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

298 lines
9.6 KiB
C
Raw Normal View History

2010-10-15 19:26:06 +00:00
/* Compute x * y + z as ternary operation.
Copyright (C) 2010-2022 Free Software Foundation, Inc.
2010-10-15 19:26:06 +00:00
This file is part of the GNU C Library.
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/>. */
2010-10-15 19:26:06 +00:00
#define NO_MATH_REDIRECT
2010-10-15 19:26:06 +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>
Use libm_alias_ldouble for ldbl-96 functions. This patch makes ldbl-96 functions use libm_alias_ldouble to define function aliases. Tested for x86_64, and tested with build-many-glibcs.py that installed stripped shared libraries are unchanged by the patch. * sysdeps/ieee754/ldbl-96/s_asinhl.c: Include <libm-alias-ldouble.h>. (asinhl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_cbrtl.c: Include <libm-alias-ldouble.h>. (cbrtl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_copysignl.c: Include <libm-alias-ldouble.h>. (copysignl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_cosl.c: Include <libm-alias-ldouble.h>. (cosl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_erfl.c: Include <libm-alias-ldouble.h>. (erfl): Define using libm_alias_ldouble. (erfcl): Likewise. * sysdeps/ieee754/ldbl-96/s_fmal.c: Include <libm-alias-ldouble.h>. (fmal): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_frexpl.c: Include <libm-alias-ldouble.h>. (frexpl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_fromfpl.c (fromfpl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_fromfpl_main.c: Include <libm-alias-ldouble.h>. * sysdeps/ieee754/ldbl-96/s_fromfpxl.c (fromfpxl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_getpayloadl.c: Include <libm-alias-ldouble.h>. (getpayloadl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_llrintl.c: Include <libm-alias-ldouble.h>. (llrintl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_llroundl.c: Include <libm-alias-ldouble.h>. (llroundl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_lrintl.c: Include <libm-alias-ldouble.h>. (lrintl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_lroundl.c: Include <libm-alias-ldouble.h>. (lroundl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_modfl.c: Include <libm-alias-ldouble.h>. (modfl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_nextupl.c: Include <libm-alias-ldouble.h>. (nextupl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_remquol.c: Include <libm-alias-ldouble.h>. (remquol): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_roundevenl.c: Include <libm-alias-ldouble.h>. (roundevenl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_roundl.c: Include <libm-alias-ldouble.h>. (roundl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_setpayloadl.c (setpayloadl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_setpayloadl_main.c: Include <libm-alias-ldouble.h>. * sysdeps/ieee754/ldbl-96/s_setpayloadsigl.c: Include <libm-alias-ldouble.h>. (setpayloadsigl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_sincosl.c: Include <libm-alias-ldouble.h>. (sincosl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_sinl.c: Include <libm-alias-ldouble.h>. (sinl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_tanhl.c: Include <libm-alias-ldouble.h>. (tanhl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_tanl.c: Include <libm-alias-ldouble.h>. (tanl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_totalorderl.c: Include <libm-alias-ldouble.h>. (totalorderl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_totalordermagl.c: Include <libm-alias-ldouble.h>. (totalordermagl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_ufromfpl.c (ufromfpl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_ufromfpxl.c (ufromfpxl): Define using libm_alias_ldouble.
