mirror of
git://sourceware.org/git/glibc.git
synced 2025-02-05 12:40:55 +08:00
powerpc: Refactor modf{f}
The modf{f} optimization is not an optimization for ISA 2.07+. This
patch move the IFUNC for powerpc64 only, move the power5+ to generic
location, and include the generic implementation for ISA 2.07+.
The performance changes are based on modf benchtests:
* POWER9 - ppc64
"modf": {
"": {
"duration": 4.97057e+09,
"iterations": 1.00688e+09,
"max": 28.76,
"min": 4.912,
"mean": 4.9366
}
}
* POWER9 - power5+
"modf": {
"": {
"duration": 4.98291e+09,
"iterations": 9.32818e+08,
"max": 15.058,
"min": 5.107,
"mean": 5.34178
}
}
* POWER8 - ppc64
"modf": {
"": {
"duration": 5.05329e+09,
"iterations": 8.38814e+08,
"max": 518.051,
"min": 5.79,
"mean": 6.02433
}
}
* POWER8 - power5+
"modf": {
"": {
"duration": 5.05573e+09,
"iterations": 8.35254e+08,
"max": 63.141,
"min": 5.873,
"mean": 6.05293
}
}
* POWER7 - ppc64
"modf": {
"": {
"duration": 4.89818e+09,
"iterations": 1.08408e+09,
"max": 57.556,
"min": 3.953,
"mean": 4.51827
}
}
* POWER7 - power5+
"modf": {
"": {
"duration": 4.83789e+09,
"iterations": 1.33409e+09,
"max": 46.608,
"min": 2.224,
"mean": 3.62636
}
}
Checked on powerpc-linux-gnu (built without --with-cpu, with
--with-cpu=power4 and with --with-cpu=power5+ and --disable-multi-arch),
powerpc64-linux-gnu (built without --with-cp and with --with-cpu=power5+
and --disable-multi-arch).
* sysdeps/powerpc/power5+/fpu/s_modf.c: Move to ...
* sysdeps/powerpc/fpu/s_modf.c: ... here. Add ISA 2.07 optimization.
* sysdeps/powerpc/power5+/fpu/s_modff.c: Move to ...
* sysdeps/powerpc/fpu/s_modff.c: ... here. Add ISA 2.07 optimization.
* sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modf-power5+.c:
Adjust include.
* sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff-power5+.c:
Likewise.
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/Makefile (sysdep_calls,
sysdep_routines): Add s_modf* objects.
(CFLAGS-s_modf-power5+.c, CFLAGS-s_modff-power5+.c,
CFLAGS-s_modf-ppc64.c, CFLAGS-s_modff-ppc64.c): New rule.
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Move
to ...
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c:
... here.
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Movo
to ...
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: Move
... here.
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf.c: Move to ...
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf.c: ... here.
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-power5+.c: Move
to ...
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-power5+.c:
... here.
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-ppc64.c: Move to ...
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-ppc64.c:
... here.
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff.c: Move to ...
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff.c: ... here.
Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
This commit is contained in:
Adhemerval Zanella
parent
69461d9896
commit
931c616eed
32
ChangeLog
32
ChangeLog
@ -1,5 +1,37 @@
|
||||
2019-07-08 Adhemerval Zanella <adhemerval.zanella@linaro.org>
|
||||
|
||||
* sysdeps/powerpc/power5+/fpu/s_modf.c: Move to ...
|
||||
* sysdeps/powerpc/fpu/s_modf.c: ... here. Add ISA 2.07 optimization.
|
||||
* sysdeps/powerpc/power5+/fpu/s_modff.c: Move to ...
|
||||
* sysdeps/powerpc/fpu/s_modff.c: ... here. Add ISA 2.07 optimization.
|
||||
* sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modf-power5+.c:
|
||||
Adjust include.
|
||||
* sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff-power5+.c:
|
||||
Likewise.
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/Makefile (sysdep_calls,
|
||||
sysdep_routines): Add s_modf* objects.
|
||||
(CFLAGS-s_modf-power5+.c, CFLAGS-s_modff-power5+.c,
|
||||
CFLAGS-s_modf-ppc64.c, CFLAGS-s_modff-ppc64.c): New rule.
|
||||
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Move
|
||||
to ...
