SC10 - supercomputing conference

Just got back from Supercomputing 2010 (SC10) in New Orleans.

The annual conference provides a good perspective of the progress of "super computers", across universities, researchers, and industry. In recent years, the implementation of supercomputing has been slowly evolving towards a mix of compute core technologies, emerging more strongly along the lines of heterogeneous computing.

There was of course too much to see and participate in each day. The two areas where I spent most of my time was in catching up on the progress of GPUs (and the variants) and noticing the surprising emerging focus on HPC clouds. I'll post more on those two areas in the coming days.

There was quite a bit of discussion around Exascale computing. Naturally, with so many researchers at the conference, there were numerous perspectives on what that even meant. Exaflops? 1000 times faster? bigger? number of cores/GPUs? Power consumption, etc etc. If nothing else, more good fodder for research and areas of discussions. Which is one of the reasons everyone gets together. So all good. Clearly though, there's a lot of very serious challenges coming down the road for the vision of super-computers 8-10 years out.

As usual, the latest Top 500 list was announced at the conference. The announcement was interesting given a pervasive feeling across the conference that measuring supercomputers with a small and relatively trivial program like Linpack was clearly outdated. It was funny how often researchers and speakers would voice annoyance or frustration at the continuing featured aspect of Linpack. I suspect this is not a new sentiment, but I was struck by the number of specific references at this conference.

A while back, HPC Challenge (as a suite of benchmarks) was created to provide a more comprehensive measurement of the many aspects of a super computer. It also provides a number of awards on the varying aspects of super-computing, essentially awarding gold, silver, and bronze awards in each category. I may not have been paying well enough, but I didn't get the impression that HPC Challenge was a focus across the conference.

At the conference a new "Top 500" benchmark suite was launched. The new suite, graph500, was introduced and the first listed results at graph500.org. This new benchmark suite is intended to focus on areas of data intensive computing, another critical aspect of supercomputing. Indeed, it's often the amount of data being processed, consumed, and in many cases transformed into visualization which represents one of several awe-inspiring sides of supercomputing. In fact, this is the killer side of HPC cloud computing - getting data to and from the compute resources in the cloud.

Anyway, came back with over 50 papers from the Proceedings and over 30 Tutorials. Plenty to dig through, discuss, and get more insights. Will work to post more thoughts as interesting pieces are uncovered.

So really, does the Advance Toolchain help performance?

We're often asked whether - and by how much - the Advance Toolchain actually helps performance for applications running on the various distros (RHEL and SLES) on POWER systems.

The Advance Toolchain of course is a set of updated rpms which provide an updated gcc compiler, processor-tuned libraries, and a number of more current tools over what is standard in the distro itself. Check out one of the README files available for more details.

The ability to easily flip to a newer "toolchain" for POWER7 systems has been particularly helpful for many applications. An article was recently completed which demonstrates the relative performance gains when leveraging the latest Advance Toolchain (version 3.0-1) from the University of Illinois over the gcc which comes packaged with each distro release.

The article "Advance Toolchain performance improvements" provides the details and graphs of component-by-component breakdowns of engineering runs of SPECcpu2006® for integer and floating point workloads. The relative performance gains and losses are graphed which provides a quick view of the possibilities of using these libraries and newer gcc.

One of the key highlights is that the graphs very nicely demonstrate the repeating performance perspective of "Well, it depends...". Not all workloads will benefit from the libraries, but many do!

Indeed, a key advantage of the Advance Toolchain is the continuing focus, updates, optimizations, and fixes which provides users with the latest technologies in a form which can be serviced and supported by IBM.


SPEC® and the benchmark names SPECint® and SPECfp® are registered trademarks of the Standard Performance Evaluation Corporation.