 |
Centers for Enabling Technologies
Overcoming technical challenges to enable effective use of Terascale and Petascale systemsDOE Program Managers
|
Centers for Enabling Technologies (CET) are interconnected multidisciplinary teams
that are coordinated with SciDAC Scientific Applications to address the Mathematical
and Computing Systems Software Environment elements of the SciDAC Scientific Computing
Software Infrastructure. This infrastructure envisions a comprehensive, integrated,
scalable, and robust high performance software environment, which overcomes difficult
technical challenges to quickly enable the effective use of terascale and petascale
systems by SciDAC applications. CETs address needs for: new algorithms which scale to
parallel systems having hundreds of thousands of processors; methodology for achieving
portability and interoperability of complex high performance scientific software packages;
operating systems and runtime tools and support for application execution performance
and system management; and effective tools for feature identification, data management
and visualization of petabyte-scale scientific data sets. CETs also address the Distributed
Science Software Environment elements of the SciDAC program.
In order to foster broad availability and use of CET-developed code, all CET applications
specified the type of open source license to be used and the mechanisms, including
web sites, workshops, and other community-based activities, that will be used to
disseminate information about CET software.
The SciDAC Centers for Enabling Technologies will focus on:
- Algorithms, methods, and libraries — Algorithms, methods and libraries that
are fully scalable to many thousands of processors with full performance portability
- Program development environments and tools — Component-based, fully integrated,
terascale and petascale program development and tools, which scale effectively and
provide maximum utility and ease of use to developers and scientific end users
- Operating system and runtime software and tools — Systems software that scales to
hundreds of thousands of processors, supports high performance application-level
communication, interoperability, optimization, and provides the highest levels of
fault tolerance, reliability, manageability, and ease of use for end users, tool
developers and system administrators
- Visualization and data management systems — Scalable, intuitive systems fully
supportive of SciDAC application requirements for moving, storing, analyzing, querying,
manipulating and visualizing multi-petabytes of scientific data and objects
- Distributed data management and computing tools — Scalable and secure systems for
the analysis of large volumes of data produced at experimental facilities, often
through complex workflows, and consumed by a large and distributed user community,
as well as end-to-end network tools and services to support high-end applications
Enabling Technologies Centers Announced in September 2006
Visualization and Data Management
Seeing the Unsee-able
Visualization and analytics software technology to increase scientific
productivity and create new possibilities for scientific insight
Principal Investigator: E. Wes Bethel
(ewbethel@lbl.gov)
Lawrence Berkeley National Laboratory
Getting the Science out of the Data
Scientific data management to help scientists spend more time studying
their results and less time managing their data
Principal Investigator: Arie Shoshani
(shoshani@lbl.gov)
Lawrence Berkeley National Laboratory
Applied Mathematics
Advancing Science via Applied Mathematics
Applied Partial Differential Equations to develop simulation tools for
solving multi-scale and multi-physics problems
Principal Investigator: Phillip Colella
(PColella@lbl.gov)
Lawrence Berkeley National Laboratory
Bigger and Better Simulations
Interoperable technologies for advanced petascale simulations to improve
accuracy and efficiency
Principal Investigator: Lori Diachin
(diachin2@llnl.gov)
Lawrence Livermore National Laboratory
Improving Application Performance at the Petascale
Towards optimal petascale simulations
Principal Investigator: David E. Keyes
(kd2112@columbia.edu)
Columbia University
Computer Science
Plug and Play Supercomputing
Common Component Architecture support facilitating software and programming
language interoperability, domain-specific common interfaces, and dynamic composability
Principal Investigator: David E. Bernholdt
(bernholdtde@ornl.gov)
Oak Ridge National Laboratory
Moving Mountains (of Data)
Enabling distributed petascale science
Principal Investigator: Ian Foster
(foster@mcs.anl.gov)
Argonne National Laboratory
Multi-core Compilers
Center for Scalable Application Development Software for Advanced Architectures
Principal Investigator: John Mellor-Crummey
(johnmc@cs.rice.edu)
Rice University
Sharing a World of Data
Scaling the Earth Systems Grid to Petascale Data to enable faster, easier
sharing of climate change research data
Principal Investigator: Dean N. Williams
(williams13@llnl.gov)
Lawrence Livermore National Laboratory
