PROGRAM AREA OVERVIEW --
ADVANCED SCIENTIFIC COMPUTING RESEARCH

 http://www.sc.doe.gov/ascr/mics/index.html

The Office of Advanced Scientific Computing Research (ASCR) supports research in computational technology and laboratory technology research, subprograms that underlie a variety of Department of Energy missions.

ASCR's primary mission, carried out by the Mathematical, Information, and Computational Sciences subprogram, is to discover, develop, and deploy the computational and networking tools that enable researchers in the scientific disciplines to analyze, model, simulate, and predict complex phenomena important to the Department of Energy. To accomplish this mission the program fosters and supports fundamental research in advanced scientific computing – applied mathematics, computer science, and networking – and operates supercomputer, networking, and related facilities. The applied mathematics research efforts provide the fundamental mathematical methods to model complex physical and biological systems.  The computer science research efforts enable scientists to efficiently run these models on the highest performance computers available and to store, manage, analyze, and visualize the massive amounts of data that result.  The networking research provides the techniques to link the data producers; e.g., supercomputers and large experimental facilities with scientists who need access to the data.

The Laboratory Technology Research subprogram funds high-risk, multidisciplinary research partnerships between the DOE’s Office of Science multi-program national laboratories and private industry.  Projects supported explore applications of basic research advances in the investigation of problems, over a full range of scientific disciplines, whose solutions have promising commercial potential.  

10. HIGH PERFORMANCE NETWORKS

The Department of Energy (DOE) supports a wide range of research activities in mathematics, information, and computational sciences to accelerate scientific discoveries. This topic addresses research needs in high-performance networks to support distributed high-end computing, remote instrumentation, and data storage; and large-scale, secure, scientific collaboration.  Emerging science experiments sponsored by the DOE are expected to generate several petabytes of data, which will be transferred to geographically distributed terascale computing facilities for analysis and visualization by thousands of scientists.  This requirement calls for networks with unprecedented capabilities – networks that, unlike today’s commercial networks, can securely deliver multi-Gigabits/sec throughput to high-end scientific applications.  Therefore, grant applications must propose advanced network technologies that can operate at 10 Gbps and beyond.  Additional information on the DOE networking requirement can be obtained in the network research sections of a DOE network planning workshop report available at: http://doecollaboratory.pnl.gov/meetings/hpnpw/finalreport/.  Grant applications are sought only in the following subtopics:

a.  Ultra High-Speed Network Components – The new vision of grid-based scientific computing in the DOE environment calls for network infrastructures with unprecedented capabilities to support its science mission.  These networks are envisioned to deliver multi-Gbps (10-100 Gbps) throughputs to distributed applications.  The network infrastructures will require advanced network technologies that are radically different from those used in today commercial networks, including the Internet.  Grant applications are sought to develop ultra high-speed network components (both hardware and software) that can deliver multi-gigabits/sec throughput to high-end scientific applications.  Components of interest include, but are not limited to: (1) cost effective 10 Gbps interfaces for GigE (Gigabit Ethernet) or OC-192 (Optical Carrier level 192), (2) dedicated channel sharing and scheduling, (3) Transmission Control Protocol (TCP) extensions for ultra high-speed data transfers, (4) scalable non-TCP transport protocols, OS-bypass for wide-area networks, and (5) ultra high-speed network security systems that include firewalls and intrusion detection systems.

b.  Traffic Engineering for Ultra High-Speed Network – Grant applications are also sought to develop scalable efficient techniques for modeling and controlling complex traffic processes in ultra high-speed networks dominated by a few very large traffic flows.  For this purpose, grant applications must focus on the development of scalable tools, techniques, and services for traffic engineering in ultra high-speed networks (10 – 40 Gbps end-to-end).  Areas of interest include, but are not limited to:  (1) scalable end-to-end network measurement and analysis tools and services, (2) innovative tools and services for predicting network performance and controlling large traffic flows, (3) advanced tools for modeling complex traffic patterns in packet-switched and agile lambda-switched networks, and (4) advanced simulation tools and techniques for very high-speed networks.  Scalability issues associated with proposed approaches must be addressed by demonstrating how the resulting system will be operated at 10 GigE and OC-192.

