[Federal Register Volume 65, Number 244 (Tuesday, December 19, 2000)]
[Notices]
[Pages 79350-79354]
From the Federal Register Online via the Government Publishing Office [www.gpo.gov]
[FR Doc No: 00-32251]


-----------------------------------------------------------------------

DEPARTMENT OF ENERGY


Office of Science Financial Assistance Program Notice 01-06: 
Scientific Discovery Through Advanced Computing: National 
Collaboratories and High Performance Networks

AGENCY: U.S. Department of Energy.

ACTION: Notice inviting grant applications.

-----------------------------------------------------------------------

SUMMARY: The Office of Advanced Scientific Computing Research (ASCR) of 
the Office of Science (SC), U.S. Department of Energy (DOE), hereby 
announces its interest in receiving applications for grants in support 
of the National Collaboratories and High Performance Networks Programs, 
which include scope supportive of the Scientific Discovery through 
Advanced Computing Initiative. Collaboratories link geographically 
dispersed researchers, data, and tools via high performance networks to 
enable remote access to facilities, access to large datasets, shared 
environments, and ease of collaboration. This announcement is focused 
on research and development to support DOE-specific activities in three 
areas: (1) High performance middleware services that include, but are 
not limited to, software to allow applications to adapt to changing 
network conditions and software that provides ease of collaboration for 
distributed teams; (2) innovative, high performance network research 
that includes, but is not limited to, high performance transport 
protocols, network measurement and analysis, and traffic engineering 
tools and services which are focused on improving the end-to-end 
performance for data intensive scientific applications; and (3) 
collaboratories to test and validate the enabling technologies for 
discipline-specific applications. Collaborations across organizations 
that include networking researchers, middleware developers and 
discipline-specific scientists are encouraged. The full text of Program 
Notice 01-06 is available via the Internet using the following web site 
address: http://www.science.doe.gov/production/grants/grants.html.

DATES: Preapplications referencing Program Notice 01-06 should be 
received by January 31, 2001. Formal applications in response to this 
notice should be received by 4:30 p.m., E.S.T., March 15, 2001, to be 
accepted for merit review and funding in FY 2001.

ADDRESSES: Preapplications referencing Program Notice 01-06 should be 
sent via e-mail using the following address: 
[email protected]. Formal applications referencing Program 
Notice 01-06, should be forwarded to: U.S. Department of Energy, Office 
of Science, Grants and Contracts Division, SC-64, 19901 Germantown 
Road, Germantown, MD 20874-1290, ATTN: Program Notice 01-06. This 
address must be used when submitting applications by U.S. Postal 
Service Express Mail or any commercial mail delivery service, or when 
hand-carried by the applicant.

FOR FURTHER INFORMATION CONTACT: For further information on this notice 
contact: National Collaboratories: Dr. Mary Anne Scott, Office of 
Advanced Scientific Computing Research, SC-31, Office of Science, U.S. 
Department of Energy, 19901 Germantown Road, Germantown, MD 20874-1290, 
telephone: (301) 903-6368, e-mail: [email protected].
    High Performance Networks: Dr. Thomas D. Ndousse, Office of 
Advanced Scientific Computing Research, SC-31,

[[Page 79351]]

Office of Science, U.S. Department of Energy, 19901 Germantown Road, 
Germantown, MD 20874-1290, telephone: (301) 903-9960, e-mail: 
[email protected].

SUPPLEMENTARY INFORMATION:

Background: Scientific Discovery Through Advanced Computing

    Advanced scientific computing will be a key contributor to 
scientific research in the 21st Century. Within the Office of Science 
(SC), scientific computing programs and facilities are already 
essential to progress in many areas of research critical to the nation. 
Major scientific challenges exist in all SC research programs that can 
best be addressed through advances in scientific supercomputing--
designing materials with selected properties, elucidating the structure 
and function of proteins, understanding and controlling plasma 
turbulence, and designing new particle accelerators. To help ensure its 
missions are met, SC is bringing together advanced scientific computing 
and scientific research in an integrated program entitled ``Scientific 
Discovery Through Advanced Computing.''

