Neither EC2 nor App Engine are really suited to HPC, they're quite valid
options for Highly Escalable Web Apps, but they don't really work for highly
intensive apps (I did a pilot for a video streaming company to asses the
feasibility of using them for the encoding engines...better don't ask about
the real costs)
On Wed, Jun 24, 2009 at 3:04 PM, Robert Grundulis <
robertmartinbrown at gmail.com> wrote:
> Hi Karl,
>> Thanks for the advice. I looked in to Google App Engine and Amazon EC2.
> Amazon is limited by being Python only. Nothing wrong with Python, it's
> just
> that there would be a fair bit of effort invovled inporting all the C++ and
> Fortran code over. EC2 looks good, but for high performance computing
> applications it seems expensive. The quote I got approximated a cost of
> around $361 per month for using their highest powered virtual server
> option.
> For that kind of money I thnk clustering a load of old, but free, servers
> would be better. There are also confidentiality issues that would prevent
> the use of an external service provider who would not be willing to sign a
> custom confidentiality guarantee.
>> I've been looking in to OSCAR (
>http://svn.oscar.openclustergroup.org/trac/oscar) which seems well suited
> to
> what I am after. Has anyone ever used it?
>> Cheers,
> Robert
>>> 2009/6/23 Karl O'Dwyer <me at karlodwyer.net>
>> > Hi Robert,
> >
> > Clustering isn't all its cracked up to be...
> >
> > It only really works if your problem can be broken up well.
> > Some problems might not suit a cluster well.
> >
> > There is some alternatives to setting up your own cluster.
> >
> > If this is part of a research project you might be able to get to
> > run on the Irish Center for High End Computing's supercomputing clusters.
> >
> > A Cloud computing Platform like Google App Engine or Azure could be
> useful.
> >
> > Or if you have a GeForce 8, 9, 100, 200-series GPU, CUDA could be your
> > solution.
> >
> > Well the best of luck what ever way you go.
> > All the Best,
> >
> > - Karl
> >
> > > Hello all,
> > >
> > > Can anyone offer me suggestions on good books or resources that would
> > help
> > > get me up to speed with Beowulf clustering?
> > >
> > > I've written an application that does calculations on fluid dynamics,
> > > propellers and hull forms (boaty stuff) and the intention is to move it
> > on
> > > to a cluster to speed it up. At the moment one calculation takes about
> 3
> > > days on a dual core Xeon, so there are obvious benefits to moving it on
> > to
> > > a
> > > cluster.
> > >
> > > I have free access to dozens of old university PCs and servers (all P4
> > and
> > > adbove) and the plan is to cluster them.
> > >
> > > The thing is I've never worked with clusters before and I don't have a
> > clue
> > > where to start. Can anyone help point me in the right direction?
> > >
> > > --
> > > Cheers,
> > > Robert Grundulis
> > > --
> >
> > --
> > Karl O'Dwyer
> >
>>>> --
> Cheers,
> Robert Grundulis
>http://www.chaptalk.com> --
> Irish Linux Users' Group mailing list
> About this list : http://mail.linux.ie/mailman/listinfo/ilug> Who we are : http://www.linux.ie/> Where we are : http://www.linux.ie/map/>
--
Vicente Werner y Sánchez
Maintained by the ILUG website team. The aim of Linux.ie is to
support and help commercial and private users of Linux in Ireland. You can
display ILUG news in your own webpages, read backend
information to find out how. Networking services kindly provided by HEAnet, server kindly donated by
Dell. Linux is a trademark of Linus Torvalds,
used with permission. No penguins were harmed in the production or maintenance
of this highly praised website. Looking for the
Indian Linux Users' Group? Try here. If you've read all this and aren't a lawyer: you should be!