References: 

1.      DOE Science Networking Challenge:  Roadmap to 2008, Report of the DOE Science Networking Workshop, Reston, VA, June 3-5, 2003 ,U.S.DOE Office of Science, 2003.  (Full text available at:  http://gate.hep.anl.gov/lprice/Roadmap/index.html)  

2.      ESnet (The Energy Sciences Network), U.S. DOE Office of Science, http://www.es.net  

3.      High Performance Networks for High Impact Science, Final Report of the High Performance Network Planning Workshop, Reston, VA, August 13-15, 2002, U.S. DOE Office of Science, 2003.  (Full text available at:  http://doecollaboratory.pnl.gov/meetings/hpnpw/finalreport/)  

4.      The NET100 Project:  Towards Network-Aware Operating Systems, http://www.net100.org/  

5.      Awduche, D., et al., Multi-Protocol Lambda Switching:  Combining MPLS Traffic Engineering Control with Optical Crossconnects, Internet Engineering Task Force Internet Draft – a work in progress.  (URL:  http://www.globecom.net/ietf/draft/draft-awduche-mpls-te-optical-01.html )  

6.      IEEE P802.3ae 10Gb/s Ethernet Task Force, IEEE, Inc., March 2002, http://grouper.ieee.org/groups/802/3/ae/public/index.html  

7.      IETF RFC2823: PPP Over Simple Data Link (SDL) Using SONET/SDH with ATM-Like Framing
Internet Society, May 2000, http://www.faqs.org/rfcs/rfc2823.html  

8.      NITRD:  National Coordination Office for Information Technology Research and Development
http://www.itrd.gov  

9.      Networked Computing for the 21st Century, FY 1999 Blue Book, Washington , DC :  National Science and Technology Council, August 1998.  (Available at:  http://www.itrd.gov.  On the left menu, select "Publications." Under “Current/Past Publications,” click on "Supplement to the President's Budget," and then on “FY 1999 Blue Book.”)  

10.  About the NGI (Next Generation Internet), http://ngi.gov  

11.  QBONE (Cooperative Advanced Quality of Service Testbed), http://qbone.internet2.edu/  

12.  Rajagopalan, B., et al., IP Over Optical Networks:  A Framework, Internet Engineering Task Force Internet Draft, a work in progress.  (URL:  http://www.cs.utk.edu/~moore/ID-PDF/draft-many-ip-optical-framework-03.pdf )  

13.  U.S. Department of Energy, Office of Science, http://www.science.doe.gov

11. SCALABLE MIDDLEWARE AND GRID TECHNOLOGIES

Advances in high performance network capabilities and collaboration technologies are making it easier for large geographically dispersed teams to collaborate effectively.  This is especially important for research teams that use major computational resources, data resources, and experimental facilities supported by DOE.  The importance of collaboratories is expected to increase in the future.  However, significant research questions must be addressed if collaboratories are to achieve their potential, namely, by providing:  (1) remote access to facilities that produce petabytes/year; (2) remote users with an experience that approaches "being there;" (3) remote visualization of terabyte to petabyte data sets from computational simulation; and (4) effective remote access to advanced scientific computers.  Research and software tool development are needed to support coordinated and dynamic resource sharing in areas such as resource discovery, resource access, authentication, authorization, accounting, etc., in the areas listed below.  Any tools or services developed should be interoperable according to emerging standards from the Global Grid Forum.  Grant applications are sought only in the following subtopics:

a.      Scalable Middleware Technologies – Grant applications are sought to develop scalable middleware technologies that will: (1) enable universal, ubiquitous, easy access to remote computing resources and scientific instruments; (2) facilitate collaboration among distributed science teams; and (3) enable a new generation of distributed high-end applications.  Areas of interest include, but are not limited to, secure directory services, scalable authentication/authorization services, deployable LAN and WAN QoS services, wide-area distributed data management, efficient multicast capabilities, automatic resource discovery protocols, remote data access services, and network-attached memory and storage systems.