2017-10-05 21:13:40 +00:00
#include <libm-alias-ldouble.h>
#include <tininess.h>
2010-10-15 19:26:06 +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 */
long double
__fmal (long double x, long double y, long double z)
{
union ieee854_long_double u, v, w;
int adjust = 0;
u.d = x;
v.d = y;
w.d = z;
if (__builtin_expect (u.ieee.exponent + v.ieee.exponent
>= 0x7fff + IEEE854_LONG_DOUBLE_BIAS
- LDBL_MANT_DIG, 0)
|| __builtin_expect (u.ieee.exponent >= 0x7fff - LDBL_MANT_DIG, 0)
|| __builtin_expect (v.ieee.exponent >= 0x7fff - LDBL_MANT_DIG, 0)
|| __builtin_expect (w.ieee.exponent >= 0x7fff - LDBL_MANT_DIG, 0)
|| __builtin_expect (u.ieee.exponent + v.ieee.exponent
<= IEEE854_LONG_DOUBLE_BIAS + LDBL_MANT_DIG, 0))
{
/* If z is Inf, but x and y are finite, the result should be
z rather than NaN. */
if (w.ieee.exponent == 0x7fff
&& u.ieee.exponent != 0x7fff
&& v.ieee.exponent != 0x7fff)
return (z + x) + y;
/* If z is zero and x are y are nonzero, compute the result
as x * y to avoid the wrong sign of a zero result if x * y
underflows to 0. */
if (z == 0 && x != 0 && y != 0)
return x * y;
/* If x or y or z is Inf/NaN, or if x * y is zero, compute as
x * y + z. */
2010-10-15 19:26:06 +00:00
if (u.ieee.exponent == 0x7fff
|| v.ieee.exponent == 0x7fff
|| w.ieee.exponent == 0x7fff
|| x == 0
|| y == 0)
2010-10-15 19:26:06 +00:00
return x * y + z;
/* If fma will certainly overflow, compute as x * y. */
if (u.ieee.exponent + v.ieee.exponent
> 0x7fff + IEEE854_LONG_DOUBLE_BIAS)
return x * y;
/* If x * y is less than 1/4 of LDBL_TRUE_MIN, neither the
result nor whether there is underflow depends on its exact
value, only on its sign. */
if (u.ieee.exponent + v.ieee.exponent
< IEEE854_LONG_DOUBLE_BIAS - LDBL_MANT_DIG - 2)
{
int neg = u.ieee.negative ^ v.ieee.negative;
long double tiny = neg ? -0x1p-16445L : 0x1p-16445L;
if (w.ieee.exponent >= 3)
return tiny + z;
/* Scaling up, adding TINY and scaling down produces the
correct result, because in round-to-nearest mode adding
TINY has no effect and in other modes double rounding is
harmless. But it may not produce required underflow
exceptions. */
v.d = z * 0x1p65L + tiny;
if (TININESS_AFTER_ROUNDING
? v.ieee.exponent < 66
: (w.ieee.exponent == 0
|| (w.ieee.exponent == 1
&& w.ieee.negative != neg
&& w.ieee.mantissa1 == 0
&& w.ieee.mantissa0 == 0x80000000)))
{
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
long double force_underflow = x * y;
math_force_eval (force_underflow);
}
return v.d * 0x1p-65L;
}
2010-10-15 19:26:06 +00:00
if (u.ieee.exponent + v.ieee.exponent
>= 0x7fff + IEEE854_LONG_DOUBLE_BIAS - LDBL_MANT_DIG)
{
/* Compute 1p-64 times smaller result and multiply
at the end. */
if (u.ieee.exponent > v.ieee.exponent)
u.ieee.exponent -= LDBL_MANT_DIG;
else
v.ieee.exponent -= LDBL_MANT_DIG;
/* If x + y exponent is very large and z exponent is very small,
it doesn't matter if we don't adjust it. */
if (w.ieee.exponent > LDBL_MANT_DIG)
w.ieee.exponent -= LDBL_MANT_DIG;
adjust = 1;
}
else if (w.ieee.exponent >= 0x7fff - LDBL_MANT_DIG)
{
/* Similarly.
If z exponent is very large and x and y exponents are
very small, adjust them up to avoid spurious underflows,
rather than down. */
if (u.ieee.exponent + v.ieee.exponent
Fix fma spurious underflows (bug 18824). Various fma implementations have logic that, when computing fma (x, y, z) where z is large (so care needs taking to avoid internal overflow) but x * y is small, scale x * y up instead of down to avoid internal underflows resulting from scaling down. (In these cases, x * y is small enough that only its sign actually matters rather than the exact value.) The threshold for scaling up instead of down was correct for "if the unscaled values were multiplied, the low part of the multiplication could underflow", and the scaling was sufficient to ensure that the low part of the multiplication did not underflow (given that cases of very small x * y - less than half the least subnormal - were previously dealt with). However, the choice in the functions wasn't between scaling up or no scaling, but between scaling up and scaling down (scaling down actually being needed when x * y isn't so small compared to z and so the exact value does matter). Thus a larger threshold is needed to ensure that scaling down doesn't produce values the multiplication of whose low parts underflows. This patch increases the thresholds accordingly. Tested for x86_64, x86 and mips64 (with the MIPS version of s_fmal.c removed so that the ldbl-128 version gets tested instead of the soft-fp one). [BZ #18824] * sysdeps/ieee754/dbl-64/s_fma.c (__fma): Increase threshold for scaling x * y up instead of down. * sysdeps/ieee754/ldbl-128/s_fmal.c (__fmal): Likewise. * sysdeps/ieee754/ldbl-96/s_fmal.c (__fmal): Likewise. * math/auto-libm-test-in: Add more tests of fma. * math/auto-libm-test-out: Regenerated.
