Energy based performance tuning for large scale high performance computing systems

Abstract

Recognition of the importance of power in the field of High Performance Computing, whether it be as an obstacle, expense or design consideration, has never been greater and more pervasive. In response to this challenge, we exploit the unique power measurement capabilities of the Cray XT architecture to gain an understanding of the power requirements of important DOE/NNSA production scientific computing applications executing at large scale (thousands of nodes). The effect of both CPU frequency and network bandwidth scaling on power usage is characterized in a series of empirical experiments and demonstrates energy savings opportunities of up to 39% with little to no impact on run-time performance. Our results provide strong evidence that next generation large-scale platforms should not only approach CPU frequency scaling differently, but could also benefit from the ability to tune other platform components, such as the network, to achieve energy efficient performance.