Stanford High Performance Computing Conference II

Tuesday, August 29th, 2006
8:00am - 5:00pm

Wallenberg Hall

The focus this year is software development and research computing, bringing together system managers, researchers, developers, computational scientists and industry affiliates to discuss recent developments and future advancement in High Performance Computing.

To register for the conference: http://www.clustercorp.com/conferences/index.html

Agenda
 
Main Theatre Session
Lab Sessions (Room 120)
Vendor Roadmap (Room 127)
8:00 am - 8:30 am
***Registration***
8:30 am - 9:15 am
******
******
9:20 am - 10:05 am
Cluster Corp.
break
***Break***
10:25 am - 11:10 am
11:15 am - 12:00 pm
Panasas
Lunch
***Lunch***
1:30 pm - 2:15 pm
Intel
2:20 pm - 3:05 pm
Break
***Break***
3:25 pm - 4:10 pm
APC
4:15 pm - 5:00 pm
Cisco
5:00 pm - 5:10 pm
***Closing Remarks***
   

(8:30 am - 9:15 am)

Keynote Speaker

Garth Gibson, Founder and CTO Panasas:

Garth Gibson
is co-founder and Chief Technology Officer at Panasas Inc. (www.panasas.com) and an associate professor of Computer Science and Electrical and Computer Engineering at Carnegie Mellon University.


*** Theatre Sessions ***

(9:20 am - 10:05 am)

SciDAC and the International Linear Collider:

Petascale Computing for Terascale Accelerator

Kwok Ko (PI, Stanford Linear Accelerator Center)

(10:25 am - 12:00 pm )

Introduction to MPI Programming:

Interactive lab session on a live cluster, laptop required with an SSH client.

Greg Bruno, Senior Programmer/Analyst, Rocks Development Team, San Diego Supercomputer Center

(1:30 pm - 2:15 pm)

Presentation of the 2006 Gordon Bell submission:

"A new planet in 7 days; A job for BlueGene/L"
Details of the 65,000 processor run on BG/L and post-processing of this large-scale simulation

Lee Shunn, Ali Mani, Steve Jones, Gianluca Iaccarino
(Center for Integrated Simulations, Stanford University)

(2:20 pm - 3:05 pm)

"An Overview of Research in High-Performance Computing in the Aeronautics & Astronautics and Mechanical Engineering Departments"

This talk will present an overview of a number of research projects currently being pursued at Stanford that rely on high-performance computing resources. The presentation will focus on the research programs, on the fundamental challenges in both modeling and algorithms, and on the changes in our research and software development practices as a result of a constantly evolving high-performance computing landscape that includes commodity clusters, GPUs and the IBM Cell processor.

Juan J. Alonso Department of Aeronautics & Astronautics Stanford University

(3:25 pm - 4:10 pm)

"Making a Galaxy one star at a time."

With a supercomputer, some new numerical techniques and a lot of physics we now can build galaxies one star at a time to compare with the ones in the observed universe.

Tom Abel (KIPAC), Professor, Department of Physics and SLAC

(4:15 pm - 5:00 pm)

Building a Vizcluster:
Greg Bruno
/UCSD, Steve Jones/Stanford


*** Lab Session ***

(9:20 am - 10:05 am)

Going parallel without C, Fortran and MPI using Star-P

Alan Edelman - Chief Science Officer, Interactive Supercomputing

 

(10:25 am - 12:00 pm)

Benchmarking Clusters for Optimal Performance:

Beginning to advanced topics including use of IMB (formerly Pallas), Stream, platform tweaks, hardware configurations. Bring your questions to the Intel Benchmarking guru!

John Benninghoff, Intel


(1:30 pm - 3:05 pm)

Intel Threading tools and Totalview:

Discussion and live demo on threading tools, compilers and Totalview for parallel debugging

Dr. Michael Wrinn, Intel (one of the developers of the OpenMP specification)


(3:25 pm - 5:00 pm)

Cluster OpenMP, Intel MPI and Trace Analyzer:

Discussion and live demo for many of Intel's software packages. Detailed discussions about parallelizing certain classes of applications that would be running in a distributed memory architecture such as a cluster.

Tom Lehmann, HPC Programs Office, Intel


*** Vendor Roadmap***

(10:25 to 11:10 room 127)

Dell HPC:

Roger Goff will be discussing current and future X86 architecture for high performance computing. Focus on future trends in large scale systems.

Roger Goff, DELL Enterprise Technologist for the HPC practice

(2:20 to 3:05 room 127)

Dell HPC:

Jim Skirvin will be discussing logistical and deployment consideration in deploying large scale systems. Reference will be on top 500 systems including Sandia National Lab, NCSA and Texas Advanced Computing Center.

Jim Skirvin, Business Development Manager for DELL's HPC practice

 

Sponsors:

The conference is free to academic, research and government affiliates. Open to affiliates
of conference sponsors. The conference is fully funded by the Dell and it's partners:

Cluster Corporation
http://www.clustercorp.com/
Dell
http://www.dell.com/hpcc
Panasas
http://www.panasas.com
Intel
http://www.intel.com/
APC
http://www.apc.com
Cisco
http://www.cisco.com
 

© Stanford University. All Rights Reserved. Stanford, CA 94305. (650) 723-2300. Terms of Use | Copyright Complaints