Awards Highlight

Most Successful SC Conference Ever SC2001 will build on SC2000 momentum

DALLAS, Texas – SC2000, the conference of high performance networking and computing, capped one of the most successful programs in the history of the conference by recognizing outstanding achievements and contributions in the field.

The awards were presented Thursday, Nov. 9, honoring a wide range of people and their accomplishments. The conference drew 5,065 registered attendees and 153 exhibitors for a week of demonstrations, technical presentations, informal discussions and an extensive educational program.

“Whether we judge the conference by attendance, passing comments in the aisles or the overflowing audiences for presentations, this has been one heck of a successful week,” said Louis Turcotte, general chair of the SC2000 conference. “SC2000 added to the very successful foundation of the conference as the SC2001 team starts planning for next year’s program in Denver.”

The IEEE Computer Society, a cosponsor of the conference, presented two special awards.

The first, the Sidney Fernbach Award, was presented to Stephen W. Attaway of Sandia National Laboratories. The award is given for an outstanding contribution in the application of high performance computers using innovative approaches. Attaway is an engineer who works in the field of computational mechanics for crash and impacts. He has worked at Sandia National Laboratories since 1987 and is currently a Distinguished Member of Technical Staff in the Computational Solid Mechanics and Structural Dynamics Department. Attaway was named a fellow of the American Society of Mechanical Engineers (ASME) in March 2000.

The second award, the second annual IEEE Computer Society Seymour Cray Computer Engineering Award, presented in recognition of innovative contributions to high performance computing systems that best exemplify Seymour Cray’s creative spirit, was given to Glen J. Culler. In 1961, he and physicist Burton Fried developed the first interactive, mathematically based graphical system – allowing scientists visualize computational solutions in real-time. During his career, Culler developed the array processor, digital speech processing and the personal supercomputer. This award includes a $10,000 honorarium and is funded from an endowment provided by SGI.

Each year at SC, the Gordon Bell Prize is awarded for the best peak computer performance, the best performance-price ratio and in a special category.

Competitors for this year’s prize for best performance tied, each achieving 1.34 teraflops. Tetsu Narumi, Ryutaro Susukita, Takahiro Koishi, Kenji Yasuoka, Hideaki Furusawa, Atsushi Kawai and Thoshikazu Ebisuzaki recorded 1.34 Tflops with their Molecular Dynamic Simulation for NaCl for a Special Purpose Computer: MDM. The team of Junichiro Makino, Toshiyuki Fukushige and Masaki Koga achieved1.349 Tflops with their Simulation of Black Holes in a Galactic Center on GRAPE-6.

The winners of the Price/Performance Category were Douglas Aberdeen, Jonathan Baxter and Robert Edwards for their 92 cents/Mflops Ultra-Large Scale Neural Network Training on a PIII Cluster.

Honorable Mention in the Price/Performance Category went to Thomas Hauser, Timothy I. Mattox, Raymond P. LeBeau, Henry G. Dietz and P. George Huang of the University of Kentucky for their “High-Cost CFD on a Low-Cost Cluster.”

In the Gordon Bell Prize special category, Alan Calder, B.C. Curtis, Jonathan Dursi, Bruce Fryxell, G. Henry, P. MacNeice, Kevin Olson, Paul Ricker, Robert Rosner, Frank Timmes, Henry Tufo, James Truran and Michael Zingale were cited for their High-Peformance Reactive Fluid Flow Simulations Using Adaptive Mesh Refinement on Thousands of Processors.

Here is a list of other awards presented at the conference:

  • Best Paper: “Is Data Distribution Necessary in OpenMPI?,” Constantine Polychronopoulos, Dimitrios Nikolopoulos, Eduard Ayguade, Jesus Labarta and Theodore Papatheodorou.
  • Best Student Paper: “A Comparison of Three Programming Models for Adaptive Applications on the Origin 2000,” Hongzhang Shan, Princeton University.
  • Best Research Gem: “Automatic TCP Window Tuning Implemented in an FTP Application,” Jim Ferguson and Jian Liu.
  • HPC Games Most Leading Edge Technology Prize: Jeff Moe, Jim Waggett, Kai Staats and Roy Jenevein for Black Lab Linux.
  • HPC Games Most Innovative Hardware Prize: Bill Dieter, Hank Dietz, Jim Lumpp, Thomas Hauser, Tim Mattox and Todd Willey for The Aggregrate.
  • HPC Games Grand Prize: James Hanna, Peter Hsieh, Robert Hillman, Walter Koziarz, Wilmar Sifre and Zen Pryk for The Red Team.
  • HPC Games Most Innovative Software Prize: James Hanna, Peter Hsieh, Robert Hillman, Walter Koziarz, Wilmar Sifre and Zen Pryk for The Red Team.

