gRRosminet wrote:

> As config files are cached by ./configure, you may need to completly 
> delete the directory and re-extract the archive.
> 
     No. Juste delete "config.cache" can do the job...

-- 
http://tth.vaboofer.com/Cette/

Post a reply to this message

Christoph Hormann wrote:
> Nicolas Calimet wrote:
> 
>>> very very slow (optimized for pentium 1) whereas using an optimized 
>>> version can improve performances by 50% !!!
>>
>>
>>
>>     You mean that the official binary was compiled with no optimization
>> at all ?  (frankly I never tried it)
> 
> 
> There has been an early 3.5 official binary version compiled without 
> optimization but the current official version is compiled with -O3.  And 
> as you also observed some time ago the speed advantage with using more 
> fancy (processor specific and possibly faulty) optimizations is 
> marginal.  There is absolutely no need to compile POV-Ray from source 
> just for the speed advantage (to actually save time this way, even if 
> you have experience compiling programs yourself, you will have to render 
> quite a lot of very slow scenes).
> 
> Christoph
> 

If you take a look at the generated Makefile, povray is compiled with 
march=i586. This is why the official binary is so slow : it doesn't take 
advantage of SSE/SSE2/3DNow2 instructions which are really faster than 
standards ones and which can be executed at the same time than other 
standard ones.
If you have an athlon thunderbird and compile povray with -march=athlon 
instead of -march=i586, you'll get a povray running about 30% faster 
than the original one. So I let you imagine what you can get with a 
athlon xp or pentium 4 optimized version.


 >> (to do this, you'll need to modify the Makefile => ask for it when 
you'll be ready)
 >    May I ?
 >    Ok, go on, I'm ready

on a clean extraction, you can change this parameters just after the 
./configure : edit the Makefile and look for the line that begin with 
CFLAGS. The mcpu=i586 and march=i586 options can be replaced by the ones 
corresponding to your computer (i686, athlon, pentium3, athlon-xp, 
pentium4 ... take a look at gcc man page).

the CXXFLAGS line should be replaced by CXXFLAGS="${CFLAGS}"


That's all !

Post a reply to this message

gRRosminet wrote:
> 
> If you take a look at the generated Makefile, povray is compiled with 
> march=i586. This is why the official binary is so slow : it doesn't take 
> advantage of SSE/SSE2/3DNow2 instructions which are really faster than 
> standards ones and which can be executed at the same time than other 
> standard ones.
> If you have an athlon thunderbird and compile povray with -march=athlon 
> instead of -march=i586, you'll get a povray running about 30% faster 
> than the original one. So I let you imagine what you can get with a 
> athlon xp or pentium 4 optimized version.

No, i am pretty sure when you get such results you have not made a 
serious comparison.  When you come up with such numbers it would be 
adequate to back them up with some benchmark results and offer the used 
executables for others to verify.

Christoph

-- 
POV-Ray tutorials, include files, Sim-POV,
HCR-Edit and more: http://www.tu-bs.de/~y0013390/
Last updated 01 May. 2004 _____./\/^>_*_<^\/\.______

Post a reply to this message

> povray is compiled with 
> march=i586. This is why the official binary is so slow : it doesn't take 
> advantage of SSE/SSE2/3DNow2 instructions which are really faster than 
> standards ones

	To take advantage of such specialized instructions, you have to
make your program _use_ them, which is not the case in povray because its
code is mostly doing (double precision) floating-point arithmetics.

> If you have an athlon thunderbird and compile povray with -march=athlon 
> instead of -march=i586, you'll get a povray running about 30% faster 
> than the original one.

	Please report results of running benchmark.ini with a version
compiled using -march=i586 and another with -march=athlon, using the
same compiler of course.

 > [snip]
> the CXXFLAGS line should be replaced by CXXFLAGS="${CFLAGS}"
> That's all !

	"Thanks for teaching" (private joke)  :-)

	- NC

Post a reply to this message

In article <40b217d1$1@news.povray.org> , Nicolas Calimet 
<pov### [at] freefr>  wrote:

>  "Thanks for teaching" (private joke)  :-)

Wasn't that "lecturing"? ;-)

(Someone who knows what this joke was about.)

    Thorsten

____________________________________________________
Thorsten Froehlich, Duisburg, Germany
e-mail: tho### [at] trfde

Visit POV-Ray on the web: http://mac.povray.org

Post a reply to this message

Christoph Hormann wrote:
> No, i am pretty sure when you get such results you have not made a 
> serious comparison.  When you come up with such numbers it would be 
> adequate to back them up with some benchmark results and offer the used 
> executables for others to verify.
> 
> Christoph



I have downloaded the official binary for linux and ran the benchmark.