2015-08-14 17:15:06 +00:00
<= IEEE854_LONG_DOUBLE_BIAS + 2 * LDBL_MANT_DIG)
{
if (u.ieee.exponent > v.ieee.exponent)
u.ieee.exponent += 2 * LDBL_MANT_DIG + 2;
else
v.ieee.exponent += 2 * LDBL_MANT_DIG + 2;
}
else if (u.ieee.exponent > v.ieee.exponent)
2010-10-15 19:26:06 +00:00
{
if (u.ieee.exponent > LDBL_MANT_DIG)
u.ieee.exponent -= LDBL_MANT_DIG;
}
else if (v.ieee.exponent > LDBL_MANT_DIG)
v.ieee.exponent -= LDBL_MANT_DIG;
w.ieee.exponent -= LDBL_MANT_DIG;
adjust = 1;
}
else if (u.ieee.exponent >= 0x7fff - LDBL_MANT_DIG)
{
u.ieee.exponent -= LDBL_MANT_DIG;
if (v.ieee.exponent)
v.ieee.exponent += LDBL_MANT_DIG;
else
v.d *= 0x1p64L;
}
else if (v.ieee.exponent >= 0x7fff - LDBL_MANT_DIG)
{
v.ieee.exponent -= LDBL_MANT_DIG;
if (u.ieee.exponent)
u.ieee.exponent += LDBL_MANT_DIG;
else
u.d *= 0x1p64L;
}
else /* if (u.ieee.exponent + v.ieee.exponent
<= IEEE854_LONG_DOUBLE_BIAS + LDBL_MANT_DIG) */
{
if (u.ieee.exponent > v.ieee.exponent)
u.ieee.exponent += 2 * LDBL_MANT_DIG + 2;
2010-10-15 19:26:06 +00:00
else
v.ieee.exponent += 2 * LDBL_MANT_DIG + 2;
if (w.ieee.exponent <= 4 * LDBL_MANT_DIG + 6)
2010-10-15 19:26:06 +00:00
{
if (w.ieee.exponent)
w.ieee.exponent += 2 * LDBL_MANT_DIG + 2;
2010-10-15 19:26:06 +00:00
else
w.d *= 0x1p130L;
2010-10-15 19:26:06 +00:00
adjust = -1;
}
/* Otherwise x * y should just affect inexact
and nothing else. */
}
x = u.d;
y = v.d;
z = w.d;
}
/* 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);
2010-10-15 19:26:06 +00:00
/* Multiplication m1 + m2 = x * y using Dekker's algorithm. */
#define C ((1LL << (LDBL_MANT_DIG + 1) / 2) + 1)
long double x1 = x * C;
long double y1 = y * C;
long double m1 = x * y;
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;
}
2010-10-15 19:26:06 +00:00
fesetround (FE_TOWARDZERO);
/* Perform m2 + a2 addition with round to odd. */
u.d = a2 + m2;
if (__glibc_likely (adjust == 0))
2010-10-15 19:26:06 +00:00
{
if ((u.ieee.mantissa1 & 1) == 0 && u.ieee.exponent != 0x7fff)
u.ieee.mantissa1 |= fetestexcept (FE_INEXACT) != 0;
feupdateenv (&env);
/* Result is a1 + u.d. */
return a1 + u.d;
}
else if (__glibc_likely (adjust > 0))
2010-10-15 19:26:06 +00:00
{
if ((u.ieee.mantissa1 & 1) == 0 && u.ieee.exponent != 0x7fff)
u.ieee.mantissa1 |= fetestexcept (FE_INEXACT) != 0;
feupdateenv (&env);
/* Result is a1 + u.d, scaled up. */
return (a1 + u.d) * 0x1p64L;
}
else
{
if ((u.ieee.mantissa1 & 1) == 0)
u.ieee.mantissa1 |= fetestexcept (FE_INEXACT) != 0;
v.d = a1 + u.d;
/* Ensure the addition is not scheduled after fetestexcept call. */
math_force_eval (v.d);
2010-10-15 19:26:06 +00:00
int j = fetestexcept (FE_INEXACT) != 0;
feupdateenv (&env);
/* Ensure the following computations are performed in default rounding
mode instead of just reusing the round to zero computation. */
asm volatile ("" : "=m" (u) : "m" (u));
/* If a1 + u.d is exact, the only rounding happens during
scaling down. */
if (j == 0)
return v.d * 0x1p-130L;
2010-10-15 19:26:06 +00:00
/* If result rounded to zero is not subnormal, no double
rounding will occur. */
if (v.ieee.exponent > 130)
return (a1 + u.d) * 0x1p-130L;
/* If v.d * 0x1p-130L with round to zero is a subnormal above
or equal to LDBL_MIN / 2, then v.d * 0x1p-130L shifts mantissa
2010-10-15 19:26:06 +00:00
down just by 1 bit, which means v.ieee.mantissa1 |= j would
change the round bit, not sticky or guard bit.
