Cluster 2002 Schedule

Cluster2002 Program

Sunday
Early Registration: 3:00 - 7:00 pm

Monday - Tutorials
Morning Tutorials: 8:00 am - 12:00 noon

Cluster Computing: The OSCAR Approach
Stephen Scott (ORNL)

Clustered Data Acquisition
Johannes Gutleber (CERN)

Lunch (on your own): 12:00 noon - 1:30 pm

Afternoon Tutorials:1:30 - 5:30 pm

InfiniBand Architecture: Where Is It Headed and
What Will Be the Impact on Cluster Computing?
D. K. Panda (Ohio State)

Supporting IPv6 on Linux Clusters
Ibrahim Haddad (Open Systems Lab)

Tuesday

Welcome and Opening Remarks: 9:00 - 9:05 am
Keynote Address: 9:05 - 10:00 am
Blades - An Emerging System Design Model for Economic Delivery of
High-Performance Computing
Kirk Bresniker
Hewlett-Packard

Exhibits open: 10:00 am - 6:00 pm

Exhibits include:
ACE Computers Intel Corporation Sixford Technologies, Inc.
Appro Linux Networks Terrasoft Solutions, Inc.
Dolphin Interconnect Myricom, Inc. Western Scientific
Einix Promicro

Break: 10:00 - 10:15 am

Concurrent Technical Sessions: 10:15 - 11:45 am

Managing Tasks I
ZENTURIO: An Experiment Management System for Cluster and Grid Computing Thomas Fahringer, Radu Prodan
An Agent-Based Infrastructure for Parallel Java on Heterogeneous Clusters Jameela Al-Jaroodi, Nader Mohamed, Hong Jiang, David Swanson
Shell over a Cluster (SHOC): Towards Achieving Single System Image via the Shell Cher-Min Tan, Chung-Pheng Tan, Weng-Fai Wong

Operating and Using Clusters
Supermon: A High-Speed Cluster Monitoring System Matthew Sottile, Ronald Minnich
Leveraging Standard Core Technologies to Programmatically Build Linux Cluster Appliances Mason Katz, Philip Papadopoulos, Greg Bruno
Clusters as Large-Scale Development Facilities Remy Evard, Narayan Desai, John-Paul Navarro, Daniel Nurmi

Network Hardware I
Experience in Offloading Protocol Processing to a Programmable NIC Arthur Maccabe, Wenbin Zhu, Jim Otto, Rolf Riesen
Supporting MPI Collective Communication on Network Processors Chamath Keppitiyagama, Qianfeng Zhang, Alan Wagner
Efficient Barrier Using Remote Memory Operations on VIA-based Clusters Rinku Gupta, Jarek Nieplocha, Vinod Tipparaju, Dhabaleswar Panda

Lunch (on your own): 11:45 am - 1:30 pm

Concurrent Technical Sessions: 1:30 - 3:00 pm

Managing Tasks II
I-Cluster: The Execution Sandbox Bruno Richard
BioOpera: Cluster-aware Computing Win Bausch, Cesare Pautasso, Reto Schaeppi, Gustavo Alonso
Selective Buddy Allocation for Scheduling Parallel Jobs on Clusters Vijay Subramani, Rajkumar Kettimuthu, Srividya Srinivasan, Jeanette Johnson, P. Sadayappan

Applications
I/O Analysis and Optimization for an AMR Cosmology Application Jianwei Li, Wei-keng Liao, Alok Choudhary, Valerie Taylor
Parallel Pattern Identification in Biological Sequences on Clusters Chun-Hsi Huang
Performance and Implementation of Distributed Data CPHF and SCF Yuri Alexeev

Network Hardware II
Design and Implementation of CC-NUMA Card II for SCI-Based PC Clustering Soo-Cheol Oh, Sang-Hwa Chung, Hankook Jang
Impact of On-Demand Connection Management in MPI over VIA Jiesheng Wu, Jiuxing Liu, Pete Wyckoff, Dhabaleswar Panda
MyVIA: A Design and Implementation of the High-Performance Virtual Interface Architecture Yu Chen, Xiaoge Wang, Zhenqiang Jiao, Jun Xie, Zhihui Du

Break: 3:00 - 3:15 pm

Plenary Session: 3:15 - 4:35 pm
Production Clustering at Pratt & Whitney: Desktop Supercomputing for Engineering Design Pete Bradley Associate Fellow High Intensity Computing Pratt & Whitney
Trends in High Performance Computing and Using Numerical Libraries on Clusters Jack Dongarra University of Tennessee

