 |
|
|
|
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Hi,
I d like to know if POV runs on multi-processor machines or if it can
run on a cluster of machines susing, for instance,
pvm or mpi.
Thanks,
Fabrice.
--
========================================================================
Fabrice MARCHAL Tel: +41-21-693-24-88 e-mail: mar### [at] itep dgcepflch
EPFL - ITEP - TSO Fax: +41-21-693-50-60 Office: GC C2 407
CH-1015 Lausanne Web (official): http://itepsg1.epfl.ch/metro
Web (unofficial): http://itepsg1.epfl.ch/marchal/jwz
========================================================================
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
On Thu, 27 Aug 1998 19:55:19 +0100, Fabrice Marchal
<fab### [at] epflch> wrote:
>Hi,
>I d like to know if POV runs on multi-processor machines or if it can
>run on a cluster of machines susing, for instance,
>pvm or mpi.
Yes. For version 3.1 of PVM-POV (corresponding to version 3.0x of POV-Ray)
go to http://www-mddsp.enel.ucalgary.ca/People/adilger/povray/pvmpov.html
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Has anyone tried POV under Beowulf (Extreme Linux)?
Jon
Ron Parker wrote in message <35e5a85a.0@news.povray.org>...
>On Thu, 27 Aug 1998 19:55:19 +0100, Fabrice Marchal
> <fab### [at] epflch> wrote:
>>Hi,
>>I d like to know if POV runs on multi-processor machines or if it can
>>run on a cluster of machines susing, for instance,
>>pvm or mpi.
>
>Yes. For version 3.1 of PVM-POV (corresponding to version 3.0x of POV-Ray)
>go to http://www-mddsp.enel.ucalgary.ca/People/adilger/povray/pvmpov.html
>
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Ron Parker wrote:
> On Thu, 27 Aug 1998 19:55:19 +0100, Fabrice Marchal
> <fab### [at] epflch> wrote:
> >Hi,
> >I d like to know if POV runs on multi-processor machines or if it can
> >run on a cluster of machines susing, for instance,
> >pvm or mpi.
>
> Yes. For version 3.1 of PVM-POV (corresponding to version 3.0x of POV-Ray)
> go to http://www-mddsp.enel.ucalgary.ca/People/adilger/povray/pvmpov.html
Many thanks, but what about mpi ? At work, I use a SGI Origin 2000 with 8
processors, linked together with mpi.
And by the way, how to use any parallel version on a dual Pentium II PC (under
WinNT, of course). Because my motherboard is dual Pentium II capable, although
I still only have one installed...
Thanks in advance
GP
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Guillaume Pottier wrote:
>
> Ron Parker wrote:
>
> > On Thu, 27 Aug 1998 19:55:19 +0100, Fabrice Marchal
> > <fab### [at] epflch> wrote:
> > >Hi,
> > >I d like to know if POV runs on multi-processor machines or if it
> can
> > >run on a cluster of machines susing, for instance,
> > >pvm or mpi.
> >
> > Yes. For version 3.1 of PVM-POV (corresponding to version 3.0x of
> POV-Ray)
> > go to
> http://www-mddsp.enel.ucalgary.ca/People/adilger/povray/pvmpov.html
>
> Many thanks, but what about mpi ? At work, I use a SGI Origin 2000
> with 8
> processors, linked together with mpi.
> And by the way, how to use any parallel version on a dual Pentium II
> PC (under
> WinNT, of course). Because my motherboard is dual Pentium II capable,
> although
> I still only have one installed...
>
> Thanks in advance
>
> GP
I think that PVM internally can (optionally?) use MPI. The only
requirement for PVM is that all of the processors can use the same file
system (NFS works just fine). With the current release of PVM you can
only use unix operating systems (linux works). The upcoming release
will allow you to use PCs too. The benefit of PVM is that it is
hardware independent. You compile the PVM library and the program (in
this case PVMPov) for each platform. Thus you can mix SGIs with Sparc
Stations. If you have an 8 processor computer you can spawn 8 pvm
processes -- all which end up on the same physical computer but
different chips.
If you get a second Pentium II chip for your motherboard I think that
the suggested method to run in parallel is to actually run two copies of
the program, one on each chip. You could set up the first chip to
render the first half of the image and the second chip for the second
half. PvmPov sort of works this way. Each process works independently
of the others except that they communicate their results with the master
process which parcels out pieces of the image.
