PPC64: Poor StrictMath performance due to non-optimized compilation

Gustavo Romero gromero at linux.vnet.ibm.com
Thu Nov 17 01:45:50 UTC 2016


Hi,

Currently, optimization for building fdlibm is disabled, except for the
"solaris" OS target [1].

As a consequence on PPC64 (Linux) StrictMath methods like, but not limited to,
sin(), cos(), and tan() perform verify poor in comparison to the same methods
in Math class [2]:

                   Math  StrictMath
              =========  ==========
sin           0m29.984s   1m41.184s
cos           0m30.031s   1m41.200s
tan           0m31.772s   1m46.976s
asin           0m4.577s    0m4.543s
acos           0m4.539s    0m4.525s
atan          0m12.929s   0m12.896s
exp            0m1.071s    0m4.570s
log            0m3.272s   0m14.239s
log10          0m4.362s   0m20.236s
sqrt           0m0.913s    0m0.981s
cbrt          0m10.786s   0m10.808s
sinh           0m4.438s    0m4.433s
cosh           0m4.496s    0m4.478s
tanh           0m3.360s    0m3.353s
expm1          0m4.076s    0m4.094s
log1p          0m13.518s  0m13.527s
IEEEremainder  0m38.803s  0m38.909s
atan2          0m20.100s  0m20.057s
pow            0m14.096s  0m19.938s
hypot          0m5.136s    0m5.122s


Switching on the O3 optimization can damage precision of those methods,
nonetheless it's possible to avoid that side effect and yet get huge benefits of
the -O3 optimization on PPC64 if -fno-expensive-optimizations is passed in
addition to the -O3  optimization flag.

In that sense the following change is proposed to resolve the issue:

diff -r 81eb4bd34611 make/lib/CoreLibraries.gmk
--- a/make/lib/CoreLibraries.gmk	Wed Nov 09 13:37:19 2016 +0100
+++ b/make/lib/CoreLibraries.gmk	Wed Nov 16 19:11:11 2016 -0500
@@ -33,10 +33,16 @@
 # libfdlibm is statically linked with libjava below and not delivered into the
 # product on its own.

-BUILD_LIBFDLIBM_OPTIMIZATION := HIGH
+BUILD_LIBFDLIBM_OPTIMIZATION := NONE

-ifneq ($(OPENJDK_TARGET_OS), solaris)
-  BUILD_LIBFDLIBM_OPTIMIZATION := NONE
+ifeq ($(OPENJDK_TARGET_OS), solaris)
+  BUILD_LIBFDLIBM_OPTIMIZATION := HIGH
+endif
+
+ifeq ($(OPENJDK_TARGET_OS), linux)
+  ifeq ($(OPENJDK_TARGET_CPU_ARCH), ppc)
+    BUILD_LIBFDLIBM_OPTIMIZATION := HIGH
+  endif
 endif

 LIBFDLIBM_SRC := $(JDK_TOPDIR)/src/java.base/share/native/libfdlibm
@@ -51,6 +57,7 @@
       CFLAGS := $(CFLAGS_JDKLIB) $(LIBFDLIBM_CFLAGS), \
       CFLAGS_windows_debug := -DLOGGING, \
       CFLAGS_aix := -qfloat=nomaf, \
+      CFLAGS_linux_ppc := -fno-expensive-optimizations, \
       DISABLED_WARNINGS_gcc := sign-compare, \
       DISABLED_WARNINGS_microsoft := 4146 4244 4018, \
       ARFLAGS := $(ARFLAGS), \


diff -r 2a1f97c0ad3d make/common/NativeCompilation.gmk
--- a/make/common/NativeCompilation.gmk	Wed Nov 09 15:32:39 2016 +0100
+++ b/make/common/NativeCompilation.gmk	Wed Nov 16 19:08:06 2016 -0500
@@ -569,16 +569,19 @@
   $1_ALL_OBJS := $$(sort $$($1_EXPECTED_OBJS) $$($1_EXTRA_OBJECT_FILES))

