2000-12-27 19:58:36 +00:00
|
|
|
#ifndef _FENV_H
|
1998-08-03 16:47:01 +00:00
|
|
|
#include <math/fenv.h>
|
2000-12-27 19:58:36 +00:00
|
|
|
|
2012-11-02 23:21:36 +00:00
|
|
|
#ifndef _ISOMAC
|
2013-09-04 20:47:21 +00:00
|
|
|
# include <stdbool.h>
|
2000-12-27 19:58:36 +00:00
|
|
|
/* Now define the internal interfaces. */
|
|
|
|
|
|
|
|
extern int __feclearexcept (int __excepts);
|
2008-04-12 00:51:34 +00:00
|
|
|
extern int __fegetexcept (void);
|
2000-12-27 19:58:36 +00:00
|
|
|
extern int __fegetexceptflag (fexcept_t *__flagp, int __excepts);
|
|
|
|
extern int __feraiseexcept (int __excepts);
|
2012-01-08 04:57:22 +00:00
|
|
|
extern int __fesetexceptflag (const fexcept_t *__flagp, int __excepts);
|
2000-12-27 19:58:36 +00:00
|
|
|
extern int __fegetenv (fenv_t *__envp);
|
2012-01-08 04:57:22 +00:00
|
|
|
extern int __fesetenv (const fenv_t *__envp);
|
|
|
|
extern int __feupdateenv (const fenv_t *__envp);
|
2015-09-15 20:36:50 +00:00
|
|
|
extern __typeof (fegetround) __fegetround __attribute_pure__;
|
2015-01-05 23:06:14 +00:00
|
|
|
extern __typeof (feholdexcept) __feholdexcept;
|
2015-01-07 00:41:23 +00:00
|
|
|
extern __typeof (fesetround) __fesetround;
|
2000-12-27 19:58:36 +00:00
|
|
|
|
Update.
2002-09-09 Jakub Jelinek <jakub@redhat.com>
* include/math.h (__finite_internal, __finitef_internal,
__finitel_internal, __isinf_internal, __isnan_internal): Remove.
(isfinite): Remove.
(__finite, __isinf, __isnan, __finitef, __isinff, __isnanf, __finitel,
__isinfl, __isnanl): Add hidden_proto.
(__fpclassify, __fpclassifyf, __fpclassifyl, __expm1l): Add
libm_hidden_proto.
* math/Makefile (libm-calls): Add s_isinf and s_isnan.
* stdio-common/printf_fp.c (__printf_fp): Remove INTUSE from
__is{inf,nan} calls.
* stdio-common/printf_size.c (printf_size): Likewise.
* sysdeps/generic/printf_fphex.c (__printf_fphex): Likewise.
* sysdeps/generic/s_ldexp.c (__ldexp): Likewise.
* sysdeps/generic/s_ldexpf.c (__ldexpf): Likewise.
* sysdeps/generic/s_ldexpl.c (__ldexpl): Likewise.
* sysdeps/generic/s_expm1l.c (__expm1l): Add libm_hidden_def.
* sysdeps/i386/fpu/s_finite.S (__finite_internal): Remove alias.
(__finite): Add hidden_def.
* sysdeps/i386/fpu/s_finitef.S (__finitef_internal): Remove alias.
(__finitef): Add hidden_def.
* sysdeps/i386/fpu/s_finitel.S (__finitel_internal): Remove alias.
(__finitel): Add hidden_def.
* sysdeps/i386/fpu/s_isinfl.c (__isinfl): Remove INTDEF. Add
hidden_def.
* sysdeps/i386/fpu/s_isnanl.c (__isnanl): Likewise.
* sysdeps/i386/fpu/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/i386/fpu/s_expm1l.S (__expm1l): Likewise.
* sysdeps/ieee754/dbl-64/s_finite.c (__finite): Remove INTDEF. Add
hidden_def.
* sysdeps/ieee754/dbl-64/s_isinf.c (__isinf): Likewise.
(__isinfl): Remove INTDEF.
* sysdeps/ieee754/dbl-64/s_isnan.c (__isnan): Remove INTDEF. Add
hidden_def.
(__isnanl): Remove INTDEF.
* sysdeps/ieee754/dbl-64/s_fpclassify.c (__fpclassify): Add
libm_hidden_def.
* sysdeps/ieee754/dbl-64/e_lgamma_r.c (sin_pi): Use __sin and __cos
instead of sin and cos.
* sysdeps/ieee754/flt-32/s_finitef.c (__finitef): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/flt-32/s_isinff.c (__isinff): Likewise.
* sysdeps/ieee754/flt-32/s_isnanf.c (__isnanf): Likewise.
* sysdeps/ieee754/flt-32/s_fpclassifyf.c (__fpclassifyf): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-128/s_finitel.c (__finitel): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/ldbl-128/s_isinfl.c (__isinfl): Likewise.
* sysdeps/ieee754/ldbl-128/s_isnanl.c (__isnanl): Likewise.
* sysdeps/ieee754/ldbl-128/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-128/s_expm1l.c (__expm1l): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-96/s_finitel.c (__finitel): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/ldbl-96/s_isinfl.c (__isinfl): Likewise.
* sysdeps/ieee754/ldbl-96/s_isnanl.c (__isnanl): Likewise.
* sysdeps/ieee754/ldbl-96/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/ia64/fpu/s_finite.S (__finite_internal, __finitef_internal,
__finitel_internal): Remove aliases.
(__finite, __finitef, __finitel): Add hidden_def.
* sysdeps/ia64/fpu/s_isnan.S (__isnan_internal, __isnanf_internal,
__isnanl_internal): Remove aliases.
(__isnan, __isnanf, __isnanl): Add hidden_def.
