diff options
author | Adhemerval Zanella <adhemerval.zanella@linaro.org> | 2019-03-18 20:18:49 +0000 |
---|---|---|
committer | Adhemerval Zanella <adhemerval.zanella@linaro.org> | 2019-07-08 17:22:22 -0300 |
commit | 931c616eedc303d48fdd3b05bc063b354a133c74 (patch) | |
tree | e820e2f8c8e7d7d9e0120e147643995b4ed62790 /sysdeps/powerpc/fpu/s_modf.c | |
parent | 69461d989669d3da051a2bfdae8d5b0ff3dc0749 (diff) | |
download | glibc-931c616eedc303d48fdd3b05bc063b354a133c74.tar.gz |
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>
Diffstat (limited to 'sysdeps/powerpc/fpu/s_modf.c')
-rw-r--r-- | sysdeps/powerpc/fpu/s_modf.c | 59 |
1 files changed, 59 insertions, 0 deletions
diff --git a/sysdeps/powerpc/fpu/s_modf.c b/sysdeps/powerpc/fpu/s_modf.c new file mode 100644 index 0000000000..2304fc48ed --- /dev/null +++ b/sysdeps/powerpc/fpu/s_modf.c @@ -0,0 +1,59 @@ +/* Copyright (C) 2013-2019 Free Software Foundation, Inc. + This file is part of the GNU C Library + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with the GNU C Library; see the file COPYING.LIB. If + not, see <http://www.gnu.org/licenses/>. */ + +/* 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) +{ + if (__builtin_isinf (x)) + { + *iptr = x; + return copysign (0.0, x); + } + else if (__builtin_isnan (x)) + { + *iptr = NAN; + return NAN; + } + + if (x >= 0.0) + { + *iptr = floor (x); + return copysign (x - *iptr, x); + } + else + { + *iptr = ceil (x); + return copysign (x - *iptr, x); + } +} +# ifndef __modf +libm_alias_double (__modf, modf) +# if LONG_DOUBLE_COMPAT (libc, GLIBC_2_0) +compat_symbol (libc, __modf, modfl, GLIBC_2_0); +# endif +# endif +#endif |