mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-03 02:11:08 +00:00
931c616eed
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>
|
||
|---|---|---|
| .. | ||
| 405 | ||
| 440 | ||
| 464 | ||
| 476 | ||
| 970 | ||
| a2 | ||
| bits | ||
| cell | ||
| fpu | ||
| power4 | ||
| power5 | ||
| power5+ | ||
| power6 | ||
| power6x | ||
| power7 | ||
| power8 | ||
| power9 | ||
| __longjmp-common.S | ||
| __longjmp.S | ||
| add_n.S | ||
| addmul_1.S | ||
| atomic-machine.h | ||
| backtrace.c | ||
| bsd-_setjmp.S | ||
| bsd-setjmp.S | ||
| bzero.S | ||
| compat-ppc-mcount.S | ||
| configure | ||
| configure.ac | ||
| crti.S | ||
| crtn.S | ||
| dl-dtprocnum.h | ||
| dl-irel.h | ||
| dl-machine.c | ||
| dl-machine.h | ||
| dl-start.S | ||
| dl-trampoline.S | ||
| gprrest0.S | ||
| gprrest1.S | ||
| gprsave0.S | ||
| gprsave1.S | ||
| Implies | ||
| Implies-after | ||
| libgcc-compat.S | ||
| lshift.S | ||
| Makefile | ||
| mcount.c | ||
| memset.S | ||
| mul_1.S | ||
| ppc-mcount.S | ||
| register-dump.h | ||
| rshift.S | ||
| rtld-memset.c | ||
| setjmp-common.S | ||
| setjmp.S | ||
| stackguard-macros.h | ||
| start.S | ||
| stpcpy.S | ||
| strchr.S | ||
| strcmp.S | ||
| strcpy.S | ||
| strlen.S | ||
| strncmp.S | ||
| sub_n.S | ||
| submul_1.S | ||
| symbol-hacks.h | ||
| sysdep.h | ||
| tls-macros.h | ||
| tst-audit.h | ||
| Versions | ||