Richard Gerber's NERSC Blog
December 25, 2017 by Richard Gerber and Kathy Kincade
As the mission High Performance Computing and Data center for the DOE Office of Science, NERSC provides services and systems that enable its 7,000 users to produce world-class science results that are published in 2,000+ peer-reviewed research papers per year. It would impossible to highlight them all, but here are some of our favorites for 2017 (in no particular order).
October 8, 2015 by Richard Gerber
Perhaps the most rewarding aspect of working at NERSC is sharing in the scientific enterprise, working day-to-day with the best scientists in the world seeking to answer the most interesting questions ever posed. How does the nanoworld work? Where did our universe come from and where is it going? How are we affecting our environment and what could we do about it?
February 27, 2015 by Jack Deslippe & Richard Gerber
At this year's NERSC user group meeting we tried something new: a code optimization "hack-a-thon." Thanks to HPC experts from NERSC and Intel and about 20 enthusiastic code developers, it was a great success! Everyone who showed up at NERSC's Oakland Scientific Facility, had fun, learned some new things, and got some big performance improvements in their code.
February 4, 2015 by Richard Gerber
Cori is coming and it’s time to start getting ready. Yes, NERSC’s Intel Xeon Phi-based system is still more than a year away, but if you’re not already thinking about how you’re going to use it, you need to get started. That’s because to get your codes to run well (or maybe at all) on NERSC’s first “many-core” system it is going to take more than a simple recompile.
January 16, 2015 by Richard Gerber
Edison's New Memory
Edison is back, now with all 28,000 memory DIMs replaced and upclocked from 1600 MHz to 1866 MHz. (This is the memory speed, not the processor speed.) So, what will this mean to you? It's hard to predict exactly, but some codes will see a noticeable performance increase, which is good news for everyone. If you know that your code is memory bandwidth limited then your code could run up to 16 percent faster. If memory bandwidth doesn't matter to you, then you may see no improvement. Most codes will probably fall somewhere in between.