A new competition sponsored by Qwest Communications International and called the SC2000 Network Challenge for Bandwidth-Intensive Applications pushed the limits of the conference’s SCinet network as two teams posted peak performance figures of more than a gigabit of data per second.

Share

SC2001 Netcast Complete Schedule

Tuesday, 13 November
Keynote Address
8:30AM-10AM
Craig Venter, President and CEO Celera Genomics
Accelerating Discovery Through Supercomputing
(Netcast Archive)
Exhibitor Showcase
Grid Applications
Dr. James Pool
Center for Advanced Computing Research, California Institute of Technology
Booth R0340
Exhibitor Showcase
Digital Worlds Institute (Courtesy SUN Microsystems)
Dr. James Oliverio
Digital Worlds Institute
Booth 645
Wednesday, 14 November
Plenary Session
8:30AM-9:15AM
Jim Gray, Microsoft Research
The World Wide Telescope: Mining the Sky

(Netcast Archive)
Gray talk begins at 3 minutes
Plenary Session
9:15AM-10AM
Fran Berman, Director of SDSC and NPACI, Professor of CSE, UCSD
Grid Computing in the Terascale Age
(Netcast Archive)
Berman talk begins at 45 minutes
Exhibitor Showcase
Internet2
Ted Hanss and Ben Teitelbaum
Internet2
Booth R0849
Exhibitor Showcase
Dancing Beyond Boundaries
University of Florida
Booth R1070
Thursday, 15 November
Plenary Session
8:30AM-9:15AM
Chris Johnson, University of Utah
Scientific Visualization: Bridging the Complexity Threshold
(Netcast Archive)
Plenary Session
9:15AM-10:30AM
Alvy Ray Smith, Digital Photography Artist
Will Digital Actors Replace Human Ones?
(Netcast Archive)
Exhibitor Showcase
SCinet
SCinet
Booth 655
Exhibitor Showcase
TBA

 

Multicast With help from Cisco Systems and the University of Oregon, the SC2001 netcast will be available in three multicast streams: H.261, MPEG-1, and MPEG-2. For additional program and client infomation, see:
http://videolab.uoregon.edu/client.html

 

RealPlayer
For the latest RealPlayer client, see:
http://www.real.com/player/index.html

 

Assistance

We will be providing information and assistance for viewing the netcast throughout SC2001. All viewers are encouraged to provide feedback on the quality, scope and effectiveness of the SC2001 netcast. Contact:

Share

Technical Papers

The technical papers component of the SC2001 program is especially strong and vibrant. Sixty papers were selected from a pool of 240 submissions covering a broad technical scope and offering a truly international perspective on high performance networking and computing. Eighty-four of the papers were student submissions, of which seventeen were accepted and six nominated for the best student paper award.

In my view, SC has come into its own with this year’s program. Several of the papers represent the unique combination of real science, novel computational methods, and in-depth performance analysis on leading-edge platforms that only comes together at SC. You will find sessions such as “Sea, Wind, and Fire,” “Groundbreaking Applications,” and “Material Science” tackling computational modeling of the ocean, atmosphere, combustion, and structures. Several of these are finalists for the Gordon Bell Prize. Clusters and Grids are well represented from hardware and software viewpoints, reflecting the emergence of these important platforms. In-depth design studies explore leading commericial architectures, novel hardware devices, and emerging interconnects. Theoretical and empirical studies investigate new parallel numerical methods, algorithms, and performance-analysis techniques. Networking and storage are explored from unusual angles, and eScience emerges in the context of new modes of interacting with computational processes and high performance architectures.

Together, these papers provide a rich treatment of the latest technical work over the broad scope of high performance networking and computing. They are complemented with workshops on selected topics and a leading Masterworks track of invited speakers.

I would like to thank the members of the Technical Papers Committee and the Program Committee, who worked so hard to bring it all together and the authors from around the world who have built such a strong program. I think you too will find it exciting.

