glibc/sysdeps/ieee754/ldbl-96/s_fma.c

101 lines
3.1 KiB
C
Raw Normal View History

2010-10-14 02:27:03 +00:00
/* Compute x * y + z as ternary operation.
Copyright (C) 2010-2021 Free Software Foundation, Inc.
2010-10-14 02:27:03 +00:00
This file is part of the GNU C Library.
Contributed by Jakub Jelinek <jakub@redhat.com>, 2010.
The GNU C Library 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.
The GNU C Library 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 the GNU C Library; if not, see
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
<https://www.gnu.org/licenses/>. */
2010-10-14 02:27:03 +00:00
#include <float.h>
#include <math.h>
#include <fenv.h>
#include <ieee754.h>
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
#include <math-barriers.h>
#include <libm-alias-double.h>
2010-10-14 02:27:03 +00:00
/* This implementation uses rounding to odd to avoid problems with
double rounding. See a paper by Boldo and Melquiond:
http://www.lri.fr/~melquion/doc/08-tc.pdf */
double
__fma (double x, double y, double z)
{
if (__glibc_unlikely (!isfinite (x) || !isfinite (y)))
return x * y + z;
else if (__glibc_unlikely (!isfinite (z)))
/* If z is Inf, but x and y are finite, the result should be z
rather than NaN. */
return (z + x) + y;
2010-10-15 19:26:06 +00:00
/* Ensure correct sign of exact 0 + 0. */
if (__glibc_unlikely ((x == 0 || y == 0) && z == 0))
{
x = math_opt_barrier (x);
return x * y + z;
}
fenv_t env;
feholdexcept (&env);
fesetround (FE_TONEAREST);
2010-10-14 02:27:03 +00:00
/* Multiplication m1 + m2 = x * y using Dekker's algorithm. */
#define C ((1ULL << (LDBL_MANT_DIG + 1) / 2) + 1)
2010-10-15 19:26:06 +00:00
long double x1 = (long double) x * C;
long double y1 = (long double) y * C;
long double m1 = (long double) x * y;
2010-10-14 02:27:03 +00:00
x1 = (x - x1) + x1;
y1 = (y - y1) + y1;
long double x2 = x - x1;
long double y2 = y - y1;
long double m2 = (((x1 * y1 - m1) + x1 * y2) + x2 * y1) + x2 * y2;
/* Addition a1 + a2 = z + m1 using Knuth's algorithm. */
long double a1 = z + m1;
long double t1 = a1 - z;
long double t2 = a1 - t1;
t1 = m1 - t1;
t2 = z - t2;
long double a2 = t1 + t2;
2014-08-01 22:13:50 +00:00
/* Ensure the arithmetic is not scheduled after feclearexcept call. */
math_force_eval (m2);
math_force_eval (a2);
feclearexcept (FE_INEXACT);
2014-08-01 22:13:50 +00:00
/* If the result is an exact zero, ensure it has the correct sign. */
if (a1 == 0 && m2 == 0)
{
feupdateenv (&env);
2014-08-01 22:13:50 +00:00
/* Ensure that round-to-nearest value of z + m1 is not reused. */
z = math_opt_barrier (z);
return z + m1;
}
2010-10-14 02:27:03 +00:00
fesetround (FE_TOWARDZERO);
/* Perform m2 + a2 addition with round to odd. */
a2 = a2 + m2;
/* Add that to a1 again using rounding to odd. */
union ieee854_long_double u;
u.d = a1 + a2;
if ((u.ieee.mantissa1 & 1) == 0 && u.ieee.exponent != 0x7fff)
u.ieee.mantissa1 |= fetestexcept (FE_INEXACT) != 0;
feupdateenv (&env);
/* Add finally round to double precision. */
return u.d;
}
#ifndef __fma
libm_alias_double (__fma, fma)
2010-10-14 02:27:03 +00:00
#endif