Gadget in extremis: Nvidia GPU-powered supercomputer

How do you solve a problem like predicting the weather in Switzerland? [Ed – Sound of Music reference? That was Austria!]


Well, if you are the Swiss National Supercomputing Center (CSCS) - a major European institution for computational research - you might throw a petaflop of GPU-accelerated processing power at the problem.

It is building a new Cray XC30 supercomputer - dubbed "Piz Daint", apparently after a mountain in the Swiss Alps - that will be extended with GPU accelerators. The goal is to expand the depth of the center's research in weather modeling.

On an Nvidia blog, Sumit Gupta writes:

tesla-k20-seriesWith NVIDIA Tesla K20X GPU accelerators (right), Piz Daint will have more than 1 petaflops of performance – that’s 1,000 trillion floating point operations per second – which is expected to make it the fastest GPU accelerator-based scientific supercomputer in Europe when it becomes operational in early 2014.

Based on the NVIDIA Kepler architecture – the world’s fastest and most energy-efficient high performance computing architecture – the Tesla GPUs will dramatically accelerate performance at an affordable cost. This is key as running complex, compute-intensive simulations of large-scale environmental phenomenon accurately takes massive computing resources.




Leave a Reply

Your email address will not be published. Required fields are marked *


You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>