| [an error occurred while processing this directive] |
SciDAC ISICs 2002 Seminar SeriesSeven
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
Seminar Announcements and AbstractsWednesday, 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. |
|||||||||||||||||||||||||||||||||