glibc/sysdeps/ieee754/ldbl-128ibm/s_tanhl.c
Joseph Myers d96164c330 Refactor code forcing underflow exceptions.
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.
2015-09-23 22:42:30 +00:00

88 lines
2.3 KiB
C

/* @(#)s_tanh.c 5.1 93/09/24 */
/*
* ====================================================
* 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.
* ====================================================
*/
#if defined(LIBM_SCCS) && !defined(lint)
static char rcsid[] = "$NetBSD: s_tanh.c,v 1.7 1995/05/10 20:48:22 jtc Exp $";
#endif
/* Tanh(x)
* Return the Hyperbolic Tangent of x
*
* Method :
* x -x
* e - e
* 0. tanh(x) is defined to be -----------
* x -x
* e + e
* 1. reduce x to non-negative by tanh(-x) = -tanh(x).
* 2. 0 <= x <= 2**-57 : tanh(x) := x*(one+x)
* -t
* 2**-57 < x <= 1 : tanh(x) := -----; t = expm1(-2x)
* t + 2
* 2
* 1 <= x <= 40.0 : tanh(x) := 1- ----- ; t=expm1(2x)
* t + 2
* 40.0 < x <= INF : tanh(x) := 1.
*
* Special cases:
* tanh(NaN) is NaN;
* only tanh(0)=0 is exact for finite argument.
*/
#include <float.h>
#include <math.h>
#include <math_private.h>
#include <math_ldbl_opt.h>
static const long double one=1.0L, two=2.0L, tiny = 1.0e-300L;
long double __tanhl(long double x)
{
long double t,z;
int64_t jx,ix;
double xhi;
/* High word of |x|. */
xhi = ldbl_high (x);
EXTRACT_WORDS64 (jx, xhi);
ix = jx&0x7fffffffffffffffLL;
/* x is INF or NaN */
if(ix>=0x7ff0000000000000LL) {
if (jx>=0) return one/x+one; /* tanh(+-inf)=+-1 */
else return one/x-one; /* tanh(NaN) = NaN */
}
/* |x| < 40 */
if (ix < 0x4044000000000000LL) { /* |x|<40 */
if (ix == 0)
return x; /* x == +-0 */
if (ix<0x3c60000000000000LL) /* |x|<2**-57 */
{
math_check_force_underflow (x);
return x*(one+x); /* tanh(small) = small */
}
if (ix>=0x3ff0000000000000LL) { /* |x|>=1 */
t = __expm1l(two*fabsl(x));
z = one - two/(t+two);
} else {
t = __expm1l(-two*fabsl(x));
z= -t/(t+two);
}
/* |x| > 40, return +-1 */
} else {
z = one - tiny; /* raised inexact flag */
}
return (jx>=0)? z: -z;
}
long_double_symbol (libm, __tanhl, tanhl);