DocumentCode
3651834
Title
Agent-based distributed power management for Kilo-core processors: Special Session: “Keeping Kilo-core chips cool: New directions and emerging solutions”
Author
Muhammad Shafique;Jorg Henkel
Author_Institution
Dept. of Embedded Syst., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany
fYear
2013
Firstpage
153
Lastpage
160
Abstract
Power management for Kilo-core processors have become an intricate problem due to the scalability issues and mixed-workloads of massively multi-threaded applications. This paper highlights the power related issues in Kilo-core processors and presents two emerging trends towards agent-based distributed and self-adaptive power management for Kilo-core processors. Agent-based power management allows applications to autonomously control the power states of their resources while operate efficiently as a whole to improve the overall system´s energy efficiency. The first approach based on our concept of virtual power gating that allows applications to temporarily reserve their resources to locally optimize for power efficiency. The second approach is game-theoretic power management to achieve fair resource allocations while maximizing the energy efficiency. We present results for scalability and energy efficiency.
Keywords
"Games","Program processors","Energy efficiency","Resource management","Multicore processing","Transfer functions","Tiles"
Publisher
ieee
Conference_Titel
Computer-Aided Design (ICCAD), 2013 IEEE/ACM International Conference on
ISSN
1092-3152
Electronic_ISBN
1558-2434
Type
conf
DOI
10.1109/ICCAD.2013.6691112
Filename
6691112
Link To Document