* sysdeps/ia64/fpu/s_isinf.S (__isinf_internal, __isinff_internal,
__isinfl_internal): Remove aliases.
(__isinf, __isinff, __isinfl): Add hidden_def.
* sysdeps/ia64/fpu/s_fpclassify.S (__fpclassify, __fpclassifyf,
__fpclassifyl): Add libm_hidden_def.
* sysdeps/ia64/fpu/s_expm1l.S (__expm1l): Likewise.
* sysdeps/m68k/s_isinfl.c (__isinfl): Remove INTDEF. Add hidden_def.
* sysdeps/m68k/fpu/s_isinf.c (INTDEFX): Remove.
(hidden_defx): Define and use.
* sysdeps/m68k/fpu/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/m68k/fpu/s_expm1l.c (__expm1l): Likewise.
* sysdeps/m68k/s_isnanl.c (__isnanl): Add hidden_def.
* sysdeps/powerpc/fpu/s_isnan.c (__isnan, __isnanf, __isnanl):
Remove INTDEF.
(__isnan, __isnanf): Add hidden_def.
* sysdeps/x86_64/fpu/s_finitel.S (__finitel_internal): Remove alias.
(__finitel): Add libm_hidden_def.
* sysdeps/x86_64/fpu/s_expm1l.S (__expm1l): Likewise.
* include/fenv.h (feraiseexcept, fesetenv): Add libm_hidden_proto.
* sysdeps/alpha/fpu/fesetenv.c (fesetenv): Add libm_hidden_ver.
* sysdeps/alpha/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/arm/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/arm/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/generic/fesetenv.c (fesetenv): Likewise.
* sysdeps/generic/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/i386/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/i386/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/m68k/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/m68k/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/mips/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/mips/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/powerpc/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/powerpc/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sparc/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/sparc/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/hppa/fpu/fesetenv.c (fesetenv): Add libm_hidden_def.
* sysdeps/hppa/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/ia64/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/ia64/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sh/sh4/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/sh/sh4/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/s390/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/s390/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/x86_64/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/x86_64/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
2002-09-10 01:40:26 +00:00
|
|
|
libm_hidden_proto (feraiseexcept)
|
Fix libm feraiseexcept namespace (bug 17723).
Various C90 and UNIX98 libm functions call feraiseexcept, which is not
in those standards. This causes linknamespace test failures - except
on x86 / x86_64, where feraiseexcept is inline (for the relevant
constant arguments) in bits/fenv.h.
This patch fixes this by making those functions call __feraiseexcept
instead. All changes are applied to all architectures rather than
considering the possibility that some might not be needed in some
cases (e.g. x86) as it seems most maintainable to keep architectures
consistent.
Where __feraiseexcept does not exist, it is added, with feraiseexcept
made a weak alias; where it is a strong alias, it is made weak.
libm_hidden_def / libm_hidden_proto are used with __feraiseexcept
(this might in some cases improve code generation for existing calls
to __feraiseexcept in some code on some architectures). Where there
are dummy feraiseexcept macros (on architectures without
floating-point exceptions support, to avoid compile errors from
references to undefined FE_* macros), corresponding dummy
__feraiseexcept macros are added. And on x86, to ensure
__feraiseexcept calls still get inlined, the inline function in
bits/fenv.h is refactored so that most of it can be reused in an
inline __feraiseexcept in a separate include/bits/fenv.h.
Calls are changed in C90/UNIX98 functions, but generally not in
functions missing from those standards. They are also changed in
libc_fe* functions (on the basis that those might be used in any libm
function), and in feupdateenv (on the same basis - may be used, via
default libc_*, in any libm function - of course feupdateenv will need
changing to __feupdateenv in a subsequent patch to make that fully
namespace-clean).
No __feraiseexcept is added corresponding to the feraiseexcept in
powerpc bits/fenvinline.h, because that macro definition is
conditional on !defined __NO_MATH_INLINES, and glibc libm is built
with -D__NO_MATH_INLINES, so changing internal calls to use
__feraiseexcept should make no difference.
Tested for x86_64 (testsuite; the only change in disassembly of
installed shared libraries is a slight code reordering in clog10, of
no apparent significance). Also tested for MIPS, where (in the
configuration tested) it eliminates math.h linknamespace failures for
n32 and n64 (some for o32 remain because of other issues).
[BZ #17723]
* include/fenv.h (__feraiseexcept): Use libm_hidden_proto.
* math/fraiseexcpt.c (__feraiseexcept): Use libm_hidden_def.
* sysdeps/aarch64/fpu/fraiseexcpt.c (feraiseexcept): Rename to
__feraiseexcept and define as weak alias of __feraiseexcept. Use
libm_hidden_weak.
* sysdeps/arm/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/hppa/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/i386/fpu/fraiseexcpt.c (__feraiseexcept): Use
libm_hidden_def.
* sysdeps/ia64/fpu/fraiseexcpt.c (feraiseexcept): Rename to
__feraiseexcept and define as weak alias of __feraiseexcept. Use
libm_hidden_weak.
* sysdeps/m68k/coldfire/fpu/fraiseexcpt.c (feraiseexcept):
Likewise.
* sysdeps/microblaze/math_private.h (__feraiseexcept): New macro.
* sysdeps/mips/fpu/fraiseexcpt.c (feraiseexcept): Rename to
__feraiseexcept and define as weak alias of __feraiseexcept. Use
libm_hidden_weak.
* sysdeps/powerpc/fpu/fraiseexcpt.c (__feraiseexcept): Use
libm_hidden_def.
