TY - GEN
T1 - Bounding energy consumption in large-scale MPI programs
AU - Rountree, Barry
AU - Lowenthal, David K.
AU - Funk, Shelby
AU - Freeh, Vincent W.
AU - De Supinski, Bronis R.
AU - Schulz, Martin
PY - 2007
Y1 - 2007
N2 - Power is now a first-order design constraint in large-scale parallel computing. Used carefully, dynamic voltage scaling can execute parts of a program at a slower CPU speed to achieve energy savings with a relatively small (possibly zero) time delay. However, the problem of when to change frequencies in order to optimize energy savings is NP-complete, which has led to many heuristic energy-saving algorithms. To determine how closely these algorithms approach optimal savings, we developed a system that determines a bound on the energy savings for an application. Our system uses a linear programming solver that takes as inputs the application communication trace and the cluster power characteristics and then outputs a schedule that realizes this bound. We apply our system to three scientific programs, two of which exhibit load imbalance - particle simulation and UMT2K. Results from our bounding technique show particle simulation is more amenable to energy savings than UMT2K. (c) 2007 ACM.
AB - Power is now a first-order design constraint in large-scale parallel computing. Used carefully, dynamic voltage scaling can execute parts of a program at a slower CPU speed to achieve energy savings with a relatively small (possibly zero) time delay. However, the problem of when to change frequencies in order to optimize energy savings is NP-complete, which has led to many heuristic energy-saving algorithms. To determine how closely these algorithms approach optimal savings, we developed a system that determines a bound on the energy savings for an application. Our system uses a linear programming solver that takes as inputs the application communication trace and the cluster power characteristics and then outputs a schedule that realizes this bound. We apply our system to three scientific programs, two of which exhibit load imbalance - particle simulation and UMT2K. Results from our bounding technique show particle simulation is more amenable to energy savings than UMT2K. (c) 2007 ACM.
UR - http://www.scopus.com/inward/record.url?scp=56749165148&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=56749165148&partnerID=8YFLogxK
U2 - 10.1145/1362622.1362688
DO - 10.1145/1362622.1362688
M3 - Conference contribution
AN - SCOPUS:56749165148
SN - 9781595937643
T3 - Proceedings of the 2007 ACM/IEEE Conference on Supercomputing, SC'07
BT - Proceedings of the 2007 ACM/IEEE Conference on Supercomputing, SC'07
T2 - 2007 ACM/IEEE Conference on Supercomputing, SC'07
Y2 - 10 November 2007 through 16 November 2007
ER -