This year’s Student Cluster Competition (SCC) at SC13 in Denver, Colorado, brought together student teams from the around the world for a grueling two-day face-off. The winning teams were revealed during an SC13 Awards Ceremony luncheon on Thursday, Nov. 21., where Team Longhorn from the University of Texas at Austin was declared the overall winner for the second year in a row.
The SC Student Cluster Competition takes place in real-time over a non-stop, 48-hour period while teams of undergraduate and/or high school students build a cluster on the SC13 exhibit floor and race to demonstrate the highest sustained performance across a series of scientific workloads without going over a set power limit. The team with the highest-performing system wins.
Under the Standard Track, six students partner with a vendor to design and build a cluster from commercially available components without exceeding the 26-amp power limit. Domain experts may offer advice on tuning and running the competition codes.
The eight Standard Track teams competing at SC13 were:
Boston University (USA)
IVEC, a joint venture between CSIRO, Curtin University, Edith Cowan University, Murdoch University and the University of Western Australia (Australia)
National University of Defense Technology (China)
The University of Colorado, Boulder (USA)
The University of the Pacific (USA)
The University of Tennessee, Knoxville (USA)
The University of Texas, Austin (USA)
Friedrich-Alexander University of Erlangen-Nuremberg (Germany)
The first-ever Commodity Cluster Track also kicked off at SC13. These five-student teams are welcome to create any manner of cluster (off-the-shelf or off-the-wall) so long as they use commercially available hardware purchased for less than $2,500 and stay within a 15-amp power limit. The new track was sponsored by Bank of America, UTRC (United Technologies Research Center), and Procter and Gamble.
The four Commodity Cluster track teams competing at SC13 were:
Slippery Rock University, Slippery Rock, Penn.
Skyline High School, Salt Lake City, Utah
Bentley University, Waltham, Mass., and Northeastern University, Boston, Mass.
Arizona State University, Tempe, Ariz.
The results of this year’s competition were revealed at SC13 and are listed at studentclustercomp.com.
And the winners are…
Overall Championship: The University of Texas, Austin (aka Team Longhorn)
Highest Linpack: National University of Defense Technology (NUDT)
Commodity Championship: Bentley and Northeastern University (Team Open Compute)
Lowest Cost Per Flop Award: Arizona State University (Team Sun Devil)
Every team who competed in this remarkable event deserves serious kudos. Participation involves months of hard work. First the team must find a vendor sponsor to provide the high-end gear and usually some financial support for travel and other incidentals. Then comes the designing, configuring, testing, and tuning the clusters. The teams take these systems to the show and compete against each another in a live benchmark face-off in full view of conference attendees until the close of the exhibit floor on Wednesday evening.
Mandatory applications include the HPCC benchmark, with an independent HPL (LINPACK) run, plus a set of real-world scientific workloads, e.g., crunching weather data, running a nanotechnology simulator and operating machine-learning software. If the contest was not challenging enough, the students were also given a “mystery application.” The primary objective is completing the greatest number of application runs during the competition period.
Points are awarded for system performance, including the quantity and quality of results. Teams are also interviewed to test how well they understand the scientific tasks they’ve been running. The team with the most points is declared the “Overall Winner.” There are also awards for highest LINPACK score and as of this year, the Commodity Cluster track winners. Some Student Cluster Competitions also bestow “Fan Favorite” awards.
Team Longhorn were repeat champs, having proven their mettle at SC12 the year before. In this video with Dan Olds, the team members from The University of Texas at Austin discuss what it means to “ride the line” and offer a detailed accounting of their Dell cluster’s specs.