Virtual Weather? How About 'Good' Weather?

Researchers from the National Center for Atmospheric Research (NCAR), the San Diego Supercomputer Center (SDSC), Lawrence Livermore National Lab (LLNL), and IBM Watson Research Center have set U.S. records for size, performance, and fidelity of computer weather simulations.

Wonderful. But I could have saved them a lot of time and trouble, having spent most of the past week in airline waiting lounges and cheap airport motels, thanks to a double dose of snow and freezing rain. Who needs simulation when you have the real McCoy. But congratulations are still in order to team members John Michalakes, Josh Hacker, and Rich Loft of NCAR; Michael McCracken, Allan Snavely, and Nick Wright of SDSC; Tom Spelce and Brent Gorda of Lawrence Livermore; and Robert Walkup of IBM who set a record for "parallelism" by running on 15,360 processors of the 103 peak teraflops IBM Blue Gene/L supercomputer. They also set a speed performance record for a U.S. weather model running on 12,090 processors of this 100 peak teraflops system, achieving 8.8 teraflops.

According to Michalakes, lead architect of the Weather Research and Forecast model (WRF) code, "To solve a problem of this size, we also had to work through issues of parallel input and output of the enormous amount of data required to produce a scientifically meaningful result. The input data to initialize the run was more than 200 gigabytes, and the code generates 40 gigabytes each time it writes output data."

With this power, they were able to create "virtual weather" on a detailed 5 kilometer horizontal grid covering one hemisphere of the globe, with 100 vertical levels, for a total of some 2 billion cells. Great, but it didn't get me home any sooner.

-- Jonathan Erickson
jerickson@ddj.com

Posted by Jon Erickson at 07:35 PM  Permalink