Nice article over at Wired Magazine’s site on the joint exascale effort by Sandia and Oak Ridge. The article talks about real issues, which is a refreshing change from a lot of the sunshine and roses we tend to see about HPC in the press
In addition, power and reliability require new solutions when you’ve got thousands or millions of processors.
“The power budget for all computers seems to be going up rapidly. We need a machine you can afford to run,” Dosanjh said, and one that actually works. With a million computing nodes working together, the odds are high that one of them will break, over the course of even a small calculation.