by Dawn Levy, Oak Ridge National Laboratory
In the quest to simulate the natural world from subatomic particles to the vast cosmos and the engineered world from turbines to advanced fuels, can scientists and engineers benefit from extreme-scale supercomputers that use application-code accelerators called GPUs (for graphics processing units)? Comparing GPU accelerators with today’s fastest central processing units (CPUs), early results from diverse areas of research show 1.5- to 3-fold speedups for most codes. That acceleration means increased realism of simulations and decreased time to results. With the availability of new, higher-performance GPUs later this year, such as the Kepler GPU chip to be installed in the 20-petaflop Titan supercomputer at Oak Ridge National Laboratory (ORNL), application speedups are expected to be even more substantial.

A special report titled Accelerating Computational Science Symposium 2012 details these findings, which were presented earlier this year at Accelerating Computational Science Symposium 2012 in Washington, D.C.

Full Story
Accelerating Computational Science Symposium 2012 Report