mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-26 23:10:06 +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.
230 lines
5.5 KiB
C
230 lines
5.5 KiB
C
/* e_jnf.c -- float version of e_jn.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 <errno.h>
|
|
#include <float.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
|
|
static const float
|
|
two = 2.0000000000e+00, /* 0x40000000 */
|
|
one = 1.0000000000e+00; /* 0x3F800000 */
|
|
|
|
static const float zero = 0.0000000000e+00;
|
|
|
|
float
|
|
__ieee754_jnf(int n, float x)
|
|
{
|
|
float ret;
|
|
{
|
|
int32_t i,hx,ix, sgn;
|
|
float a, b, temp, di;
|
|
float z, w;
|
|
|
|
/* J(-n,x) = (-1)^n * J(n, x), J(n, -x) = (-1)^n * J(n, x)
|
|
* Thus, J(-n,x) = J(n,-x)
|
|
*/
|
|
GET_FLOAT_WORD(hx,x);
|
|
ix = 0x7fffffff&hx;
|
|
/* if J(n,NaN) is NaN */
|
|
if(__builtin_expect(ix>0x7f800000, 0)) return x+x;
|
|
if(n<0){
|
|
n = -n;
|
|
x = -x;
|
|
hx ^= 0x80000000;
|
|
}
|
|
if(n==0) return(__ieee754_j0f(x));
|
|
if(n==1) return(__ieee754_j1f(x));
|
|
sgn = (n&1)&(hx>>31); /* even n -- 0, odd n -- sign(x) */
|
|
x = fabsf(x);
|
|
SET_RESTORE_ROUNDF (FE_TONEAREST);
|
|
if(__builtin_expect(ix==0||ix>=0x7f800000, 0)) /* if x is 0 or inf */
|
|
return sgn == 1 ? -zero : zero;
|
|
else if((float)n<=x) {
|
|
/* Safe to use J(n+1,x)=2n/x *J(n,x)-J(n-1,x) */
|
|
a = __ieee754_j0f(x);
|
|
b = __ieee754_j1f(x);
|
|
for(i=1;i<n;i++){
|
|
temp = b;
|
|
b = b*((double)(i+i)/x) - a; /* avoid underflow */
|
|
a = temp;
|
|
}
|
|
} else {
|
|
if(ix<0x30800000) { /* x < 2**-29 */
|
|
/* x is tiny, return the first Taylor expansion of J(n,x)
|
|
* J(n,x) = 1/n!*(x/2)^n - ...
|
|
*/
|
|
if(n>33) /* underflow */
|
|
b = zero;
|
|
else {
|
|
temp = x*(float)0.5; b = temp;
|
|
for (a=one,i=2;i<=n;i++) {
|
|
a *= (float)i; /* a = n! */
|
|
b *= temp; /* b = (x/2)^n */
|
|
}
|
|
b = b/a;
|
|
}
|
|
} else {
|
|
/* use backward recurrence */
|
|
/* x x^2 x^2
|
|
* J(n,x)/J(n-1,x) = ---- ------ ------ .....
|
|
* 2n - 2(n+1) - 2(n+2)
|
|
*
|
|
* 1 1 1
|
|
* (for large x) = ---- ------ ------ .....
|
|
* 2n 2(n+1) 2(n+2)
|
|
* -- - ------ - ------ -
|
|
* x x x
|
|
*
|
|
* Let w = 2n/x and h=2/x, then the above quotient
|
|
* is equal to the continued fraction:
|
|
* 1
|
|
* = -----------------------
|
|
* 1
|
|
* w - -----------------
|
|
* 1
|
|
* w+h - ---------
|
|
* w+2h - ...
|
|
*
|
|
* To determine how many terms needed, let
|
|
* Q(0) = w, Q(1) = w(w+h) - 1,
|
|
* Q(k) = (w+k*h)*Q(k-1) - Q(k-2),
|
|
* When Q(k) > 1e4 good for single
|
|
* When Q(k) > 1e9 good for double
|
|
* When Q(k) > 1e17 good for quadruple
|
|
*/
|
|
/* determine k */
|
|
float t,v;
|
|
float q0,q1,h,tmp; int32_t k,m;
|
|
w = (n+n)/(float)x; h = (float)2.0/(float)x;
|
|
q0 = w; z = w+h; q1 = w*z - (float)1.0; k=1;
|
|
while(q1<(float)1.0e9) {
|
|
k += 1; z += h;
|
|
tmp = z*q1 - q0;
|
|
q0 = q1;
|
|
q1 = tmp;
|
|
}
|
|
m = n+n;
|
|
for(t=zero, i = 2*(n+k); i>=m; i -= 2) t = one/(i/x-t);
|
|
a = t;
|
|
b = one;
|
|
/* estimate log((2/x)^n*n!) = n*log(2/x)+n*ln(n)
|
|
* Hence, if n*(log(2n/x)) > ...
