POV-Ray : Newsgroups : povray.news-submissions : Processor benchmarking using POV-Ray Server Time
28 Mar 2024 04:34:32 EDT (-0400)
  Processor benchmarking using POV-Ray (Message 1 to 4 of 4)  
From: Hughes, B 
Subject: Processor benchmarking using POV-Ray
Date: 19 Aug 2003 03:43:25
Message: <3f41d51d@news.povray.org>
Below is the web address to an article from two months ago, which might not
be worthy of "news" for www.povray.org web site but could be of interest to
people keeping tabs on the usual AMD vs. Intel scores. Unfortunately the
reviewer seems to be using the old chess.pov benchmark instead of the newer
one with version 3.5. I've only just now e-mailed the reviewer to ask about
it.

http://www.pcstats.com/articleview.cfm?articleid=1409&page=3

My personal observation would be that the gap between AMD and Intel has
narrowed significantly since the previous crop of processors. Intel is so
bad with FPU!  :-)

Here's another web page showing off the P-R 3.5 benchmark.

http://www.linuxhardware.org/features/03/02/19/1544249.shtml

And another. Anyone ever see this before? I know I couldn't recall it,
especially not on a DELL web page.

http://www.dell.com/us/en/slg/topics/power_ps2q01-beowulf.htm

-- 
Bob H.


Post a reply to this message

From: Thorsten Froehlich
Subject: Re: Processor benchmarking using POV-Ray
Date: 19 Aug 2003 17:00:01
Message: <3f428fd1$1@news.povray.org>
In article <3f41d51d@news.povray.org> , "Hughes, B." <omn### [at] charternet>
wrote:

> Below is the web address to an article from two months ago, which might not
> be worthy of "news" for www.povray.org web site but could be of interest to
> people keeping tabs on the usual AMD vs. Intel scores. Unfortunately the
> reviewer seems to be using the old chess.pov benchmark instead of the newer
> one with version 3.5. I've only just now e-mailed the reviewer to ask about
> it.
>
> http://www.pcstats.com/articleview.cfm?articleid=1409&page=3

Is this on Linux or Windos?

> My personal observation would be that the gap between AMD and Intel has
> narrowed significantly since the previous crop of processors. Intel is so
> bad with FPU!  :-)
>
> Here's another web page showing off the P-R 3.5 benchmark.
>
> http://www.linuxhardware.org/features/03/02/19/1544249.shtml

This site claims turing off SSE2 yields better performance on a P4.  Unless
I missed something in that article, this is simply wrong.

Honestly, I don't think any of the benchmarks using POV-Ray on these two
pages where conducted well...

    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: Hughes, B 
Subject: Re: Processor benchmarking using POV-Ray
Date: 19 Aug 2003 19:03:16
Message: <3f42acb4$1@news.povray.org>
"Thorsten Froehlich" <tho### [at] trfde> wrote in message
news:3f428fd1$1@news.povray.org...
> In article <3f41d51d@news.povray.org> , "Hughes, B."
<omn### [at] charternet>
> wrote:
>
> > Below is the web address to an article from two months ago
> >
> > http://www.pcstats.com/articleview.cfm?articleid=1409&page=3
>
> Is this on Linux or Windows?

I'm awaiting word from the reviewer for more info but they seem oriented
only to Windows. For example, the Winstone benchmark used and mention of Win
2000, WinME, XP.

> > Here's another web page showing off the P-R 3.5 benchmark.
> >
> > http://www.linuxhardware.org/features/03/02/19/1544249.shtml
>
> This site claims turning off SSE2 yields better performance on a P4.
Unless
> I missed something in that article, this is simply wrong.

Hmmm, I wonder if it could be that they only tried those complies from that
particular binaries download page. Seeing as there is only that one
P4-optimised one there, others are Pentium and P3.

> Honestly, I don't think any of the benchmarks using POV-Ray on these two
> pages where conducted well...

I had been looking around at popular (via google.com) web pages for such
information and I can agree with you about the questionable validity or
quality of them. As can be seen at the two well-known POV-Ray benchmarking
places (haveland.com, tabsnet.com) the variances and unseen methods used do
not always help, decidedly, show which processors (and compiled versions)
are best. It still seems a realm few people delve into extremely deeply.

If I take the generality into account though (and that's all I was looking
for), I must conclude AMD has lost a little ground in the race recently, yet
still could be preferrable over an Intel CPU in the future. Only time will
tell. Uh, no pun intended there... but it works here.

Bob H.


Post a reply to this message

From: Warp
Subject: Re: Processor benchmarking using POV-Ray
Date: 19 Aug 2003 19:52:08
Message: <3f42b828@news.povray.org>
Hughes, B. <omn### [at] charternet> wrote:
> If I take the generality into account though (and that's all I was looking
> for), I must conclude AMD has lost a little ground in the race recently

  That would be true only if AMD's processor is as expensive as Intel's.
I haven't been looking at prices recently, but at least in the past AMD
has always been less expensive.

-- 
#macro N(D)#if(D>99)cylinder{M()#local D=div(D,104);M().5,2pigment{rgb M()}}
N(D)#end#end#macro M()<mod(D,13)-6mod(div(D,13)8)-3,10>#end blob{
N(11117333955)N(4254934330)N(3900569407)N(7382340)N(3358)N(970)}//  - Warp -


Post a reply to this message

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