The Opportunity and the Challenge

    Extraordinary advances in computing technology in the past decade 
have set the stage for a major advance in scientific computing. Within 
the next five to ten years, computers that are 1,000 times faster than 
today's computers will become available. These advances herald a new 
era in scientific computing. Using such computers, it will be possible 
to dramatically extend our exploration of the fundamental processes of 
nature (e.g., the structure of matter from the most elementary 
particles to the building blocks of life) as well as advance our 
ability to predict the behavior of a broad range of complex natural and 
engineered systems (e.g., the earth's climate or an automobile engine).
    To exploit this opportunity, these computing advances must be 
translated into corresponding increases in the performance of the 
scientific codes used to model physical, chemical, and biological 
systems. This is a daunting problem. Current advances in computing 
technology are being driven by market forces in the commercial sector, 
not by scientific computing. Harnessing commercial computing technology 
for scientific research poses problems unlike those encountered in 
previous supercomputers, in magnitude as well as in kind. As noted in 
the 1998 repor t\1\ from the NSF/DOE ``National Workshop on Advanced 
Scientific Computing'' and the 1999 report \2\ from the President's 
Information Technology Advisory Committee, this problem will only be 
solved by increasing investments in computer software--in research and 
development on scientific simulation codes as well as on the 
mathematical and computing systems software that underlie these codes.
---------------------------------------------------------------------------

    \1\ This workshop was sponsored by the National Science 
Foundation and the Department of Energy and hosted by the National 
Academy of Sciences on July 30-31, 1998. Copies of the report may be 
obtained from: http://www.er.doe.gov/production/octri/mics/index.html
    \2\ Copies of the PITAC report may be obtained from: http://www.ccic.gov/ac/report/.
---------------------------------------------------------------------------

Investment Plan of the Office of Science

    To meet the challenge posed by the new generation of terascale 
computers, SC will fund a set of coordinated investments as outlined in 
the long plan for scientific computing, Scientific Discovery through 
Advanced Computing,\3\ submitted to Congress on March 30, 2000. First, 
it will create a Scientific Computing Software Infrastructure that 
bridges the gap between the advanced computing technologies being 
developed by the computer industry and the scientific research programs 
sponsored by the Office of Science. Specifically, the SC effort 
proposes to:
---------------------------------------------------------------------------

    \3\ Copies of the SC computing plan, Scientific Discovery 
through Advanced Computing, can be downloaded from the SC web site 
at: http://www.sc.doe.gov/production/octr/index.html.
---------------------------------------------------------------------------

     Create a new generation of Scientific Simulation Codes 
that take full advantage of the extraordinary computing capabilities of 
terascale computers.
     Create the Mathematical and Computing Systems Software to 
enable the Scientific Simulation Codes to effectively and efficiently 
use terascale computers.
     Create a Collaboratory Software Environment to enable 
geographically separated scientists to effectively work together as a 
team and to facilitate remote access to both facilities and data.
    These activities will be supported by a Scientific Computing 
Hardware Infrastructure that has been tailored to meet the needs of its 
research programs. The Hardware Infrastructure is robust, to provide 
the stable computing resources needed by the scientific applications; 
agile, to respond to innovative advances in computer technology that 
impact scientific computing; and flexible, to allow the most 
appropriate and economical resources to be used to solve each class of 
problems. Specifically, the SC proposes to support:
     A Flagship Computing Facility, the National Energy 
Research Scientific Computing Center (NERSC), to provide the robust, 
high-end computing resources needed by a broad range of scientific 
research programs.
     Topical Computing Facilities to provide computing 
resources tailored for specific scientific applications and to serve as 
the focal point for an application community as it strives to optimize 
its use of terascale computers.
     Experimental Computing Facilities to assess the promise of 
new computing technologies being developed by the computer industry for 
scientific applications.
    Both sets of investments will create exciting opportunities for 
teams of researchers from laboratories and universities to create new 
revolutionary computing capabilities for scientific discovery.

The Benefits

    The Scientific Computing Software Infrastructure, along with the 
upgrades to the hardware infrastructure, will enable laboratory and 
university researchers to solve the most challenging scientific 
problems faced by the Office of Science at a level of accuracy and 
detail never before achieved. These developments will have significant 
benefit to all of the government agencies who rely on high-performance 
scientific computing to achieve their mission goals as well as to the 
U.S. high-performance computing industry.