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c:
|
||||
... here.
|
||||
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Movo
|
||||
to ...
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: Move
|
||||
... here.
|
||||
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf.c: Move to ...
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf.c: ... here.
|
||||
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-power5+.c: Move
|
||||
to ...
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-power5+.c:
|
||||
... here.
|
||||
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-ppc64.c: Move to ...
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-ppc64.c:
|
||||
... here.
|
||||
* sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff.c: Move to ...
|
||||
* sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff.c: ... here.
|
||||
|
||||
* sysdeps/powerpc/fpu/e_hypot.c (two60, two500, two600, two1022,
|
||||
twoM500, twoM600, two60factor, pdnum): Remove.
|
||||
(TEST_INFO_NAN, GET_TW0_HIGH_WORD): Remove macro.
|
||||
|
||||
@ -15,9 +15,15 @@
|
||||
License along with the GNU C Library; see the file COPYING.LIB. If
|
||||
not, see <http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
#include <libm-alias-double.h>
|
||||
/* ISA 2.07 provides fast GPR to FP instruction (mfvsr{d,wz}) which make
|
||||
generic implementation faster. Also disables for old ISAs that do not
|
||||
have ceil/floor instructions. */
|
||||
#if defined(_ARCH_PWR8) || !defined(_ARCH_PWR5X)
|
||||
# include <sysdeps/ieee754/ldbl-opt/s_modf.c>
|
||||
#else
|
||||
# include <math.h>
|
||||
# include <math_ldbl_opt.h>
|
||||
# include <libm-alias-double.h>
|
||||
|
||||
double
|
||||
__modf (double x, double *iptr)
|
||||
@ -44,7 +50,10 @@ __modf (double x, double *iptr)
|
||||
return copysign (x - *iptr, x);
|
||||
}
|
||||
}
|
||||
# ifndef __modf
|
||||
libm_alias_double (__modf, modf)
|
||||
#if LONG_DOUBLE_COMPAT (libc, GLIBC_2_0)
|
||||
# if LONG_DOUBLE_COMPAT (libc, GLIBC_2_0)
|
||||
compat_symbol (libc, __modf, modfl, GLIBC_2_0);
|
||||
# endif
|
||||
# endif
|
||||
#endif
|
||||
@ -15,8 +15,14 @@
|
||||
License along with the GNU C Library; see the file COPYING.LIB. If
|
||||
not, see <http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <math.h>
|
||||
#include <libm-alias-float.h>
|
||||
/* ISA 2.07 provides fast GPR to FP instruction (mfvsr{d,wz}) which make
|
||||
generic implementation faster. Also disables for old ISAs that do not
|
||||
have ceil/floor instructions. */
|
||||
#if defined(_ARCH_PWR8) || !defined(_ARCH_PWR5X)
|
||||
# include <sysdeps/ieee754/flt-32/s_modff.c>
|
||||
#else
|
||||
# include <math.h>
|
||||
# include <libm-alias-float.h>
|
||||
|
||||
float
|
||||
__modff (float x, float *iptr)
|
||||
@ -43,4 +49,7 @@ __modff (float x, float *iptr)
|
||||
return copysignf (x - *iptr, x);
|
||||
}
|
||||
}
|
||||
# ifndef __modff
|
||||
libm_alias_float (__modf, modf)
|
||||
# endif
|
||||
#endif
|
||||
@ -16,16 +16,5 @@
|
||||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
|
||||
#undef weak_alias
|
||||
#define weak_alias(a,b)
|
||||
#undef strong_alias
|
||||
#define strong_alias(a,b)
|
||||
#undef compat_symbol
|
||||
#define compat_symbol(a,b,c,d)
|
||||
|
||||
#define __modf __modf_power5plus
|
||||
|
||||
#include <sysdeps/powerpc/power5+/fpu/s_modf.c>
|
||||
#include <sysdeps/powerpc/fpu/s_modf.c>
|
||||
|
||||
@ -16,12 +16,5 @@
|
||||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
|
||||
#undef weak_alias
|
||||
#define weak_alias(a,b)
|
||||
|
||||
#define __modff __modff_power5plus
|
||||
|
||||
#include <sysdeps/powerpc/power5+/fpu/s_modff.c>
|
||||
#include <sysdeps/powerpc/fpu/s_modff.c>
|
||||
|
||||
@ -1,4 +1,13 @@
|
||||
ifeq ($(subdir),math)
