Title Page with PIs, departments, institutions, mailing and e-mail, phone, fax

One page abstract give key words or a list of disciplines/sub-disciplines covered

There is general expectation that computational science will make increasing and critical use of distributed heterogeneous metacomputing environments. However this implies the development and integration of new technologies from several different disciplines and their testing on complex applications. In this proposal we bring together experts from distributed computing, virtual environments, high speed networking and web based collaboration. These are integrated in terms of carefully chosen applications with which we will be able to motivate and assess the technology base. We believe that any successful system must be able to harness multiple distributed computers, data analysis and visualization subsystems as well as a distributed team of users. This requires a multidisciplinary approach in any successful approach to this problem. This scenario can be expected both for academic applications (as seen today in nationally distributed Grand Challenges) and for Industrial problems as envisaged in multidisciplinary analysis and design for next generation manufacturing.

We build on the Advanced Resource Management System (ARMS, from the Cornell Theory Center), an advanced metacomputing resource management tool that has already been designed to handle both compute and visualization systems. The latter will span virtual environments from advanced CAVE^TM capabilities at the Cornell Theory Center and the University of Houston, as well as conventional workstation-based analysis. A centerpiece of this proposal will be the integration of advanced networking with ARMS which will be lead valuable insight to Internet 2 and NGI as this develops. TANGOsim (Syracuse University) is a recently developed Java Server-based collaborative environment that includes an event-driven simulator with the conventional services offered in comparable systems offered by the National Center for Supercomputing Applications(Habanero) and IBM. TANGOsim links applications written in any language. It can be integrated naturally with the compute services offered by ARMS, which is also based on a similar Web technology base. These base technologies will be tied together with industrial (medical, seismic, and manufacturing) and academic applications involving all members of the proposal team. We have included a strong networking research group from Cornell, which will allow us to assess the results of effort from application, computing, and networking perspectives. We believe that we have put together a team that combines leading-edge expertise and technologies in the diverse components needed in future distributed metacomputing environments. Further, in each case, base technologies (ARMS, TANGOsim, virtual environments) are well developed and this proposal will only fund their integration.

The partners in this proposal are the Cornell Theory Center (CTC), the University of Houston (UH) and Syracuse University (NPAC/Syracuse). In the following we describe the component technologies ARMS, TANGOsim, Virtual Environments and Networking. These are integrated by the applications described at the end with a significant assessment effort.

Advanced Resource Management System (ARMS)

The Cornell Theory Center (CTC) has been developing an advanced resource management and scheduling system for distributed, heterogeneous computational, visualization, network, and data acquisition resources. This system, called ARMS, deterministically schedules applications on these resources so that network connectivity and quality of service are ensured. ARMS is a technology enabler, in that it provides access for applications to these distributed resources in a seamless, cohesive fashion. This will allow researchers from all areas to focus on their areas of expertise without being concerned with the logistics of running their applications or experiments on geographically distributed heterogeneous resources. ARMS includes a two-level intelligent scheduling system that uses an Informix distributed database. The database maintains status and availability information, which is then used to schedule jobs with specific computing, synthetic environment, software, data, and networking resource requirements. The foundation for ARMS is based on key components from the EASY-IBM LoadLeveler application programming interface (API) project . Through a minimal set of API calls, all the necessary information about local and remote computational resources and user job requirements can be queried reliably. This API is being extended to work with other major scheduling systems such as Platform Computing's LSF.

ARMS provides secure, survivable resource management and job scheduling. Local resource monitoring agents will be developed that can relay status and availability information to the ARMS database using the Ensemble system developed at Cornell University. Ensemble, is a reliable networking protocol that guarantees the arrival of information and also its ordered arrival. ARMS relies on DCE/DFS for cross-realm authentication where we are working closely with Lawrence Livermore National Laboratory. The growing complexity of distributed environments suggests that distributed system monitoring tools and navigational tools will be extremely important for both systems administrators and users. We propose the development of Web-based Java tools for ARMS which will allow location of resources and monitoring of their status and availability.

