Cluster-grappling kids clash: Battle of the Big Iron in the Big Easy

Bring your HPC weapons to the Mississippi

Not actually HPC Ninjas

More than perhaps any other school, Purdue has used its participation in the cluster competitions to build up both its HPC course offerings and student interest in becoming HPC ninjas (note: computer science graduates from Purdue don’t have the term “HPC Ninja” on their sheepskins. They don’t receive actual sheepskins either, for that matter).

I recorded an interview with Dr. Gerry McCartney, Purdue CIO, where we discussed how Purdue has leveraged the cluster competitions to enhance its HPC classroom offerings and enrich the student experience. It’ll be posted in my HPC column soon ...

Team Singapore (National University of Singapore) is a first-time competitor in the student cluster wars. While we haven’t seen this team before, and thus don’t know much about it, it did submit one of the finest architectural proposals I’ve seen.

It’s clear that the team has put a lot of thought into its cluster configuration. Its architectural doc discussed in detail how it made its processor, memory, node, and accelerator decisions. Very well done on its part.

The result? A six-node cluster that’s composed of two ‘thin’ and four ‘fat’ nodes. A thin node is composed of dual 14-core Xeon E5-2697 v3 CPUs and a fat node is configured with dual 12-core Xeon E5-2697 v2 CPUs. What makes the fat nodes fat is the addition of dual NVIDIA K40 GPUs to goose their compute performance.

As it said in its proposal, the system is designed to provide high performance on both CPU-only and GPU friendly codes. The team aimed to have a cluster that had enough CPU power to perform well on less accelerator friendly applications such as ADCIRC.

The real key for Team Singapore, like most of the other teams, will be how well it was able to control its power usage. According to the team, just the CPU portion of its cluster pulls almost 2,700 Watts.

Adding GPUs to the mix, at 234 Watts each, will require the team to idle some CPUs, which requires a delicate and perilous balancing act in the midst of the competition.

Team Tennessee (University of Tennessee, Knoxville) returned for a second try at the SC cluster crown. Its first attempt was less than auspicious. Hardware problems forced the team to rebuild its entire system during the competition. This is like making a stock car team swap out transmissions in the middle of a race. Tennessee had a good team, but couldn’t prove it at SC13.

Putting the doomed SC13 competition behind them, Team Tennessee formed another team, revamped its hardware configuration, and brought it all to New Orleans.

It’s mostly a new crop of kids, so there’s not a lot of competition experience, but I got the feeling that these kids really wanted to prove something this year.

Team Tennessee had the smallest cluster in the competition, at least in terms of CPU power. It has a five-node, 96-core system, with 512GB of memory. But the team is swinging with the big guys due to its eight NVIDIA K40 Tesla accelerators.

Something that caught my attention in Tennessee’s final architectural proposal is how it cited its use of application and profiling tools from team sponsor Cray. It also discussed how it stuck closely to tools and operating environments along the lines of its other team sponsor, the US National Institute for Computational Sciences – folks who know their way around a cluster.

Finally, they talked about how the applications this year all use GPU ports, which isn’t something that the other teams necessarily found. It looks like the kids from Knoxville have really dug into the innards of the competition applications and like what they see.

Next up is our first interview with the teams, then presentations from each team (a new requirement this year), then detailed results and analysis. Stay tuned. ®

Bootnote

Youtube Video

* The original 1814 Battle of New Orleans was the last major battle of the War of 1812 and effectively ended the conflict. American rebels, led by General Andrew Jackson (with an assist from French semi-pirate Jean Laffite) achieved a solid victory over the British.

If you’re interested in more info about the first Battle of New Orleans, I would recommend listening to the authoritative account contained in the Johnny Horton song “The Battle of New Orleans (check it out on YouTube here). What ever happened to songwriter/historians like Mr. Horton? He was also responsible for other historical songs like “Sink the Bismarck”, “North to Alaska” and “John Paul Jones”.