ACADEMIA

HPC Analytics, SC|05’s newest initiative, has announced six finalists for its challenge that honors top technical and commercial applications developed from leading-edge, advanced analytics techniques to solve complex, real-world problems. The HPC Analytics Challenge is a unique opportunity for researchers, engineers, and analysts to showcase innovative techniques in rigorous data analysis and high-end visualization to develop and demonstrate applications showcasing powerful analytics techniques for solving complex, real-world problems. Finalists of the HPC Analytics Challenge will convene at SC|05, the premier international conference on high performance computing, networking, storage, and analysis on November 12-18. “We were pleasantly surprised by the number of participants for this first year,” said Tim Leite, HPC Analytics Committee Chair. “The numbers, quality and range of applications greatly exceeded our expectations, and the presentations will generate great excitement for next year’s initiative.” The HPC Analytics program finalists include: Terascale Music Mining – this project’s goal is to create secure, accessible, terascale collections of music materials in a variety of audio, symbolic and metadata forms. Network Traffic Analysis with Query Driven Visualization -- this entry is used in the field of information management to successfully perform queries, feature identification and characterization of 24 weeks of netflow data consisting of 1.1 billion records of 25 fields each. SPICE: Simulated Pore Interactive Computing Experiment -- the project aims to understand the vital process of translocation of biomolecules across protein pores by computing the free energy profile of the translocating biomolecule along the vertical axis of the pore. Bridging the Macro and Micro: a Computing Intensive Earthquake Study using Discovery Net -- results from this group provide valuable scientific insights into earthquake analysis, and also showcase how novel HPC methods and knowledge discovery methods enable such results to be achieved. Visualization of Large-Scale Unsteady Computational Fluid Dynamics Datasets -- a new scientific visualization tool has been developed for investigators to more effectively interrogate large unsteady datasets. Real Time Change Detection and Alerts from Highway Traffic Data -- this team has developed a test-bed containing real-time data from over 830 highway traffic sensors in the Chicago region, weather and text data about events that might affect traffic. The goal is to detect interesting changes in traffic conditions in real-time. The finalists will present their applications on Tuesday, November 15, at 1:30-5:00 p.m during the SC|05 conference. The awards ceremony will commence at 3:30 p.m. on Thursday, November 17. For more information visit its Web site.