Background: National Collaboratories and High Performance Networks

    The current core programs in ASCR are intended to enhance the 
Department's ability to satisfy mission requirements through advanced 
technologies such as distributed computing, national collaboratories, 
high performance networks, remote access to facilities, and remote 
access to petabyte-scale datasets with complex internal structure. 
Within this context, the National Collaboratories and High Performance 
Networks Programs provide a coordinated program of technology research 
and development that leverages the strengths of computer and 
computational science research programs and partners with science 
application pilot projects. Likewise, these programs support the 
Scientific Discovery through Advanced Computing by enabling integration 
of multi-institutional, geographically-dispersed researcher into 
effective, efficient teams and by providing

[[Page 79352]]

distributed computing environments and tools to support the use of 
remote computers and access to data and facilities.
    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 the 
teams using the major computational resources, data resources, and 
experimental facilities supported by DOE. With leadership from DOE, 
these geographically distributed laboratories or collaboratories have 
begun to play an important role in the Nation's scientific enterprise. 
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, to enable 
remote access facilities that produce petabytes/year; to provide remote 
users an experience that approaches the same as ``being there;'' to 
provide remote visualization of terabyte to petabyte data sets from 
computational simulation; and to enable effective remote access to 
advanced scientific computers.
    Solving the challenging network and distributed computing problems 
calls for new modalities of scientific research. Many scientific 
applications when deployed on existing networks fail to meet the end-
to-end expectations for performance. This is especially true for 
distributed high-end applications such as remote visualization and high 
capacity data transfer. Recent advances in optical networks brought 
about by Dense Wave Division Multiplexing (DWDM) are resulting in 
unprecedented increases for bandwidth in the core networks. However, 
many challenging protocol engineering, traffic engineering, and high-
performance middleware problems must be addressed before complex 
scientific high-end applications and collaboratories can benefit from 
this increase in bandwidth. Harnessing this bandwidth at the 
application level poses some important and challenging problems.
    Research is needed to understand what services collaboratories 
require and how these services should be integrated with the large 
number of network devices and network-attached devices that must work 
together. Examples of the components and services that need to be 
integrated include: data archives on tape, high performance disk 
caches, visualization and data analysis servers, authentication and 
security services, directory services, network resources, and 
computational systems including the computer on a scientist's desk. All 
of these physical and software services must be tied together by common 
software framework building blocks or ``middleware'' to enable the 
collaboratories of the future to succeed.
    Further, at the network level, research is needed for advanced 
services to develop advanced network services and tools to deliver high 
end-to-end performance to distributed scientific applications. There 
are several areas that can contribute to improving the end-to-end 
performance for secure multi-gigabits/sec transport that some of DOE's 
advanced scientific applications require. These include: enhancement of 
existing transport protocols, the development of accurate measurement 
and analysis techniques, and the network services that can provide 
online performance predictions.
    These challenges will be addressed through an integrated program of 
fundamental research in high performance networking and collaboratory 
technologies in partnership with key scientific disciplines that 
provide the applications--the research may be focused for short-term 
results (within three years) or long term (five-years and greater). 
This announcement seeks applications in three areas:
    1. Middleware: research and development projects that will address 
individual technology elements to enable universal, ubiquitous, easy 
access to remote resources or that will contribute to the ease with 
which distributed teams work together. Enabling high performance for 
scientific applications is an important consideration.
    2. Collaboratory Pilots: research and development of enabling 
technologies that is integrated with and required by distributed 
scientific applications. An example of such a distributed application 
is the real-time data acquisition, reduction and visualization for 
macromolecular crystallography using a high intensity X-ray light 
source facility remotely. Another distributed application could be an 
extensive network measurement and analysis infrastructure employed to 
diagnose and predict end-to-end performance.
    3. High Performance Network Engineering: research, development, and 
testing of advanced network protocols, traffic engineering, and network 
services that can significantly improve capabilities, end-to-end 
performance, and controllability of networks infrastructures designed 
to support distributed scientific applications.
    To the extent that software and/or infrastructure development is 
involved, all applications to this notice should address the issues 
that characterize a successful research lifecycle. That is, technology 
transfer strategies should be provided for the transition of research 
code and/or infrastructure into robust production. Long term software 
evolution and maintenance and end user support should also be 
considered.
    Integration of work efforts across all projects funded under this 
notice will occur following the awards, to preclude duplication of 
effort and to maximize leveraging and coordination. Projects are 
expected to work closely with other SciDAC teams, where identified 
during this integration. Coordination through a participatory 
management process will continue for the life of the projects.

