Salishan 2010

Theme: Tackling Big Data: HPC Approaches to Informatics

Keynote Address: Amdahl’s Law and Extreme Data Intensive Computing, Alexander S. Szalay, The Johns Hopkins University

Session 1: Applications

• Advanced Scientific Computing Research Program --Positioning for Exascale, Walter M. Polansky, U.S. Department of Energy
• Cyber Analytics Applications for Data-Intensive Computing, Mike Fisk, Los Alamos National Laboratory
• Scalable Peer-to-Peer Data Mining for Data-Intensive Astroinformatics, Kirk Borne, George Mason University
• Synthetic Information and Decision Informatics for Complex Systems, Chris Barrett, Virginia Technical Institute

Session 2: Methods

• The Emerging Data Informatics Architecture, Boyd T. Livingston, National Security Agency (NSA)
• Pregel: A Model for Distributed, Large-Scale Graph Processing, James C. Dehnert, Google, Inc.*
• Network Discovery, Characterization and Prediction: A “Grand Challenge” Research Project, David Rogers, Sandia National Laboratories
• The Spectrum of Data Intensive Computing Activities at LANL, Francis J. Alexander, Los Alamos National Laboratory

Working Dinner/Speaker

• Computing at Extreme Scale, Stuart Feldman, Google*

Session 3: Large Data Environments

• Scientific Data Management Challenges in Extreme Scale Systems, Arie Shoshani, Lawrence Berkeley National Laboratory
• Does 10by10 Replace 90/10, Andrew Chien, Intel Labs, Future Technologies Researchn
• Large Scale Text Analysis Using the Map/Reduce Hierarchy, David Buttler, Lawrence Livermore National Laboratory
• Real Life Data Intensive Applications – Challenges and Solutions, Jacek Becla, Stanford University

Session 4: Architectures for Data Intensive Computing

• Large-Scale Distributed Stream Processing with InfoSphere Streams, Henrique Andrade, Exploratory Stream Processing Systems Group, IBM Watson (Hawthorne)
• Cloud Computing for Science, Kate Keahey, Argonne National Laboratory
• The X-caliber Architecture for Informatics Supercomputers, Richard C. Murphy, Sandia National Laboratories*
• Addressing the Challenges of Petascale Systems Deployment, Mark Seager, Lawrence Livermore National Laboratory

Session 5: Programming Models

• Killer Micros II: The Software Strikes Back, Burton Smith, Microsoft Corporation
• Methods for Enabling Next Generation Knowledge Discovery, Ryutaro Himeno, Shoaib Mufti, Cray, Inc.
• Requirements and Performance of Data Intensive, Irregular Applications, John Feo, Pacific Northwest National Laboratory
• Programming Models for Data Intensive Computing on the LexisNexis High Performance Computing Cluster, John Holt, LexisNexis

*will not be posted