* sysdeps/powerpc/nofpu/fraiseexcpt.c (__feraiseexcept): Likewise.
* sysdeps/powerpc/powerpc32/e500/nofpu/fraiseexcpt.c
(__feraiseexcept): Likewise.
* sysdeps/s390/fpu/fraiseexcpt.c (feraiseexcept): Rename to
__feraiseexcept and define as weak alias of __feraiseexcept. Use
libm_hidden_weak.
* sysdeps/sh/sh4/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sparc/fpu/fraiseexcpt.c (__feraiseexcept): Use
libm_hidden_def.
* sysdeps/tile/math_private.h (__feraiseexcept): New macro.
* sysdeps/unix/sysv/linux/alpha/fraiseexcpt.S (__feraiseexcept):
Use libm_hidden_def.
* sysdeps/x86_64/fpu/fraiseexcpt.c (__feraiseexcept): Use
libm_hidden_def.
(feraiseexcept): Define as weak not strong alias. Use
libm_hidden_weak.
* sysdeps/x86/fpu/bits/fenv.h (__feraiseexcept_invalid_divbyzero):
New inline function. Factored out of ...
(feraiseexcept): ... here. Use __feraiseexcept_invalid_divbyzero.
* sysdeps/x86/fpu/include/bits/fenv.h: New file.
* math/e_scalb.c (invalid_fn): Call __feraiseexcept instead of
feraiseexcept.
* math/w_acos.c (__acos): Likewise.
* math/w_asin.c (__asin): Likewise.
* math/w_ilogb.c (__ilogb): Likewise.
* math/w_j0.c (y0): Likewise.
* math/w_j1.c (y1): Likewise.
* math/w_jn.c (yn): Likewise.
* math/w_log.c (__log): Likewise.
* math/w_log10.c (__log10): Likewise.
* sysdeps/aarch64/fpu/feupdateenv.c (feupdateenv): Likewise.
* sysdeps/aarch64/fpu/math_private.h
(libc_feupdateenv_test_aarch64): Likewise.
* sysdeps/alpha/fpu/feupdateenv.c (__feupdateenv): Likewise.
* sysdeps/arm/fenv_private.h (libc_feupdateenv_test_vfp): Likewise.
* sysdeps/arm/feupdateenv.c (feupdateenv): Likewise.
* sysdeps/ia64/fpu/feupdateenv.c (feupdateenv): Likewise.
* sysdeps/m68k/fpu/feupdateenv.c (__feupdateenv): Likewise.
* sysdeps/mips/fpu/feupdateenv.c (feupdateenv): Likewise.
* sysdeps/powerpc/fpu/e_sqrt.c (__slow_ieee754_sqrt): Likewise.
* sysdeps/s390/fpu/feupdateenv.c (feupdateenv): Likewise.
* sysdeps/sh/sh4/fpu/feupdateenv.c (feupdateenv): Likewise.
* sysdeps/sparc/fpu/feupdateenv.c (__feupdateenv): Likewise.
2014-12-30 17:08:09 +00:00
|
|
|
libm_hidden_proto (__feraiseexcept)
|
2010-02-10 06:34:17 +00:00
|
|
|
libm_hidden_proto (fegetenv)
|
2014-12-31 22:07:52 +00:00
|
|
|
libm_hidden_proto (__fegetenv)
|
2013-11-28 16:50:38 +00:00
|
|
|
libm_hidden_proto (fegetround)
|
2015-01-02 20:44:42 +00:00
|
|
|
libm_hidden_proto (__fegetround)
|
Update.
2002-09-09 Jakub Jelinek <jakub@redhat.com>
* include/math.h (__finite_internal, __finitef_internal,
__finitel_internal, __isinf_internal, __isnan_internal): Remove.
(isfinite): Remove.
(__finite, __isinf, __isnan, __finitef, __isinff, __isnanf, __finitel,
__isinfl, __isnanl): Add hidden_proto.
(__fpclassify, __fpclassifyf, __fpclassifyl, __expm1l): Add
libm_hidden_proto.
* math/Makefile (libm-calls): Add s_isinf and s_isnan.
* stdio-common/printf_fp.c (__printf_fp): Remove INTUSE from
__is{inf,nan} calls.
* stdio-common/printf_size.c (printf_size): Likewise.
* sysdeps/generic/printf_fphex.c (__printf_fphex): Likewise.
* sysdeps/generic/s_ldexp.c (__ldexp): Likewise.
* sysdeps/generic/s_ldexpf.c (__ldexpf): Likewise.
* sysdeps/generic/s_ldexpl.c (__ldexpl): Likewise.
* sysdeps/generic/s_expm1l.c (__expm1l): Add libm_hidden_def.
* sysdeps/i386/fpu/s_finite.S (__finite_internal): Remove alias.
(__finite): Add hidden_def.
* sysdeps/i386/fpu/s_finitef.S (__finitef_internal): Remove alias.
(__finitef): Add hidden_def.
* sysdeps/i386/fpu/s_finitel.S (__finitel_internal): Remove alias.
(__finitel): Add hidden_def.
* sysdeps/i386/fpu/s_isinfl.c (__isinfl): Remove INTDEF. Add
hidden_def.
* sysdeps/i386/fpu/s_isnanl.c (__isnanl): Likewise.
* sysdeps/i386/fpu/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/i386/fpu/s_expm1l.S (__expm1l): Likewise.
* sysdeps/ieee754/dbl-64/s_finite.c (__finite): Remove INTDEF. Add
hidden_def.
* sysdeps/ieee754/dbl-64/s_isinf.c (__isinf): Likewise.
