TY - JOUR
T1 - A multi-agent framework for thermal aware task migration in many-core systems
AU - Ge, Yang
AU - Qiu, Qinru
AU - Wu, Qing
N1 - Funding Information:
Manuscript received July 29, 2010; revised January 24, 2011 and May 16, 2011; accepted June 13, 2011. Date of publication August 30, 2011; date of current version July 19, 2012. This work was supported by the National Science Foundation under Grant CNS-0845947. Y. Ge and Q. Qiu are with the Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY 13244 USA (e-mail: [email protected]; [email protected]). Q. Wu is with the Information Directorate of United States Air Force Research Laboratory, Rome, NY 13440 USA (e-mail: [email protected]). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TVLSI.2011.2162348
PY - 2012
Y1 - 2012
N2 - In deep submicrometer era, thermal hot spots, and large temperature gradients significantly impact system reliability, performance, cost, and leakage power. As the system complexity increases, it is more and more difficult to perform thermal management in a centralized manner because of state explosion and the overhead of monitoring the entire chip. In this paper, we propose a framework for distributed thermal management in many-core systems where balanced thermal profile can be achieved by proactive task migration among neighboring cores. The framework has a low cost agent residing in each core that observes the local workload and temperature and communicates with its nearest neighbor for task migration and exchange. By choosing only those migration requests that will result in balanced workload without generating thermal emergency, the proposed framework maintains workload balance across the system and avoids unnecessary migration. Experimental results show that, our distributed management policy achieves almost the same performance as a global management policy when the tasks are initially randomly distributed. Compared with existing proactive task migration technique, our approach generates less hotspot, less migration overhead with negligible performance overhead.
AB - In deep submicrometer era, thermal hot spots, and large temperature gradients significantly impact system reliability, performance, cost, and leakage power. As the system complexity increases, it is more and more difficult to perform thermal management in a centralized manner because of state explosion and the overhead of monitoring the entire chip. In this paper, we propose a framework for distributed thermal management in many-core systems where balanced thermal profile can be achieved by proactive task migration among neighboring cores. The framework has a low cost agent residing in each core that observes the local workload and temperature and communicates with its nearest neighbor for task migration and exchange. By choosing only those migration requests that will result in balanced workload without generating thermal emergency, the proposed framework maintains workload balance across the system and avoids unnecessary migration. Experimental results show that, our distributed management policy achieves almost the same performance as a global management policy when the tasks are initially randomly distributed. Compared with existing proactive task migration technique, our approach generates less hotspot, less migration overhead with negligible performance overhead.
KW - Distributed control
KW - dynamic thermal management
KW - multi-agent
KW - prediction
KW - task migration
UR - http://www.scopus.com/inward/record.url?scp=84864770865&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864770865&partnerID=8YFLogxK
U2 - 10.1109/TVLSI.2011.2162348
DO - 10.1109/TVLSI.2011.2162348
M3 - Article
AN - SCOPUS:84864770865
SN - 1063-8210
VL - 20
SP - 1758
EP - 1771
JO - IEEE Transactions on Very Large Scale Integration (VLSI) Systems
JF - IEEE Transactions on Very Large Scale Integration (VLSI) Systems
IS - 10
M1 - 6004860
ER -