[Beowulf] Roadrunner shutdown

[Nicole Hemsoth]

Hey guys--

Been following this thread and finally, after a week of pestering, was able
to get someone to talk about the Roadrunner's retirement. Tried to get the
answers to some of the thoughts I found here in addition to poking at them
to find out what they're going to fill that 6,000 square foot void with.
Anyway.
http://www.hpcwire.com/hpcwire/2013-04-04/revelations_on_roadrunner_s_retirement.html?featured=top--
hope this is some good info.

Nic

On Thu, Apr 4, 2013 at 10:18 PM, Vincent Diepeveen <diep at xs4all.nl> wrote:

> Note that as for nuke explosions i have no idea how those look like -
> maybe someone more knowledgeable wants to comment on that.
>
> As a total layman there i would suspect that it's important where the
> protons/neutrons/whatever-tons/supertiny-tons are located. I'd be
> modelling that naively using
> matrixcalculations.
>
> So that would mean the only low level library you need is a
> matrixcalculation and some relative simple functions - with the
> matrixcalculations
>   eating 99% of all system time on that massive supercomputer out of
> all calculations done on it.
>
> In such case one would need surprisingly little very well optimized
> code to make optimal usage out of such massive supercomputer.
>
> Any other 'secret' batchjob i'd be running on a different
> supercomputer. If there is no need to run a massive vector oriented
> workload type matrixcalculation -
> one just shouldn't run on such type of supercomputer i feel. NASA
> still had that 10240 socket supercomputer back then if i remember well,
> to give one example...
>
>
>
> On Apr 4, 2013, at 5:39 PM, Max R. Dechantsreiter wrote:
>
> > Vincent,
> >
> >> It doesn't matter whether you code for blue gene, cuda or phi - from
> >> a software viewpoint it's all vector type coding you've got to do.
> >> the price of 1 coder is total peanuts compared to
> >> the price of those supercomputers. So specialistic written software
> >> is what you need anyway.
> >
> > Simply porting an application shouldn't take much effort,
> > as long as vendor-specific libraries aren't involved.
> > However, special and sometimes intensive efforts are often
> > required to achieve good performance (high utilization).
> >
> > The unfortunate fact is that funds are more easily spent
> > on hardware than on the human resources needed to utilize
> > them effectively.
> >
> > Max
> > ---
> > http://www.linkedin.in/in/benchmarking
>
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
>



-- 
Nicole Hemsoth
Managing Editor, HPCwire
http://www.hpcwire.com <http://www.datanami.com>
(919) 899-9614
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.beowulf.org/pipermail/beowulf/attachments/20130404/321237c5/attachment.html>