(__isinfl): Remove INTDEF.
* sysdeps/ieee754/dbl-64/s_isnan.c (__isnan): Remove INTDEF. Add
hidden_def.
(__isnanl): Remove INTDEF.
* sysdeps/ieee754/dbl-64/s_fpclassify.c (__fpclassify): Add
libm_hidden_def.
* sysdeps/ieee754/dbl-64/e_lgamma_r.c (sin_pi): Use __sin and __cos
instead of sin and cos.
* sysdeps/ieee754/flt-32/s_finitef.c (__finitef): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/flt-32/s_isinff.c (__isinff): Likewise.
* sysdeps/ieee754/flt-32/s_isnanf.c (__isnanf): Likewise.
* sysdeps/ieee754/flt-32/s_fpclassifyf.c (__fpclassifyf): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-128/s_finitel.c (__finitel): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/ldbl-128/s_isinfl.c (__isinfl): Likewise.
* sysdeps/ieee754/ldbl-128/s_isnanl.c (__isnanl): Likewise.
* sysdeps/ieee754/ldbl-128/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-128/s_expm1l.c (__expm1l): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-96/s_finitel.c (__finitel): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/ldbl-96/s_isinfl.c (__isinfl): Likewise.
* sysdeps/ieee754/ldbl-96/s_isnanl.c (__isnanl): Likewise.
* sysdeps/ieee754/ldbl-96/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/ia64/fpu/s_finite.S (__finite_internal, __finitef_internal,
__finitel_internal): Remove aliases.
(__finite, __finitef, __finitel): Add hidden_def.
* sysdeps/ia64/fpu/s_isnan.S (__isnan_internal, __isnanf_internal,
__isnanl_internal): Remove aliases.
(__isnan, __isnanf, __isnanl): Add hidden_def.
* sysdeps/ia64/fpu/s_isinf.S (__isinf_internal, __isinff_internal,
__isinfl_internal): Remove aliases.
(__isinf, __isinff, __isinfl): Add hidden_def.
* sysdeps/ia64/fpu/s_fpclassify.S (__fpclassify, __fpclassifyf,
__fpclassifyl): Add libm_hidden_def.
* sysdeps/ia64/fpu/s_expm1l.S (__expm1l): Likewise.
* sysdeps/m68k/s_isinfl.c (__isinfl): Remove INTDEF. Add hidden_def.
* sysdeps/m68k/fpu/s_isinf.c (INTDEFX): Remove.
(hidden_defx): Define and use.
* sysdeps/m68k/fpu/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/m68k/fpu/s_expm1l.c (__expm1l): Likewise.
* sysdeps/m68k/s_isnanl.c (__isnanl): Add hidden_def.
* sysdeps/powerpc/fpu/s_isnan.c (__isnan, __isnanf, __isnanl):
Remove INTDEF.
(__isnan, __isnanf): Add hidden_def.
* sysdeps/x86_64/fpu/s_finitel.S (__finitel_internal): Remove alias.
(__finitel): Add libm_hidden_def.
* sysdeps/x86_64/fpu/s_expm1l.S (__expm1l): Likewise.
* include/fenv.h (feraiseexcept, fesetenv): Add libm_hidden_proto.
* sysdeps/alpha/fpu/fesetenv.c (fesetenv): Add libm_hidden_ver.
* sysdeps/alpha/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/arm/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/arm/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/generic/fesetenv.c (fesetenv): Likewise.
* sysdeps/generic/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/i386/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/i386/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/m68k/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/m68k/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/mips/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/mips/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/powerpc/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/powerpc/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sparc/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/sparc/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/hppa/fpu/fesetenv.c (fesetenv): Add libm_hidden_def.
* sysdeps/hppa/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/ia64/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/ia64/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sh/sh4/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/sh/sh4/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/s390/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/s390/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/x86_64/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/x86_64/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
2002-09-10 01:40:26 +00:00
|
|
|
libm_hidden_proto (fesetenv)
|
2015-01-06 23:36:20 +00:00
|
|
|
libm_hidden_proto (__fesetenv)
|
2005-07-08 18:54:49 +00:00
|
|
|
libm_hidden_proto (fesetround)
|
2015-01-07 00:41:23 +00:00
|
|
|
libm_hidden_proto (__fesetround)
|
2005-07-08 18:54:49 +00:00
|
|
|
libm_hidden_proto (feholdexcept)
|
2015-01-05 23:06:14 +00:00
|
|
|
libm_hidden_proto (__feholdexcept)
|
2010-10-11 13:27:05 +00:00
|
|
|
libm_hidden_proto (feupdateenv)
|
2015-01-07 19:01:20 +00:00
|
|
|
libm_hidden_proto (__feupdateenv)
|
2010-10-11 13:27:05 +00:00
|
|
|
libm_hidden_proto (fetestexcept)
|
2012-11-03 19:48:53 +00:00
|
|
|
libm_hidden_proto (feclearexcept)
|
Update.
2002-09-09 Jakub Jelinek <jakub@redhat.com>
* include/math.h (__finite_internal, __finitef_internal,
__finitel_internal, __isinf_internal, __isnan_internal): Remove.
(isfinite): Remove.
(__finite, __isinf, __isnan, __finitef, __isinff, __isnanf, __finitel,
__isinfl, __isnanl): Add hidden_proto.
(__fpclassify, __fpclassifyf, __fpclassifyl, __expm1l): Add
libm_hidden_proto.
* math/Makefile (libm-calls): Add s_isinf and s_isnan.