ARMS is being tested in several testbeds. Development work is being done primarily at CTC on its 512 node IBM SP system and SGI Power Onyx systems. As code matures it is deployed to a campus-based distributed system with ATM network connectivity. In addition, mature ARMS code has been tested on a national testbed including CTC, Pennsylvania State University, the University of California at Los Angeles, and the University of Maryland. The geographical distance between these sites has proven to be an excellent test of ARMS' capabilities. The reliable and deterministic service that ARMS will be able to guarantee will make it an essential part of the NGI. It will provide a mechanism to predict and control network traffic - a feature that is missing in the current Internet. Our working closely with key distributed application developers will ensure the ultimate usability of the ARMS system

Network Infrastructure

Our team has considerable experience in ATM network technology, with both CTC and Syracuse operating multiple FORE switches and an IBM 8260 operating in a production environment for over two years. Initially, we propose to use this infrastructure by setting up a virtual network between specified resources which would be completely under the control of ARMS. This will be done by creating Permanent Virtual Paths (PVPs) with guaranteed bandwidth in a full mesh between computing resources- ARMS will have full control of dynamically allocating appropriate Permanent Virtual Circuits (PVCs) or Switched Virtual Circuits (SVCs) within the allocated bandwidth of the PVPs. Once tested in the local area, this concept can be extended, subject to approval, across the vBNS network to resources at the collaborating sites.

An interesting case arises when there are multiple alternative paths between two systems- one of which may have higher bandwidth but also higher latency. Different requirements of different parts of a particular ìjobî may be transported over different paths based on their bandwidth and latency requirements. Early simulations of path latencies can be accomplished by creating ìloopedî virtual paths out into and back from the vBNS network.

Collaboration

Recent Web technology developments open the way for new collaborative computing environments that integrate traditional video conferencing, distributed simulation as developed by the DMSO office(SIMNET), and emerging ideas of computational steering. In this proposal we will link the ARMS system with TANGOsim developed at NPAC. TANGOsim uses Java Servers to manage Web collaboration in the traditional fashion already seen in Habanero (NCSA) and Shaking Hands (IBM but originating in NPAC). The Java Server supplies session management with multicasting allowing shared applications between multiple users. TANGOsim was built to support command and control with scripted environments allowing real and virtual members in the command teams. This is implemented as an event driven simulator replacing the simple session manager used in the other Web collaboration systems.

Since ARMS and TANGOsim are built on a modern Web backbone we can integrate them so that ARMS provides the asynchronous scheduling and TANGOsim the synchronous collaborative computational steering, linking in each case distributed computers, databases, visualization and multiple collaborating computational scientists. TANGOsim has been developed with other funding for command and control and distance education. Here we propose funding for its integration with ARMS and the special features needed for distributed computational steering. TANGOsim is implemented as a Java Server linking a net of Java Applets with a special downloadable plug-in providing the critical connectivity. It already supports client applications written in Java, JavaScript, and C++ (and hence other traditional languages). We have demonstrated a prototype visualization client for a 3D GIS (Geographical Information System) with a custom VRML browser written in C++. Other major capabilities of TANGOsim include a video teleconferencing module and integration with a state-of-the-art digital video server that supports efficient multicast services. Further over the next few months, we will add a database backend (using the new JDBC Java Database Connectivity) which will allow one to log the complete multimedia collaborative session. TANGOsim provides traditional basic servicesó chatboard, shared whiteboard and multimedia mail. Further we have ported several interesting educational applications, the WebWisdom dissemination systems and some interesting Physics education applets , to collaborative mode. These will be used in our first application area described later.

This proposal involves the integration of ARMS and TANGOsim with at a lower level TANGOsim integrating the components of a synchronous computational steering environment. The details of this integration will depend on the evolution of Web technology but we expect to continue the basic architecture built around Netscape's LiveConnect on the client and Java Servers. Note that TANGOsim can be viewed as "just integration technology" for collaboration systems "just" provide integration between the involved clients.

