Thursday, 30 May 2013

ISC'13 Preview - Supercomputing in Leipzig

ISC'13 - 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 colleagues.

This year, ISC will be in Leipzig - a new location. That means as well as the #HPC [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 [there I go again] news stories and themes to watch out for in Leipzig? I have already been interviewed by InsideHPC as an early ISC'13 preview, and have written a blog for the official ISC blog (comparing #HPC and #F1) - but here are some further thoughts.

Take the MIC

Well, as far as big #HPC [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 by HPC Wire of China's MIC (sorry Xeon Phi) based 50+ petaflops supercomputer. Yes, at the ISC'13 issue of the Top500 list, China's Tianhe-2 supercomputer will smash aside the USA's Titan supercomputer 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! I'll reserve further comment on the Tianhe-2 story for a upcoming blog post at my own HPC blog (hpcnotes.com).

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).


Remember GPUs?

In my preview for ISC last year, 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.

Big Data

There are bound to be plenty of #BigData [hashtag!] themes emerging at ISC'13 - it is still in buzzword status after all! There may even be a few genuine case studies and success stories about the crossover between #HPC and #BigData. But I venture to suggest most mentions of #BigData 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 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 conference without abundant #exascale discussion? The key question for ISC'13 is not whether #exascale will be discussed - it definitely will be - but what will dominate the #exascale 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?

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.)


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.

2 comments:

  1. Any guess if AMD fusion architecture will be available as server processors or HPC oriented coz the current marketing trend from AMD targets tablets and desktop gaming.

    ReplyDelete
    Replies
    1. Yes, I think Fusion is intended for HPC use too. In fact, I think a web search should turn up a few examples.

      Delete

NAG moderates all replies and reserves the right to not publish posts that are deemed inappropriate.