Computer science students Jim Given (CS/Mathematics), Reid McKenzie, Julian Michael (CS/Physics), Suvamsh Shivaprasad, and Zachary Tschirhart (CS/Aerospace Engineering/Mathematics) and their teammate Eric Dawson (Biology) comprised this year's UT's winning Student Cluster team. For the 2nd year in a row, UT's team won the student cluster overall competition at the international Student Cluster conference!
At SC13 in Denver, our team defeated teams from China's National University of Defense Technology (NUDT--the leading HPC institution in China, and maker of the current #1 system in the world), Australia's 5-institution consortium team, and Germany (Friedrich-Alexander University of Erlangen-Nuremburg), as well as teams from a Massachusetts university consortium, U. Colorado, U. of the Pacific (put together by LBL), and the faux UT (Knoxville, via their joint institute with ORNL).
The team was expertly coached by Carlos Rosales, John Cazes, and John Lockman of TACC, and had two of last year's championship team members as student advisors: Michael Teng (CS) and Andrew Wiley (CS, ECE). Thank you to Raytheon for sponsoring this year's team.
Student Cluster Competition
Eight student teams from universities in the United States, Germany, China and Australia were selected to compete in the Standard Track of the Student Cluster Competition at SC13. This year’s teams include the first ever team from Australia, who traveled nearly 9,000 miles from Perth for the competition.
Prior to the competition, a team works with its advisor and vendor partners to design and build a cutting-edge, commercially available small cluster constrained by the 26-amp power limit (Standard track) or $2500 USD cost limit and a 15-amp power limit (Commodity track). Teams were encouraged to enlist the help of domain specialists to assist with building, tuning, and understanding how the applications work. A fourth mystery application was revealed on Monday night when the competition officially kicked off.
During SC13, teams assemble, test, and tune their machines and run the HPCC benchmarks until the starting bell rang at the Exhibit Opening Gala, when they were given the competition data sets for all four applications. In full view of conference attendees, teams executed the prescribed workload while showing progress and science visualization output on large high-resolution displays in their areas. Teams race to correctly complete the greatest number of application runs during the competition period until the close of the exhibit floor on Wednesday evening.
The showcase portion of the competition allowed teams to show off what they’ve learned and what they can do with their equipment. Veteran HPC experts were present to judge the visualizations and interviewed each team on their cluster and application knowledge.
The winning team in each track was based on a combined score for workload completed, benchmark performance, conference attendance, and interviews. Recognition was given for the highest LINPACK (Standard track) and FLOPS-per-dollar LINPACK (Commodity track).