Publication Details

Automatic Design of Arbitrary-Size Approximate Sorting Networks with Error Guarantee

MRÁZEK Vojtěch and VAŠÍČEK Zdeněk. Automatic Design of Arbitrary-Size Approximate Sorting Networks with Error Guarantee. In: Power and Timing Modeling, Optimization and Simulation (PATMOS), 2016 26rd International Workshop on. Bremen: Institute of Electrical and Electronics Engineers, 2016, pp. 221-228. ISBN 978-1-5090-0733-2.
Czech title
Automatický návrh různě velkých aproximačních řadicích sítí s garancí chyby
Type
conference paper
Language
english
Authors
Mrázek Vojtěch, Ing., Ph.D. (DCSY FIT BUT)
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY FIT BUT)
Keywords


approximate computing
sorting networks
genetic programming

Abstract

Despite the fact that hardware sorters offer great performance, they become expensive as the number of inputs increases. In order to address the problem of high-performance and power-efficient computing, we propose a scalable method for construction of power-efficient sorting networks suitable for hardware implementation. The proposed approach exploits the error resilience which is present in many real-world applications such as digital signal processing, biological computing and large-scale scientific computing. The method is based on recursive construction of large sorting networks using smaller instances of approximate sorting networks. The design process is tunable and enables to achieve desired tradeoffs between the accuracy and power consumption or implementation cost. A search-based design method is used to obtain approximate sorting networks. To measure and analyze the accuracy of approximate networks, three data-independent quality metrics are proposed. Namely, guarantee of error probability, worst-case error and error distribution are discussed. A significant improvement in the implementation cost and power consumption was obtained. For example, 20% reduction in power consumption was achieved by introducing a small error in 256-input sorter. The difference in rank is proved to be not worse than 2 with probability at least 99%. In addition to that, it is guaranteed that the worst-case difference is equal to 6.

Published
2016
Pages
221-228
Proceedings
Power and Timing Modeling, Optimization and Simulation (PATMOS), 2016 26rd International Workshop on
Conference
26th International Workshop on Power And Timing Modeling, Optimization and Simulation, Bremen, DE
ISBN
978-1-5090-0733-2
Publisher
Institute of Electrical and Electronics Engineers
Place
Bremen, DE
DOI
10.1109/PATMOS.2016.7833691
UT WoS
000401809900038
EID Scopus
2-s2.0-85014115335
BibTeX 
@INPROCEEDINGS{FITPUB11175,
   author = "Vojt\v{e}ch Mr\'{a}zek and Zden\v{e}k Va\v{s}\'{i}\v{c}ek",
   title = "Automatic Design of Arbitrary-Size Approximate Sorting Networks with Error Guarantee",
   pages = "221--228",
   booktitle = "Power and Timing Modeling, Optimization and Simulation (PATMOS), 2016 26rd International Workshop on",
   year = 2016,
   location = "Bremen, DE",
   publisher = "Institute of Electrical and Electronics Engineers",
   ISBN = "978-1-5090-0733-2",
   doi = "10.1109/PATMOS.2016.7833691",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11175"
}
Files
Back to top