(See http://doecollaboratory.pnl.gov/ for a list of currently funded 
projects in National Collaboratories and background of the program that 
began as the DOE 2000 Initiative.)

(See http://www.er.doe.gov/production/octr/mics/network--research.htm. 
For background on the High Performance Networks Program.)

Solicitation Emphasis Areas

    1. Middleware technology research and development projects are to 
have certain characteristics. Products of this research and development 
are expected to provide services that interoperate and feature common 
interfaces. It should be easy to learn and use the tools. Applications 
in response to this notice should delineate an effective strategy for 
coupling with requirements from the scientific applications of the 
potential collaboratories. Applications in response to this notice 
should also provide a plan for software maintenance and support.
    Middleware technology research and development projects that enable 
collaboration may focus on providing a broad set of tools or toolkits 
to support, but are not limited to, the following areas of interest:
     Collaborative Visualization.
     Collaborative Problem Solving Environments.
     Real-time Analysis.
     Group Collaboration.
     Data Management.
     Science Portals.
     On-line Instrumentation.
     Data Grids.
    In addition, middleware technology research and development 
projects may address standard services and protocols that are needed to 
enable persistent, universal, and ubiquitous access to networked 
resources, such as, but are not limited to, the following:

[[Page 79353]]

     Directory Services.
     Authentication/Authorization Services.
     Co-scheduling Distributed Resources.
     Multicast and efficient broadcast capabilities.
     Automatic resource discovery protocols.
     Remote data access services.
     Network-attached memory and storage systems.
     Communications services.
    For middleware technology research and development projects, it is 
estimated that between four and eight awards could be made in FY 2001, 
contingent upon the availability of appropriated funds. The scope of a 
single-focus project is expected to range from $150K to $500K.
    Collaboratory pilots should have certain characteristics. The 
project should:
     Address a problem of national scientific or engineering 
significance clearly related to the mission of DOE and have high 
visibility.
     Involve geographically separated groups of personnel and/
or facilities that are inherently required to collaborate or be used 
remotely for success of the project.
    The project may:
     Focus on developing and providing a set of middleware 
services needed by a broad set of applications requiring distributed 
computing capabilities.
     Focus solely on advanced network development and testing 
such as a measurement and analysis infrastructure to accurately 
measure, calibrate, diagnose performance related problems, and predict 
the end-to-end performance of operational high-speed networks.
    All responses to this notice must provide a plan for transition to 
sustaining activities and services for end users on completion of the 
project. The scope of a collaboratory pilot is expected to be about 
$0.5M to $2.5M total per year. This is the total for all the 
institutions participating and it is expected that a single institution 
would be funded at a level of no more than $600K. It is estimated that 
three to five awards will be made for this area during FY 2001.
    It is also possible for middleware technology research and 
development projects and/or collaboratory pilots to address an element 
for evaluating systems and their impact on the process of science, 
namely identifying factors that facilitate or impede the adoption of 
technology.
    2. High Performance Network Engineering is key to the DOE vision of 
collaborative scientific research environments in which geographically 
distributed research teams and computing resources are interconnected 
to form a virtual computing research environment. Emerging high-end 
scientific applications, when deployed on existing networks, fail to 
meet the expected end-to-end performance, latency, security, and 
guaranteed quality of service required for complex scientific 
investigations. The high-performance network program addresses these 
challenges in the current announcement by focusing in three major 
research areas of high performance network engineering:
     Network Measurement and Analysis: Focuses on the 
fundamental issues of end-to-end performance through measurement and 
analysis.
     High-performance Transport Protocols: Addresses the 
performance and security enhancement issues of traditional protocols 
operating in high-speed, high-performance networks.
     Advanced Traffic Engineering Tools And Services: Deals 
with advanced tools and service for managing, differentiating, and 
controlling network traffic in order to satisfy the end-to-end 
performance objectives.
