![](/i/fill.gif) |
![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
From: S Tayefeh
Subject: BENCHMARK: Itanium, Opteron, Xeon, Athlon (GCC, ICC)
Date: 10 Aug 2004 06:55:56
Message: <4118a9bc$1@news.povray.org>
|
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Hi!
I have had the chance to compile and run POV3.6 on various platforms
using Gnu C/C++ Compiler and Intel C/C++ Compiler.
I have run tests on these Linux-Machines (further specs see below):
* INTEL Itanium, 0.8 GHz,
* AMD Athlon TB, 0.8 GHz,
* AMD Opteron 244, 1.8 GHz,
* INTEL Pentium IV Xeon, 2.4 GHz
Of course, it's not particularly fair to compare a 1.8GHz Opteron machine
with a 0.8 GHz Athlon --keep that in mind, please!
Benchmark for var. archs and compilers:
using POV-Rays official benchmark.pov script
with suggested options -w384 -h384 +a0.3 +v -d -f -x
numbers = processor time [seconds]
LOWER NUMBERS = BETTER
ICC8.0 GCC3.x.x
---------------------------------
ITANIUM (64) 10880 8715
---------------------------------
OPTERON (64) n.a. 1580
---------------------------------
XEON (32) 2458 3757
---------------------------------
ATHLON (32) n.a. 5012
---------------------------------
(64=64bit arch, 32=32bit arch)
* AMD Opteron 244, 1.8 GHz, 4 GByte RAM
(dual processor boards in cluster)
RedHat Linux
* INTEL Pentium IV Xeon, 2.4 GHz, 2 GByte RAM
(dual processor boards in cluster)
RedHat Linux
* INTEL Itanium, 0.8 GHz, 2 GByte Ram
(dual processor board)
Debian Linux
* AMD Athlon TB, 0.8 GHz, 256 kB Ram
(single processor board)
Debian Linux
Obviously, you won't make use of an Itanium machine
because of it's speed ;-) I was wondering why the Intel Compiler
produced a code that performed ~20% slower than the one produced
by GCC, so I randomly chose some of POVs example-scene files for
render with both codes, and here is what I got:
SCRIPT ICC8.0 GCC3.x
--------------------------------------
box.pov 5.87 5.80
mesh2.pov 45.14 40.06
glassthing.pov 299.09 320.25
parallel_lights.pov 19.37 21.69
circular.pov 143.74 175.14
shadows.pov 67.86 89.82
fog_ft.pov 10.30 9.21
atten2.pov 30.70 34.06
caustic2.pov 22.60 19.50
skysph2.pov 32.85 21.26
radiosity2.pov 187.19 207.37
cornell.pov 71.10 81.8
shear.pov 0.03 0.03
perspective.pov 0.02 0.03
panoramic.pov 0.03 0.03
focalblur.pov 0.03 0.03
abyss.pov 486.54 536.31
gaussianblob.pov 213.71 230.85
--------------------------------------
MEAN 91.00 99.70
So here is what I expected. Overall-performance codes produced by
the Intel-Compiler is ~10% better than GCC-Codes. It seems, that calculation
of simple objects with no further options like fog etc perform better with
GCC-POV Code. However, scripts like 'circular.pov', 'abyss.pov' or
'shadows.pov' show drastical improovement with ICC-POV-Code.
I run the same scripts on the Xeon Machine and noticed an overall
improovement of approx. 12% using ICC (ICC: 28.9s, GCC: 33.0s).
Comments and suggestions welcome...
Sincerely
S. Tayefeh
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
From: Christoph Hormann
Subject: Re: BENCHMARK: Itanium, Opteron, Xeon, Athlon (GCC, ICC)
Date: 10 Aug 2004 07:10:02
Message: <cfaac1$crb$1@chho.imagico.de>
|
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
S Tayefeh wrote:
>
> Hi!
>
> I have had the chance to compile and run POV3.6 on various platforms
> using Gnu C/C++ Compiler and Intel C/C++ Compiler.
>
> I have run tests on these Linux-Machines (further specs see below):
> * INTEL Itanium, 0.8 GHz,
> * AMD Athlon TB, 0.8 GHz,
> * AMD Opteron 244, 1.8 GHz,
> * INTEL Pentium IV Xeon, 2.4 GHz
>
> Of course, it's not particularly fair to compare a 1.8GHz Opteron machine
> with a 0.8 GHz Athlon --keep that in mind, please!