* stdio-common/printf_fp.c (__printf_fp): Remove INTUSE from
__is{inf,nan} calls.
* stdio-common/printf_size.c (printf_size): Likewise.
* sysdeps/generic/printf_fphex.c (__printf_fphex): Likewise.
* sysdeps/generic/s_ldexp.c (__ldexp): Likewise.
* sysdeps/generic/s_ldexpf.c (__ldexpf): Likewise.
* sysdeps/generic/s_ldexpl.c (__ldexpl): Likewise.
* sysdeps/generic/s_expm1l.c (__expm1l): Add libm_hidden_def.
* sysdeps/i386/fpu/s_finite.S (__finite_internal): Remove alias.
(__finite): Add hidden_def.
* sysdeps/i386/fpu/s_finitef.S (__finitef_internal): Remove alias.
(__finitef): Add hidden_def.
* sysdeps/i386/fpu/s_finitel.S (__finitel_internal): Remove alias.
(__finitel): Add hidden_def.
* sysdeps/i386/fpu/s_isinfl.c (__isinfl): Remove INTDEF. Add
hidden_def.
* sysdeps/i386/fpu/s_isnanl.c (__isnanl): Likewise.
* sysdeps/i386/fpu/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/i386/fpu/s_expm1l.S (__expm1l): Likewise.
* sysdeps/ieee754/dbl-64/s_finite.c (__finite): Remove INTDEF. Add
hidden_def.
* sysdeps/ieee754/dbl-64/s_isinf.c (__isinf): Likewise.
(__isinfl): Remove INTDEF.
* sysdeps/ieee754/dbl-64/s_isnan.c (__isnan): Remove INTDEF. Add
hidden_def.
(__isnanl): Remove INTDEF.
* sysdeps/ieee754/dbl-64/s_fpclassify.c (__fpclassify): Add
libm_hidden_def.
* sysdeps/ieee754/dbl-64/e_lgamma_r.c (sin_pi): Use __sin and __cos
instead of sin and cos.
* sysdeps/ieee754/flt-32/s_finitef.c (__finitef): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/flt-32/s_isinff.c (__isinff): Likewise.
* sysdeps/ieee754/flt-32/s_isnanf.c (__isnanf): Likewise.
* sysdeps/ieee754/flt-32/s_fpclassifyf.c (__fpclassifyf): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-128/s_finitel.c (__finitel): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/ldbl-128/s_isinfl.c (__isinfl): Likewise.
* sysdeps/ieee754/ldbl-128/s_isnanl.c (__isnanl): Likewise.
* sysdeps/ieee754/ldbl-128/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-128/s_expm1l.c (__expm1l): Add
libm_hidden_def.
* sysdeps/ieee754/ldbl-96/s_finitel.c (__finitel): Remove INTDEF.
Add hidden_def.
* sysdeps/ieee754/ldbl-96/s_isinfl.c (__isinfl): Likewise.
* sysdeps/ieee754/ldbl-96/s_isnanl.c (__isnanl): Likewise.
* sysdeps/ieee754/ldbl-96/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/ia64/fpu/s_finite.S (__finite_internal, __finitef_internal,
__finitel_internal): Remove aliases.
(__finite, __finitef, __finitel): Add hidden_def.
* sysdeps/ia64/fpu/s_isnan.S (__isnan_internal, __isnanf_internal,
__isnanl_internal): Remove aliases.
(__isnan, __isnanf, __isnanl): Add hidden_def.
* sysdeps/ia64/fpu/s_isinf.S (__isinf_internal, __isinff_internal,
__isinfl_internal): Remove aliases.
(__isinf, __isinff, __isinfl): Add hidden_def.
* sysdeps/ia64/fpu/s_fpclassify.S (__fpclassify, __fpclassifyf,
__fpclassifyl): Add libm_hidden_def.
* sysdeps/ia64/fpu/s_expm1l.S (__expm1l): Likewise.
* sysdeps/m68k/s_isinfl.c (__isinfl): Remove INTDEF. Add hidden_def.
* sysdeps/m68k/fpu/s_isinf.c (INTDEFX): Remove.
(hidden_defx): Define and use.
* sysdeps/m68k/fpu/s_fpclassifyl.c (__fpclassifyl): Add
libm_hidden_def.
* sysdeps/m68k/fpu/s_expm1l.c (__expm1l): Likewise.
* sysdeps/m68k/s_isnanl.c (__isnanl): Add hidden_def.
* sysdeps/powerpc/fpu/s_isnan.c (__isnan, __isnanf, __isnanl):
Remove INTDEF.
(__isnan, __isnanf): Add hidden_def.
* sysdeps/x86_64/fpu/s_finitel.S (__finitel_internal): Remove alias.
(__finitel): Add libm_hidden_def.
* sysdeps/x86_64/fpu/s_expm1l.S (__expm1l): Likewise.
* include/fenv.h (feraiseexcept, fesetenv): Add libm_hidden_proto.
* sysdeps/alpha/fpu/fesetenv.c (fesetenv): Add libm_hidden_ver.
* sysdeps/alpha/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/arm/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/arm/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/generic/fesetenv.c (fesetenv): Likewise.
* sysdeps/generic/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/i386/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/i386/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/m68k/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/m68k/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/mips/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/mips/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/powerpc/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/powerpc/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sparc/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/sparc/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/hppa/fpu/fesetenv.c (fesetenv): Add libm_hidden_def.
* sysdeps/hppa/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/ia64/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/ia64/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/sh/sh4/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/sh/sh4/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/s390/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/s390/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
* sysdeps/x86_64/fpu/fesetenv.c (fesetenv): Likewise.
