Abstract | ||
---|---|---|
Most applications running on supercomputers achieve only a fraction of the peak performance of the system. In this paper we analyze the performance and energy efficiency of co-scheduling one memory bandwidth bound and one compute bound application on the same node. We present auto pin+, a tool designed to monitor and optimize co-scheduling of applications. Our analysis shows that co-scheduling can improve both energy efficiency and overall throughput of a supercomputer. At best, runtime can be decreased by 28% and the energy consumption by 12%, respectively, compared to best case dedicated execution. The overall efficiency however strongly depends on the ratio of jobs available in the queue. We furthermore present a simple adaptive strategy depending on the available jobs in the queue. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICPPW.2015.38 | ICPP Workshops |
Keywords | Field | DocType |
HPC,co-scheduling,energy efficiency,job scheduling | Memory bandwidth,Supercomputer,Efficient energy use,Computer science,Queue,Parallel computing,Bandwidth (signal processing),Job scheduler,Throughput,Energy consumption,Distributed computing | Conference |
ISSN | Citations | PageRank |
1530-2016 | 5 | 0.55 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jens Breitbart | 1 | 17 | 5.22 |
Josef Weidendorfer | 2 | 115 | 17.98 |
Carsten Trinitis | 3 | 151 | 29.80 |