This is an archived page of the 2007 conference


The 8th LCI International Conference on High-Performance Clustered Computing will be held May 14-17, 2007 in South Lake Tahoe, California. The 4-day event, including conference and tutorials, will feature a broad range of presentations and papers from HPC and large-scale cluster computing professionals in industry, academia, and government. Speakers will address efforts to integrate and develop science and engineering applications for large-scale clusters, to achieve maximum performance and scalability. A full day of tutorials will be offered as part of the overall program.

The technical program will include both peer-reviewed paper presentations and discipline- and industry-specific sessions offering researchers and industry leaders the opportunity to present their experiences with applications. tools, user environments, and administration of large-scale clusters. Presentations from industry are specifically being invited from the petroleum and geophysics, bioinformatics, aerospace and automotive, and finance sectors.

Last updated: May 10, 2007.

monday | tuesday | wednesday | thursday

Monday, May 14, 2007

8:30 AM Tutorials [Chair: Mike Pflugmacher, NCSA, USA]
Tutorial I
SAN Persistent Binding and Multipathing in the 2.6 Kernel, Andy Loftus, NCSA, USA
Tutorial II
Parallel and MPI Debugging and Memory Debugging in Clusters, Chris Gottbrath, TotalView Technologies, LLC, USA
Tutorial III
MPI Performance Maximization, Jeff Squyres, Cisco, Inc. USA; George Bosilca, University of Tennessee, USA
Tutorial IV
Parallel Performance Evaluation Tools for HPC Systems: TAU, PAPI, KOJAK and Vampir, Sameer Shende, University of Oregon, USA and Shirley Moore, ORNL, USA
Tutorial V
Optimizing Data Transport: A Tutrial on Deploying GridFTP, John Bresnahan, ANL, USA
10:00 Am Break
10:30 am Tutorial I
Tutorial II
Tutorial III
Tutorial IV
Tutorial V
12:00 pm Lunch
1:30 pm Tutorial VI
Exploration of Parallel File Systems at NCSA, Michelle Butler and Anthony Tong, NCSA, USA
Tutorial VII
Allinea's Tools for Debugging and Profiling, David Lecomber, Allinea, USA
Tutorial VIII
Intel Programming with Cluster OpenMP,
Jay P. Hoeflinger, Intel, USA
Tutorial IX
Introduction to Parallel Computing for Scientific Numerical Applications Using MPI for Better Scalability and Parallel Performance,
Byong-Do Kim, NCSA, USA
3:00 pm Break
3:30 pm Tutorial VI
Tutorial VII
Tutorial VIII
Tutorial IX
5:00 pm End of Tutorials
6:30 pm Welcome, Dave Norton, LCI 2007 Conference Chair
6:45 pm Invited Presentation: [Chair: Dave Norton, PGI, USA]
Operations at Scale - Lessons to Be Remembered, Robert Ballance, SNL, USA
9:00 pm
Opening Reception

Tuesday, May 15, 2007

8:15 am Welcome, John Towns, NCSA, USA
8:30 am Keynote [Chair: John Towns, NCSA, USA]:
Parallelism and Power in the Age of Petascale Computing
Horst Simon, LBNL, USA
9:30 am Break
10:00 am Parallel I/O,
File Systems, & Storage

[Chair: Terry Jones, LLNL, USA]

pNFS and Linux: Working Towards a Heterogeneous Future
Dean Hildebrand, Peter Honeyman, and William Adamson, University of Michigan, USA

Efficient Methods for Parallel I/O
Jeff Larkin, Cray, USA and Mark Fahey, Oak Ridge National Laboratory, USA

SAN Lessons Learned
Andy Loftus and Chad Kerner, NCSA, USA

Practical Experiences of Setting Up, Managing, and Diagnosing a Large Parallel Filesystem
Jim Laros, SNL, USA
Tools & Programming Environments
[Chair: Shirley Moore, University of Tennessee, USA]

Detecting and Solving Memory Problems in Linux Clusters
Chris Gottbrath, TotalView Technologies, LLC, USA

Automated MPI Correctness Checking: What if There Were a Magic Option?
Patrick Ohly and Werner Krotz-Vogel, Intel Corporation, DE

A Framework for Scalable Parameter Estimation on Clusters
Tom Bulatewicz, Daniel Andresen, Stephen Welch, Wei Jin, Sanjoy Das, and Matthew Miller, Kansas State University, USA

