Boosting XML Filtering with a Scalable FPGA-based Architecture - Computer Science > Hardware ArchitectureReport as inadecuate

Boosting XML Filtering with a Scalable FPGA-based Architecture - Computer Science > Hardware Architecture - Download this document for free, or read online. Document in PDF available to download.

Abstract: The growing amount of XML encoded data exchanged over the Internet increasesthe importance of XML based publish-subscribe pub-sub and content basedrouting systems. The input in such systems typically consists of a stream ofXML documents and a set of user subscriptions expressed as XML queries. Thepub-sub system then filters the published documents and passes them to thesubscribers. Pub-sub systems are characterized by very high input ratios,therefore the processing time is critical. In this paper we propose a -purehardware- based solution, which utilizes XPath query blocks on FPGA to solvethe filtering problem. By utilizing the high throughput that an FPGA providesfor parallel processing, our approach achieves drastically better throughputthan the existing software or mixed hardware-software architectures. TheXPath queries subscriptions are translated to regular expressions which arethen mapped to FPGA devices. By introducing stacks within the FPGA we are ableto express and process a wide range of path queries very efficiently, on ascalable environment. Moreover, the fact that the parser and the filterprocessing are performed on the same FPGA chip, eliminates expensivecommunication costs that a multi-core system would need thus enabling veryfast and efficient pipelining. Our experimental evaluation reveals more thanone order of magnitude improvement compared to traditional pub-sub systems.

Author: Abhishek Mitra UC Riverside, Marcos Vieira UCR, Petko Bakalov ESRI, Walid Najjar UCR, Vassilis Tsotras UCR


Related documents