mirror of
git://sourceware.org/git/glibc.git
synced 2024-12-15 04:20:28 +08:00
69461d9896
The powerpc hypot is slight optimized by:
- Commit 8df4e219e4, both isnan and isinf are always inlined and thus
the check TEST_INF_NAN does not make sense anymore. The generic
check for POWER7 should be faster on all powerpc configuration.
- The redundant check 'y > two60factor && (x / y) > two60' is removed.
Both changes leads to unrequired ifunc especialization for power7 and
thus they are removed. Finally The code is also cleanup a bit by inlining
the constants floating points.
The performance changes using the hypot benchtests are:
- POWER9 without patch:
"hypot": {
"overflow": {
"duration": 4.98585e+09,
"iterations": 4.84932e+08,
"max": 46.551,
"min": 10.229,
"mean": 10.2815
},
"higher_two500": {
"duration": 5.00192e+09,
"iterations": 4.24843e+08,
"max": 33.319,
"min": 11.606,
"mean": 11.7736
},
"subnormal": {
"duration": 5.0075e+09,
"iterations": 4.06792e+08,
"max": 22.178,
"min": 12.15,
"mean": 12.3097
},
"less_two500": {
"duration": 5.00685e+09,
"iterations": 4.08772e+08,
"max": 22.784,
"min": 12.052,
"mean": 12.2485
},
"default": {
"duration": 5.06002e+09,
"iterations": 4.09894e+08,
"max": 20.648,
"min": 11.874,
"mean": 12.3447
}
}
- POWER9 with patch:
"hypot": {
"overflow": {
"duration": 4.91848e+09,
"iterations": 7.28039e+08,
"max": 47.958,
"min": 6.436,
"mean": 6.75579
},
"higher_two500": {
"duration": 4.9359e+09,
"iterations": 6.63376e+08,
"max": 20.783,
"min": 7.321,
"mean": 7.44057
},
"subnormal": {
"duration": 4.9479e+09,
"iterations": 6.19772e+08,
"max": 18.856,
"min": 7.817,
"mean": 7.98341
},
"less_two500": {
"duration": 4.94275e+09,
"iterations": 6.3889e+08,
"max": 17.452,
"min": 7.597,
"mean": 7.73647
},
"default": {
"duration": 5.03645e+09,
"iterations": 5.70718e+08,
"max": 18.904,
"min": 8.55,
"mean": 8.82476
}
}
- POWER7 without patch
"hypot": {
"overflow": {
"duration": 4.86637e+09,
"iterations": 6.43196e+08,
"max": 53.958,
"min": 7.328,
"mean": 7.56592
},
"higher_two500": {
"duration": 4.99842e+09,
"iterations": 3.11012e+08,
"max": 78.227,
"min": 15.696,
"mean": 16.0715
},
"subnormal": {
"duration": 4.99841e+09,
"iterations": 3.08935e+08,
"max": 51.392,
"min": 15.983,
"mean": 16.1795
},
"less_two500": {
"duration": 5.00108e+09,
"iterations": 2.99464e+08,
"max": 73.247,
"min": 16.416,
"mean": 16.7001
},
"default": {
"duration": 5.04645e+09,
"iterations": 3.52608e+08,
"max": 70.073,
"min": 13.38,
"mean": 14.3118
}
}
- POWER7 with patch
"hypot": {
"overflow": {
"duration": 4.80785e+09,
"iterations": 8.00001e+08,
"max": 66.262,
"min": 5.888,
"mean": 6.00981
},
"higher_two500": {
"duration": 4.9859e+09,
"iterations": 3.39449e+08,
"max": 5148.44,
"min": 14.539,
"mean": 14.6882
},
"subnormal": {
"duration": 4.9905e+09,
"iterations": 3.28874e+08,
"max": 64.905,
"min": 14.971,
"mean": 15.1745
},
"less_two500": {
"duration": 4.99494e+09,
"iterations": 3.19755e+08,
"max": 103.696,
"min": 14.972,
"mean": 15.6211
},
"default": {
"duration": 5.03951e+09,
"iterations": 4.02502e+08,
"max": 61.008,
"min": 12.368,
"mean": 12.5205
}
}
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/fpu/e_hypot.c (two60, two500, two600, two1022,
twoM500, twoM600, two60factor, pdnum): Remove.
