@article{freeh_kappiah_lowenthal_bletsch_2008, title={Just-in-time dynamic voltage scaling: Exploiting inter-node slack to save energy in MPI programs}, volume={68}, ISSN={["1096-0848"]}, DOI={10.1016/j.jpdc.2008.04.007}, abstractNote={Although users of high-performance computing are most interested in raw performance, both energy and power consumption have become critical concerns. As a result, improving energy efficiency of nodes on HPC machines has become important, and the prevalence of power-scalable clusters, where the frequency and voltage can be dynamically modified, has increased. On power-scalable clusters, one opportunity for saving energy with little or no loss of performance exists when the computational load is not perfectly balanced. This situation occurs frequently, as keeping the load balanced between nodes is one of the long-standing fundamental problems in parallel and distributed computing. Indeed, despite the large body of research aimed at balancing load both statically and dynamically, this problem is quite difficult to solve. This paper presents a system called Jitter that reduces the frequency and voltage on nodes that are assigned less computation and, therefore, have idle or slack time. This saves energy on these nodes, and the goal of Jitter is to attempt to ensure that they arrive “just in time” so that they avoid increasing overall execution time. Specifically, we dynamically determine which nodes have enough slack time such that they can execute at a reduced frequency with little performance cost—which will greatly reduce the consumed energy on that node. In particular, Jitter saves 12.8% energy with 0.4% time increase–which is essentially the same as a hand-tuned solution–on the Aztec benchmark.}, number={9}, journal={JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING}, author={Freeh, Vincent W. and Kappiah, Nandini and Lowenthal, David K. and Bletsch, Tyler K.}, year={2008}, month={Sep}, pages={1175–1185} }
 @article{freeh_lowenthal_pan_kappiah_springer_rountree_femal_2007, title={Analyzing the energy-time trade-off in high-performance computing applications}, volume={18}, ISSN={["1558-2183"]}, DOI={10.1109/TPDS.2007.1026}, abstractNote={Although users of high-performance computing are most interested in raw performance both energy and power consumption has 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 trade-off can be dynamically adjusted. This paper analyzes the energy-time trade-off 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 runtime, predict when each type of bottleneck occurs. Our results show that, for programs that have a memory or communication bottleneck, a power-scalable 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}, number={6}, journal={IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS}, author={Freeh, Vincent W. and Lowenthal, David K. and Pan, Feng and Kappiah, Nandini and Springer, Rob and Rountree, Barry L. and Femal, Mark E.}, year={2007}, month={Jun}, pages={835–848} }