Virtual Environments

Recently, higher bandwidth communications channels have made collaborative science and engineering using shared virtual environments practical. Research efforts have focused on two main areas: software infrastructure and application development. Researchers concentrating on software infrastructure have developed software architectures, network protocols, and data-sharing algorithms to enable distributed, shared, virtual environments. Application developers have built specific applications to serve as proofs-of-concept for the effectiveness of distributed, shared virtual environments. To achieve real-time collaboration over long distances, two approaches have emerged: (1) rendering graphics locally on similar platforms and exchanging state data at high rates over a communications link and; (2) rendering graphics at a single facility and delivering those graphics, over communications channels, to remote users. We propose to work with both approaches. UH will develop high performance remote rendering software, based on work initially done at SGI and ongoing at the UH with Darpa support. This will support the remote "writing" of frame buffers so that a powerful graphics supercomputer at one site can effectively drive the displays of inexpensive workstations on the scientist's or engineer's desktop. In this effort, much of the focus will be on enhancing interaction and collaboration including use of acoustic and haptic interfaces.

Another major use of visualization will be its application as a user interface to large-scale mathematical models and simulations. We will seek to make possible the more effective use of such models and simulations executing on supercomputers, locally or remotely. This will be accomplished by allowing scientists and engineers to construct and work directly with near-real-time meaningful representations of the physical systems that they are attempting to understand.

Linking this technology with ARMS and TANGOsim (which supports such custom viewers) allows us to deliver this environment and to multiple distributed users by creating an effective interface and giving the deterministic control of the scheduling of the multiple resources required.

Integration and Assessment

We propose to deploy a distributed collaborative computing environment that focuses on high level user services. Little experience exists on either the useful features of such a system or on the needed infrastructure capabilities in areas of network, parallel multimedia database for session logs, and computational services including visualization. Thus our proposal will be structured as a set of application experiments described below where we will carefully assess both the value of particular system features and needed performance and functionality of underlying infrastructure. This assessment will use traditional computer and network performance tools augmented by enhancements in TANGOsim to log message traffic through the session manger. Here we will follow the strategy exploited in our Virtual Programming Laboratory of using a web implementation of Illinois's Pablo system with ,performance data logged in TANGOsim's backend database using the SDDF data format.

Selected Test Applications

Our approach is applicable to general large scale computational problems but here we focus on two general areas -- one from education and the other a classic grand challenge. Our assessment of these two areas should allow our work to generalize more broadly.

The Virtual Classroom

To test the usability of the ARMS system for the development of distributed programming environments, we have been working on several prototype applications and collaborative tools layered on top of ARMS. CTC and Syracuse have collaborated on the development of a secure Web-based scheduler interface that provides ARMS users with a common interface for submitting jobs to the ARMS scheduler and for browsing and editing DFS filespace, no matter where the jobs reside. "Smart Make" facility, another interface under development, will allow users to submit source code to the ARMS scheduler, which in turn will locate the necessary software and computing resources for the code, build the correct executable, and store metadata on the executable pertaining to its resource requirements.

CTC is already a leader in the area of asynchronous Web-based education through its Virtual Workshop. Syracuse has already integrated its HPCC and Web course system WebWisdom with Tango to deliver training in classic synchronous style. This application is particularly demanding of network responsiveness for users. Within the context of this educational framework CTC and Syracuse have collaborated on the development of a secure Web-based interface that provides users with a common interface for submitting jobs to the ARMS scheduler and for browsing and editing DFS filespace, no matter where the jobs reside. Until this point in time the Virtual Workshops have been asynchronous but with the integration and development of TANGOsim in the Virtual Workshop environment, we will create a truly Virtual Classroom environment. ARMS will enable advanced reservation of networking resources so that during a Virtual Workshop or class session users will be able to interact as they would in a physical meeting or class room. We will use the digital server technology developed by NPAC which is already being used in their ATM K-12 experiment -- the Living SchoolBook.

Applications for visualization

The application that we propose for metacomputing environments is shared virtual workspaces. Such a metacomputing application can also be viewed as a metacomputing technology, which in itself should be demonstrated and measured in terms of end-user feasibility and value.

As end-user applications we propose 3-D medical imaging and video, and 3-D seismic data sets for exploration and reservoir modeling, and engineering design in the manufacturing industry. These applications are selected because first they involve large, complex, 3-D data sets, second the interpretation of the data sets are typically done by parties in different geographical locations, third the end--user has strong demands on quality of representation, ease of perception, and performance ("quality-of-service"). University of Houston has excellent relationships to all three user categories, and a realistic assessment of accomplishments can be achieved.