Analyzing the Energy-Time Tradeoff in High-Performance Computing Applications

Although users of high-performance computing are most interested in raw performance, both energy and power consumption have become critical concerns. One approach to lowering energy and power is to use high-performance cluster nodes that have several power-performance states, so that the energy-time tradeoff can be dynamically adjusted. This paper analyzes the energy-time tradeoff of a wide range of applications–serial and parallel— on a power-scalable cluster. We use a cluster of frequency- and voltage-scalable AMD-64 nodes, each equipped with a power meter. We study the effects of memory and communication bottlenecks via direct measurement of time and energy. We also investigate metrics that can, at run time, predict when each type of bottleneck occurs. Our results show that for programs that have a memory or communication bottleneck, a powerscalable cluster can save significant energy with only a small time penalty. Furthermore, we find that for some programs, it is possible to both consume less energy and execute in less time by increasing the number of nodes while reducing the frequency-voltage setting of each node.