|
|
* single 8.8722839355e+01
|
|
* double 7.09782712893383973096e+02
|
|
* long double 1.1356523406294143949491931077970765006170e+04
|
|
* then recurrent value may overflow and the result is
|
|
* likely underflow to zero
|
|
*/
|
|
tmp = n;
|
|
v = two/x;
|
|
tmp = tmp*__ieee754_logf(fabsf(v*tmp));
|
|
if(tmp<(float)8.8721679688e+01) {
|
|
for(i=n-1,di=(float)(i+i);i>0;i--){
|
|
temp = b;
|
|
b *= di;
|
|
b = b/x - a;
|
|
a = temp;
|
|
di -= two;
|
|
}
|
|
} else {
|
|
for(i=n-1,di=(float)(i+i);i>0;i--){
|
|
temp = b;
|
|
b *= di;
|
|
b = b/x - a;
|
|
a = temp;
|
|
di -= two;
|
|
/* scale b to avoid spurious overflow */
|
|
if(b>(float)1e10) {
|
|
a /= b;
|
|
t /= b;
|
|
b = one;
|
|
}
|
|
}
|
|
}
|
|
/* j0() and j1() suffer enormous loss of precision at and
|
|
* near zero; however, we know that their zero points never
|
|
* coincide, so just choose the one further away from zero.
|
|
*/
|
|
z = __ieee754_j0f (x);
|
|
w = __ieee754_j1f (x);
|
|
if (fabsf (z) >= fabsf (w))
|
|
b = (t * z / b);
|
|
else
|
|
b = (t * w / a);
|
|
}
|
|
}
|
|
if(sgn==1) ret = -b; else ret = b;
|
|
}
|
|
if (ret == 0)
|
|
ret = __copysignf (FLT_MIN, ret) * FLT_MIN;
|
|
else
|
|
math_check_force_underflow (ret);
|
|
return ret;
|
|
}
|
|
strong_alias (__ieee754_jnf, __jnf_finite)
|
|
|
|
float
|
|
__ieee754_ynf(int n, float x)
|
|
{
|
|
float ret;
|
|
{
|
|
int32_t i,hx,ix;
|
|
u_int32_t ib;
|
|
int32_t sign;
|
|
float a, b, temp;
|
|
|
|
GET_FLOAT_WORD(hx,x);
|
|
ix = 0x7fffffff&hx;
|
|
/* if Y(n,NaN) is NaN */
|
|
if(__builtin_expect(ix>0x7f800000, 0)) return x+x;
|
|
if(__builtin_expect(ix==0, 0))
|
|
return -HUGE_VALF+x; /* -inf and overflow exception. */
|
|
if(__builtin_expect(hx<0, 0)) return zero/(zero*x);
|
|
sign = 1;
|
|
if(n<0){
|
|
n = -n;
|
|
sign = 1 - ((n&1)<<1);
|
|
}
|
|
if(n==0) return(__ieee754_y0f(x));
|
|
SET_RESTORE_ROUNDF (FE_TONEAREST);
|
|
if(n==1) {
|
|
ret = sign*__ieee754_y1f(x);
|
|
goto out;
|
|
}
|
|
if(__builtin_expect(ix==0x7f800000, 0)) return zero;
|
|
|
|
a = __ieee754_y0f(x);
|
|
b = __ieee754_y1f(x);
|
|
/* quit if b is -inf */
|
|
GET_FLOAT_WORD(ib,b);
|
|
for(i=1;i<n&&ib!=0xff800000;i++){
|
|
temp = b;
|
|
b = ((double)(i+i)/x)*b - a;
|
|
GET_FLOAT_WORD(ib,b);
|
|
a = temp;
|
|
}
|
|
/* If B is +-Inf, set up errno accordingly. */
|
|
if (! isfinite (b))
|
|
__set_errno (ERANGE);
|
|
if(sign>0) ret = b; else ret = -b;
|
|
}
|
|
out:
|
|
if (isinf (ret))
|
|
ret = __copysignf (FLT_MAX, ret) * FLT_MAX;
|
|
return ret;
|
|
}
|
|
strong_alias (__ieee754_ynf, __ynf_finite)
|