b.      Scalable Grid Technologies – Grant applications are sought to develop scalable grid technologies to support the emerging distributed computing network that provides dependable, consistent, pervasive, scaleable, and efficient access to various resources integrated into a distributed infrastructure that can be accessed wherever and whenever by DOE scientists.  These resources include visualization systems, computer systems, data storage and archive systems, and scientific instruments.  Areas of interest include, but are not limited to, collaborative visualization systems, collaborative problem solving services, application level fast data transfer toolkits, real-time analysis, group collaboration, co-scheduling of distributed resources, grid accounting and billing mechanisms, data management tools, science portals, on-line instrumentation, and fast data transfer management services. 

References:

1.      U.S. DOE Collaboratories , U.S. DOE Office of Science, http://doecollaboratory.pnl.gov  

2.      Foster, I. and Kasselman, C., eds., The Grid:  Blueprint for a New Computing Infrastructure, San Francisco , CA :  Morrgan Kaufmann Publishers, 1999.  (ISBN: 1-55860-475-8)  

3.      Berman, F., et al., eds., Grid Computing:  Making the Global Infrastructure a Reality, John Wiley & Sons, 2003. (ISBN 0-470-85319-0) (Resource site at:  http://www.grid2002.org)  

4.      Global Grid Forum (GFF), http://www.globalgridforum.com/  

5.      The Globus Project:  Related Papers, http://www.globus.org/research/papers.html  

6.      Particle Physics Data Grid, U.S. DOE Office of Science, http://www.ppdg.net  

7.      Earth System Grid Project, U.S. DOE Office of Science, http://www.earthsystemgrid.org/

8.      National Fusion Grid Project, U.S. DOE Office of Science, http://www.fusiongrid.org  

9.      SciDAC (Scientific Discovery through Advanced Computing), U.S. DOE Office of Science
http://www.osti.gov/scidac  

10.  U.S. Department of Energy, Office of Science, http://www.science.doe.gov/

12. TECHNOLOGY FOR SOFTWARE LIBRARIES

The Advanced Scientific Computing Research (ASCR) program has been fully or partially responsible for funding the research and development of a wide range of robust high-quality numerical algorithms for scientific computation.  These include the development of libraries such as EISPACK, LINPACK, LAPACK, ScaLAPACK, ARPACK, CLAWPACK, PETSc, TAO, CHOMBO, ebCHOMBO, SALSA, MPSALSA, LOCA, HYPRE, SuperLU, FronTier, and many others.  However, critical issues still require resolution to ensure that the value of such scientific software is maintained and that the large investment in the research and development of these algorithms is maximized.  These issues include enhancing user interfaces, providing distribution support, providing maintenance activities such as collecting and tracking bug reports, fixing bugs, and providing portability across platforms (including porting to new computational architectures).  Grant applications are sought only in the following subtopic:

a.  Deployment and Maintenance of Robust Numerical Software Libraries – Grant applications are sought to:  (1) develop new maintenance and distribution mechanisms to ensure that updated scientific libraries are subjected to validation and verification testing; (2) implement formal tracking mechanisms for bug reports, bug fixes, and update notification for a wide range of scientific algorithm libraries; (3) develop and maintain mechanisms for providing cost effective portability of scientific libraries across a wide range of computer architectures, from desktop systems to massively parallel leadership-class supercomputers; (4) develop and maintain high-quality user documentation for each component of scientific software, including advice on domains of applicability for each module; and (5) develop comprehensive email- or web-based user support services for scientific libraries.  The ASCR program will assure that successful grant applicants will obtain access to relevant computational facilities, as needed for their research.