>
>
> Benchmark for var. archs and compilers:
>
> using POV-Rays official benchmark.pov script
> with suggested options -w384 -h384 +a0.3 +v -d -f -x
Please use the benchmark.ini coming with POV-Ray. This makes sure the
results are comparable with those made by others, using the above
options does not!
> numbers = processor time [seconds]
> LOWER NUMBERS = BETTER
>
> ICC8.0 GCC3.x.x
> ---------------------------------
> ITANIUM (64) 10880 8715
> ---------------------------------
> OPTERON (64) n.a. 1580
> ---------------------------------
> XEON (32) 2458 3757
> ---------------------------------
> ATHLON (32) n.a. 5012
> ---------------------------------
> (64=64bit arch, 32=32bit arch)
>
> * AMD Opteron 244, 1.8 GHz, 4 GByte RAM
> (dual processor boards in cluster)
> RedHat Linux
> * INTEL Pentium IV Xeon, 2.4 GHz, 2 GByte RAM
> (dual processor boards in cluster)
> RedHat Linux
> * INTEL Itanium, 0.8 GHz, 2 GByte Ram
> (dual processor board)
> Debian Linux
> * AMD Athlon TB, 0.8 GHz, 256 kB Ram
> (single processor board)
> Debian Linux
>
>
>
> Obviously, you won't make use of an Itanium machine
> because of it's speed ;-) I was wondering why the Intel Compiler
> produced a code that performed ~20% slower than the one produced
> by GCC, so I randomly chose some of POVs example-scene files for
> render with both codes, and here is what I got:
>
> [...]
Without telling about the compiler options used this is pretty useless -
you did not even mention if the Opteron/Itanium tests use a 64bit
compile or not. Also 'GCC3.x.x' is a somewhat incomplete information.
Christoph
--
POV-Ray tutorials, include files, Sim-POV,
HCR-Edit and more: http://www.tu-bs.de/~y0013390/
Last updated 06 Jul. 2004 _____./\/^>_*_<^\/\.______
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
From: S Tayefeh
Subject: Re: BENCHMARK: Itanium, Opteron, Xeon, Athlon (GCC, ICC)
Date: 10 Aug 2004 07:55:56
Message: <4118b7cc$1@news.povray.org>
|
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Christoph Hormann wrote:
> Please use the benchmark.ini coming with POV-Ray. This makes sure the
> results are comparable with those made by others, using the above
> options does not!
I'm afraid I didn't notice that .ini. Next time, I'll do!
> Without telling about the compiler options used this is pretty useless -
> you did not even mention if the Opteron/Itanium tests use a 64bit
> compile or not. Also 'GCC3.x.x' is a somewhat incomplete information.
You're right. This was supposed to be a quick test, however, here are
the most important spec. for all but Athlon (coming later):
******************************************************
*** ITANIUM:
******************************************************
> uname -a
> Linux xxxxx 2.4.26-1-itanium-smp #1 SMP Tue Jun 8 20:39:36 MDT 2004
ia64 GNU/Linux
* GCC: gcc (GCC) 3.3.4 (Debian 1:3.3.4-6sarge1) (64-Bit, I suppose)
* ICC: icc 8.0 (64-Bit)
GCC-OPTIONS:
------------
CFLAGS =
CPP = gcc -E
CPPFLAGS = -I/usr/X11R6/include
CXXCPP = g++ -E
CXXFLAGS = -pipe -Wno-multichar -O3
LDFLAGS = -L/usr/X11R6/lib
LIBS = -ltiff -ljpeg -lpng12 -lz -lXpm -lSM -lICE -lX11 -lm
X_CFLAGS = -I/usr/X11R6/include
X_LIBS = -L/usr/X11R6/lib
X_PRE_LIBS = -lSM -lICE
ICC-options:
------------
CFLAGS = -g
CPP = /<path>/icc -E
CPPFLAGS = -I/usr/X11R6/include