(TEST_INFO_NAN, GET_TW0_HIGH_WORD): Remove macro.
(__ieee754_hypot): Replace static variables with inline definition,
remove ununsed branches.
* sysdeps/powerpc/powerpc64/fpu/multiarch/Makefile
(libm-sysdep_routines): Remove e_hypot-* objects.
(CFLAGS-e_hypot-power7.c, CFLAGS-e_hypotf-power7.c): Remove rule.
* sysdeps/powerpc/powerpc64/fpu/multiarch/e_hypot-power7.c: Remove
file.
* sysdeps/powerpc/powerpc64/fpu/multiarch/e_hypot-ppc64.c: Likewise.
* sysdeps/powerpc/powerpc64/fpu/multiarch/e_hypot.c: Likewise.
* sysdeps/powerpc/powerpc64/fpu/multiarch/e_hypotf-power7.c: Likewise.
* sysdeps/powerpc/powerpc64/fpu/multiarch/e_hypotf-ppc64.c: Likewise.
* sysdeps/powerpc/powerpc64/fpu/multiarch/e_hypotf.c: Likewise.
Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
86 lines
2.3 KiB
C
86 lines
2.3 KiB
C
/* Pythagorean addition using doubles
|
|
Copyright (C) 2011-2019 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library
|
|
Contributed by Adhemerval Zanella <azanella@br.ibm.com>, 2011
|
|
|
|
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/>. */
|
|
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
#include <math-underflow.h>
|
|
#include <stdint.h>
|
|
|
|
/* __ieee754_hypot(x,y)
|
|
*
|
|
* This a FP only version without any FP->INT conversion.
|
|
* It is similar to default C version, making appropriates
|
|
* overflow and underflows checks as well scaling when it
|
|
* is needed.
|
|
*/
|
|
|
|
double
|
|
__ieee754_hypot (double x, double y)
|
|
{
|
|
if ((isinf (x) || isinf (y))
|
|
&& !issignaling (x) && !issignaling (y))
|
|
return INFINITY;
|
|
if (isnan (x) || isnan (y))
|
|
return x + y;
|
|
|
|
x = fabs (x);
|
|
y = fabs (y);
|
|
|
|
if (y > x)
|
|
{
|
|
double t = x;
|
|
x = y;
|
|
y = t;
|
|
}
|
|
if (y == 0.0)
|
|
return x;
|
|
|
|
/* if y is higher enough, y * 2^60 might overflow. The tests if
|
|
y >= 1.7976931348623157e+308/2^60 (two60factor) and uses the
|
|
appropriate check to avoid the overflow exception generation. */
|
|
if (y <= 0x1.fffffffffffffp+963 && x > (y * 0x1p+60))
|
|
return x + y;
|
|
|
|
if (x > 0x1p+500)
|
|
{
|
|
x *= 0x1p-600;
|
|
y *= 0x1p-600;
|
|
return sqrt (x * x + y * y) / 0x1p-600;
|
|
}
|
|
if (y < 0x1p-500)
|
|
{
|
|
if (y <= 0x0.fffffffffffffp-1022)
|
|
{
|
|
x *= 0x1p+1022;
|
|
y *= 0x1p+1022;
|
|
double ret = sqrt (x * x + y * y) / 0x1p+1022;
|
|
math_check_force_underflow_nonneg (ret);
|
|
return ret;
|
|
}
|
|
else
|
|
{
|
|
x *= 0x1p+600;
|
|
y *= 0x1p+600;
|
|
return sqrt (x * x + y * y) / 0x1p+600;
|
|
}
|
|
}
|
|
return sqrt (x * x + y * y);
|
|
}
|
|
strong_alias (__ieee754_hypot, __hypot_finite)
|