HPCC Program Accomplishments and Plans

1. Networking

The HPCC Program provides network connectivity among advanced computing resources, scientific instruments, and members of the research and education communities. The Program has successfully accommodated the phenomenal growth in the number of network users and their demands for significantly higher and ever increasing speeds while maintaining operational stability. R&D in advanced networking technologies is guiding the development of a commercial communications infrastructure for the Nation. The development and deployment of this new technology is jointly funded and conducted by the HPCC Program, state and local governments, the computer and telecommunications industries, and academia.

1.1. The Internet

One illustration of the global reach of HPCC technologies is that the Internet now extends across the country and around much of the world. Initially the domain of government scientists and U.S. academics, by the beginning of FY 1994:

Almost two million computers were accessible over the Internet.
More than 15,000 regional, state, and local U.S. networks and 6,300 foreign networks in approximately 100 countries were part of the Internet.
Nearly 1,000 4-year colleges and universities, 100 community colleges, 1,000 U.S. high schools, and 300 academic libraries in the U.S. were connected.

The HPCC Programs Internet investment primarily supports the high speed "backbone" networks linking Federally-funded high performance computing centers.

1.2. The Interagency Internet

The Interagency Internet, that portion of the Internet funded by HPCC, is a system of value-added services carried on the Nation's existing telecommunications infrastructure for use in federally-funded research and education. Its three-level architecture consists of high speed backbone networks (such as NSFNET) that link mid-level or regional networks, which in turn connect networks at individual institutions. At the beginning of the HPCC Program in FY 1992, most of the backbones were running at T1 speeds (1.5 Mb/s megabits per second or millions of bits per second), and international connections had been established. Peak monthly traffic on NSFNET had reached 10 billion packets (of widely varying size). In FY 1992, NSFNET speed was upgraded to T3 (45 Mb/s) and NSF made awards to industry for network registration, information, and database services and for a Clearinghouse for Networked Information Discovery and Retrieval. By the beginning of FY 1994:

Peak monthly NSFNET traffic reached 30 billion packets.
DOE established six ATM (asynchronous transfer mode) testbeds to evaluate different approaches for integrating this technology between wide area and local area networks.
NASA provided T3 services to two of its Grand Challenge centers (Ames Research center and Goddard Space Flight center) through direct connection to NSFNET. In addition, service to several remote investigators was upgraded to T1 data rates.
NASA launched its Advanced Communications Technology Satellite (ACTS).

Advanced Communications Technology Satellite (ACTS) deployed by the Space Shuttle.
NIH and NSF funded 15 Medical Connections grants for academic medical centers and consortia to connect to the Internet.
Five "gigabit testbeds" established by NSF and ARPA (described below) became operational. In addition, a DOD-oriented testbed founded by ARPA focuses on terrain visualization applications.
ARPA established a gigabit testbed in the Washington, DC area in cooperation with more than six other agencies in the area.

Projected FY 1994 Accomplishments

Awards will be made to implement a new NSFNET network architecture (including network access points (NAPs), a routing arbiter, a very high speed backbone, and regional networks).
Additional very high speed backbones will link HPCRCs (High Performance Computing Research centers, described below).
Connectivity for DOE's ESnet will grow to 27 sites.
More universal and faster Internet connections for the research and education community
Improved network information services and tools

Proposed FY 1995 Activities

NSFNET -- Implement new architecture (awards were made in FY 1994); implement very high speed backbone to NSF Supercomputer centers; establish some additional high speed links for demanding applications
DOE -- Upgrade ESnet services to T3 and selected sites to 155 Mb/s; upgrade connectivity to Germany and Italy to T1 and to Russia to 128 Kb/s (kilobits per second or thousands of bits per second)
NASA's AEROnet and NSI -- Establish internal T3 and higher speed network backbone to five NASA centers
Expand connectivity to schools (K-12 through university) -- connectivity funded by NSF and NIH will reach a total of 1,500 schools, 50 libraries, and 30 medical centers; NASAs Spacelink computer information system for educators will be made available via the Internet; toll-free dial-up access will be provided to teachers without Internet access.
NIH -- Acquire gigabit (billions of bits per second) local networks for use with multiple parallel computers and as a backbone to enable development of the Xconf image conferencing system
Integrate NOAA's more than 30 environmental data centers into the Internet through high speed connectivity and new data management tools
Expand EPA connectivity to reach a substantial percentage of Federal, state, and industrial environmental problem-solving groups and test distributed computing approaches to complex cross-media environmental modeling
Continue to support and improve information services such as the NSFNET Internet Network Information center (InterNIC)