|
||||
# These functions are built both for libc and libm because they're required
|
||||
# by printf. While the libc objects have the prefix s_, the libm ones are
|
||||
# prefixed with m_.
|
||||
sysdep_calls := s_modf-power5+ \
|
||||
s_modf-ppc64 \
|
||||
s_modff-power5+ \
|
||||
s_modff-ppc64
|
||||
|
||||
sysdep_routines += $(sysdep_calls)
|
||||
libm-sysdep_routines += s_ceil-power5+ \
|
||||
s_ceil-ppc64 \
|
||||
s_ceilf-power5+ \
|
||||
@ -22,7 +31,8 @@ libm-sysdep_routines += s_ceil-power5+ \
|
||||
s_llround-power6x \
|
||||
s_llround-power5+ \
|
||||
s_llround-ppc64 \
|
||||
s_llroundf-ppc64
|
||||
s_llroundf-ppc64 \
|
||||
$(sysdep_calls:s_%=m_%)
|
||||
|
||||
CFLAGS-s_ceil-power5+.c = -mcpu=power5+
|
||||
CFLAGS-s_ceilf-power5+.c = -mcpu=power5+
|
||||
@ -37,4 +47,11 @@ CFLAGS-s_llrint-power6x.c += -mcpu=power6x
|
||||
CFLAGS-s_llround-power8.c += -mcpu=power8
|
||||
CFLAGS-s_llround-power6x.c += -mcpu=power6x
|
||||
CFLAGS-s_llround-power5+.c += -mcpu=power5+
|
||||
|
||||
CFLAGS-s_modf-power5+.c += -mcpu=power5+
|
||||
CFLAGS-s_modff-power5+.c += -mcpu=power5+
|
||||
# These files quiet sNaNs in a way that is optimized away without
|
||||
# -fsignaling-nans.
|
||||
CFLAGS-s_modf-ppc64.c += -fsignaling-nans
|
||||
CFLAGS-s_modff-ppc64.c += -fsignaling-nans
|
||||
endif
|
||||
|
||||
@ -16,4 +16,5 @@
|
||||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modf-power5+.c>
|
||||
#define __modf __modf_power5plus
|
||||
#include <sysdeps/powerpc/fpu/s_modf.c>
|
||||
@ -16,4 +16,5 @@
|
||||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff-power5+.c>
|
||||
#define __modff __modff_power5plus
|
||||
#include <sysdeps/powerpc/fpu/s_modff.c>
|
||||
@ -1,10 +1,4 @@
|
||||
ifeq ($(subdir),math)
|
||||
# These functions are built both for libc and libm because they're required
|
||||
# by printf. While the libc objects have the prefix s_, the libm ones are
|
||||
# prefixed with m_.
|
||||
sysdep_calls := s_modf-power5+ s_modf-ppc64 \
|
||||
s_modff-power5+ s_modff-ppc64
|
||||
|
||||
sysdep_routines += $(sysdep_calls)
|
||||
libm-sysdep_routines += s_logb-power7 s_logbf-power7 \
|
||||
s_logbl-power7 s_logb-ppc64 s_logbf-ppc64 \
|
||||
@ -14,11 +8,4 @@ libm-sysdep_routines += s_logb-power7 s_logbf-power7 \
|
||||
CFLAGS-s_logbf-power7.c = -mcpu=power7
|
||||
CFLAGS-s_logbl-power7.c = -mcpu=power7
|
||||
CFLAGS-s_logb-power7.c = -mcpu=power7
|
||||
CFLAGS-s_modf-power5+.c = -mcpu=power5+
|
||||
CFLAGS-s_modff-power5+.c = -mcpu=power5+
|
||||
|
||||
# These files quiet sNaNs in a way that is optimized away without
|
||||
# -fsignaling-nans.
|
||||
CFLAGS-s_modf-ppc64.c += -fsignaling-nans
|
||||
CFLAGS-s_modff-ppc64.c += -fsignaling-nans
|
||||
endif
|
||||
|
||||
Loading…
Reference in New Issue
Block a user