Draft Initial Statement of Work for NPAC ARL PET Activities

Preamble

This covers a planning period which will be used to prepare background information and get initial start on some activities which will go into "production mode" as soon as possible. This work will be motivated by guidelines for PET activities emerging from recent meeting at Houston which include:

• Need for clear early successes linked to an overall long term vision.
• Particular attention to visible PET wide activities.

A general strategy emerged from conversations between Ginny Too and Fox at Houston. Although this will evolve and perhaps change significantly, we will start the planning along this initial strategy outlined below.

• FMS use of HPCC is currently very small and straightforward "porting" approach for existing codes is not likely to exhibit early successes (One exception is noted in next bullet). Thus our major initial strategy is based on "new ways of doing things" using web technologies (especially Java and VRML 2.0). These have natural applicability to distributed virtual environments and "human/machine in the loop" distributed simulations.
• One simple early use of HPCC is to host parallel versions of large scale embedded simulations such as a weather simulation which is part of some FMS models.
• There could be interest in large scale parallel databases.
• There is some synergy between IMT and FMS which should be explored.
• Training in advanced Web technologies at ARL could be useful.

Later developments at the Houston meeting identified ARL(Grosch) and NPAC(Bernholdt) as lead for PET wide software repositories.

Proposed Activities

The activities in the initial planning period through June 30,97 will include:

• Exchange of Information describing NPAC and ARL activities
• One or more visits by Fox and NPAC staff to ARL involving NPAC presentations to ARL and vice versa.
• NPAC will study relevant technologies with attention to those features that seem relevant for later projects. These technologies include:
  • VRML 2.0 (VRML97 and Java3D) for distributed virtual environments. We will update ourselves on work in this area at NRL (Monterey).
  • Networking issues relevant for cross MSRC distributed simulations
  • Use of Java and technologies such as NPAC's TANGOsim for FMS
  • Parallel databases
• NPAC will work with Ohio state ARL (and ASC) in trying to proactively jump-start the software repositories in SIP and CCM. We have discussed this with Bender (Ohio State) but not ARL as this point emerged late in the meeting.
• NPAC will update training material so relevant tutorials can be delivered