* sysdeps/x86_64/fpu/fraiseexcpt.c (feraiseexcept): Likewise.
2002-09-10 01:40:26 +00:00
|
|
|
|
Set/restore rounding mode only when needed
The most common use case of math functions is with default rounding
mode, i.e. rounding to nearest. Setting and restoring rounding mode
is an unnecessary overhead for this, so I've added support for a
context, which does the set/restore only if the FP status needs a
change. The code is written such that only x86 uses these. Other
architectures should be unaffected by it, but would definitely benefit
if the set/restore has as much overhead relative to the rest of the
code, as the x86 bits do.
Here's a summary of the performance improvement due to these
improvements; I've only mentioned functions that use the set/restore
and have benchmark inputs for x86_64:
Before:
cos(): ITERS:4.69335e+08: TOTAL:28884.6Mcy, MAX:4080.28cy, MIN:57.562cy, 16248.6 calls/Mcy
exp(): ITERS:4.47604e+08: TOTAL:28796.2Mcy, MAX:207.721cy, MIN:62.385cy, 15543.9 calls/Mcy
pow(): ITERS:1.63485e+08: TOTAL:28879.9Mcy, MAX:362.255cy, MIN:172.469cy, 5660.86 calls/Mcy
sin(): ITERS:3.89578e+08: TOTAL:28900Mcy, MAX:704.859cy, MIN:47.583cy, 13480.2 calls/Mcy
tan(): ITERS:7.0971e+07: TOTAL:28902.2Mcy, MAX:1357.79cy, MIN:388.58cy, 2455.55 calls/Mcy
After:
cos(): ITERS:6.0014e+08: TOTAL:28875.9Mcy, MAX:364.283cy, MIN:45.716cy, 20783.4 calls/Mcy
exp(): ITERS:5.48578e+08: TOTAL:28764.9Mcy, MAX:191.617cy, MIN:51.011cy, 19071.1 calls/Mcy
pow(): ITERS:1.70013e+08: TOTAL:28873.6Mcy, MAX:689.522cy, MIN:163.989cy, 5888.18 calls/Mcy
sin(): ITERS:4.64079e+08: TOTAL:28891.5Mcy, MAX:6959.3cy, MIN:36.189cy, 16062.8 calls/Mcy
tan(): ITERS:7.2354e+07: TOTAL:28898.9Mcy, MAX:1295.57cy, MIN:380.698cy, 2503.7 calls/Mcy
So the improvements are:
cos: 27.9089%
exp: 22.6919%
pow: 4.01564%
sin: 19.1585%
tan: 1.96086%
The downside of the change is that it will have an adverse performance
impact on non-default rounding modes, but I think the tradeoff is
justified.
2013-06-12 05:06:48 +00:00
|
|
|
/* Rounding mode context. This allows functions to set/restore rounding mode
|
|
|
|
only when the desired rounding mode is different from the current rounding
|
|
|
|
mode. */
|
|
|
|
struct rm_ctx
|
|
|
|
{
|
|
|
|
fenv_t env;
|
|
|
|
bool updated_status;
|
|
|
|
};
|
Move fenv.h override inline functions to generic math_private.h.
The tile version of math_private.h defines some inline functions for
fenv.h functions, to optimize away internal calls to these functions
that do nothing given no support for floating-point exceptions and
rounding modes. (Some functions may have error cases for invalid
arguments, but those aren't applicable to the internal calls from
within glibc.) Other configurations lacking support for exceptions
and rounding modes lack such inline functions. This patch moves them
to the generic math_private.h, appropriately conditioned, so that all
such configurations can benefit from the.
include/fenv.h is made to check whether there are any non-default
rounding modes; that needs to be done there, rather than later,
because get-rounding-mode.h defines values for otherwise unsupported
FE_* rounding modes. It also gives an error for FE_TONEAREST
undefined, a case that already did not work for building the glibc
testsuite; the convention has by now been established that all
architectures need to provide a version of bits/fenv.h that at least
defines FE_TONEAREST.
Tested with build-many-glibcs.py. As expected, installed stripped
shared libraries are unchanged for tile and for architectures
supporting exceptions and rounding modes, but changed for non-tile
architectures not supporting exceptions and rounding modes that
previously lacked this optimization (e.g. Nios II libm.so is about 1kB
smaller).
The optimization is not in fact complete (does not cover feholdexcept
/ __feholdexcept, so a few calls to those remain unnecessarily within
libm even after this patch), but that can be dealt with separately.
* include/fenv.h [!_ISOMAC && !FE_TONEAREST]: Give #error.
[!_ISOMAC] (FE_HAVE_ROUNDING_MODES): New macro.
* sysdeps/generic/math_private.h
[!FE_HAVE_ROUNDING_MODES && FE_ALL_EXCEPT == 0] (fegetenv): New
inline function.
[!FE_HAVE_ROUNDING_MODES && FE_ALL_EXCEPT == 0] (__fegetenv):
Likewise.
[!FE_HAVE_ROUNDING_MODES && FE_ALL_EXCEPT == 0] (fesetenv):
Likewise.
[!FE_HAVE_ROUNDING_MODES && FE_ALL_EXCEPT == 0] (__fesetenv):
Likewise.
[!FE_HAVE_ROUNDING_MODES && FE_ALL_EXCEPT == 0] (feupdateenv):
Likewise.
[!FE_HAVE_ROUNDING_MODES && FE_ALL_EXCEPT == 0] (__feupdateenv):
Likewise.
[!FE_HAVE_ROUNDING_MODES] (fegetround): Likewise.
[!FE_HAVE_ROUNDING_MODES] (__fegetround): Likewise.
