I have only been peripherally keeping up with what’s going on inside the HPCS program at DARPA, but I was surprised at how strongly this story at CNN slants making supercomputers easier to use as the “point” of the recent IBM/Cray announcement.
This is a good thing, though. As “universal intellectual amplifiers” (Dan Reed’s phrase, not mine) that can have impact in all the research we do, making supercomputers easier to use is one of the most important things we can do.
[…] As discussed here earlier this year, the DARPA HPCS program has had a lot of positive publicity about its focus on usability and productivity in HPC systems. The question of how to evaluate HPC technologies in terms of productivity has been the subject of quite a bit of research funded under the first two phases of the HPCS program. Take a look at the highproductivity.org publications list for some of the results. […]