TY - GEN
T1 - Energy efficient real-time task scheduling on CPU-GPU hybrid clusters
AU - Mei, Xinxin
AU - CHU, Xiaowen
AU - Liu, Hai
AU - LEUNG, Yiu Wing
AU - Li, Zongpeng
N1 - Funding Information:
ACKNOWLEDGEMENT This work is partially supported by HKBU Grant FRG2/14-15/059 and Shenzhen Basic Research Grant SCI-2015-SZTIC-002.
PY - 2017/5
Y1 - 2017/5
N2 - Conserving the energy consumption of large data centers is of critical significance, where a few percent in consumption reduction translates into millions-dollar savings. This work studies energy conservation on emerging CPU-GPU hybrid clusters through dynamic voltage and frequency scaling (DVFS). We aim at minimizing the total energy consumption of processing a sequence of real-time tasks under deadline constraints. We compute the appropriate voltage/frequency setting for each task through mathematical optimization, and assign multiple tasks to the cluster with heuristic scheduling algorithms. In performance evaluation driven by real-world power measurement traces, our scheduling algorithm shows comparable energy savings to the theoretical upper bound. With a GPU scaling interval where analytically at most 38% of energy can be saved, we record 30-36% of energy savings. Our results are applicable to energy management on modern heterogeneous clusters. In particular, our model stresses the nonlinear relationship between task execution time and processor speed for GPU-accelerated applications, for more accurately capturing real-world GPU energy consumption.
AB - Conserving the energy consumption of large data centers is of critical significance, where a few percent in consumption reduction translates into millions-dollar savings. This work studies energy conservation on emerging CPU-GPU hybrid clusters through dynamic voltage and frequency scaling (DVFS). We aim at minimizing the total energy consumption of processing a sequence of real-time tasks under deadline constraints. We compute the appropriate voltage/frequency setting for each task through mathematical optimization, and assign multiple tasks to the cluster with heuristic scheduling algorithms. In performance evaluation driven by real-world power measurement traces, our scheduling algorithm shows comparable energy savings to the theoretical upper bound. With a GPU scaling interval where analytically at most 38% of energy can be saved, we record 30-36% of energy savings. Our results are applicable to energy management on modern heterogeneous clusters. In particular, our model stresses the nonlinear relationship between task execution time and processor speed for GPU-accelerated applications, for more accurately capturing real-world GPU energy consumption.
UR - http://www.scopus.com/inward/record.url?scp=85021417951&partnerID=8YFLogxK
U2 - 10.1109/INFOCOM.2017.8057205
DO - 10.1109/INFOCOM.2017.8057205
M3 - Conference proceeding
AN - SCOPUS:85021417951
T3 - Proceedings - IEEE INFOCOM
BT - INFOCOM 2017 - IEEE Conference on Computer Communications
PB - IEEE
T2 - IEEE International Conference on Computer Communications, IEEE INFOCOM 2017
Y2 - 1 May 2017 through 4 May 2017
ER -