ACM Home Page
Please provide us with feedback. Feedback
Dynamic tuning of configurable architectures: the AWW online algorithm
Full text PdfPdf (294 KB)
Source
International Conference on Hardware Software Codesign archive
Proceedings of the 6th IEEE/ACM/IFIP international conference on Hardware/Software codesign and system synthesis table of contents
Atlanta, GA, USA
SESSION: Exploration, profiling and tuning of embedded systems table of contents
Pages 97-102  
Year of Publication: 2008
ISBN:978-1-60558-470-6
Authors
Chen Huang  University of California, Riverside, Riverside, CA, USA
David Sheldon  University of California, Riverside, Riverside, CA, USA
Frank Vahid  University of California, Riverside, Riverside, CA, USA
Sponsors
SIGDA: ACM Special Interest Group on Design Automation
SIGBED: ACM Special Interest Group on Embedded Systems
ACM: Association for Computing Machinery
SIGMICRO: ACM Special Interest Group on Microarchitectural Research and Processing
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 10,   Downloads (12 Months): 67,   Citation Count: 0
Additional Information:

abstract   references   index terms   collaborative colleagues  

Tools and Actions: Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1450135.1450158
What is a DOI?

ABSTRACT

Architectures with software-writable parameters, or configurable architectures, enable runtime reconfiguration of computing platforms to the applications they execute. Such dynamic tuning can improve application performance, as well as energy. However, reconfiguring incurs a temporary performance cost. Thus, online algorithms are needed that decide when to reconfigure and which configuration to choose such that overall performance is optimized. We introduce the adaptive weighted window (AWW) algorithm, and compare with several other algorithms, including algorithms previously developed by the online algorithm community. We describe experiments showing that AWW results are within 4% of the offline optimal on average. AWW outperforms the other algorithms, and is robust across three datasets and across three categories of application sequences too. AWW improves a non-dynamic approach on average by 6%, and by up to 30% in low-reconfiguration-time situations.


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
D.H. Albonesi. Selective Cache Ways: On-Demand Cache Resource Allocation. Journal of Instruction Level. Parallelism, May 2000.
2
3
 
4
5
 
6
W.R. Burley and S. Irani. On algorithm design for metrical task system. Algorithmica, 1997, Vol. 18, pp. 461--485.
 
7
8
 
9
10
11
12
 
13
14
15

Collaborative Colleagues:
Chen Huang: colleagues
David Sheldon: colleagues
Frank Vahid: colleagues