Panel Session: 4:45 - 6:00 pm

Scalable Systems Software: Big Clusters - Big Problems?
Pete Beckman - Director, Turbo Labs
José Moreira - IBM Blue Gene System Software Group
John Kochmar - Pittsburgh Supercomputer Center Advanced Systems Group
Al Geist - Head, DOE Scalable Systems Software Project

Abstract: This interactive panel session will begin with each panelist spending 15 minutes describing their experiences and how they are addressing the problems of systems software for big clusters. They will also express what they considered to be major issues in scalability for the next generation of machines. Audience questions and comments will be encouraged during these position presentations, and the last 20 minutes will be an open Q&A session between the panel and the audience.

Poster Session / Reception:6:00 - 8:00 pm

Low-Cost Non-intrusive Debugging Strategies for Distributed Parallel Programs M. Beynon, H. Andrade, and J. Saltz	Silkroad II: A Multi-paradigm Runtime System for Cluster Computing L. Peng, W. Wong, and C. Yeun
Algorithmic Mechanism Design for Load Balancing in Distributed Systems D. Grosu and A. Choronopoulos	Community Services: A Toolkit for Rapid Deployment of Network Services B.-D. Lee and J. Weissman
A Data Parallel Programming Model Based on Distributed Objects R. Diaconescu and R. Conradi	A Cluster Based Hybrid Join Algorithm: Analysis and Evaluation Peter Kirkovits and Erich Schikuta
MAGE -- A Metacomputing Environment for Parallel Program Development on Cluster Computers M. McMahon, B. DeLong, M. Fotta, G. Weinstock, and A. Williams	COMB: A Portable Benchmark Suite for Assessing MPI Overlap W. Lawry, C. Wilson, A. Maccabe, and R. Brightwell
A Distributed Data Implementation of Parallel FCI Program Z. Gan, Y. Alexeev, R. Kendall, and M. Gordon	User-Level Remote Data Access in Overlay Metacomputers J. Siegel and P. Lu
Design of a Middleware-Based Cluster Management Platform with Tool Management and Migration F. De Turck, S. Vanhastel, P. Thysebaert, B. Volckaert, P. Demeester, and B. Dhoedt	Job Scheduling for Prime Time vs. Non-prime Time V. Lo and J. Mache

Information for Poster Presenters

Wednesday

Opening Remarks: 9:00 - 9:05 am
Keynote Address: 9:05 - 10:00 am
First Light of the Earth Simulator and Its PC Cluster Applications
Keiji Tani, Takayuki Aoki and Satoshi Matsuoka
Global Scientific Information and Computing Center
Tokyo Institute of Technology
Satoru Ohkura, Hitoshi Uehara and Tetsuo Aoyagi
Japan Marine Science and Technology Center

Exhibits open: 10:00 am - 6:30 pm

Exhibits include:
ACE Computers Intel Corporation Sixford Technologies, Inc.
Appro Linux Networks Terrasoft Solutions, Inc.
Dolphin Interconnect Myricom, Inc. Western Scientific
Einix Promicro

Concurrent Technical Sessions: 10:15 - 11:45 am

Programming Clusters I
High Performance User-Level Sockets over Gigabit Ethernet Pavan Balaji, Piyush Shivam, Pete Wyckoff, Dhabaleswar Panda
Protocol-Dependent Message-Passing Performance on Linux Clusters Dave Turner, Xuehua Chen
Mixed Mode Matrix Multiplication Meng-Shiou Wu, Srinivas Aluru, Ricky A. Kendal

Scalable Clusters I
Cplant Runtime System Support for Multi-Processor and Heterogeneous Compute Nodes Kevin Pedretti, Ron Brightwell, Joshua Williams
Scalable Cluster Administration - Chiba City Approach and Lessons Learned John-Paul Navarro, Narayan Desai, Remy Evard, Dan Nurmi
Disaster Tolerant Wolfpack Geo-Clusters Richard Wilkins, Xing Du, Robert Cochran, Matthias Popp

Novel and Innovative Hardware
Memory Mapped Networks: A New Deal for Distributed Shared Memories? Emmanuel Cecchet
Adaptive Message Management Using a Hybrid Channel Model in a Parallel File System Joon-Hyung Hwangbo, Sang-Ki Lee, Yoon-Young Lee, Dae-Wha Seo
The Bladed Beowulf: A Cost-Effective Alternative to Traditional Beowulfs Wu-chun Feng, Michael Warren, Eric Weigle