v.d * 0x1p-130L never normalizes by shifting up,
2010-10-15 19:26:06 +00:00
so round bit plus sticky bit should be already enough
for proper rounding. */
if (v.ieee.exponent == 130)
2010-10-15 19:26:06 +00:00
{
/* If the exponent would be in the normal range when
rounding to normal precision with unbounded exponent
range, the exact result is known and spurious underflows
must be avoided on systems detecting tininess after
rounding. */
if (TININESS_AFTER_ROUNDING)
{
w.d = a1 + u.d;
if (w.ieee.exponent == 131)
return w.d * 0x1p-130L;
}
2010-10-15 19:26:06 +00:00
/* v.ieee.mantissa1 & 2 is LSB bit of the result before rounding,
v.ieee.mantissa1 & 1 is the round bit and j is our sticky
bit. */
w.d = 0.0L;
w.ieee.mantissa1 = ((v.ieee.mantissa1 & 3) << 1) | j;
w.ieee.negative = v.ieee.negative;
v.ieee.mantissa1 &= ~3U;
v.d *= 0x1p-130L;
w.d *= 0x1p-2L;
return v.d + w.d;
2010-10-15 19:26:06 +00:00
}
v.ieee.mantissa1 |= j;
return v.d * 0x1p-130L;
2010-10-15 19:26:06 +00:00
}
}
Use libm_alias_ldouble for ldbl-96 functions. This patch makes ldbl-96 functions use libm_alias_ldouble to define function aliases. Tested for x86_64, and tested with build-many-glibcs.py that installed stripped shared libraries are unchanged by the patch. * sysdeps/ieee754/ldbl-96/s_asinhl.c: Include <libm-alias-ldouble.h>. (asinhl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_cbrtl.c: Include <libm-alias-ldouble.h>. (cbrtl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_copysignl.c: Include <libm-alias-ldouble.h>. (copysignl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_cosl.c: Include <libm-alias-ldouble.h>. (cosl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_erfl.c: Include <libm-alias-ldouble.h>. (erfl): Define using libm_alias_ldouble. (erfcl): Likewise. * sysdeps/ieee754/ldbl-96/s_fmal.c: Include <libm-alias-ldouble.h>. (fmal): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_frexpl.c: Include <libm-alias-ldouble.h>. (frexpl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_fromfpl.c (fromfpl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_fromfpl_main.c: Include <libm-alias-ldouble.h>. * sysdeps/ieee754/ldbl-96/s_fromfpxl.c (fromfpxl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_getpayloadl.c: Include <libm-alias-ldouble.h>. (getpayloadl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_llrintl.c: Include <libm-alias-ldouble.h>. (llrintl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_llroundl.c: Include <libm-alias-ldouble.h>. (llroundl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_lrintl.c: Include <libm-alias-ldouble.h>. (lrintl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_lroundl.c: Include <libm-alias-ldouble.h>. (lroundl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_modfl.c: Include <libm-alias-ldouble.h>. (modfl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_nextupl.c: Include <libm-alias-ldouble.h>. (nextupl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_remquol.c: Include <libm-alias-ldouble.h>. (remquol): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_roundevenl.c: Include <libm-alias-ldouble.h>. (roundevenl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_roundl.c: Include <libm-alias-ldouble.h>. (roundl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_setpayloadl.c (setpayloadl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_setpayloadl_main.c: Include <libm-alias-ldouble.h>. * sysdeps/ieee754/ldbl-96/s_setpayloadsigl.c: Include <libm-alias-ldouble.h>. (setpayloadsigl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_sincosl.c: Include <libm-alias-ldouble.h>. (sincosl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_sinl.c: Include <libm-alias-ldouble.h>. (sinl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_tanhl.c: Include <libm-alias-ldouble.h>. (tanhl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_tanl.c: Include <libm-alias-ldouble.h>. (tanl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_totalorderl.c: Include <libm-alias-ldouble.h>. (totalorderl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_totalordermagl.c: Include <libm-alias-ldouble.h>. (totalordermagl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_ufromfpl.c (ufromfpl): Define using libm_alias_ldouble. * sysdeps/ieee754/ldbl-96/s_ufromfpxl.c (ufromfpxl): Define using libm_alias_ldouble.
2017-10-05 21:13:40 +00:00
libm_alias_ldouble (__fma, fma)