Titan Supercomputer Debuts with Nvidia GPUs
The Titan supercomputer, launched at the Oak Ridge National Laboratory, will help scientists conduct research on climate change and materials science.A new era of supercomputing was launched today with the debut of Oak Ridge National Laboratory’s (ORNL) Titan, a system capable of running through more than 20,000 trillion calculations each second (20 petaflops) by employing a family of thousands of Nvidia graphics processing units (GPUs), first created for computer gaming. According to the ORNL, it is the world’s most powerful supercomputer for open science, boasting a computing capacity on par with each of the world’s 7 billion people being able to carry out 3 million calculations per second. Supported by the Department of Energy, Titan has more than 700 terabytes of memory. Titan will also occupy the same space as its Jaguar predecessor while using only marginally more electricity, thanks to the combination of central processing units (CPUs), the traditional foundation of high-performance computers, and more recent GPUs. Because they handle hundreds of calculations simultaneously, GPUs can go through many more than CPUs in a given time. “One challenge in supercomputers today is power consumption,” Oak Ridge associate laboratory director for computing and computational sciences Jeff Nichols said in a statement. “Combining GPUs and CPUs in a single system requires less power than CPUs alone and is a responsible move toward lowering our carbon footprint. Titan will provide unprecedented computing power for research in energy, climate change, materials, and other disciplines to enable scientific leadership.” The Cray XK7 system contains 18,688 nodes, with each holding a 16-core AMD Opteron 6274 processor and an Nvidia Tesla K20 GPU accelerator. Titan will enable researchers to run scientific calculations with greater speed and accuracy—the machine will provide research in energy, climate change, efficient engines, materials, and other disciplines-- by relying on its 299,008 CPU cores to guide simulations and allowing the Nvidia GPUs to do the intensive calculations and processing.