   # Pickup extra OPENJDK_TARGET_OS_TYPE and/or OPENJDK_TARGET_OS dependent variables for CFLAGS.
-  $1_EXTRA_CFLAGS:=$$($1_CFLAGS_$(OPENJDK_TARGET_OS_TYPE)) $$($1_CFLAGS_$(OPENJDK_TARGET_OS))
+  $1_EXTRA_CFLAGS:=$$($1_CFLAGS_$(OPENJDK_TARGET_OS_TYPE)) $$($1_CFLAGS_$(OPENJDK_TARGET_OS)) \
+      $$($1_CFLAGS_$(OPENJDK_TARGET_OS)_$(OPENJDK_TARGET_CPU_ARCH))
   ifneq ($(DEBUG_LEVEL),release)
     # Pickup extra debug dependent variables for CFLAGS
     $1_EXTRA_CFLAGS+=$$($1_CFLAGS_debug)
     $1_EXTRA_CFLAGS+=$$($1_CFLAGS_$(OPENJDK_TARGET_OS_TYPE)_debug)
     $1_EXTRA_CFLAGS+=$$($1_CFLAGS_$(OPENJDK_TARGET_OS)_debug)
+    $1_EXTRA_CFLAGS+=$$($1_CFLAGS_$(OPENJDK_TARGET_OS)_$(OPENJDK_TARGET_CPU_ARCH)_debug)
   else
     $1_EXTRA_CFLAGS+=$$($1_CFLAGS_release)
     $1_EXTRA_CFLAGS+=$$($1_CFLAGS_$(OPENJDK_TARGET_OS_TYPE)_release)
     $1_EXTRA_CFLAGS+=$$($1_CFLAGS_$(OPENJDK_TARGET_OS)_release)
+    $1_EXTRA_CFLAGS+=$$($1_CFLAGS_$(OPENJDK_TARGET_OS)_$(OPENJDK_TARGET_CPU_ARCH)_release)
   endif

   # Pickup extra OPENJDK_TARGET_OS_TYPE and/or OPENJDK_TARGET_OS dependent variables for CXXFLAGS.


After enabling the optimization it's possible to again up to 3x on performance
regarding the aforementioned methods without losing precision:

                           StrictMath, original              StrictMath, optimized
                   ============================       ============================
sin                1.7136493465700542 1m41.184s      1.7136493465700542  0m33.895s
cos                0.1709843554185943 1m41.200s      0.1709843554185943  0m33.884s
tan             -5.5500322522995315E7 1m46.976s   -5.5500322522995315E7  0m36.461s
asin                              NaN  0m4.543s                     NaN   0m3.175s
acos                              NaN  0m4.525s                     NaN   0m3.211s
atan             1.5707961389886132E8 0m12.896s    1.5707961389886132E8   0m7.100s
exp                          Infinity  0m4.570s                Infinity   0m3.187s
log              1.7420680845245087E9 0m14.239s    1.7420680845245087E9   0m7.170s
log10             7.565705562087342E8 0m20.236s     7.565705562087342E8   0m9.610s
sqrt              6.66666671666567E11  0m0.981s     6.66666671666567E11   0m0.948s
cbrt             3.481191648389617E10 0m10.808s    3.481191648389617E10  0m10.786s
sinh                         Infinity  0m4.433s                Infinity   0m3.179s
cosh                         Infinity  0m4.478s                Infinity   0m3.174s
tanh              9.999999971990079E7  0m3.353s     9.999999971990079E7   0m3.208s
expm1                        Infinity  0m4.094s                Infinity   0m3.185s
log1p            1.7420681029451895E9 0m13.527s    1.7420681029451895E9   0m8.756s
IEEEremainder                502000.0 0m38.909s                502000.0  0m14.055s
atan2             1.570453905253704E8 0m20.057s     1.570453905253704E8  0m10.510s
pow                          Infinity 0m19.938s                Infinity  0m20.204s
hypot            5.000000099033372E15  0m5.122s    5.000000099033372E15   0m5.130s


I believe that as the FC is passed but FEC is not the change can, after the due
scrutiny and review, be pushed if a special exception approval grants it. Once
on 9, I'll request the downport to 8.

Could I open a bug to address that issue?

Thank you very much.


Regards,
Gustavo

[1] http://hg.openjdk.java.net/jdk9/hs/jdk/file/81eb4bd34611/make/lib/CoreLibraries.gmk#l39
[2] https://github.com/gromero/strictmath (comparison script used to get the results)



More information about the ppc-aix-port-dev mailing list