HPCwire: Is Underutilizing Processors Such an Awful Idea?

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Translation Disclaimer

Subscribe | Sign In

Visit additional Tabor Communication Publications

Leading HPC
Solution Providers

October 28, 2010

Is Underutilizing Processors Such an Awful Idea?

Michael Feldman

As we move from multicore to manycore processors, memory bandwidth is going to become an increasingly annoying problem. For some HPC applications it already is. As pointed at in a recent HPCwire blog, a Sandia study found that certain classes of data-intensive applications actually run slower once you try to spread the computations beyond eight cores. The problem turned out to be insufficient memory bandwidth and the contention between processor for memory access.

That is certainly not the case for all applications. But beyond that, it's not always useful to focus on memory bandwidth limitations when considering how to get the most out of your processors. A recent blog post penned by TACC'ers Dan Stanzione and Tommy Minyard suggest we look at the problem somewhat differently. To being with, the authors think the whole notion of trying just to maximize core usage is somewhat misplaced. They write:

Leaving a core idle is considered "wasteful". This is not surprising, but upon careful reflection doesn't make that much sense... No one considers it a "waste" if while running a job on every core of your machine, half your memory is empty, or half your network is unused, or you are only using half the available IOPS or bandwidth to your disk drive.

Stanzione and Minyard go on to say that the real metric you should be concerned about is how much work your cluster is getting done in a given time period. So for certain workload mixes, it might make sense to let cores go idle in order to ensure the remaining cores are left with enough memory bandwidth for fast execution. Or you could mix compute-intensive applications with data-intensive ones so that both cores and memory usage can be more utilized -- assuming you have the right mix of applications to choose from.

Of course, not every HPC installation has the luxury of choosing an optimal mix of applications. What if you're stuck with running a memory-hungry application, like the Weather Research and Forecasting (WRF) code, all of the time?

The TACC authors actually came up with some interesting data points using WRF on Xeon platforms. They found that going beyond 8 cores per node yielded diminishing returns in speedup (not quite so bad as the Sandia study, which demonstrated lost performance beyond 8 cores). Using Intel Westmere CPUs they were only able to achieve a 12 percent performance improvement going from 8 to 10 cores, and just 2.7 percent when going from 10 to 12 cores.

So what do you do in this scenario? Stanzione and Minyard write:

Well, maybe it tells the WRF developers that you can do a whole lot more computation between memory accesses essentially for free on the new processors. Maybe it says you can run some not-so-memory-intensive jobs alongside your WRF jobs on those extra cores essentially for free. But perhaps the most important thing it says is that to get maximum throughput nowadays, you shouldn't assume that the best and most efficient configuration is to use every core in every socket for your job. For some kinds of programs you will, for some kinds of programs you won't... but isn't it nice to have all that extra compute power lying around for the times that you need it?

Well yes, that is nice, especially if you can afford to deploy such systems. On the other hand, the AMD folks might point out that their Opteron solutions achieve a better balance between CPU FLOPS and memory bandwidth than the Xeons. The NVIDIA folks, one assumes, would have an entirely different suggestion.

Full story at Dell Technology Center

Share Options

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

Become a Registered User Today!

Registered Users Log in join the Discussion

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Subscribe to All Content

All

May 23, 2012

May 22, 2012

May 21, 2012

May 18, 2012

May 17, 2012

May 16, 2012

May 15, 2012

May 14, 2012

May 11, 2012

Feature Articles

NVIDIA Works On CPU Co-Dependency Issues with Kepler GPU

NVIDIA is telling everyone that the GK110, its new Kepler GPU aimed at supercomputing, is all about improving performance per watt. But the other driving theme behind the new architecture is reducing the GPU's reliance on its CPU host. How well it accomplishes both these goals areas could determine the success of the new chip in high performance computing.
Read more...

OpenACC Starts to Gather Developer Mindshare

PGI, Cray, and CAPS enterprise are moving quickly to get their new OpenACC-supported compilers into the hands of GPGPU developers. At NVIDIA's GPU Technology Conference this week, there was plenty of discussion around the new HPC accelerator framework, and all three OpenACC compiler makers, as well as NVIDIA, were talking up the technology.
Read more...

NVIDIA Launches Kepler Into HPC

NVIDIA has introduced its first Kepler-generation GPU product for high performance computing, and revealed some of the inner working of the new architecture. The announcement took place at the kickoff of the company's GPU Technology Conference taking place this week in San Jose, California.
Read more...