POV-Ray : Newsgroups : povray.news-submissions : POV-RAY (SMPOV) Performance Test with Opteron, Xeon and AthlonMP Server Time
28 Mar 2024 17:01:14 EDT (-0400)
  POV-RAY (SMPOV) Performance Test with Opteron, Xeon and AthlonMP (Message 1 to 6 of 6)  
From: pennter napper
Subject: POV-RAY (SMPOV) Performance Test with Opteron, Xeon and AthlonMP
Date: 27 Nov 2003 15:50:55
Message: <3fc663af$1@news.povray.org>
Hi, you will find the whole contest here:

http://www.3dchips.net/content/review.php?id=67

http://www.3dchips.net/content/review.php?id=67&page=20 (SMPOV)

Pit


Post a reply to this message

From: Thorsten Froehlich
Subject: Re: POV-RAY (SMPOV) Performance Test with Opteron, Xeon and AthlonMP
Date: 27 Nov 2003 17:02:48
Message: <3fc67488$1@news.povray.org>
In article <3fc663af$1@news.povray.org> , "pennter napper" 
<amo### [at] nettercom> wrote:

> Hi, you will find the whole contest here:
>
> http://www.3dchips.net/content/review.php?id=67
>
> http://www.3dchips.net/content/review.php?id=67&page=20 (SMPOV)

Hmm, they didn't use the official version, used one of the most unsuitable
scenes instead of the benchmark and they don't even say which settings they
used.  Is this really worthy news for the povray.org website?  I don't think
so.

    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

From: Pit
Subject: Re: POV-RAY (SMPOV) Performance Test with Opteron, Xeon and
Date: 13 Dec 2003 09:05:01
Message: <web.3fdb1be0450b9bc3548e3d130@news.povray.org>
>Hmm, they didn't use the official version, used one of the most unsuitable
>scenes instead of the benchmark and they don't even say which settings they
>used.  Is this really worthy news for the povray.org website?  I don't think
>so.
>
>    Thorsten
>
>____________________________________________________
>Thorsten Froehlich, Duisburg, Germany
>e-mail: tho### [at] trfde
>
>Visit POV-Ray on the web: http://mac.povray.org
>

We got information that the optics scene is accepted by the povray
community. By the way we used the povray standard settings (1600x1200).

Regards,
Pit


Post a reply to this message

From: Christopher James Huff
Subject: Re: POV-RAY (SMPOV) Performance Test with Opteron, Xeon and
Date: 20 Dec 2003 11:37:55
Message: <cjameshuff-777733.11380020122003@netplex.aussie.org>
In article <web.3fdb1be0450b9bc3548e3d130@news.povray.org>,
 "Pit" <nomail@nomail> wrote:

> We got information that the optics scene is accepted by the povray
> community. By the way we used the povray standard settings (1600x1200).

Who told you that? I wrote the thing, and it is about as bad of a 
general benchmark scene as you can design...it would only be useful if 
you're specifically measuring the speed of photons in media. The 
optics.pov demo scene has two purposes: to demonstrate a working scene 
using photons in scattering media, and to look pretty. It is "accepted 
by the POV-Ray community"...as a demo scene. The accepted benchmark 
scene is, surprisingly enough, benchmark.pov, which is in the same 
folder as optics.pov.

-- 
Christopher James Huff <cja### [at] earthlinknet>
http://home.earthlink.net/~cjameshuff/
POV-Ray TAG: chr### [at] tagpovrayorg
http://tag.povray.org/


Post a reply to this message

From: Thorsten Froehlich
Subject: Re: POV-RAY (SMPOV) Performance Test with Opteron, Xeon and
Date: 24 Dec 2003 05:20:23
Message: <3fe96867$1@news.povray.org>
In article <web.3fdb1be0450b9bc3548e3d130@news.povray.org> , "Pit" 
<nomail@nomail> wrote:

> We got information that the optics scene is accepted by the povray
> community. By the way we used the povray standard settings (1600x1200).

Whatever you source of information is, it is plain wrong.  Almost any other
demo scene that comes with POV-Ray is more suitable than optics.pov.  And it
really is not hard to find out which is an accepted benchmark scene if you
check povray.org webside (download page) or just search for
<http://www.google.com/search?q=povray+benchmark>
(btw, ignore the second entry, it is ancient junk, and it suggests Google's
ranking system is breaking more and more as they try to eliminate commercial
misuse of their ranking).

    Thorsten

____________________________________________________
Thorsten Froehlich
e-mail: mac### [at] povrayorg

I am a member of the POV-Ray Team.
Visit POV-Ray on the web: http://mac.povray.org


Post a reply to this message

From: Theo Gottwald * * *
Subject: Re: POV-RAY (SMPOV) Performance Test with Opteron, Xeon and
Date: 1 Jan 2004 14:00:18
Message: <3ff46e42$1@news.povray.org>
Hi all,

To make a test with a clear result is even more hard, when the two
competitors are close to each other like A64 and XEON. So the last
percentage depends on the choosen Test-Scene..

I remember that I sent a e-mail to Mr. Hauser who did the Test, telling him
about the problem to choose "Scene X" for a Test as well as a factors like
Resolution, total Rendering-time/Overhead.

As A64 and XEON are not far from each other, but have quite big diffrences
in Architecture, you can choose "Scene X" which renders better on CPU X.
Because the sort of calculations that are needed, are faster with the
current CPU-Architecture.

So the best choice would have been to take a scene which contains all sorts
of calculation (benchmark.pov) for single CPU-Testing. Alternatively it
would have been possible to render all Scnenes and give the results "by
feature" or "for all scenes" (A64 faster with Photons, XEON better with ...
etc.).

However I think they did not want to get too special with this test, and
someone informed them wrong about optics.pov or they read it in a posting
maybe.

Knowing that we can still say that both systems (A64 and XEON) are ok for
use with POV-Ray /SMPOV and there is not one of them which is far behind the
competitor.

Happy new year for you all
--Theo

"Thorsten Froehlich" <tho### [at] trfde> schrieb im Newsbeitrag
news:3fe96867$1@news.povray.org...
> In article <web.3fdb1be0450b9bc3548e3d130@news.povray.org> , "Pit"
> <nomail@nomail> wrote:
>
> > We got information that the optics scene is accepted by the povray
> > community. By the way we used the povray standard settings (1600x1200).
>
> Whatever you source of information is, it is plain wrong.  Almost any
other
> demo scene that comes with POV-Ray is more suitable than optics.pov.  And
it
> really is not hard to find out which is an accepted benchmark scene if you
> check povray.org webside (download page) or just search for
> <http://www.google.com/search?q=povray+benchmark>
> (btw, ignore the second entry, it is ancient junk, and it suggests
Google's
> ranking system is breaking more and more as they try to eliminate
commercial
> misuse of their ranking).
>
>     Thorsten
>
> ____________________________________________________
> Thorsten Froehlich
> e-mail: mac### [at] povrayorg
>
> I am a member of the POV-Ray Team.
> Visit POV-Ray on the web: http://mac.povray.org


Post a reply to this message

Copyright 2003-2023 Persistence of Vision Raytracer Pty. Ltd.