References:

1.      Anderson, E., et al., LAPACK Users' Guide, 2nd ed., Philadelphia, PA:  Society for Industrial and Applied Mathematics (SIAM), 1995.  (ISBN: 0-89871-345-5)  

2.      Dongarra J. and Walker, D., “Software Libraries for Linear Algebra Computations on High Performance Computers,” SIAM Review, 37:151-180, 1995.  (ISSN: 0036-1445)  

3.      Dongarra, J. J., et al., “Algorithm 679:  A Set of Level 3 Basic Linear Algebra Subprograms,” ACM (Association for Computing) Transactions on Mathematical Software, 16(1):18-28, March 1990.  (ISSN: 0098-3500)  

4.      Dongarra, J. J., et al., “Algorithm 656:  An Extended Set of FORTRAN Basic Linear Algebra Subroutines,” ACM Transactions on Mathematical Software, 14(1):18-32, March 1988.  (ISSN: 0098-3500)  

5.      Geist, A., ed., et al., PVM:  Parallel Virtual Machine. A Users' Guide and Tutorial for Networked Parallel Computing, Cambridge, MA:  MIT Press, 1994.  (ISBN: 0262571080)  

6.      Hwang, K., Advanced Computer Architecture:  Parallelism, Scalability, Programmability, McGraw-Hill, 1993.  (ISBN: 0-07-031622-8)  

7.      Koebel, C., et al., The High Performance Fortran Handbook, Cambridge, MA:  MIT Press, 1994.  

8.      Pollicini, A. A., Using Toolpack Software Tools, Kluwer Academic Publishers, 1989.  (ISBN: 0-7923-0033-5)  

9.      Blackford, L. S., et al., The ScaLAPACK Users Guide, Philadelphia , PA :  SIAM , 1997.  (ISBN: 0-89871-397-8)  

10.  Smith, B. T., et al., “Matrix Eigensystem Routines,” EISPACK Guide Lecture Notes in Computer Science, 2nd ed., Vol. 6, Springer-Verlag, 1976.  (ISBN: 0-38707-546-1)  

11.  Lehoucq, R. B., et al., ARPACK Users Guide:  Solution of Large-Scale Eigenvalue Problems with Implicitly Restarted Arnoldi Methods, Philadelphia , PA :  SIAM , 1998.  (ISBN: 0-89871-407-9)  

12.  Balay, S., et al., “Efficient Management of Parallelism in Object Oriented Numerical Software Libraries,” in Modern Software Tools in Scientific Computing, pp. 163-202, Birkhauser Press, 1997.  (ISBN: 0-8176-3974-8).  

13.  Balay, et al., PETSc Users Manual, Argonne National Laboratory, 2002.  (Report No. ANL-95/11 - Rev. 2.1.6) (Full text available at:  http://www-unix.mcs.anl.gov/petsc/petsc-2/snapshots/petsc-current/docs/manual.pdf)  

14.  LeVeque, R. J., Finite Volume Methods for Hyperbolic Problems, Cambridge University Press, 2002.  (ISBN: 0521009243)  

15.  Benson, S., et al., TAO Users Manual, Technical Report, Argonne National Laboratory, 2003.  (Report No. ANL/MCS-TM-242-Revision 1.5) (Full text available at:  http://www-unix.mcs.anl.gov/tao/docs/manual/manual.html)  

16.  Shadid, J., et al., MPSalsa Version 1.5:  A Finite Element Computer Program for Reacting Flow Problems: Part 1 – Theoretical Development, Technical Report, Sandia National Laboratories, 1998.  (Report No. SAND98-2864) (NTIS Order No. DE00002641.  See Solicitation General Information and Guidelines, section 7.1.)  

17.  Salinger, A. G., et al., LOCA 1.1:  Library Of Continuation Algorithms:  Theory and Implementation Manual, Technical Report, Sandia National Laboratories, October 2002.  (Report No. SAND2002-0396) (Full text available at:  http://www.cs.sandia.gov/loca/loca1.1_book.pdf)  

18.  Falgout, R. D., and Yang, U. M., “Hypre:  a Library of High Performance Preconditioners,” in Computational Science - ICCS 2002 Part III, Sloot, P. M., et al., eds., Springer-Verlag, 2002.  (For ordering information and to view abstract, see Lecture Notes in Computer Science, 2331:632-641 at:  http://www.springer.de/comp/lncs/.) (Also available as Lawrence Livermore National Laboratory technical report UCRL-JC-146175.)