Sessions Chronologically
Sessions Alphabetically
 Architectures

    • Scientific Computing on the Itanium™…

ACMIEEE

    • The Sun Fireplane System Interconnect…

ACMIEEE

    • Parallel Graphics and Interactivity…

ACMIEEE

 Algorithmic Load Balancing

    • Large Scale Parallel Structured…

ACMIEEE

    • Parallel Interval-Newton…

ACMIEEE

    • Dynamic Load Balancing of SAMR…

ACMIEEE

 Software Scalability

    • Scalable Parallel Application Launch…

ACMIEEE

    • Scaling Iregular Parallel Codes…

ACMIEEE

    • A Parallel Java Grande Benchmark…

ACMIEEE

 Algorithms

    • Stable, Globally Non-iterative…

ACMIEEE

    • Stochastic Search for Signal…

ACMIEEE

    • A Hypergraph-Partitioning Approach…

ACMIEEE

 Communication Structures

    • ORT—A Communication Library…

ACMIEEE

    • On-the-fly Calculation…

ACMIEEE

    • Removing the Overhead…

ACMIEEE

 Architectures

    • Scientific Computing on the Itanium™…

ACMIEEE

    • The Sun Fireplane System Interconnect…

ACMIEEE

    • Parallel Graphics and Interactivity…

ACMIEEE

 Material Science Applications

    • Scalable Atomistic Simulation…

ACMIEEE

    • An 8.61 Tflop/s Molecular…

ACMIEEE

    • Multi-teraflops Spin Dynamics…

ACMIEEE

 Communication Structures

    • ORT—A Communication Library…

ACMIEEE

    • On-the-fly Calculation…

ACMIEEE

    • Removing the Overhead…

ACMIEEE

 Mesh Methods

    • Achieving Extreme Resolution…

ACMIEEE

    • A Distributed Memory Unstructured…

ACMIEEE

    • Multilevel Algorithms for Generating…

ACMIEEE

 Computational Grid  Applications

    • Applying Scheduling and Tuning…

ACMIEEE

    • An Automatic Design Optimization…

ACMIEEE

    • Numerical Libraries and the Grid…

ACMIEEE

 Computational Grid Portals  and Networks

    • The XCAT Science Portal

ACMIEEE

    • A Jini-based Computing…

ACMIEEE

    • Efficient Network and I/O…

ACMIEEE

 Computational Grid Environments and  Security

    • Supporting Efficient Execution… .

pdf 208K

    • Optimisation of Component-based… .

pdf 128K

    • Adapting Globus and Kerberos… .

