Researchers break records with MILLION-CORE calculation
One app, million cores – but it wasn't Crysis...
Magic Quadrant for Enterprise Backup/Recovery
HPC blog Stanford’s Engineering Center for Turbulence Research (SECTR) has claimed a new record in computer science by running a fluid dynamics problem using a code named CharLES that utilised more than one million cores in the hulking great IBM Sequoia at once.
According to the Stanford researchers, it’s the first time this many cores have been devoted to a fluid simulation. In this case, the boffins were modeling jet engine exhaust in an attempt to reduce the noise during takeoffs and landings.
If you need a million-core system to run your code, there aren’t a lot of choices today. In fact, there are only two million-core plus supercomputers that we know of: 1) Oak Ridge’s AMD/NVIDIA-based Titan and 2) Lawrence Livermore National Lab’s Bluegene/Q-based Sequoia. The Stanford guys used the 1,572,000-core Sequoia system, probably because it’s an easy drive from Palo Alto to Livermore, CA. (Head over the Dunbarton Bridge, then take the 880 to the 580. That’s how I’d go.)
The computer code used in this study is named CharLES and was developed by former Stanford senior research associate, Frank Ham. This code utilizes unstructured meshes to simulate turbulent flow in the presence of complicated geometry.
Stanford University also alluded to the difficulty inherent in pushing applications to this scale. I was surprised to read that the combined Stanford/LLNL team was able to pull this off with only “a few weeks” of planning and tuning. That’s definitely a resume-worthy achievement. ®
COMMENTS
Re: The future of home computing
I'm sure this is just a satirical jibe at the met office, but something sciency in me compells me to inform you that the mathematics of chaos, not the ineptitude of the met office, is the reason they can't predict the weather.
What the met office actually do is run a large number of simulations, all with perturbations from the current weather situation and determine the probability of certain events. E.g. say they run 20 simulations and it rains in 15 of them, then they say there's a 75% chance of rain. This was taken away from our TV weather reports because people are stupid and don't what that means. So they say "It will rain today". Then, when it's bright sunshine (as predicted in 25% of the simulations), people say "blah blah, crap forcasters!" and laugh.
Re: The future of home computing
Here across the pond, about the only thing the National Weather Service gets wrong to the point that people gripe is exact snowfall locations and amounts (perhaps not something you need to worry about in the UK, but here, there is a bit of a difference between 2" and 6") and tornado warnings that turn out to be false alarms. The former is because a slight shift (a dozen miles, if even) in the upper atmosphere can change both the type and the amount of snowfall, while the latter is erring on the side of caution, as tornadoes not just ruin your picnic, but probably put the sandwiches through the house down the street (maybe a slight exaggeration).
Maybe it's the island location that plays havoc with the weather forecast, or maybe the expectations are so high, it's absurd. Given than the NWS is able to predict the general path and area of impact of most hurricanes five days in advance within a 300 nautical mile error, I'd say we're doing pretty good. Just because it rains on you when you forgot your umbrella doesn't mean it's the end of the world.
Re: The future of home computing
>> Can we therefore conlcude that in about 15 years time this will be the kind of power we will have in home computers.
Yes. We can also conclude these computers will have performance issues when running the latest version of Windows.
IT infrastructure monitoring strategies
Requirements Checklist for Choosing a Cloud Backup and Recovery Service Provider
Data control in the cloud
Cloud based data management
Enabling efficient data center monitoring
