incremental equipment for better balance (e.g. memory, disks, lines)

upgrades to prevent center obsolescence increased capacity to meet industrial needs and opportunities "batch" and remote visualization equipment for movies

and lesser priority items including:

courses

grand challenges in computational science new technologies and new techniques in parallelism scientists to help in parallelization and visualization interactive visualization at the user level

1. Status quo. NSF funds it all centrally, as we do now in competition with computer science. This is the worst of all possible worlds because the use of the facility is completely decoupled from the supply of the service. By being in CISE, nearly everyone associated with the budget, gets the erroneous conclusion that people working on computer science and engineering research have something to do with the centers. Little or no coupling or use of the centers is made by computer science. The machines aren’t suitable for computing research, nor are adequate funds available for computational science.

If I make the decision to trade-off, it will not favor the centers, but rather centers will be funded at about the same as overall science.

2. Central facility. NSF funds ASC as an NSF central facility. This allows the Director, who has the purview for all facilities and research to make the trade-offs across the foundation.

3. NSF Directorate use taxation. NSF funds it via some combination of the directorates on a taxed basis. The overall budget is set by AD’s. DASC would present the options, and administer the program.

4. Directorate-based centers. The centers (all or in part) are "given" to the research directorates. NCAR provides an excellent model for say BBS, and MPS. Engineering might also operate a facility. I see great economy, increased quality, and effectiveness coming through specialization of programs, databases, and support. This is partially happening.

5. Co-pay. In order to differentially charge for all the upgrades and incrementally nice facilities a tax would be levied on various allocation awards. Such a tax would be nominal (e.g. 5%) in order to deal with the infinite appetite for new hardware and software. This would allow other agencies who use the computer to also help pay.

6. Manufacturer support. Somehow, I don’t see this changing for a long time. A change would require knowing something about the power and throughput of the machines so that manufacturers could compete to provide lower costs. BTW:Erich Bloch and I visited Cray Research and succeeded in getting their assistance.

7. Make the centers larger to share support costs. Manufacturers or service providers could contract with the centers to "run" facilities. This would reduce our costs somewhat on a per machine basis.

8. Fewer physical centers. While we could keep the number of centers constant, greater economy of scale would be created by locating machines in a central facility and running them more like LASL and LLNL where each run 8 Crays to share operators, mass storage and other forms of hardware and software support. With decent networks, multiple centers are even less important.

9. Simply have fewer centers. but with perhaps increasing power.

10. Maintain centers at their current or constant core levels for some specified period. Each center would be totally responsible for upgrades, etc. and their own ultimate fate.

11. Free market mechanism. Provide grant money for users to buy time. This might cost more because I sure we get free rides at places like Berkeley, Michigan, Texas and the increasing number of other institutions who do provide megaflops to their users.

1. consolidate equipment in fewer equipment-based centers to reduce cost and operate fewer physical centers at a greater economy of scale

2. have 3 or 4 directorate based centers and 2 or 3 general centers

3. use co-pay as a means to look at real need and as a way to fund specialized facilities such as 35mm movie equipment