|Name:||Algorithms & Analysis(1) ISC'13 Award Winning PosterPerformance of the Fusion Code GYRO on Three Generations of Cray Computers|
|Time:||Monday, June 17, 2013
1:10 PM - 1:30 PM
|Room:||Multi-Purpose Area 4 (MPA 4)
CCL - Congress Center Leipzig
|Speakers:||Vince Betro, University of Tennessee|
|Abstract:||GYRO is a code used for the direct numerical simulation of plasma microturbulence. It has been ported to a variety of modern MPP platforms including several modern commodity clusters, IBM SPs, and Cray XT and XE series machines. We briefly describe the mathematical structure of the equations, the data layout, and the redistribution scheme. Also, while the performance and scaling of GYRO on many of these systems has been shown before, here we show the comparative performance and scaling on three generations of Cray supercomputers simultaneously including the newest addition - the Cray CS300-AC™ Cluster Supercomputer. We also show that the recently added hybrid OpenMP/MPI implementation shows a great deal of promise not only on traditional HPC systems that utilize fast CPUs and proprietary interconnects but also on a coprocessor architecture in a cluster environment in native mode. Three machines of varying sizes were used in the experiment, all of which are located at the National Institute for Computational Sciences at the University of Tennessee at Knoxville and Oak Ridge National Laboratory. Kraken is a 112,896 core Cray XT5 with AMD Opteron™ Istanbul CPUs; Ares is an 896 core Cray XE6 with AMD Opteron™ Interlagos CPUs; and Beacon is a 1,024 core Cray CS300-AC™ Cluster Supercomputer with Intel® Xeon® E5-2670 (Sandybridge) CPUs and Intel® Xeon Phi™ coprocessors. The advantages, limitations, and performance of using each system are discussed, as well as the direction of future optimizations.
Vincent C. Betro, University of Tennessee; Mark Fahey, University of Tennessee