AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-12-03 02:11:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
2918b0d0ec
glibc/sysdeps/i386/fpu
History
Joseph Myers 30dcf959d2 Avoid "inexact" exceptions in i386/x86_64 trunc functions (bug 15479). 
As discussed in
<https://sourceware.org/ml/libc-alpha/2016-05/msg00577.html>, TS
18661-1 disallows ceil, floor, round and trunc functions from raising
the "inexact" exception, in accordance with general IEEE 754 semantics
for when that exception is raised.  Fixing this for x87 floating point
is more complicated than for the other versions of these functions,
because they use the frndint instruction that raises "inexact" and
this can only be avoided by saving and restoring the whole
floating-point environment.

As I noted in
<https://sourceware.org/ml/libc-alpha/2016-06/msg00128.html>, I have
now implemented a GCC option -fno-fp-int-builtin-inexact for GCC 7,
such that GCC will inline these functions on x86, without caring about
"inexact", when the default -ffp-int-builtin-inexact is in effect.
This allows users to get optimized code depending on the options they
pass to the compiler, while making the out-of-line functions follow TS
18661-1 semantics and avoid "inexact".

This patch duly fixes the out-of-line trunc function implementations
to avoid "inexact", in the same way as the nearbyint implementations.

I do not know how the performance of implementations such as these
based on saving the environment and changing the rounding mode
temporarily compares to that of the C versions or SSE 4.1 versions (of
course, for 32-bit x86 SSE implementations still need to get the
return value in an x87 register); it's entirely possible other
implementations could be faster in some cases.

Tested for x86_64 and x86.

