403E568B, 261D5190 */
/* sb2 */ 3.25792512996573918826e+02, /* 40745CAE, 221B9F0A */
/* sb3 */ 1.53672958608443695994e+03, /* 409802EB, 189D5118 */
/* sb4 */ 3.19985821950859553908e+03, /* 40A8FFB7, 688C246A */
/* sb5 */ 2.55305040643316442583e+03, /* 40A3F219, CEDF3BE6 */
/* sb6 */ 4.74528541206955367215e+02, /* 407DA874, E79FE763 */
/* sb7 */ -2.24409524465858183362e+01 /* C03670E2, 42712D62 */
};
/*
* Coefficients for approximation to erf on [0,0.84375]
*/
/*
* Coefficients for approximation to erf in [0.84375,1.25]
*/
/*
* Coefficients for approximation to erfc in [1.25,1/0.35]
*/
/*
* Coefficients for approximation to erfc in [1/.35,28]
*/
double
erf(double x) {
double R, S, P, Q, s, y, z, r;
#if defined(FPADD_TRAPS_INCOMPLETE_ON_NAN)
return (x);
#endif
}
return (x + efx * x);
}
z = x * x;
s = one +
y = r / s;
return (x + x * y);
}
if (hx >= 0)
return (erx + P / Q);
else
return (-erx - P / Q);
}
if (hx >= 0)
else
}
x = fabs(x);
s = one / (x * x);
} else { /* |x| >= 1/0.35 */
}
z = x;
((int *) &z)[LOWORD] = 0;
if (hx >= 0)
return (one - r / x);
else
return (r / x - one);
}
double
erfc(double x) {
double R, S, P, Q, s, y, z, r;
#if defined(FPADD_TRAPS_INCOMPLETE_ON_NAN)
return (x);
#endif
/* erfc(+-inf)=0,2 */
}
return (one - x);
z = x * x;
s = one +
y = r / s;
return (one - (x + x * y));
} else {
r = x * y;
r += (x - half);
return (half - r);
}
}
if (hx >= 0) {
return (z - P / Q);
} else {
z = erx + P / Q;
return (one + z);
}
}
x = fabs(x);
s = one / (x * x);
} else {
/* |x| >= 1/.35 ~ 2.857143 */
}
z = x;
((int *) &z)[LOWORD] = 0;
if (hx > 0)
return (r / x);
else
return (two - r / x);
} else {
if (hx > 0)
else
}
}