ISC'13 Preview-Supercomputing in Leipzig
ISC'13(link is external) - the summer's big international conference for the world of supercomputing - is only a few weeks away. As usual, I will be attending, along with several of my NAG(link is external) colleagues.
This year, ISC will be in Leipzig - a new location. That means as well as the #HPC(link is external) [do I need hashtags in a blog post???] fun of the conference itself, we will all have to learn the foibles of a new host city. Which bar will replace the cornerstone that was the Radisson Blu in Hamburg? How quickly can we learn the layout of the conference center itself?
More to the point, what will be the big #HPC(link is external) [there I go again] news stories and themes to watch out for in Leipzig? I have already beeninterviewed by InsideHPC(link is external) as an early ISC'13 preview, and have written a blog for the official ISC blog (comparing #HPC and #F1)(link is external) - but here are some further thoughts.
Take the MIC
Well, as far as big #HPC(link is external) [getting silly now] news goes, I'm glad I didn't try to write this blog last week! I think the stand out news story of ISC'13 is pretty obvious (barring another dramatic reveal) - the excellent expose(link is external) by HPC Wire(link is external) of China's MIC (sorry Xeon Phi) based 50+ petaflops supercomputer. Yes, at the ISC'13 issue of the Top500 list(link is external), China's Tianhe-2 supercomputer will smash aside the USA's Titan supercomputer(link is external)at ORNL to take the crown as the world's fastest supercomputer - by a huge margin.
Indeed, in a painful turn of events, Titan may be dumped out of the Top500 leadership position before it has even passed it's acceptance tests(link is external)! I'll reserve further comment on the Tianhe-2 story for a upcoming blog post at my own HPC blog(link is external) (hpcnotes.com(link is external)).
I believe Tianhe-2 will not be the only Xeon Phi news story at ISC'13 - there will probably be a few other Xeon Phi based supercomputers to be announced or updated, along with several product announcements etc (including some from NAG(link is external)).
In my preview for ISC last year(link is external), I suggested ISC'12 would be a battle between MIC and GPU and other potential processor options (e.g. ARM, DSPs, AMD Fusion, ...). I think that will be true again at ISC'13 - in terms of a battle for press/attendee mind-share, but with the difference that Xeon Phi has probably taken a solid lead for the first time.
The problem for GPUs (in terms of excitement) is that they are not new anymore - people have tried heard about them, have tried them, have learnt CUDA, have found performance successes or not, and there has been plenty of dissemination. ARM still has the benefit of being the cool new player in this space - and while still young in terms of HPC product/market maturity - has shown great promise through various demonstration projects. Likewise, the AMD Fusion technology looks interesting.
NAG, of course, is please to be working with all of the above - in terms of providing training courses, programming services, HPC consulting, our Library products, etc.
There are bound to be plenty of #BigData(link is external) [hashtag!] themes emerging at ISC'13 - it is still in buzzword status(link is external) after all! There may even be a few genuine case studies and success stories about the crossover between #HPC(link is external) and #BigData(link is external). But I venture to suggest most mentions of#BigData(link is external) at ISC'13 will be gratuitous rather than core to the topic at hand. Call me a cynic?
Use of HPC by industry
I have predicted(link is external) that the HPC community will see a strong focus on industrial HPC this year, especially engagement between centers of HPC expertise and industry users. [Note that I say “centers of HPC expertise” – it is critical that this does not mean only supercomputer centers – there is a lot of real expertise in HPC outside of the supercomputer centers – e.g., within the main HPC vendors, or specialist HPC expertise providers such as NAG, or in some cases within the industrial end users themselves.] I would expect there to be plenty of conversation around this topic at ISC'13.
Surely we can't forget exascale?
Really, a #supercomputing(link is external) conference without abundant #exascale(link is external) discussion? The key question for ISC'13 is not whether #exascale(link is external) will be discussed - it definitely will be - but what will dominate the #exascale(link is external)
discussion? The technical details and challenges of achieving exaflops
performance (either peak or real applications)? Or the politics and
funding issues? For example, the perceived risk to exascale funding in
the USA, or the ambitions of China, Europe, and others towards #exascale(link is external)?
The HPC ecosystem
I am a keen
advocate that HPC is seen as a complete ecosystem of hardware, software,
people, processes, etc. and not merely the hardware that is often the
default focus of HPC. A supercomputer on its own is just a device for
converting money into waste heat (via some floating point units and an
oversized electricity bill). I'm hoping all parts of this ecosystem get
appropriate attention in the conversations at ISC'13. (Read more on my
views on this theme in the InsideHPC interview(link is external).)
What will you be looking out for at ISC'13? Leave a comment or get in touch for a direct conversation with me or NAG.