    (a) Network Measurement and Analysis: Applications may address 
innovative scalable network measurement and analysis infrastructures, 
tools, services, etc., that can be used to accurately measure, 
calibrate, diagnose performance related problems, and predict the end-
to-end performance of operational high-speed network networks. This may 
involve passive and active measurement, SNMP derived data, or a 
combination and may include, but not be limited to, the following:
     Bandwidth estimation techniques for high-speed links (OC-
12, OC-48).
     Measurement infrastructures to collect, store, and analyze 
traffic traces.
     Distributed agent architecture for network measurement and 
analysis.
     On-line analysis and data mining of measured data.
     Dynamic end-to-end path selection based on online 
analysis.
     Measurement and calibration of transport protocol 
performance.
    Applications focusing on measurement and analysis infrastructures 
are expected to work in close collaboration with DOE's Energy Science 
Network (ESnet) in the deployment measurement facilities. A network 
research testbed facility has been established, with the cooperation of 
ESnet, for experimental network research activities. Researchers 
requiring the use of this experimental facility are encouraged to work 
closely with the ESnet Research Support Subcommittee (ESRSC) chartered 
to coordinate the activities of the testbed. A complete description of 
this experimental facility can be found at http://www.es.net.
    (b) High-Performance Transport Protocols: The performance 
expectation for the delivery of multi-gigabits/sec throughput to 
distributed scientific applications far exceeds the capability of 
current networks. This performance expectation raises some fundamental 
questions concerning the capability of conventional routing protocols 
optimized for low-speed, best-effort traffic. The current announcement 
addresses transport protocol performance issues by seeking innovative 
approaches that may include but are not be limited to the following:
     Transport protocol measurement, tuning, and calibration 
tools.
     Adaptive extensions of transport protocols for high-speed 
networks.
     High-performance network traffic characterization.
     Transport protocol parallelization at high-speed.
    The objective is to reduce the contribution of transport protocol 
on end-to-end congestion. Potential applications must provide a sound 
mathematical analysis of the proposed enhancements when subjected to 
high-end scientific applications that potentially exercise its 
important features.
    (c) Advanced Traffic Engineering Tools and Services: Addresses the 
resource and performance optimization of high-performance and high-
speed networks, including advanced traffic management and control 
strategies, services, and tools that can be used for traffic 
differentiation and for steering traffic. Applications may focus on, 
but are not limited to, the following:
     QoS-based routing and source routing.
     Dynamic routing and traffic control.
     Congestion notification and avoidance.
     Bandwidth brokering services.
     Advanced traffic management tools and services.
     Simulation of large traffic flows.
    Applications addressing these and other related issues should 
concentrate on those activities that lead to a significant improvement 
in end-to-end performance of applications running across high 
performance networks.
    The high-performance network research program anticipates funding 
projects in these three areas in FY 2001. It should also be noted that 
a collaboratory pilot (as discussed under

[[Page 79354]]

section 2.) may focus solely on advanced network development and 
testing such as a measurement and analysis infrastructure to accurately 
measure, calibrate, diagnose performance related problems, and predict 
the end-to-end performance of operational high-speed networks. The 
scope of a single project is expected to range from $150K to $500K.

Preapplications

    Potential applicants are strongly encouraged to submit a brief 
preapplication that consists of two to three pages of narrative 
describing the research objectives and technical approach(s). 
Preapplications will be reviewed relative to the scope and research 
needs of the ASCR National Collaboratories and High Performance 
Networks Programs, as outlined in the summary paragraph and in the 
SUPPLEMENTARY INFORMATION. The preapplication should identify, on the 
cover sheet, the title of the project, the institution, principal 
investigator name, telephone, fax, and e-mail address. The focus 
element (Middleware Technology, Collaboratory Pilots, or High 
Performance Network Engineering) for the preapplication should also be 
clearly identified. A response to each preapplication discussing the 
potential programmatic relevance of a formal application will be 
communicated to the Principal Investigator within 7 to 14 days of 
receipt.