pdf 108K

 Computational Grid I/O

    • LegionFS: A Secure and Scalable…

ACMIEEE

    • High-Performance Remote Access…

ACMIEEE

    • Gathering at the Well…

ACMIEEE

 Computational Grid I/O

    • LegionFS: A Secure and Scalable…

ACMIEEE

    • High-Performance Remote Access…

ACMIEEE

    • Gathering at the Well…

ACMIEEE

 Algorithmic Load Balancing

    • Large Scale Parallel Structured…

ACMIEEE

    • Parallel Interval-Newton…

ACMIEEE

    • Dynamic Load Balancing of SAMR…

ACMIEEE

 Computational Grid Portals  and Networks

    • The XCAT Science Portal

ACMIEEE

    • A Jini-based Computing…

ACMIEEE

    • Efficient Network and I/O…

ACMIEEE

 Sea, Wind, and Fire

    • Coastal Ocean Modeling…

ACMIEEE

    • Terascale Spectral Element…

ACMIEEE

    • High Resolution Weather Modeling…

ACMIEEE

 Efficient Layouts for  Hierarchical Memories

    • A Ghost Cell Expansion…

ACMIEEE

    • Improving Parallel Irregular…

ACMIEEE

    • Increasing Temporal Locality…

ACMIEEE

 Reconfigurable Architectures

    • Delivering Acceleration…

ACMIEEE

    • Parallel Dedicated hardware…

ACMIEEE

    • Cost Effectiveness of an Adaptable…

ACMIEEE

 Fast I/O

    • MPI-IO/GPFS…

ACMIEEE

    • A Case Study in Application…

ACMIEEE

    • The Design of I/O-efficient…

ACMIEEE

 Groundbreaking Applications

    • Solution of a Three-Body…

ACMIEEE

    • Parallel Implementation and…

ACMIEEE

    • Modeling of Seismic Wave…

ACMIEEE

 Groundbreaking Applications

    • Solution of a Three-Body…

ACMIEEE

    • Parallel Implementation and…

ACMIEEE

    • Modeling of Seismic Wave…

ACMIEEE

 Information Retrieval and Transaction  Processing

    • Efficient Execution of Multiple…

ACMIEEE

    • Dynamic Page Placement…

ACMIEEE

    • Compressing Inverted Files…

ACMIEEE

 Information Retrieval and Transaction  Processing

    • Efficient Execution of Multiple…

ACMIEEE

    • Dynamic Page Placement…

ACMIEEE

    • Compressing Inverted Files…

ACMIEEE

 Performance Prediction

    • On Using SCALEA for Performace…

ACMIEEE

    • Modeling and Detecting Performance…

ACMIEEE

    • Predictive Performance and Scalability…

ACMIEEE

 Material Science Applications

    • Scalable Atomistic Simulation…

ACMIEEE

    • An 8.61 Tflop/s Molecular…

ACMIEEE

    • Multi-teraflops Spin Dynamics…

ACMIEEE

 Algorithms

    • Stable, Globally Non-iterative…

ACMIEEE

    • Stochastic Search for Signal…

ACMIEEE

    • A Hypergraph-Partitioning Approach…

ACMIEEE

 Mesh Methods

    • Achieving Extreme Resolution…

ACMIEEE

    • A Distributed Memory Unstructured…

ACMIEEE

    • Multilevel Algorithms for Generating…

ACMIEEE

 Novel Graphics and Grids

    • Fast Matrix Multiplies…

ACMIEEE

    • Next-Generation Visual…

ACMIEEE

    • Global Static Indexing…

ACMIEEE

 Networking

    • EMP: Zero-copy OS-bypass…

ACMIEEE

    • Design and Implementation of FMPL…

ACMIEEE

    • A New Routing Mechanism…

ACMIEEE

 Computational Grid  Applications

    • Applying Scheduling and Tuning…

ACMIEEE

    • An Automatic Design Optimization…

ACMIEEE

    • Numerical Libraries and the Grid…

ACMIEEE

 Novel Graphics and Grids

    • Fast Matrix Multiplies…

ACMIEEE

    • Next-Generation Visual…

ACMIEEE

    • Global Static Indexing…

ACMIEEE

 Networking

    • EMP: Zero-copy OS-bypass…

ACMIEEE

    • Design and Implementation of FMPL…

ACMIEEE

    • A New Routing Mechanism…

ACMIEEE

 Performance Prediction

    • On Using SCALEA for Performace…

ACMIEEE

    • Modeling and Detecting Performance…

ACMIEEE

    • Predictive Performance and Scalability…

ACMIEEE

 Computational Grid Environments and  Security

    • Supporting Efficient Execution…

ACMIEEE

    • Optimisation of Component-based…

ACMIEEE

    • Adapting Globus and Kerberos…

ACMIEEE

 Reconfigurable Architectures

    • Delivering Acceleration…

ACMIEEE

    • Parallel Dedicated hardware…

ACMIEEE

    • Cost Effectiveness of an Adaptable…

ACMIEEE

 Efficient Layouts for  Hierarchical Memories

    • A Ghost Cell Expansion…

ACMIEEE

    • Improving Parallel Irregular…

ACMIEEE

    • Increasing Temporal Locality…

ACMIEEE

 Sea, Wind, and Fire

    • Coastal Ocean Modeling…

ACMIEEE

    • Terascale Spectral Element…

ACMIEEE

    • High Resolution Weather Modeling…

ACMIEEE

 Fast I/O

    • MPI-IO/GPFS…

ACMIEEE

    • A Case Study in Application…

ACMIEEE

    • The Design of I/O-efficient…

ACMIEEE

 Software Scalability

    • Scalable Parallel Application Launch…

ACMIEEE

    • Scaling Iregular Parallel Codes…

ACMIEEE

    • A Parallel Java Grande Benchmark…

ACMIEEE

 

Share

AWARDS CAP SC2001

HIGH-PERFORMANCE COMPUTING AND NETWORKING CONFERENCE

DENVER, CO — SC2001, the conference of high-performance networking and computing capped the most successful programs in its history by recognizing outstanding achievements and contributions in these fields.

The conference attracted nearly 200 exhibitors and over 5200 attendees, each of whom on average will spend between $3.5- and $7-million on planned purchases as a result of the week-long event.

The awards presented this afternoon honored a range of people and their accomplishments.

The primary award was the third annual IEEE Computer Society Seymour Cray Computer Engineering Award. This honor recognizes innovative contributions to high-performance computing systems that exemplify Seymour Cray’s creative spirit.

This year it was awarded to John L. Hennessy, President of Stanford University. Included is a $10,000 honorarium funded by an SGI endowment.

The Gorden Bell Prize is named after the Digital Equipment vice president. It is awarded annually at SC for the best peak computer performance, the best performance/price ratio and for a special category.

The Gordon Bell winner was the team of Toshiyuki Fukushige and Junichiro Makino, who achieved a simulation of black holes in a galactic center at a computer processing speed of 11.55 trillion floating operations per second.

The Gordon Bell Price/Performance prize went to Joon Hwang, Seung Kim and Chang Lee. Their study of impact locating on aircraft structure by low-cost cluster cost 24.6 cents/Mflops, or less than a U.S. quarter per 1-million floating operations per second.

The winner of the Gordon Bell Prize in the special category of supporting efficient execution in the heterogeneous distributed computing environments with Cactus and Globus. The winner was the team of Gabrielle Allen,Thomas Dramlitsch, Ian Foster, Nick Karonis, Matei Ripeanu, Edward Seidel and Brian Toonen.

The Best Student Paper was awarded to a computational grid application of tomography, a technique to reconstruct the three-dimensional structure of an object from a series of two-dimensional projections. The award went to a team of Shava Smallen, Henri Cazsanova and Francine Berman, and carries a $500 cash award.

Finally, the award for Best Research Poster went to Sumir Chandra, Johan Steensland and Manish Parashar.

Share