Processing large volumes of information generally requires massive amounts of computational power, which consumes a significant amount of energy. An emerging challenge is the development of "environmentally friendly" systems that are not only efficient in terms of time, but also energy efficient. In this poster, we outline our initial efforts at developing greener filtering systems by employing Field Programmable Gate Arrays (FPGA) to perform the core information processing task. FPGAs enable code to be executed in parallel at a chip level, while consuming only a fraction of the power of a standard (von Neuman style) processor. On a number of test collections, we demonstrate that the FPGA filtering system performs 10-20 times faster than the Itanium based implementation, resulting in considerable energy savings.
|Title of host publication||SIGIR '09 Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval|
|Place of Publication||New York, NY, USA|
|Number of pages||2|
|Publication status||Published - 19 Jul 2009|