	[BZ #15479]
	* sysdeps/i386/fpu/s_trunc.S (__trunc): Save and restore
	floating-point environment rather than just control word.
	* sysdeps/i386/fpu/s_truncf.S (__truncf): Likewise.
	* sysdeps/i386/fpu/s_truncl.S (__truncl): Save and restore
	floating-point environment, with "invalid" exceptions merged in,
	rather than just control word.
	* sysdeps/x86_64/fpu/s_truncl.S (__truncl): Likewise.
	* math/libm-test.inc (trunc_test_data): Do not allow spurious
	"inexact" exceptions.
2016-06-27 17:26:52 +00:00
..
doasin.c Update. 2001-03-12 00:04:52 +00:00
e_acos.S Fix x86 acos near 1 (bug 13942). 2012-04-30 18:56:39 +00:00
e_acosf.S Fix acos (-1) in round-downwards mode on x86 (bug 14034). 2012-04-30 09:38:06 +00:00
e_acosh.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_acoshf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_acoshl.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_acosl.c Fix x86 acos near 1 (bug 13942). 2012-04-30 18:56:39 +00:00
e_asin.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
e_asinf.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
e_atan2.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
e_atan2f.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
e_atan2l.c Optimize libm 2011-10-12 11:27:51 -04:00
e_atanh.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_atanhf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_atanhl.S Fix i386 atanhl (sNaN) (bug 20219). 2016-06-07 23:08:32 +00:00
e_exp2.S Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980). 2015-09-18 21:53:22 +00:00
e_exp2f.S Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980). 2015-09-18 21:53:22 +00:00
e_exp2l.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
e_exp10.S Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980). 2015-09-18 21:53:22 +00:00
e_exp10f.S Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980). 2015-09-18 21:53:22 +00:00
e_exp10l.S Fix exp10 inaccuracy and exceptions (bugs 13884, 13914). 2012-05-06 18:23:44 +00:00
e_exp.S Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980). 2015-09-18 21:53:22 +00:00
e_expf.S Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980). 2015-09-18 21:53:22 +00:00
e_expl.S Fix i386/x86_64 expl, exp10l, expm1l for sNaN input (bug 20226). 2016-06-08 21:55:06 +00:00
e_fmod.S Optimize libm 2011-10-12 11:27:51 -04:00
e_fmodf.S Optimize libm 2011-10-12 11:27:51 -04:00
e_fmodl.c Optimize libm 2011-10-12 11:27:51 -04:00
e_hypot.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_hypotf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_ilogb.S Remove useless __ilogb*_finite aliases 2012-04-18 00:40:13 +02:00
e_ilogbf.S Remove useless __ilogb*_finite aliases 2012-04-18 00:40:13 +02:00
e_ilogbl.S Remove useless __ilogb*_finite aliases 2012-04-18 00:40:13 +02:00
e_log2.S Fix log2 (1) in round-downward mode (bug 17042). 2014-06-10 12:07:15 +00:00
e_log2f.S Fix log2 (1) in round-downward mode (bug 17042). 2014-06-10 12:07:15 +00:00
e_log2l.S Fix i386/x86_64 log2l (sNaN) (bug 20235). 2016-06-09 18:04:30 +00:00
e_log10.S Fix log10 (1) in round-downward mode (bug 16977). 2014-05-23 12:07:50 +00:00
e_log10f.S Fix log10 (1) in round-downward mode (bug 16977). 2014-05-23 12:07:50 +00:00
e_log10l.S Fix i386/x86_64 log10l (sNaN) (bug 20228). 2016-06-08 22:59:18 +00:00
e_log.S Fix i386/x86_64 log* (1) zero sign for -ffinite-math-only (bug 19213). 2015-11-05 21:56:31 +00:00
e_logf.S Fix i386/x86_64 log* (1) zero sign for -ffinite-math-only (bug 19213). 2015-11-05 21:56:31 +00:00
e_logl.S Fix i386/x86_64 logl (sNaN) (bug 20227). 2016-06-08 22:24:06 +00:00
e_pow.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_powf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
e_powl.S Fix x86_64 / x86 powl inaccuracy for integer exponents (bug 19848). 2016-03-24 01:32:52 +00:00
e_rem_pio2.c Update. 1999-07-14 00:54:57 +00:00
e_remainder.S Optimize libm 2011-10-12 11:27:51 -04:00
e_remainderf.S Optimize libm 2011-10-12 11:27:51 -04:00
e_remainderl.S Optimize libm 2011-10-12 11:27:51 -04:00
e_scalb.S Avoid excess range in results from i386 scalb functions (bug 18981). 2015-09-18 20:34:59 +00:00
e_scalbf.S Avoid excess range in results from i386 scalb functions (bug 18981). 2015-09-18 20:34:59 +00:00
e_scalbl.S Fix i386/x86_64 scalbl with sNaN input (bug 20296). 2016-06-23 22:17:41 +00:00
e_sqrt.S Fix x86 sqrt rounding (bug 14032). 2013-11-29 16:31:16 +00:00
e_sqrtf.S Optimize libm 2011-10-12 11:27:51 -04:00
e_sqrtl.c Optimize libm 2011-10-12 11:27:51 -04:00
fclrexcpt.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fedisblxcpt.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
feenablxcpt.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fegetenv.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fegetexcept.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fegetround.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
feholdexcpt.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fenv_private.h Fix yn overflow handling in non-default rounding modes (bug 16561, bug 16562). 2014-06-27 14:52:13 +00:00
fesetenv.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fesetround.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
feupdateenv.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fgetexcptflg.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fraiseexcpt.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
fsetexcptflg.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
ftestexcept.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
halfulp.c Update. 2001-03-12 00:04:52 +00:00
i386-math-asm.h Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
Implies Use x86_64 fpu/bits/fenv.h for i386 and x86_64 2012-06-06 10:13:19 -07:00
k_rem_pio2l.c Update. 1999-07-14 00:54:57 +00:00
libm-test-ulps i386: move ULPs to i686/multiarch and regenerate new ones for i386 2015-12-20 16:36:45 +01:00
math_private.h Fix math_private.h multiple include guards. 2015-11-20 23:46:23 +00:00