PerfTrack: Scalable Application Performance Diagnosis for Linux Clusters
Rashawn Knapp, Kathryn Mohror, Aaron Amauba, Karen Karavanic, Portland State University, USA; Thomas Conerly, Caitlin Gaebel High School, USA; Abraham Neben, Wilson High School, USA; John May, Lawrence Livermore National Laboratory, USA
Technical Briefs: Resource Management, Networks, & Power
[Chair: MIke Pflugmacher, NCSA, USA]

Anatomy of Ethernet Resiliency and Scalibility for Cluster Computing
Debbie Montano, Force 10, USA

Grids for the Real World: Addressing Sovereignty and Ease of Use
David Jackson, Cluster Resources, USA

How Long Can You Go?
Wade Vinson, HP, USA

Stateless Booting
Egan Ford, IBM, USA

Benefits of Centralized Service Processor Management in Clustered Environments

Ivan Passos, Avocent, USA

Best Practices in Cluster Management
Richard Friedman, Scali, USA

OCS and LSF HPC: An Integrated Solution for System and Workload Management
Mehdi Bozzo-Rey, Platform Computing, USA
12:00 pm Lunch
1:00 pm Network & Cluster Opitmization [Chair: Ron Brightwell, SNL, USA]

Data-Intensive Cluster Optimization, Benoit Marchand, eXludus, USA

DataDirect Networks Presentation, Rick Scott, DataDirect Networks, USA

Myri-10G: The Technically Superior HPC Interconnect, Tom Leinberger, Myricom, USA

Open Fabrics Enterpirse Edition (OFED) Update, Jamie Riotto, Cisco, USA

Qlogic Presentation
3:05 pm Break
3:30 pm Resource Management &

[Chair: Kent Milfeld, TACC, USA]

An Architecture for Dynamic Allocation of Compute Cluster Bandwidth
John Bresnahan and Ian Foster, University of Chicago, USA

Experiences Deploying a 10-Gigabit Ethernet Computing Environment to Support Regional Computational Science
Jason Cope, Theron Voran and Matthew Woitaszek, University of Colorado at Boulder, USA; Adam Boggs, Sean McCreary, Michael Oberg, and
Henry M. Tufo, National Center for Atmospheric Research, USA

The Application Level Placement Scheduler (ALPS)
Michael Karo, Richard Lagerstrom and Carl Albing, Cray Inc., USA
Performance Analysis & Applications
[Chair: Phil Roth, ORNL, USA]

A Case Study in Using Local I/O and GPFS to Improve Simulation Scalability
Vincent Bannister, Microsoft, USA; Gary Howell and Eric Sills, HPC/ITD NCSU, USA; Tim Kelley and Qianyi Zhang, NCSU, USA

Visualizing I/O Performance during the BGL Deployment
Andrew Uselton and Brian Behlendorf, Lawrence Livermore National Laboratory, USA

Load Balancing in Pre-Processing of Large-Scale Distributed Sparse Computing
Olfa Hamdi and Zaher Mahjoub, Faculty of Sciences of Tunis, TN; Nahid Emad, Univeristy of Versailles, FR
5:00 pm Break
7:00 pm Dinner and Speaker [Chair: Dave Norton, PGI, USA]
Tales of Tahoe, Don Lane, U.S. Forest Service, USA

Wednesday, May 16, 2007

8:15 am Welcome, Dave Norton, PGI, USA
8:30 am Keynote [Chair: Dave Norton, PGI, USA]:
Advances in Regional Climate System Modeling for a Better Understanding of Land Use and Climate Change Impacts in California Norman L. Miller, UC Berkeley, USA
9:30 am Break
9:45 am DARPA HPCS Systems [Chair: Henry Tufo, NCAR, USA]
IBM PERCS: Rama K. Govindaraju, IBM, USA
Cray Cascade: Luiz DeRose, Cray Inc., USA
10:45 AM Break
11:00 AM Software for Clustered Systems
[Chair: Karen Karavanic, Portland State Univeristy, USA]

Optimizing Application Performance on x64 Processor-based Systems with PGI Compilers and Tools, Douglas Miles, PGI, USA

Debugging and Optimizing Applications for Multicore MPP Architectures, Michael Rudgyard, Allinea, USA

Improving System Performance with Scali MPI Connect, Richard Friedman, Scali, USA