1.3. Gigabit Speed Networking R&D

New technologies are needed for the new breed of applications that require high performance computers and that are demanded by users across the U.S. These technologies must move more information faster in a shared environment of perhaps tens of thousands of networks with millions of users. Huge files of data, images, and videos must be broken into small pieces and moved to their destinations without error, on time, and in order. These technologies must manage a users interaction with applications. For example, a researcher needs to continuously display on a local workstation output from a simulation model running on a remote high performance system in order to use that information to modify simulation parameters.

As these gigabit speed networks are deployed, the current barriers to more widespread use of high performance computers will be surmounted. At the same time, high speed workstations and small and mid-size scalable parallel systems will gain wider use.

A teraflops (a trillion floating point operations per second) computing technology base needs gigabit speed networking technologies.

HPCC-supported gigabit testbeds funded jointly by NSF and ARPA test high speed networking technologies and their application in the real world.

The HPCC Program is developing a suite of complementary networking technologies to take fullest advantage of this increased computational power. R&D focuses on increasing the speed of the underlying network technologies as well as developing innovative ways of delivering bits to end users and systems. These include satellite, broadcast, optical, and affordable local area designs.

The HPCC Program's gigabit testbeds are putting these technologies to the test in resource-demanding applications in the real world. These testbeds provide working models of the emerging commercial communications infrastructure, and accelerate the development and deployment of gigabit speed networks.

In FY 1994-1995, HPCC-funded research is addressing the following:

ATM/SONET (Asynchronous Transfer Mode/Synchronous Optical Network) technology -- "fast packet switched" cell relay technology (in which small packets of fixed size can be rapidly routed over the network) that may scale to gigabit speeds
Interfacing ATM to HiPPI (High Performance Parallel Interface) and HiPPI switches and cross connects to make heterogeneous distributed high performance computing systems available at high network speeds
All-optical networking
High speed LANs (Local Area Networks)
Packetized video and voice and collaborative workspaces (such as virtual reality applications that use remote instruments)
Telecommuting
Intelligent user interfaces to access the network
Network management (for example, reserving network resources, routing information over the networks, and addressing information not only to fixed geographical locations but also to people wherever they may be)
Network performance measurement technology (to identify bottlenecks, for example)
Networking standards (such as for interoperability) and protocols (including networks that handle multiple protocols such as TCP/IP, GOSIP/OSI, and popular proprietary protocols)

Additional FY 1995 plans include completing DOE's high speed LAN pilot projects and providing select levels of production-quality video/voice teleconferencing capability. NASA and ARPA plan experiments in mitigating transmission delay to the ACTS satellite. NASA plans to extend terrestrial ATM networks to remote locations via satellite and to demonstrate distributed airframe/propulsion simulation via satellite.

1.4. Network Security

Network data security is vital to HPCC agencies and to many other users such as the medical and financial communities. FY 1994-1995 research is directed at incorporating security in the management of current and future networks by protecting network trunks and individual systems. Examples include:

Joint ARPA/NSA projects in gigabit encryption systems for use with ATM
Use of the ARPA-developed KERBEROS authentication system by DOE for distributed environment authentication and secure information search and retrieval
Methods for certifying and accrediting information sent over the network

NSA is addressing the compatibility of DOD private networks with commercial public networks.

The rapid growth of networks and of the number of computers connected to those networks has prompted the establishment of incident response teams that monitor and react to unauthorized activities, potential network intrusions, and potential system vulnerabilities. Each team serves a specific constituency such as an organization or a network. One of the first such teams was CERT, the Computer Emergency Response Team, based at the Software Engineering Institute in Pittsburgh, PA. CERT was established in 1989 by ARPA in response to increasing Internet security concerns, and serves as a response team for much of the Internet. FIRST, the Forum of Incident Response and Security Teams, was formed under DOD, DOE, NASA, NIST, and CERT leadership. FIRST is a growing global coalition of response teams that alert each other about actual or potential security problems, coordinate responses to such problems, and share information and develop tools in order to improve the overall level of network security.

Next Section
Table of Contents
Home Page