[!FE_HAVE_ROUNDING_MODES] (fesetround): Likewise.
[!FE_HAVE_ROUNDING_MODES] (__fesetround): Likewise.
* sysdeps/tile/math_private.h (fegetenv): Remove inline function.
(__fegetenv): Likewise.
(fesetenv): Likewise.
(__fesetenv): Likewise.
(feupdateenv): Likewise.
(__feupdateenv): Likewise.
(fegetround): Likewise.
(__fegetround): Likewise.
(fesetround): Likewise.
(__fesetround): Likewise.
2018-02-01 20:54:44 +00:00
|
|
|
|
|
|
|
/* Track whether rounding mode macros were defined, since
|
|
|
|
get-rounding-mode.h may define default versions if they weren't.
|
|
|
|
FE_TONEAREST must always be defined (even if no changes of rounding
|
|
|
|
mode are supported, glibc requires it to be defined to represent
|
|
|
|
the default rounding mode). */
|
|
|
|
# ifndef FE_TONEAREST
|
|
|
|
# error "FE_TONEAREST not defined"
|
|
|
|
# endif
|
|
|
|
# if defined FE_DOWNWARD || defined FE_TOWARDZERO || defined FE_UPWARD
|
|
|
|
# define FE_HAVE_ROUNDING_MODES 1
|
|
|
|
# else
|
|
|
|
# define FE_HAVE_ROUNDING_MODES 0
|
|
|
|
# endif
|
|
|
|
|
Move fenv.h soft-float inlines from fenv_private.h to include/fenv.h.
<fenv_private.h> has inline versions of various <fenv.h> functions,
and their __fe* variants, for systems (generally soft-float) without
support for floating-point exceptions, rounding modes or both.
Having these inlines in a separate header introduces a risk of a
source file including <fenv.h> and compiling OK on x86_64, but failing
to compile (because the feraiseexcept inline is actually a macro that
discards its argument, to avoid the need for #ifdef FE_INVALID
conditionals), or not being properly optimized, on systems without the
exceptions and rounding modes support (when these inlines were in
math_private.h, we had a few cases where this broke the build because
there was no obvious reason for a file to need math_private.h and it
didn't need that header on x86_64). By moving those inlines to
include/fenv.h, this risk can be avoided, and fenv_private.h becomes
more clearly defined as specifically the header for the internal
libc_fe* and SET_RESTORE_ROUND* interfaces.
This patch makes that move, removing fenv_private.h includes that are
no longer needed (or replacing them by fenv.h includes in a few cases
that didn't already have such an include).
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/fenv_private.h [FE_ALL_EXCEPT == 0]: Move this
code ....
[!FE_HAVE_ROUNDING_MODES]: And this code ....
* include/fenv.h [!_ISOMAC]: ... to here.
* math/fraiseexcpt.c (__feraiseexcept): Undefine as macro.
(feraiseexcept): Likewise.
* math/fromfp.h: Do not include <fenv_private.h>.
* math/s_cexp_template.c: Likewise.
* math/s_csin_template.c: Likewise.
* math/s_csinh_template.c: Likewise.
* math/s_ctan_template.c: Likewise.
* math/s_ctanh_template.c: Likewise.
* math/s_iseqsig_template.c: Likewise.
* math/w_acos_compat.c: Likewise.
* math/w_acosf_compat.c: Likewise.
* math/w_acosl_compat.c: Likewise.
* math/w_asin_compat.c: Likewise.
* math/w_asinf_compat.c: Likewise.
* math/w_asinl_compat.c: Likewise.
* math/w_j0_compat.c: Likewise.
* math/w_j0f_compat.c: Likewise.
* math/w_j0l_compat.c: Likewise.
* math/w_j1_compat.c: Likewise.
* math/w_j1f_compat.c: Likewise.
* math/w_j1l_compat.c: Likewise.
* math/w_jn_compat.c: Likewise.
* math/w_jnf_compat.c: Likewise.
* math/w_log10_compat.c: Likewise.
* math/w_log10f_compat.c: Likewise.
* math/w_log10l_compat.c: Likewise.
* math/w_log2_compat.c: Likewise.
* math/w_log2f_compat.c: Likewise.
* math/w_log2l_compat.c: Likewise.
* math/w_log_compat.c: Likewise.
* math/w_logf_compat.c: Likewise.
* math/w_logl_compat.c: Likewise.
* sysdeps/ieee754/dbl-64/s_llrint.c: Likewise.
* sysdeps/ieee754/dbl-64/s_llround.c: Likewise.
* sysdeps/ieee754/dbl-64/s_lrint.c: Likewise.
* sysdeps/ieee754/dbl-64/s_lround.c: Likewise.
* sysdeps/ieee754/dbl-64/wordsize-64/s_lround.c: Likewise.
* sysdeps/ieee754/flt-32/s_llrintf.c: Likewise.
* sysdeps/ieee754/flt-32/s_llroundf.c: Likewise.
* sysdeps/ieee754/flt-32/s_lrintf.c: Likewise.
* sysdeps/ieee754/flt-32/s_lroundf.c: Likewise.
* sysdeps/ieee754/k_standardl.c: Likewise.
* sysdeps/ieee754/ldbl-128/e_expl.c: Likewise.
* sysdeps/ieee754/ldbl-128/s_fmal.c: Likewise.
* sysdeps/ieee754/ldbl-128/s_llrintl.c: Likewise.
* sysdeps/ieee754/ldbl-128/s_llroundl.c: Likewise.
* sysdeps/ieee754/ldbl-128/s_lrintl.c: Likewise.
* sysdeps/ieee754/ldbl-128/s_lroundl.c: Likewise.