Lunch (on your own): 11:45 am - 1:30 pm

Concurrent Technical Sessions: 1:30 - 3:00 pm

Programming Clusters II
Goals Driving Design: PVM and MPI William Gropp
Design and Validation of Portable Communication Infrastructure for Fault-Tolerant Cluster Middleware Ming Li, Wenchao Tao, Daniel Goldberg, Israel Hsu, Yuval Tamir
A Parallelization Technique that Improves Performance and Cluster Utilization Efficiency for Heterogeneous Clusters of Workstations David Garza-Salazar, Gerardo Diaz-Cuellar

Scalable Clusters II
An Extensible, Portable, Scalable Cluster Management Software Architecture James Laros, Lee Ward, Nathan Dauchy, Ron Brightwell, Trammell Hudson
Processor Allocation on Cplant: Achieving General Processor Locality Using One-Dimensional Allocation V. Leung, E. Arkin, M. Bender, D. Bunde, J. Johnston, A. Lal, J. Mitchell, C. Phillips, S. Seiden
Scalable Resource Management in High-Performance Computers Eitan Frachtenberg, Fabrizio Petrini, Juan Fernandez, Salvador Coll

Network Software
Reliable Blast UDP: Predictable High Performance Bulk Data Transfer Eric He, Jason Leigh, Oliver Yu, Thomas A. DeFant
Integrated Admission and Congestion Control for QoS Support in Clusters Ki Hwan Yum, Eun Jung Kim, Chita R. Das, Mazin Yousif, José Duato
Socket Cloning for Cluster-Based Web Servers Yiu-fai Sit, Cho-Li Wang, Francis Lau

Break: 3:00 - 3:15 pm

Plenary Session: 3:15 - 5:15 pm
Indexing the Web -- A Challenge for Supercomputers Monika Henzinger Google Inc.
Interconnects: Which One Is Right for You? Brett M. Bode Ames Laboratory / Iowa State University
Launching into the Future of Commodity Cluster Computing Thomas Sterling JPL / Caltech

Industry Exhibits / Reception: 6:00 - 7:30 pm

Banquet
Museum of Science and Industry
7:30 - 10:00 pm

Thursday

Opening Remarks: 9:00 - 9:05 am
Keynote Address: 9:05 - 10:00 am
Blue Gene/L, a System-on-a-Chip
George Chiu
IBM

Break:
10:00 - 10:15 am

Concurrent Technical Sessions: 10:15 - 11:45 am

Programming Clusters III
Scalable Loop Self-Scheduling Schemes for Heterogeneous Clusters Anthony Chronopoulos
Compiling Tiled Iteration Spaces for Clusters Georgios Goumas, Nikolaos Drosinos, Maria Athanasaki, Nectarios Koziris
An Architecture for Integrated Resource Management of MPI Jobs Steven Sistare, Jack Test

Java and Clusters
JESSICA2: A Distributed Java Virtual Machine with Transparent Thread Migration Support Wenzhang Zhu, Cho-Li Wang, Francis C. M. Lau
CEJVM: Cluster-Enabled Java Virtual Machine Muhammad Umar Janjua
On the Evaluation of JavaSymphony for Cluster Applications Thomas Fahringer, Radu Prodan

I/O on Clusters
Non-contiguous I/O through PVFS Avery Ching, Alok Choudhary, William Gropp, Wei-keng Liao, Rob Ross
Using Idle Disks in a Cluster as a High-Performance Storage System J�rgen S. Hansen, Renaud Lachaize
Kernel-Level Caching for Optimizing I/O by Exploiting Inter-Application Data Sharing Murali Vilayannur, Mahmut Kandemir, Anand Sivasubramaniam

Lunch (on your own): 11:45 am - 1:30 pm

Plenary Session: 1:30 - 2:50 pm

MPI in 2002: Has It Been Ten Years Already?
Ewing Lusk
Argonne National Laboratory

Research Directions in Parallel I/O for Clusters
Walt Ligon
Clemson University

Cluster Steering Committee Meeting: 3:00 - 5:00 pm

Plenary Session: 1:30 - 2:50 pm
MPI in 2002: Has It Been Ten Years Already? Ewing Lusk Argonne National Laboratory
Research Directions in Parallel I/O for Clusters Walt Ligon Clemson University