Linpack evaluation on a supercomputer with heterogeneous accelerators
Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan
IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2010
@inproceedings{endo2010linpack,
title={Linpack evaluation on a supercomputer with heterogeneous accelerators},
author={Endo, T. and Nukada, A. and Matsuoka, S. and Maruyama, N.},
booktitle={Parallel & Distributed Processing (IPDPS), 2010 IEEE International Symposium on},
pages={1–8},
organization={IEEE},
year={2010}
}
We report Linpack benchmark results on the TSUBAME supercomputer, a large scale heterogeneous system equipped with NVIDIA Tesla GPUs and ClearSpeed SIMD accelerators. With all of 10,480 Opteron cores, 640 Xeon cores, 648 ClearSpeed accelerators and 624 NVIDIA Tesla GPUs, we have achieved 87.01TFlops, which is the third record as a heterogeneous system in the world. This paper describes careful tuning and load balancing method required to achieve this performance. On the other hand, since the peak speed is 163 TFlops, the efficiency is 53%, which is lower than other systems. This paper also analyses this gap from the aspect of system architecture.
July 17, 2011 by hgpu