math-tests.h Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
mpatan2.c Update. 2001-03-12 00:04:52 +00:00
mpatan.c Update. 2001-03-12 00:04:52 +00:00
mpexp.c Update. 2001-03-12 00:04:52 +00:00
mplog.c Update. 2001-03-12 00:04:52 +00:00
mpsqrt.c Update. 2001-03-12 00:04:52 +00:00
s_asinh.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_asinhf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_asinhl.S Fix i386 asinhl (sNaN) (bug 20218). 2016-06-07 22:54:58 +00:00
s_atan.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
s_atanf.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
s_atanl.c Update. 2001-05-06 17:03:45 +00:00
s_cbrt.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_cbrtf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_cbrtl.S Fix i386 cbrtl (sNaN) (bug 20224). 2016-06-08 21:02:40 +00:00
s_ceil.S Avoid "inexact" exceptions in i386/x86_64 ceil functions (bug 15479). 2016-06-27 17:24:30 +00:00
s_ceilf.S Avoid "inexact" exceptions in i386/x86_64 ceil functions (bug 15479). 2016-06-27 17:24:30 +00:00
s_ceill.S Avoid "inexact" exceptions in i386/x86_64 ceil functions (bug 15479). 2016-06-27 17:24:30 +00:00
s_copysign.S Update. 1999-07-14 00:54:57 +00:00
s_copysignf.S Update. 1999-07-14 00:54:57 +00:00
s_copysignl.S Update. 1999-07-14 00:54:57 +00:00
s_expm1.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_expm1f.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_expm1l.S Fix x86/x86_64 expm1l inaccuracy and exceptions (bugs 13885, 13923). 2012-05-07 19:13:08 +00:00
s_fabs.S Update. 2002-04-03 00:36:12 +00:00
s_fabsf.S Update. 2002-04-03 00:36:12 +00:00
s_fabsl.S Update. 2002-04-03 00:36:12 +00:00
s_fdim.c Fix i386 fdim double rounding (bug 20255). 2016-06-14 16:41:50 +00:00
s_finite.S Update. 2002-09-10 01:40:26 +00:00
s_finitef.S Update. 2002-09-10 01:40:26 +00:00
s_finitel.S Update. 2002-09-10 01:40:26 +00:00
s_floor.S Avoid "inexact" exceptions in i386/x86_64 floor functions (bug 15479). 2016-06-27 17:25:47 +00:00
s_floorf.S Avoid "inexact" exceptions in i386/x86_64 floor functions (bug 15479). 2016-06-27 17:25:47 +00:00
s_floorl.S Avoid "inexact" exceptions in i386/x86_64 floor functions (bug 15479). 2016-06-27 17:25:47 +00:00
s_fmax.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_fmaxf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_fmaxl.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_fmin.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_fminf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_fminl.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_fpclassifyl.c Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_frexp.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_frexpf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_frexpl.S Fix frexp (NaN) (bug 20250). 2016-06-13 17:27:19 +00:00
s_isinfl.c Use <> for math.h and math_private.h everywhere. 2012-03-09 16:09:10 -08:00
s_isnanl.c Use <> for math.h and math_private.h everywhere. 2012-03-09 16:09:10 -08:00
s_llrint.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_llrintf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_llrintl.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_log1p.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
s_log1pf.S Refactor i386 libm code forcing underflow exceptions. 2015-09-24 21:41:00 +00:00
s_log1pl.S Fix i386/x86_64 log1pl (sNaN) (bug 20229). 2016-06-08 23:11:42 +00:00
s_logb.S Update. 1999-07-14 00:54:57 +00:00
s_logbf.S Update. 1999-07-14 00:54:57 +00:00
s_logbl.c Update. 2001-09-18 14:13:20 +00:00
s_lrint.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_lrintf.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_lrintl.S Update copyright dates with scripts/update-copyrights. 2016-01-04 16:05:18 +00:00
s_nearbyint.S Simplify x86 nearbyint functions. 2016-06-22 15:40:30 +00:00
s_nearbyintf.S Simplify x86 nearbyint functions. 2016-06-22 15:40:30 +00:00
s_nearbyintl.S Simplify x86 nearbyint functions. 2016-06-22 15:40:30 +00:00
s_nextafterl.c Fix x86/x86_64 nextafterl incrementing negative subnormals (bug 20205). 2016-06-03 21:30:12 +00:00
s_nexttoward.c Make nextafter, nexttoward set errno (bug 6799). 2015-11-02 18:54:19 +00:00
s_nexttowardf.c Make nextafter, nexttoward set errno (bug 6799). 2015-11-02 18:54:19 +00:00
s_remquo.S Remove remaining bounded-pointers support from i386 .S files. 2013-02-21 22:21:52 +00:00
s_remquof.S Remove remaining bounded-pointers support from i386 .S files. 2013-02-21 22:21:52 +00:00
s_remquol.S Remove remaining bounded-pointers support from i386 .S files. 2013-02-21 22:21:52 +00:00
s_rint.S Update. 1999-07-14 00:54:57 +00:00
s_rintf.S Update. 1999-07-14 00:54:57 +00:00
s_rintl.c Update. 2001-09-18 14:13:20 +00:00
s_scalbln.c Update. 1999-07-14 00:54:57 +00:00
s_scalblnf.c Update. 1999-07-14 00:54:57 +00:00
s_scalblnl.c Update. 1999-07-14 00:54:57 +00:00
s_scalbn.S Avoid excess range in results from i386 scalb functions (bug 18981). 2015-09-18 20:34:59 +00:00
s_scalbnf.S Avoid excess range in results from i386 scalb functions (bug 18981). 2015-09-18 20:34:59 +00:00
s_scalbnl.S Make scalbn set errno (bug 6803). 2015-09-16 21:11:00 +00:00
s_significand.S Update. 1999-07-14 00:54:57 +00:00
s_significandf.S Update. 1999-07-14 00:54:57 +00:00
s_significandl.c (__significandl): Really return significand and not the exponent. 2003-01-07 07:42:11 +00:00
s_trunc.S Avoid "inexact" exceptions in i386/x86_64 trunc functions (bug 15479). 2016-06-27 17:26:52 +00:00
s_truncf.S Avoid "inexact" exceptions in i386/x86_64 trunc functions (bug 15479). 2016-06-27 17:26:52 +00:00
s_truncl.S Avoid "inexact" exceptions in i386/x86_64 trunc functions (bug 15479). 2016-06-27 17:26:52 +00:00
slowexp.c Update. 2001-03-12 00:04:52 +00:00
slowpow.c Update. 2001-03-12 00:04:52 +00:00
t_exp.c Update. 1999-07-14 00:54:57 +00:00
Versions Update. 2000-06-14 00:55:24 +00:00
w_sqrt.c Fix x86 sqrt rounding (bug 14032). 2013-11-29 16:31:16 +00:00