Well, this is the day we had to leave. We saw many things, met many people, had many good conversations. Oddly enough we did not have time to attend talks. I sat in on one BOF.
Here is what I observed. IBM is pushing Blue Gene everywhere. In the sessions I did see or hear about from others, it appears that IBM operatives/employees were trying to make a case, even when told that infinite speed wasn’t the issue. Even though they built this wonderful hardware, there is a danger that they lost sight of the real issue.
It is time to insight, pure and simple. So even if you make the computation infinitely fast, you still have the time to prepare the model, and the time to understand the results. These times can be large for some problems. Not all tasks are bounded by the speed of the processors, or the speed of the memory, or the interconnect latency. Some problems are bound by the raw performance of the wetware guiding them, and using these incredibly fast CPUs.
Yeah, its nice to have really fast stuff. It is. But if your computation speed far outstrips your ability to comprehend what it is you are computing, then your computation speed really isn’t worth as much to the end user as you might like.
Shorter version: Drop the hard sell, and work on the stuff around the amazingly fast machine. It needs work.
Well, the plane is going to board in a minute, so I have to sign out from Seattle. I’ll try to summarize in the next few days. This has been an incredible trip from many perpectives, and we are quite happy with the volume and level of interest of the people there. Some folks are committed to solving real problems, and while it is a super computing conference, the application of near infinite power does not all problems solve. There is something more to it. Much more. And that is what makes this so fun and exciting.
See you in Orlando. Hopefully with a booth or booth space of our own.