Title :
Self-Scaling Stream Processing: A Bio-Inspired Approach to Resource Allocation through Dynamic Task Replication
Author :
Mudry, Pierre-André ; Tempesti, Gianluca
Author_Institution :
Ecole Polytech. Fedfale de Lausanne, Lausanne, Switzerland
fDate :
July 29 2009-Aug. 1 2009
Abstract :
In this article, we show how the use of a bio-inspired dynamic task replication algorithm, in the context of stream processing, can be used to significantly improve the performance of embedded programs. We also show that this programming methodology, which is not tied to a particular implementation, can also be used as an heuristic for task mapping in the context of embedded multiprocessors systems. The technique was applied to a 36-processor system implemented on a scalable mesh of FPGAS for two different case studies: for AES encryption, it resulted in a ten-fold speedup compared to a static implementation, while for MJPEG compression a throughput multiplication of 11 was obtained.
Keywords :
field programmable gate arrays; multiprocessing systems; resource allocation; 36-processor system; FPGA; bioinspired dynamic task replication algorithm; embedded multiprocessors systems; resource allocation; self-scaling stream processing; Resource management; Adaptable architectures; Cellular architecture; Load balancing and task assignment; Multiple data stream architectures (Multiprocessors); Multiprocessor systems; Reconfigurable hardware;
Conference_Titel :
Adaptive Hardware and Systems, 2009. AHS 2009. NASA/ESA Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-0-7695-3714-6
DOI :
10.1109/AHS.2009.25
