[an error occurred while processing this directive]
[an error occurred while processing this directive]    

SciDAC ISICs 2002 Seminar Series


Seven Integrated Software Infrastructure Centers (ISICs) were created as part of the initial round of the DOE's Scientific Discovery through Advanced Computing (SciDAC) program. As stated in the call for proposals,

The software infrastructure vision of SciDAC is for a comprehensive, portable, and fully integrated suite of systems software and tools for the effective management an utilization of terascale computational resources...

Though clearly intended to support SciDAC applications, the tools which are planned have much broader utility.

The purpose of this seminar series is to offer ORNL researchers an overview of the centers and their research plans, so that they can make connections with relevant ISIC people and activities and use the ISICs' products to enhance their own research.

For further information about the seminar series, please contact David Bernholdt

The SciDAC ISICs

Center (Acroynms)
Lead PI
Local PIs
Seminar Date
Center for Component Technology for Terascale Simulation Software (CCTTSS, CCA)
Rob Armstrong, SNL
David Bernholdt , Jim Kohl
20 March 2002
Algorithmic and Software Framework for Applied Partial Differential Equations (APDEC)
Phil Colella, LBNL none
9 April 2002
High-End Computer System Performance: Science and Engineering (PERC)
David Bailey, LBNL
Pat Worley
TBD
Scalable Systems Software Center (SSS)
Al Geist, ORNL
Al Geist
TBD
Scientific Data Management Center (SDM)
Arie Shoshoni, LBNL
Randy Burris , Tom Potok , Nagiza Samatova
TBD
Terascale Optimal PDE Simulations Center (TOPS)
David Keyes, Old Dominion
Jack Dongarra , Victor Eijkhout (UT)
TBD
Terascale Simulation Tools and Technology Center (TSTT)
Jim Glimm, SUNY-Stony Brook
Ed D'Azevedo
TBD

Seminar Announcements and Abstracts

Wednesday, 20 March 2002, 10:00am, 6010/Conference Room

Component-Based Software for High-Performance Computing: An Introduction to the Common Component Architecture

David E. Bernholdt, ORNL

The  Common  Component  Architecture  (CCA)  is  an approach to the component-based  development  of  software targeted specifically to the needs of high-performance (teracale and beyond) simulations. Components  allow  software  developers  to  describe  the  calling interfaces of libraries  and  applications  in  a  manner  that  hides  low-level details,  such  as  the  implementation  language,  parallelism, or location  on  a  network.  Components capsulate  the  knowledge, experience, and work of other scientists, and they provide building blocks  that  speed  application  development.   I will outline the ideas  behind  component-based software development and explain the important features of CCA's approach to the problem.


Tuesday 9 April 2002, 10:00am, 6010/Conference Room

Adaptive Mesh Refinement for Multiphysics Problems

Phillip Colella, Lawrence Berkeley National Laboratory

In this talk, we will discuss a variety of algorithmic ideas that arise in extending the block-structured adaptive mesh refinement approach of Berger and Oliger to time-dependent problems in which a mixture of elliptic, parabolic and hyperbolic behaviors appear, such as in imcompressible fluid flows, coupled fluid dynamics and radiation, and low-Mach-number combustion. Some of the issues to be addressed include the formulation of appropriate coarse-fine matching conditions;  the influence of refinement in time on matching conditions for elliptic and parabolic problems, and on free-stream preservation; and error estimators at refinement boundaries.



[an error occurred while processing this directive]