mirror of
git://sourceware.org/git/glibc.git
synced 2025-02-17 13:00:43 +08:00
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>
|
||
|---|---|---|
| .. | ||
| e_hypot.c | ||
| e_hypotf.c | ||
| e_sqrt.c | ||
| e_sqrtf.c | ||
| fclrexcpt.c | ||
| fe_mask.c | ||
| fe_nomask.c | ||
| fedisblxcpt.c | ||
| feenablxcpt.c | ||
| fegetenv.c | ||
| fegetexcept.c | ||
| fegetmode.c | ||
| fegetround.c | ||
| feholdexcpt.c | ||
| fenv_const.c | ||
| fenv_libc.h | ||
| fenv_private.h | ||
| fesetenv.c | ||
| fesetexcept.c | ||
| fesetmode.c | ||
| fesetround.c | ||
| feupdateenv.c | ||
| fgetexcptflg.c | ||
| fix-fp-int-compare-invalid.h | ||
| fraiseexcpt.c | ||
| fsetexcptflg.c | ||
| ftestexcept.c | ||
| get-rounding-mode.h | ||
| libm-test-ulps | ||
| libm-test-ulps-name | ||
| Makefile | ||
| math_ldbl.h | ||
| math_private.h | ||
| math-barriers.h | ||
| math-tests-trap-force.h | ||
| round_to_integer.h | ||
| s_ceil.c | ||
| s_ceilf.c | ||
| s_copysign.c | ||
| s_copysignf.c | ||
| s_floor.c | ||
| s_floorf.c | ||
| s_fma.c | ||
| s_fmaf.c | ||
| s_lrintf.c | ||
| s_modf.c | ||
| s_modff.c | ||
| s_nearbyint.c | ||
| s_nearbyintf.c | ||
| s_rint.c | ||
| s_rintf.c | ||
| s_round.c | ||
| s_roundf.c | ||
| s_trunc.c | ||
| s_truncf.c | ||
| t_sqrt.c | ||
| tst-setcontext-fpscr.c | ||