By Scientific researchers are used to relying on computers to complement the physical experiments they do in “wet laboratories.” Especially in fields like drug discovery or DNA sequencing, innovation depends on computers being used in tandem with laboratory work. But because these applications are so complex, they require large and expensive supercomputing facilities, limiting the number of scientists who can take advantage of new methods.
The GPU is changing this, and today we introduced an initiative specifically for this biochemical research community.
Tesla Bio Workbench features a dozen applications designed for biological research. They have now been ported to CUDA and optimized for the GPU, delivering speed gains anywhere from 10x to 100x or more. In some cases we are even seeing computation times go from years to days, enabling certain classes of experiment that were previously impossible to do because of the time it took to run them.
We like to call the Tesla Bio Workbench a “computational laboratory,” because it lets researchers do on a Tesla-based computer system what they would in a conventional wet laboratory. Just as a wet lab has all the test tubes, Bunsen burners and chemicals that biochemists need to do their experiments, Tesla Bio Workbench has all the applications that researchers need to simulate these experiments.
Applications such as AMBER, LAMMPS and VMD, which are relied upon by more than 200,000 scientists, are a part of this program. You can hear directly from some of the key developers behind these codes in remarks they made at the SC09 conference about the advances they are making with GPUs.
As well as the applications, Tesla Bio Workbench includes a new community site where interested scientists can check out the latest benchmarks, read academic papers and tutorials, join discussion forums with the application developers themselves and more.
And it’s not just the medical and life-science community that can benefit from this technology. It turns out that making many household products more effective and environmentally friendly is as much a computer problem as it is a balance of chemicals.
For instance, researchers at Temple University are developing a computer simulation model that provides companies like Procter & Gamble with a fast, cost-effective and accurate tool for improving shampoos and liquid detergents. The research hinges on surfactant molecules, the agents that determine the cleaning capacity and texture of shampoos, laundry detergents and many other cleaning products.
“The computer models needed to accurately simulate surfactant properties are extremely demanding in terms of computational power,” said Axel Kohlmeyer of the Institute for Computational Molecular Science at Temple University. “We discovered that by adding just two NVIDIA Tesla C1060 GPUs, each node in our newest cluster can do 16 times more work, and thus multiplies our local compute capacity far beyond what we could previously get through the national supercomputing centers.”
Axel and the team at Temple were kind enough to let us go on campus and film them for a day to learn more about this interesting field, so be sure to check out the video for more information.
Tagged: CUDA, GPGPU, Supercomputing, Tesla