* sysdeps/ieee754/ldbl-128/s_nearbyintl.c: Likewise.
* sysdeps/ieee754/ldbl-128ibm/s_llrintl.c: Likewise.
* sysdeps/ieee754/ldbl-128ibm/s_llroundl.c: Likewise.
* sysdeps/ieee754/ldbl-128ibm/s_lrintl.c: Likewise.
* sysdeps/ieee754/ldbl-128ibm/s_lroundl.c: Likewise.
* sysdeps/ieee754/ldbl-96/s_fma.c: Likewise.
* sysdeps/ieee754/ldbl-96/s_fmal.c: Likewise.
* sysdeps/ieee754/ldbl-96/s_llrintl.c: Likewise.
* sysdeps/ieee754/ldbl-96/s_llroundl.c: Likewise.
* sysdeps/ieee754/ldbl-96/s_lrintl.c: Likewise.
* sysdeps/ieee754/ldbl-96/s_lroundl.c: Likewise.
* math/w_ilogb_template.c: Include <fenv.h> instead of
<fenv_private.h>.
* math/w_llogb_template.c: Likewise.
* sysdeps/powerpc/fpu/e_sqrt.c: Likewise.
* sysdeps/powerpc/fpu/e_sqrtf.c: Likewise.
2018-09-04 19:52:06 +00:00
|
|
|
/* When no floating-point exceptions are defined in <fenv.h>, make
|
|
|
|
feraiseexcept ignore its argument so that unconditional
|
|
|
|
feraiseexcept calls do not cause errors for undefined exceptions.
|
|
|
|
Define it to expand to a void expression so that any calls testing
|
|
|
|
the result of feraiseexcept do produce errors. */
|
|
|
|
# if FE_ALL_EXCEPT == 0
|
|
|
|
# define feraiseexcept(excepts) ((void) 0)
|
|
|
|
# define __feraiseexcept(excepts) ((void) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
/* Similarly, most <fenv.h> functions have trivial implementations in
|
|
|
|
the absence of support for floating-point exceptions and rounding
|
|
|
|
modes. */
|
|
|
|
|
|
|
|
# if !FE_HAVE_ROUNDING_MODES
|
|
|
|
# if FE_ALL_EXCEPT == 0
|
|
|
|
extern inline int
|
|
|
|
fegetenv (fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
__fegetenv (fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
feholdexcept (fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
__feholdexcept (fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
fesetenv (const fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
__fesetenv (const fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
feupdateenv (const fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
__feupdateenv (const fenv_t *__e)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
# endif
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
fegetround (void)
|
|
|
|
{
|
|
|
|
return FE_TONEAREST;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
__fegetround (void)
|
|
|
|
{
|
|
|
|
return FE_TONEAREST;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
fesetround (int __d)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern inline int
|
|
|
|
__fesetround (int __d)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
# endif
|
|
|
|
|
2013-09-04 20:47:21 +00:00
|
|
|
#endif
|
Set/restore rounding mode only when needed
The most common use case of math functions is with default rounding
mode, i.e. rounding to nearest. Setting and restoring rounding mode
is an unnecessary overhead for this, so I've added support for a
context, which does the set/restore only if the FP status needs a
change. The code is written such that only x86 uses these. Other
architectures should be unaffected by it, but would definitely benefit
if the set/restore has as much overhead relative to the rest of the
code, as the x86 bits do.
Here's a summary of the performance improvement due to these
improvements; I've only mentioned functions that use the set/restore
and have benchmark inputs for x86_64:
Before:
cos(): ITERS:4.69335e+08: TOTAL:28884.6Mcy, MAX:4080.28cy, MIN:57.562cy, 16248.6 calls/Mcy
exp(): ITERS:4.47604e+08: TOTAL:28796.2Mcy, MAX:207.721cy, MIN:62.385cy, 15543.9 calls/Mcy
pow(): ITERS:1.63485e+08: TOTAL:28879.9Mcy, MAX:362.255cy, MIN:172.469cy, 5660.86 calls/Mcy
sin(): ITERS:3.89578e+08: TOTAL:28900Mcy, MAX:704.859cy, MIN:47.583cy, 13480.2 calls/Mcy
tan(): ITERS:7.0971e+07: TOTAL:28902.2Mcy, MAX:1357.79cy, MIN:388.58cy, 2455.55 calls/Mcy
After:
cos(): ITERS:6.0014e+08: TOTAL:28875.9Mcy, MAX:364.283cy, MIN:45.716cy, 20783.4 calls/Mcy
exp(): ITERS:5.48578e+08: TOTAL:28764.9Mcy, MAX:191.617cy, MIN:51.011cy, 19071.1 calls/Mcy
pow(): ITERS:1.70013e+08: TOTAL:28873.6Mcy, MAX:689.522cy, MIN:163.989cy, 5888.18 calls/Mcy
sin(): ITERS:4.64079e+08: TOTAL:28891.5Mcy, MAX:6959.3cy, MIN:36.189cy, 16062.8 calls/Mcy
tan(): ITERS:7.2354e+07: TOTAL:28898.9Mcy, MAX:1295.57cy, MIN:380.698cy, 2503.7 calls/Mcy
So the improvements are:
cos: 27.9089%
exp: 22.6919%
pow: 4.01564%
sin: 19.1585%
tan: 1.96086%
The downside of the change is that it will have an adverse performance
impact on non-default rounding modes, but I think the tradeoff is
justified.
2013-06-12 05:06:48 +00:00
|
|
|
|
2000-12-27 19:58:36 +00:00
|
|
|
#endif
|