Collaboration

    Applicants are encouraged to collaborate with researchers in other 
institutions, such as: universities, industry, non-profit 
organizations, federal laboratories and Federally Funded Research and 
Development Centers (FFRDCs), including the DOE National Laboratories, 
where appropriate, and to include cost sharing wherever feasible. 
Additional information on collaboration is available in the Application 
Guide for the Office of Science Financial Assistance Program that is 
available via the Internet at: http://www.sc.doe.gov/production/grants/Colab.html.

Program Funding

    It is anticipated that up to $6 million will be available for all 
National Collaboratories and High Performance Networks Programs awards 
in Fiscal Year 2001; from ten to as many as fifteen awards are 
anticipated, contingent on availability of appropriated funds in FY 
2001 and the size of the awards. Multiple year funding is expected, 
also contingent on availability of funds and progress of the research.
    Awards are expected to be at most $500,000 per year for individual 
middleware technology and network engineering R&D projects. Awards for 
collaboratory pilots are expected to be at most $2.5 million per year. 
Since pilots are expected to be multi-institution projects, awards 
under this notice would range from $200,000 to $600,000 for 
participation in a pilot. The term for projects can be from one to 
three years.

Merit Review

    Applications will be subjected to scientific merit review (peer 
review) and will be evaluated against the following evaluation 
criteria, which are listed in descending order of importance codified 
at 10 CFR 605.10(d):
    (1) Scientific and/or Technical Merit of the Project;
    (2) Appropriateness of the Proposed Method or Approach;
    (3) Competency of Applicant's Personnel and Adequacy of Proposed 
Resources;
    (4) Reasonableness and Appropriateness of the Proposed Budget.
    The evaluation under item 1, Scientific and/or Technical Merit of 
the Project, will also consider the following elements:
    (a) The potential of the proposed project to make a significant 
impact in the effectiveness of SciDAC applications researchers.
    (b) The degree to which an application area can benefit from 
collaborative technology.
    (c) The extent to which the project will test important 
collaborative technologies.
    (d) The extent to which the results of the project are extensible 
to other program or discipline areas.
    The evaluation under item 2, Appropriateness of the Proposed Method 
or Approach, will also consider the following elements:
    (a) The degree to which the project adheres to the management 
philosophy of incorporating collaboration into the project execution.
    (b) The quality of the plan for ensuring interoperability and 
integration with software produced by other SciDAC efforts.
    (c) The extent to which the project incorporates broad community 
(industry/academia/other federal programs) interaction.
    (d) Quality and clarity of proposed work schedule and deliverables.
    (e) Knowledge of and coupling to previous efforts for collaborative 
technologies such as DOE 2000.
    The evaluation will include program policy factors such as the 
relevance of the proposed research to the terms of the announcement and 
the agency's programmatic needs. Note, external peer reviewers are 
selected with regard to both their scientific expertise and the absence 
of conflict-of-interest issues. Non-federal reviewers will often be 
used, and submission of an application constitutes agreement that this 
is acceptable to the investigator(s) and the submitting institution.

Submission Information

    The Project Description must be 20 pages or less, exclusive of 
attachments. It must contain an abstract or project summary on a 
separate page with the name of the applicant, mailing address, phone, 
FAX and E-mail listed. The application must include letters of intent 
from collaborators (briefly describing the intended contribution of 
each to the research), and short curriculum vitaes for the applicant 
and any co-PIs.
    To provide a consistent format for the submission, review and 
solicitation of grant applications submitted under this notice, the 
preparation and submission of grant applications must follow the 
guidelines given in the Application Guide for the Office of Science 
Financial Assistance Program, 10 CFR Part 605. Access to SC's Financial 
Assistance Application Guide is possible via the World Wide Web at: 
http://www.science.doe.gov/production/grants/grants.html.

    The Catalog of Federal Domestic Assistance number for this 
program is 81.049, and the solicitation control number is ERFAP 10 
CFR Part 605.

    Issued in Washington, DC on: December 7, 2000.
John Rodney Clark,
Associate Director of Science for Resource Management.
[FR Doc. 00-32251 Filed 12-18-00; 8:45 am]
BILLING CODE 6450-01-U