Cited By
View all- Dayarathna MWen YFan R(2016)Data Center Energy Consumption Modeling: A SurveyIEEE Communications Surveys & Tutorials10.1109/COMST.2015.248118318:1(732-794)Online publication date: 27-Jan-2016
Evaluation of Core Hopping on POWER7
Pages 55 - 60
Abstract
Controlling and limiting the peak runtime temperature of a microprocessor has the potential to reduce chip leakage power consumption, improve chip reliability, reduce provisioned cooling, and reduce operational costs. Previously, the technique of core hopping has been proposed as one method to reduce peak runtime temperature. However, there is no study that shows core hopping is beneficial for modern many-core microprocessors found in high-end servers. This paper thoroughly examines heat spreading in the 8-core POWER7 microprocessor which provides 5 temperature sensors per core. We find that the POWER7 heatsink has excellent heat spreading capabilities which negates the benefits of core hopping. We conclude that high-performance servers with similar thermal solutions will also not see benefit from core-hopping methods.
References
[1]
P. Bailis et al. Dimetrodon: Processor-level preventive thermal management via idle cycle injection. In DAC-48, pages 89--94, 2011.
[2]
M. Broyles et al. IBM EnergyScale for POWER7 processor-based systems. white paper, IBM, 2010.
[3]
J. Choi et al. Thermal-aware task scheduling at the system software level. In ISLPED'07, pages 213--218, 2007.
[4]
CNET News. http://news.cnet.com/2100-1001-954456.html.
[5]
R. Cochran and S. Reda. Consistent runtime thermal prediction and control through workload phase detection. In DAC-47, pages 62--67, 2010.
[6]
M. Floyd et al. Introducing the adaptive energy management features of the POWER7 chip. IEEE Micro, 31(2):60--75, 2011.
[7]
Y. Ge et al. Distributed task migration for thermal management in many-core systems. In DAC-47, pages 579--584, 2010.
[8]
Intel Corp. Intel is leading the way in designing energy-efficient platforms (white paper).
[9]
J. Kong et al. Recent thermal management techniques for microprocessors. ACM Computing Surveys, 44(3):13:1--13:42, June 2012.
[10]
E. Kursun and C.-Y. Cher. Variation-aware thermal characterization and management of multi-core architectures. In ICCD-26, pages 280--285, 2008.
[11]
E. Kursun et al. Low-overhead core swapping for thermal management. In PACS'04, pages 46--60, 2005.
[12]
S. Lingampalli et al. Performance optimization of multi-core processors using core hopping - thermal and structures. In SEMI-THERM'12, pages 112--117, 2012.
[13]
A. Raghavan et al. Computational sprinting. In HPCA-18, pages 1--12, 2012.
[14]
A. Raghu et al. Thermal-aware power migration in many-core processors. In ASME'10, pages 385--392, 2010.
[15]
A. Shayesteh et al. Reducing the latency and area cost of core swapping through shared helper engines. In ICCD-23, pages 17--23, 2005.
[16]
B. Sinharoy et al. IBM POWER7 multicore server processor. IBM Journal of Research and Development, 55(3):191--219, may 2011.
[17]
J. Srinivasan and S. V. Adve. Predictive dynamic thermal management for multimedia applications. In ICS'03, pages 109--120, 2003.
[18]
I. Yeo et al. Predictive dynamic thermal management for multicore systems. In DAC-45, pages 734--739, 2008.
Index Terms
- Evaluation of Core Hopping on POWER7
Recommendations
Power-performance management on an IBM POWER7 server
ISLPED '10: Proceedings of the 16th ACM/IEEE international symposium on Low power electronics and designThe processor and cooling subsystems of high-performance servers consume a significant portion of total system power. In this paper, we use the server energy-efficiency benchmark SPECpower_ssj2008 to assess dynamic power management strategies for these ...
An application-centric evaluation of OpenCL on multi-core CPUs
Although designed as a cross-platform parallel programming model, OpenCL remains mainly used for GPU programming. Nevertheless, a large amount of applications are parallelized, implemented, and eventually optimized in OpenCL. Thus, in this paper, we ...
OpenCL Performance Evaluation on Modern Multi Core CPUs
IPDPSW '13: Proceedings of the 2013 IEEE 27th International Symposium on Parallel and Distributed Processing Workshops and PhD ForumUtilizing heterogeneous platforms for computation has become a general trend making the portability issue important. OpenCL (Open Computing Language) serves the purpose by enabling portable execution on heterogeneous architectures. However, ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
December 2014
80 pages
Copyright © 2014 Authors.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 December 2014
Published in SIGMETRICS Volume 42, Issue 3
Check for updates
Author Tags
Qualifiers
- Extended-abstract
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 55Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 17 Dec 2024
Other Metrics
Citations
Cited By
View all- Dayarathna MWen YFan R(2016)Data Center Energy Consumption Modeling: A SurveyIEEE Communications Surveys & Tutorials10.1109/COMST.2015.248118318:1(732-794)Online publication date: 27-Jan-2016
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in