Author: Alan Blatecky
Institute: Renaissance Computing Institute, University of North Carolina
"...TeraGrid has come to a major fork in the road and needs to significantly change direction and/or change into something quite different."
| Attachment | Size |
|---|---|
| Blatecky_TeraGrid White Paper.pdf | 25.36 KB |
Rather than saying that "TeraGrid has gotten off track by confusing acquisition of FLOPS with cyberinfrastructure," I would instead suggest that TeraGrid spent seven years working on both. During that time scientists were fighting and screaming to get access to FLOPS while the grid infrastructure projects went around looking for users. It is perfectly rational to direct funds towards the in-demand good (FLOPS) while reducing the complexity of the required infrastructure by funding fewer sites.