glibc/sysdeps/ieee754/dbl-64/e_sqrt.c
Joseph Myers b4d5b8b021 Do not include math-barriers.h in math_private.h.
This patch continues the math_private.h cleanup by stopping
math_private.h from including math-barriers.h and making the users of
the barrier macros include the latter header directly.  No attempt is
made to remove any math_private.h includes that are now unused, except
in strtod_l.c where that is done to avoid line number changes in
assertions, so that installed stripped shared libraries can be
compared before and after the patch.  (I think the floating-point
environment support in math_private.h should also move out - some
architectures already have fenv_private.h as an architecture-internal
header included from their math_private.h - and after moving that out
might be a better time to identify unused math_private.h includes.)

Tested for x86_64 and x86, and tested with build-many-glibcs.py that
installed stripped shared libraries are unchanged by the patch.

	* sysdeps/generic/math_private.h: Do not include
	<math-barriers.h>.
	* stdlib/strtod_l.c: Include <math-barriers.h> instead of
	<math_private.h>.
	* math/fromfp.h: Include <math-barriers.h>.
	* math/math-narrow.h: Likewise.
	* math/s_nextafter.c: Likewise.
	* math/s_nexttowardf.c: Likewise.
	* sysdeps/aarch64/fpu/s_llrint.c: Likewise.
	* sysdeps/aarch64/fpu/s_llrintf.c: Likewise.
	* sysdeps/aarch64/fpu/s_lrint.c: Likewise.
	* sysdeps/aarch64/fpu/s_lrintf.c: Likewise.
	* sysdeps/i386/fpu/s_nextafterl.c: Likewise.
	* sysdeps/i386/fpu/s_nexttoward.c: Likewise.
	* sysdeps/i386/fpu/s_nexttowardf.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_atan2.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_atanh.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_exp.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_exp2.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_j0.c: Likewise.
	* sysdeps/ieee754/dbl-64/e_sqrt.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_expm1.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_fma.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_fmaf.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_log1p.c: Likewise.
	* sysdeps/ieee754/dbl-64/s_nearbyint.c: Likewise.
	* sysdeps/ieee754/dbl-64/wordsize-64/s_nearbyint.c: Likewise.
	* sysdeps/ieee754/flt-32/e_atanhf.c: Likewise.
	* sysdeps/ieee754/flt-32/e_j0f.c: Likewise.
	* sysdeps/ieee754/flt-32/s_expm1f.c: Likewise.
	* sysdeps/ieee754/flt-32/s_log1pf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_nearbyintf.c: Likewise.
	* sysdeps/ieee754/flt-32/s_nextafterf.c: Likewise.
	* sysdeps/ieee754/k_standardl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_asinl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_expl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/e_powl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_fmal.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_nearbyintl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_nextafterl.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_nexttoward.c: Likewise.
	* sysdeps/ieee754/ldbl-128/s_nexttowardf.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_asinl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_fmal.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_nextafterl.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_nexttoward.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_nexttowardf.c: Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_rintl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/e_atanhl.c: Likewise.
	* sysdeps/ieee754/ldbl-96/e_j0l.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_fma.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_fmal.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_nexttoward.c: Likewise.
	* sysdeps/ieee754/ldbl-96/s_nexttowardf.c: Likewise.
	* sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c: Likewise.
	* sysdeps/m68k/m680x0/fpu/s_nextafterl.c: Likewise.
2018-05-11 15:11:38 +00:00

141 lines
4.9 KiB
C

/*
* IBM Accurate Mathematical Library
* written by International Business Machines Corp.
* Copyright (C) 2001-2018 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: uroot.c */
/* */
/* FUNCTION: usqrt */
/* */
/* FILES NEEDED: dla.h endian.h mydefs.h */
/* uroot.tbl */
/* */
/* An ultimate sqrt routine. Given an IEEE double machine number x */
/* it computes the correctly rounded (to nearest) value of square */
/* root of x. */
/* Assumption: Machine arithmetic operations are performed in */
/* round to nearest mode of IEEE 754 standard. */
/* */
/*********************************************************************/
#include "endian.h"
#include "mydefs.h"
#include <dla.h>
#include "MathLib.h"
#include "root.tbl"
#include <math-barriers.h>
#include <math_private.h>
/*********************************************************************/
/* An ultimate sqrt routine. Given an IEEE double machine number x */
/* it computes the correctly rounded (to nearest) value of square */
/* root of x. */
/*********************************************************************/
double
__ieee754_sqrt (double x)
{
static const double
rt0 = 9.99999999859990725855365213134618E-01,
rt1 = 4.99999999495955425917856814202739E-01,
rt2 = 3.75017500867345182581453026130850E-01,
rt3 = 3.12523626554518656309172508769531E-01;
static const double big = 134217728.0;
double y, t, del, res, res1, hy, z, zz, p, hx, tx, ty, s;
mynumber a, c = { { 0, 0 } };
int4 k;
a.x = x;
k = a.i[HIGH_HALF];
a.i[HIGH_HALF] = (k & 0x001fffff) | 0x3fe00000;
t = inroot[(k & 0x001fffff) >> 14];
s = a.x;
/*----------------- 2^-1022 <= | x |< 2^1024 -----------------*/
if (k > 0x000fffff && k < 0x7ff00000)
{
int rm = __fegetround ();
fenv_t env;
libc_feholdexcept_setround (&env, FE_TONEAREST);
double ret;
y = 1.0 - t * (t * s);
t = t * (rt0 + y * (rt1 + y * (rt2 + y * rt3)));
c.i[HIGH_HALF] = 0x20000000 + ((k & 0x7fe00000) >> 1);
y = t * s;
hy = (y + big) - big;
del = 0.5 * t * ((s - hy * hy) - (y - hy) * (y + hy));
res = y + del;
if (res == (res + 1.002 * ((y - res) + del)))
ret = res * c.x;
else
{
res1 = res + 1.5 * ((y - res) + del);
EMULV (res, res1, z, zz, p, hx, tx, hy, ty); /* (z+zz)=res*res1 */
res = ((((z - s) + zz) < 0) ? max (res, res1) :
min (res, res1));
ret = res * c.x;
}
math_force_eval (ret);
libc_fesetenv (&env);
double dret = x / ret;
if (dret != ret)
{
double force_inexact = 1.0 / 3.0;
math_force_eval (force_inexact);
/* The square root is inexact, ret is the round-to-nearest
value which may need adjusting for other rounding
modes. */
switch (rm)
{
#ifdef FE_UPWARD
case FE_UPWARD:
if (dret > ret)
ret = (res + 0x1p-1022) * c.x;
break;
#endif
#ifdef FE_DOWNWARD
case FE_DOWNWARD:
#endif
#ifdef FE_TOWARDZERO
case FE_TOWARDZERO:
#endif
#if defined FE_DOWNWARD || defined FE_TOWARDZERO
if (dret < ret)
ret = (res - 0x1p-1022) * c.x;
break;
#endif
default:
break;
}
}
/* Otherwise (x / ret == ret), either the square root was exact or
the division was inexact. */
return ret;
}
else
{
if ((k & 0x7ff00000) == 0x7ff00000)
return x * x + x; /* sqrt(NaN)=NaN, sqrt(+inf)=+inf, sqrt(-inf)=sNaN */
if (x == 0)
return x; /* sqrt(+0)=+0, sqrt(-0)=-0 */
if (k < 0)
return (x - x) / (x - x); /* sqrt(-ve)=sNaN */
return 0x1p-256 * __ieee754_sqrt (x * 0x1p512);
}
}
strong_alias (__ieee754_sqrt, __sqrt_finite)