What It’s Like To….Build The World’s Most Powerful Supercomputer
Deputy Associate Director of Computation at Lawrence Livermore National Lab, Michel McCoy does extraordinary work.
By Michel McCoy & Alice Dragoon
When I picked up the phone late in September, a very pleased and excited research leader from IBM was on the line, telling me that we’d just made history. Since February 2000, we’d been working together to build a new supercomputer for the Department of Energy, to be sited at Lawrence Livermore National Lab. IBM was calling to tell me that a small prototype of our Blue Gene/L supercomputer had just roared through 36.01 teraflops—more than 36 trillion calculations!—in one second. Testing just eight racks of what will be a 64-rack system, IBM scientists had beaten the previous world record of 35.86 teraflops set in 2002 by NEC’s Earth Simulator in Japan.
By next June, Blue Gene will hit well over 200 teraflops.
We’d been worried we didn’t have enough time to get anything running on the new machine with the new operating system and a new software stack. So reaching 70 percent of peak capacity at this point was extremely exciting. It was like the day my first daughter was born. I felt like we’d gotten a sign from the gods that we’d done at least a few things right. Then in November, we earned the number-one spot on the list of the world’s fastest supercomputers when a 16-rack version of Blue Gene/L tested out at 70.72 teraflops. By next June we’ll have all 64 racks installed and we expect to be able to hit well over 200 teraflops—the equivalent of everyone on earth performing 35,000 calculations per second.
We still have to harden the technology. It’s not superstabilized. But we’re talking about something utterly new and really exciting. We’re enabling scientists in ways they didn’t believe possible. In the past, studying the transition to turbulence in fluids required using approximations; more detailed, atomistic calculations were prohibitively expensive. I was talking recently with a scientist about Blue Gene’s capacity and he got all excited, saying, Oh my God, I can run calculations on 50 billion atoms instead of just 1 billion!
To be working on a leading-edge project like this is one of the things that makes this life worthwhile. My life is pretty ordinary overall but to be part of something that’s unique and has such promise to be valuable to the laboratory and to the nation is extraordinarily special.