Hi,

We run a small architectural lighting design consultancy.  We use DIALux 4.1
for most of our photometrics, and POV-Ray to render the associated files.
We're about to purchase a computer which will largely function as a
rendering machine (the other tasks it'll be doing are relatively trivial).
We're trying to work out what specs we need.

The essential questions are:

1.  We're looking at dual-core processors for faster rendering - how do we
go for bang for your buck?

2.  How much RAM do we actually need (I've never seen POVRay run past 790Mb
on our current Pentium M based machine, which has 2Gb).

3.  How much difference does the graphics card make?  What type of card
should we look at using.

4.  Any other advice that you think useful.

Thomas.

Post a reply to this message

Thomas spake:

> 1.  We're looking at dual-core processors for faster rendering - how do we
> go for bang for your buck?

IMO get the fastest dual-core processor you can get. Beter yet, get a quad 
motherboard (I think HP makes some nice ones) that will take four
processors. You can then theoretically render four times faster, but you'll
have to break your scene up into four segments. I have one processor, and I
use  a "segments of two" approach when dual-core rendering - one virtual
CPU gets the "top" the other the "bottom". If one finishes before the
other, the remaining part is again divided by two, etc. You'll be able to
do this by fours if you get a quad based board.
 
> 2.  How much RAM do we actually need (I've never seen POVRay run past
> 790Mb on our current Pentium M based machine, which has 2Gb).

2Gb sounds more than suffiecient. I have 1Gb and have successfully rendered
scenes with thousands and thousands of objects without touching swap. I do
guess though that if you run four copies of povray (if you get a quad
board) you might need four times the RAM, since a scene will be in memory
four times (once for each pov process on each processor).
 
> 3.  How much difference does the graphics card make?  What type of card
> should we look at using.

The graphics card will have zero impact on pov. Any run of the mill card
which can display 32 bit color at, say, 1024x768 should be more than
enough. Graphics accelerator cards are useless as regards povray, and will
have zero impact on the rendering time or processing load to calculate a
scene.
 
> 4.  Any other advice that you think useful.

Get the absolute fastest of everything you can. RAM, CPU and bus. It is
amazing how Pov can turn even the "fastest" PC into a sloth with the
processing demands it can make when you really start flooring quality and
radiosity / photons etc...

-- 
Stefan Viljoen
Software Support Technician / Programmer
Polar Design Solutions

Post a reply to this message

Wasn't it Thomas who wrote:
>
>4.  Any other advice that you think useful.
>

Be aware that POV-Ray uses mainly floating point arithmetic, but the
vast majority of published processor speed information relates to the
speed of integer arithmetic. 

-- 
Mike Williams
Gentleman of Leisure

Post a reply to this message

Stefan Viljoen <spamnot@ <removethis>polard.com> wrote:
> IMO get the fastest dual-core processor you can get. Beter yet, get a quad 
> motherboard (I think HP makes some nice ones) that will take four
> processors. You can then theoretically render four times faster, but you'll
> have to break your scene up into four segments. I have one processor, and I
> use  a "segments of two" approach when dual-core rendering - one virtual
> CPU gets the "top" the other the "bottom". If one finishes before the
> other, the remaining part is again divided by two, etc. You'll be able to
> do this by fours if you get a quad based board.

  Please notice that if you do that, ie. render the scene in "four segments",
the amount of memory required will be four times as large. Often not very
feasible. It's also troublesome.

  You should know better than to suggest that, given that the new
POV-Ray 3.7 can use multiple processors with basically no increased
memory requirements.

-- 
                                                          - Warp

Post a reply to this message

Warp spake:

> Stefan Viljoen <spamnot@ <removethis>polard.com> wrote:
>> IMO get the fastest dual-core processor you can get. Beter yet, get a
>> quad motherboard (I think HP makes some nice ones) that will take four
>> processors. You can then theoretically render four times faster, but
>> you'll have to break your scene up into four segments. I have one
>> processor, and I
>> use  a "segments of two" approach when dual-core rendering - one virtual
>> CPU gets the "top" the other the "bottom". If one finishes before the
>> other, the remaining part is again divided by two, etc. You'll be able to
>> do this by fours if you get a quad based board.
> 
>   Please notice that if you do that, ie. render the scene in "four
>   segments",
> the amount of memory required will be four times as large. Often not very
> feasible. It's also troublesome.

I think I did mention that farther down my reply post. That might be a valid
reason to get as much memory as you can, as the poster seemed set to go
for.
 
>   You should know better than to suggest that, given that the new
> POV-Ray 3.7 can use multiple processors with basically no increased
> memory requirements.

Hmm - I did not know that and thus I stand corrected. 

Regards,
-- 
Stefan Viljoen
Software Support Technician / Programmer
Polar Design Solutions

Post a reply to this message

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Mike Williams wrote:
> Wasn't it Thomas who wrote:
> 
>>4.  Any other advice that you think useful.
>>
> Be aware that POV-Ray uses mainly floating point arithmetic, but the
> vast majority of published processor speed information relates to the
> speed of integer arithmetic. 
> 
	Here's a pretty complete page of floating point benchmarks:
http://www.spec.org/cgi-bin/osgresults?conf=cfp2000;op=form

		Jerome
- --
******************************
*      Jerome M. Berger      *
*  mailto:jeb### [at] freefr   *
*  http://jeberger.free.fr/  *
******************************
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.2 (GNU/Linux)

iD8DBQFD/Kyxd0kWM4JG3k8RAk6+AKCoSkp1mocfgj87eCdVrKi8wIPtxACgh6+v
EdzHmrNbVD+OETSRvpPPCTA=
=iaYv
-----END PGP SIGNATURE-----

Post a reply to this message

Stefan Viljoen <spamnot@<removethis>polard.com> wrote:

> I have one processor, and I
> use  a "segments of two" approach when dual-core rendering - one virtual
> CPU gets the "top" the other the "bottom". If one finishes before the
> other, the remaining part is again divided by two, etc.
>
 Can you explain that in more detail?  Sounds fascinating (and completely
unknown to me.) Thanks!

Ken

Post a reply to this message

"Thomas" <t_p### [at] hotmailcom> wrote:

> 4.  Any other advice that you think useful.
>
As mentioned, a fast bus speed will help. I recently bought an emachines
model T6412 (64-bit, single processor) machine, with a 1600MHZ front-side
bus, which is faster than many other (?) machines out there, that I've
seen.  Very good bang for the buck.

Ken

Post a reply to this message

Kenneth <kdw### [at] earthlinknet> wrote:
>  Can you explain that in more detail?  Sounds fascinating (and completely
> unknown to me.) Thanks!

  Just use POV-Ray 3.7 (when it comes out; if you are using Windows, you
can try the beta).

-- 
                                                          - Warp

Post a reply to this message

Warp <war### [at] tagpovrayorg> wrote:

>   Just use POV-Ray 3.7 (when it comes out; if you are using Windows, you
> can try the beta).
>
 I'm still trying to understand v3.6.1 ALPHA!  ;-)

Ken

Post a reply to this message