CXX = /<path>/icc
CXXCPP = /<path>/icc -E
CXXDEPMODE = depmode=gcc3
CXXFLAGS = -O3
LDFLAGS = -L/usr/X11R6/lib
LIBS = -ltiff -ljpeg -lpng12 -lz -lXpm -lSM -lICE -lX11 -lm
X_CFLAGS = -I/usr/X11R6/include
X_LIBS = -L/usr/X11R6/lib
X_PRE_LIBS = -lSM -lICE
*****************************************************************
**** XEON:
*****************************************************************
> uname -a
> Linux xxxxx 2.4.24 #2 SMP Mon Jan 12 13:39:44 CET 2004 i686 unknown
* gcc 2.96 (32-Bit)
* icc 7.1 (32-Bit)
GCC-OPTIONS:
------------
CFLAGS = -pipe -O3 -msse -malign-double -minline-all-stringops
CPP = gcc -E
CPPFLAGS = -I/usr/X11R6/include
CXX = g++
CXXCPP = g++ -E
CXXDEPMODE = depmode=gcc3
CXXFLAGS = -pipe -Wno-multichar -O3 -msse -march=i686 -malign-double
-minline-all-stringops
LDFLAGS = -L/usr/X11R6/lib
LIBS = -ljpeg -lXpm -lSM -lICE -lX11 -lm
X_CFLAGS = -I/usr/X11R6/include
X_EXTRA_LIBS =
X_LIBS = -L/usr/X11R6/lib
X_PRE_LIBS = -lSM -lICE
ICC-OPTIONS:
------------
CFLAGS = -O3 -ip -march=pentium4 -mcpu=pentium4
CPP = icc -E
CPPFLAGS = -I/usr/X11R6/include
CXX = icc
CXXCPP = icc -E
CXXDEPMODE = depmode=icc
CXXFLAGS = -O3 -ip -march=pentium4 -mcpu=pentium4
LDFLAGS = -L/usr/X11R6/lib
LIBS = -ljpeg -lXpm -lSM -lICE -lX11 -lm
X_CFLAGS = -I/usr/X11R6/include
X_LIBS = -L/usr/X11R6/lib
X_PRE_LIBS = -lSM -lICE
*****************************************************************
**** OPTERON:
*****************************************************************
> uname -a
> Linux xxxxx 2.4.21-15.ELsmp #1 SMP Thu Apr 22 00:09:01 EDT 2004
x86_64 x86_64 x86_64 GNU/Linux
* gcc (GCC) 3.2.3 20030502 (Red Hat Linux 3.2.3-34) (64-Bit)
GCC-Options:
------------
CFLAGS = -pipe -O3 -msse -mfpmath=sse -msse2 -march=k8 -mcpu=k8
-minline-all-stringops
CPP = gcc -E
CPPFLAGS = -I/usr/X11R6/include
CXX = g++
CXXCPP = g++ -E
CXXFLAGS = -pipe -Wno-multichar -O3 -msse -mfpmath=sse -msse2 -march=k8
-mcpu=k8 -minline-all-stringops
LDFLAGS = -L/usr/X11R6/lib64
LIBS = -ljpeg -lXpm -lSM -lICE -lX11 -lm
X_CFLAGS = -I/usr/X11R6/include
X_LIBS = -L/usr/X11R6/lib64
X_PRE_LIBS = -lSM -lICE
Cheers
ST
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
From: Christoph Hormann
Subject: Re: BENCHMARK: Itanium, Opteron, Xeon, Athlon (GCC, ICC)
Date: 10 Aug 2004 08:30:02
Message: <cfaevs$djq$1@chho.imagico.de>
|
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
S Tayefeh wrote:
>
>> Without telling about the compiler options used this is pretty useless
>> - you did not even mention if the Opteron/Itanium tests use a 64bit
>> compile or not. Also 'GCC3.x.x' is a somewhat incomplete information.
>
>
> You're right. This was supposed to be a quick test, however, here are
> the most important spec. for all but Athlon (coming later):
>
Thanks. The Xeon test is not very representative when not using
-march=pentium4 (which gcc 2.96 probably does not support). Can't say
much about the Itanium and ICC compiles.
For a really useful comparison you should use the same compiler version
and same options except the -march and other processor specific flags
on all machines.
Christoph
--
POV-Ray tutorials, include files, Sim-POV,
HCR-Edit and more: http://www.tu-bs.de/~y0013390/
Last updated 06 Jul. 2004 _____./\/^>_*_<^\/\.______
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |