ACM Home Page
Please provide us with feedback. Feedback
Energy optimization techniques in cluster interconnects
Full text PdfPdf (287 KB)
Source International Symposium on Low Power Electronics and Design archive
Proceedings of the 2003 international symposium on Low power electronics and design table of contents
Seoul, Korea
SESSION: Sensor networks and communication systems table of contents
Pages: 459 - 464  
Year of Publication: 2003
ISBN:1-58113-682-X
Authors
E. J. Kim  Pennsylvania State University, University Park, PA
K. H. Yum  The University of Texas at San Antonio, San Antonio, TX
G. M. Link  Pennsylvania State University, University Park, PA
N. Vijaykrishnan  Pennsylvania State University, University Park, PA
M. Kandemir  Pennsylvania State University, University Park, PA
M. J. Irwin  Pennsylvania State University, University Park, PA
M. Yousif  The University of Texas at San Antonio, San Antonio, TX
C. R. Das  Pennsylvania State University, University Park, PA
Sponsors
ACM: Association for Computing Machinery
SIGDA: ACM Special Interest Group on Design Automation
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 6,   Downloads (12 Months): 40,   Citation Count: 22
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/871506.871620
What is a DOI?

ABSTRACT

Designing energy-efficient clusters has recently become an important concern to make these systems economically attractive for many applications. Since the links and switch buffers consume the major portion of the power budget of the cluster, the focus of this paper is to optimize the energy consumption in these two components. To minimize power in the links, we propose a novel dynamic link shutdown (DLS) technique. The DLS technique makes use of an appropriate adaptive routing algorithm to shutdown the links intelligently. We also present an optimized buffer design for reducing leakage energy. Our analysis on different networks using a complete system simulator reveals that the proposed DLS technique can provide optimized performance-energy behavior (up to 40% energy savings with less than 5% performance degradation in the best case) for the cluster interconnects.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
W. Dally, P. Carvey, and L. Dennison. The Avici Terabit Switch/Router. In Proc. Hot Interconnects 6, 1998.
 
2
 
3
InfiniBand Trade Association. InfiniBand Architecture Specification, Volume 1, Release 1.0, October 2000. Available from http://www.infinibandta.org.
 
4
 
5
J. Kim and M. Horowitz. Adaptive Supply Serial Links with Sub-1V Operation and Per-Pin Clock Recovery. In Proc. ISSCC, 2002.
 
6
 
7
 
8
9
 
10
The New York Times. There's money in housing internet servers, April 2001. http://www.internetweek.com/story/INW20010427S0010.
 
11
T. G. Tip. RDRAM Power Estimation and Thermal Considerations, October 2001. http://www.rambus.com/rdf/presentations/2_A3_Thermal_Yip2.pdf.
 
12
 
13
G.-Y. Wei, S. Sidiropoulos, D. Liu, J. Kim, and M. Horowitz. A Variable-Frequency Parallel I/O Interface with Adaptive Power-Supply Regulation. IEEE J. of Solid-State Circuits, 35, Nov. 2000.
14

CITED BY  22

Collaborative Colleagues:
E. J. Kim: colleagues
K. H. Yum: colleagues
G. M. Link: colleagues
N. Vijaykrishnan: colleagues
M. Kandemir: colleagues
M. J. Irwin: colleagues
M. Yousif: colleagues
C. R. Das: colleagues