-Eric Brown
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Eric Brown wrote:
>
> Guillaume Pottier wrote:
> >
> > Ron Parker wrote:
> >
<...>
>
> I think that PVM internally can (optionally?) use MPI. The only
I don't think so, as spawning processes, as down in PVM and used in
pvmpov, is introduced in MPI 2.0 and to my knowledge very rarely
implemented, at least not in mpich. I think lam has it, but I don't like
the configuration possibilities. :-(
So I don't think so.
On the other hand I have a port of pvmpov to mpi on the very end of my
priority list :-)
Mostly because pvm is not that stable, at least on our SUNMP. I talked
to Harald Deischinger ( he did the port to 3.0 ) and he knows of some
strange behaviours of pvmpov (sometimes some blocks don't get rendered)
and he knows of no reason :-). So perhaps a port would be nice. But not
at all urgent in my world, so hang on hang on.
Axel
> requirement for PVM is that all of the processors can use the same file
> system (NFS works just fine). With the current release of PVM you can
> only use unix operating systems (linux works). The upcoming release
> will allow you to use PCs too. The benefit of PVM is that it is
> hardware independent. You compile the PVM library and the program (in
> this case PVMPov) for each platform. Thus you can mix SGIs with Sparc
> Stations. If you have an 8 processor computer you can spawn 8 pvm
> processes -- all which end up on the same physical computer but
> different chips.
>
<...>
> -Eric Brown
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
I have tried it using Beowulf software redily available on the net, not
necessarily that which comes with the "Extreme Linux" distribution.
It works spectacularly well!!!
See my web site at http://www.crak.com for details.
By the way, pvmmpov runs so fast on our overclocked four Celeron cluster
(f at 450 MHZ) that we have time available at reasonable rates for those
of you who have time consuming renders.
We can render the skyvase.pov benchmark in 29 seconds using pvmpov.
JK
"Jon S. Berndt" wrote:
>
> Has anyone tried POV under Beowulf (Extreme Linux)?
>
> Jon
>
> Ron Parker wrote in message <35e5a85a.0@news.povray.org>...
> >On Thu, 27 Aug 1998 19:55:19 +0100, Fabrice Marchal
> > <fab### [at] epflch> wrote:
> >>Hi,
> >>I d like to know if POV runs on multi-processor machines or if it can
> >>run on a cluster of machines susing, for instance,
> >>pvm or mpi.
> >
> >Yes. For version 3.1 of PVM-POV (corresponding to version 3.0x of POV-Ray)
> >go to http://www-mddsp.enel.ucalgary.ca/People/adilger/povray/pvmpov.html
> >
--
CRAK Software (Password Recovery Software)
Http://www.crak.com
joh### [at] crakcom
602 863 9274 or 1 800 505 2725 In the USA
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
That error has been fixed on the lates distribution.
JK
Axel Hecht wrote:
>
> Eric Brown wrote:
> >
> > Guillaume Pottier wrote:
> > >
> > > Ron Parker wrote:
> > >
> <...>
>
> >
> > I think that PVM internally can (optionally?) use MPI. The only
>
> I don't think so, as spawning processes, as down in PVM and used in
> pvmpov, is introduced in MPI 2.0 and to my knowledge very rarely
> implemented, at least not in mpich. I think lam has it, but I don't like
> the configuration possibilities. :-(
> So I don't think so.
>
> On the other hand I have a port of pvmpov to mpi on the very end of my
> priority list :-)
> Mostly because pvm is not that stable, at least on our SUNMP. I talked
> to Harald Deischinger ( he did the port to 3.0 ) and he knows of some
> strange behaviours of pvmpov (sometimes some blocks don't get rendered)
> and he knows of no reason :-). So perhaps a port would be nice. But not
> at all urgent in my world, so hang on hang on.
>
> Axel
>
> > requirement for PVM is that all of the processors can use the same file
> > system (NFS works just fine). With the current release of PVM you can
> > only use unix operating systems (linux works). The upcoming release
> > will allow you to use PCs too. The benefit of PVM is that it is
> > hardware independent. You compile the PVM library and the program (in
> > this case PVMPov) for each platform. Thus you can mix SGIs with Sparc
> > Stations. If you have an 8 processor computer you can spawn 8 pvm
> > processes -- all which end up on the same physical computer but
> > different chips.
> >
> <...>
>
> > -Eric Brown
--
CRAK Software (Password Recovery Software)
Http://www.crak.com
joh### [at] crakcom
602 863 9274 or 1 800 505 2725 In the USA
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
|
|