Adaptive Computing in HPC Today, David Jackson, Cluster Resources, USA

The Transition to Multi-core: Is Your Software Ready?, Matthew Papakipos, PeakStream, USA
1:30 pm Break
6:00 pm New Systems [Chair: Brent Gorda, LLNL, USA]
Road Runner: John Turner, LANL, USA
Abe: John Towns, NCSA, USA
Ranger: Kent Milfeld, TACC, USA
Jaguar: Shane Canon, ORNL, USA
7:00 pm Speaker's Corner [Chair: Dave Norton, PGI, USA]
Supercomputing Cluster Challenge, Brent Gorda, LLNL, USA
8:00 pm Posters and Reception [Chair: Gregg Rohaly, HP, USA]

Thursday, May 17, 2007

8:15 am Welcome, Luiz DeRose, Cray Inc., USA
8:30 am Keynote [Chair: Luiz DeRose, Cray Inc., USA]:
From Beowulf to Cray-o-wulf: Extending Linux Clustering Paradigm to Supercomputing Scale, Peter Ungaro, Cray Inc., USA
9:30 am Break
10:00 am OS Alternatives
[Chair: Greg Lindahl, Qlogic, USA]

Linux Kernel Improvement: Toward Dynamic Power Management of Beowulf Clusters
Fengping Hu and Jeffrey Evans, Purdue University, USA

HPC System Call Usage Trends
Terry Jones, Lawrence Livermore National Laboratory, USA; Andrew Tauferner and Todd Inglett, IBM, USA

Compute Node Linux (CNL): From Capability to Capacity
Kevin Peterson, Cray Inc., USA

Starting with Linux: A System Design Case Study
John Goodhue and Win Treese, SiCortex Inc. USA
Emerging Technology
[Chair: Rick Kufrin, NCSA, USA]

Intel Woodcrest: An Evaluation for Scientific Computing
Philip Roth and Jeffrey Vetter, Oak Ridge National Laboratory, USA

The PeakStream Platform: High-Productivity Software Development for GPUs
Matthew Papakipos, PeakStream, Inc. USA

Effective Use of Commodity Multi-Core Systems in HPC
Kent Milfeld, Kazushige Goto, Avi Purkayastha, Chona Guiang, and Karl Schulz, University of Texas at Austin, USA

Future of Storage: Commodity Clusters and Parallel I/O
Alex Sayyah, DDN, USA
Technical Briefs: I/O
[Chair: Barney Maccabe, UNM, USA]

Considerations for Scalable Environmental Sciences Applications on Conventional HPC Linux Platforms
Stan Posey, Panasas, USA

Experiences with Parallel Commodity Storage
David Chaffin, Texas Tech HPCC, USA

Performance, Reliability, and Operational Issues for High Performance NAS Storage
Matthew O'Keefe, Alvarri, USA

Architecting High Performance, Scalable & Highly Available Cluster Storage with Best-of-Breed Storage Software and DDN S2A Technology
Jeff Denworth & Bob Woolery, DataDirect, USA
12:00 pm Lunch
1:00 pm Upcoming Hardware Technology [Chair: Erik Scott, Shell, USA]

HPC Technologies from Intel, David Barkai and David Lombard, Intel, USA

Evolution of HPC Cluster Nodes: General Purpose or Purpose Built?, Jeff Underhill, AMD, USA

Cool, Tight, Fast, Reliable HPC Clustering with Blades and InfiniBand, Kent Koeninger, HP, USA

Trends in High Performance Computing Commodity Clusters, Jay Urbanski, IBM, USA

High Performance Clustering for Big Science, Kevin Noreen, Dell, USA
3:05 pm Break
3:15 pm Awards
3:30 pm Invited Presentation [Chair: Bob Ballance, SNL, USA]
HPC I/O Road Map: The Next Five Years, Gary Grider, Los Alamos National Laboratory, USA
4:00 pm Panel: High Performance I/O: The Road Less Traveled?
Moderator: Timothy Thomas, HPC@UNM, USA
Panelists: Walt Ligon, Clemson University, USA; Ethan Miller and Scott Brandt, UC at Santa Cruz, USA; Brent Welch, Panasas, USA; Kevin Canady, Cluster File Systems, Inc., USA; Gary Grider, LANL, USA
5:15 pm Closing Remarks
6:00 pm Informal Gathering of Attendees
7:15 PM End of Conference


Allinea logo    Cisco logo    Cluster Resources logo    Cray logo

DataDirect Networks logo    Dell logo    Exludus logo    IBM logo

HP logo    Intel logo    Myricom logo    NCSA logo

PeakStream logo    Portland Group logo    Scali logo    NCSA logo

Media Sponsors:

LinuxHPC logo