Official : 45 minutes 08 seconds ( 2708 seconds )
gcc pentium4 optimized : 36 minutes 43 seconds ( 2203 seconds )
ICC pentium4 optimized : 33 minutes 01 seconds ( 1981 seconds )

ratios (official / optimized) :
Official : 1
gcc pentium4 optimized : 1.229
icc pentium4 optimized : 1.367

Post a reply to this message

In article <40b229f2@news.povray.org> , gRRosminet <pov### [at] les-charlesnet>
wrote:

> I have downloaded the official binary for linux and ran the benchmark.
>
> Official : 45 minutes 08 seconds ( 2708 seconds )
> gcc pentium4 optimized : 36 minutes 43 seconds ( 2203 seconds )
> ICC pentium4 optimized : 33 minutes 01 seconds ( 1981 seconds )

And the gcc and Intel C++ compiler versions happen to be?

I suppose they were more recent versions of the compiler used for the
official version two years ago?  If so, your statement about optimisations
happens to have no validity at all...

    Thorsten

____________________________________________________
Thorsten Froehlich, Duisburg, Germany
e-mail: tho### [at] trfde

Visit POV-Ray on the web: http://mac.povray.org

Post a reply to this message

Thorsten Froehlich wrote:
> In article <40b229f2@news.povray.org> , gRRosminet <pov### [at] les-charlesnet>
> wrote:
> 
> 
>>I have downloaded the official binary for linux and ran the benchmark.
>>
>>Official : 45 minutes 08 seconds ( 2708 seconds )
>>gcc pentium4 optimized : 36 minutes 43 seconds ( 2203 seconds )
>>ICC pentium4 optimized : 33 minutes 01 seconds ( 1981 seconds )
> 
> 
> And the gcc and Intel C++ compiler versions happen to be?
> 
> I suppose they were more recent versions of the compiler used for the
> official version two years ago?  If so, your statement about optimisations
> happens to have no validity at all...

I unsubscribe povray.unix.

I should have done it way before, just as I has already done for most 
official ngs. Nobody in the community needs this kind of permanent 
aggressivity. Please try to get a life.

-- 

Post a reply to this message

<woz### [at] club-internetfr>  wrote:

>>>I have downloaded the official binary for linux and ran the benchmark.
>>>
>>>Official : 45 minutes 08 seconds ( 2708 seconds )
>>>gcc pentium4 optimized : 36 minutes 43 seconds ( 2203 seconds )
>>>ICC pentium4 optimized : 33 minutes 01 seconds ( 1981 seconds )
>>
>>
>> And the gcc and Intel C++ compiler versions happen to be?
>>
>> I suppose they were more recent versions of the compiler used for the
>> official version two years ago?  If so, your statement about optimisations
>> happens to have no validity at all...
>
> I unsubscribe povray.unix.
>
> I should have done it way before, just as I has already done for most
> official ngs. Nobody in the community needs this kind of permanent
> aggressivity. Please try to get a life.

There is not a single aggressive word in my statement at all.  Yet, you
start a personal insult out of thin air.  If you don't want to read simple
questions and plain statements about obvious facts, I suppose to unsubscribe
is indeed the only way to go.

    Thorsten

____________________________________________________
Thorsten Froehlich, Duisburg, Germany
e-mail: tho### [at] trfde

Visit POV-Ray on the web: http://mac.povray.org

Post a reply to this message

> Official : 45 minutes 08 seconds ( 2708 seconds )
> gcc pentium4 optimized : 36 minutes 43 seconds ( 2203 seconds )
> ICC pentium4 optimized : 33 minutes 01 seconds ( 1981 seconds )

	As was implied by Thorsten's answer, to make a reliable comparison
you cannot simply use the two-years-old official binary, which was probably
compiled at best with gcc-3.1.x.  You should take the source and recompile
them with the gcc you are using to produce your pentium4-optimized version.
	Also please report the gcc and icc versions as well as the details
of processor and OS on which you run the benchmarks.  Also be sure to render
the benchmark.ini file (and its accompagnying benchmark.pov scene) available
on povray.org at  http://www.povray.org/download/benchmark.php

	Please note there is no agressivity at all in this suggestion:
I'm actually quite interested in seeing such results -- when benchmarks
are made properly.

	- NC

Post a reply to this message