Thursday, 24 May 2012

ISC'12 Hamburg Preview

ISC'12 - the summer's big international conference for the world of supercomputing - is next month in Hamburg.

I will be attending, along with several of my NAG colleagues. Will you be attending? What will you be looking to learn? I will be listening out for these five key topics.

GPU vs MIC vs Other

As at ISC'11 last year (and SC11), I think there will be a strong fight for attention in the key area of manycore/GPU devices - and a matching search for evidence of real progress. So far the loudest voice has been NVidia and CUDA, especially following NVidia's successful GTC event recently. However, interest in Intel's MIC (Knights Corner) is strong and growing - MIC has often been a big discussion topic in workshops, conferences and meetings over the last year. As the MIC product launch gets closer, people will be making obvious comparisons with NVidia's Kepler announced at the GTC.

What about others - will anyone else develop a strong voice in this manycore world? AMD Fusion? ARM? DSP-based products? Will we talk with the same energy about the software issues of manycore, or just the hardware choices?

What is happening with Exascale?

The quest to attain exascale computing rumbles on. I'd expect exascale to take a big share of the debate and agenda at ISC'12. What is happening with the exascale programs around the world? How are the budgets in the weak global economy affecting the exascale ambition? How are the various national pride (I mean national competitiveness) efforts towards exascale progressing? Will the software challenges get the level of investment needed? What new technologies will emerge to be studied as candidates to solve part of the problems getting to exascale?

Is exascale so old hat - do we need to move to discussion of zettaFLOPS to be trendy now? Will zettaFLOPS be impossible (Sterling) or inevitable (Barr)? Maybe we should spare some discussion for making multi-petaFLOPS work properly first?



Top 500, Top 10, Tens of PetaFLOPS

Will any of the next batch of supercomputers vying for title of most powerful in the world leap from the shadows at ISC'12? Will the Top 500 have a new leader? What about the 10/20/30 petaFLOPS systems in build? Has K grown since SC11? Is Sequoia fully built yet? Is Jaguar still Jaguar or has it morphed into Titan? Will it be called Jagan or Tituar if it has only partly morphed? Mira? Blue Waters? Etc.?

Or will there be other big new entries in the Top 10? I believe there will be at least one new multi-petaFLOPS entry in the Top 10. And I'm sure there will be several new entries in the Top50.

Finding the advantage in software

We will hear about applications of HPC to a wide range of problems - academic research, industrial research and engineering, etc. But will we learn how software has enabled those successes? Or will we focus only on the big machines that the software ran on? What about the computational software engineering skills needed? Or the pre/post-processing and workflow challenges? Without attention to these broader aspects of HPC, we are left only with a big box of computers and an electricity bill - much less powerful than a balanced portfolio of supercomputers + software + people + ...

Big Data and HPC

Some of you will have heard me say over the last few months that "cloud" is a buzzword of the past now, as was "green computing" before it. Marketing departments need a new catchphrase to use. I believe "Big Data" is that new buzzword. Just as broad swathes of the HPC product space were labelled "cloud solutions" last year, so will they be mandated to be "big data" solutions this year. Am I joking? Partly. Am I cynical? Of course. Am I right? Probably.

There is a serious side to this too - big data is potentially a huge user of HPC technologies - and HPC in turn generates big data. So the cross-over is real. We just need to seek out the nuggets of value and genuine new solutions among the buzzword deluge.


What will you be looking out for at ISC'12? Leave a comment or get in touch for a direct conversation with me or NAG.

2 comments:

  1. This comment has been removed by a blog administrator.

    ReplyDelete
  2. Wolfgang Gentzsch27 May 2012 at 08:59

    Andrew, thanks, these are my key topics as well. I have a sixth one: "HPC going mainstream", a buzz for quite some years, but still not really here. We are seeing the 'few' big users all the time, but not the many small ones. So in Hamburg I will look especially for industrial HPC use cases, especially from the SMEs. The more I find, the more I get confident that it will come...
    "Big Data and HPC" is similar, for many years we are seeing the few big ones (e.g. in business analytics) but not really the many small ones.
    BTW, if you want to see at least a good handful of each, stop by ISC's child (or spin-off), the ISC Cloud Conference in September in Mannheim, http://www.isc-events.com/cloud12/, with HPC and Big Data in the Cloud. We have tried hard to invite those speakers with real experience presenting their HPC Cloud use cases.

    ReplyDelete

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