Developing energy efficient filtering systems

ABSTRACT

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.

REFERENCES

• 1: C. L. Belady. In the data center, power and cooling costs more than the it equipment it supports. Electronics Cooling, 13(1), 2007.
• 2: Nicholas J. Belkin , W. Bruce Croft, Information filtering and information retrieval: two sides of the same coin?, Communications of the ACM, v.35 n.12, p.29-38, Dec. 1992 [doi>10.1145/138859.138861]
• 3: Victor Lavrenko , W. Bruce Croft, Relevance based language models, Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval, p.120-127, September 2001, New Orleans, Louisiana, United States [doi>10.1145/383952.383972]
• 4: Cameron McNairy , Rohit Bhatia, Montecito: A Dual-Core, Dual-Thread Itanium Processor, IEEE Micro, v.25 n.2, p.10-20, March 2005 [doi>10.1109/MM.2005.34]
• 5: S. Sharp. Virtex-4 Dynamic Power Comparison -- A Case Study, dec 2005.
• 6: O. Storaasli, D. Strenski, and C. Inc. Exploring Accelerating Science Applications with FPGAs. Proc. of the Reconfigurable Systems Summer Institute, July, 2007.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.4 Systems and Software
          Subjects: Performance evaluation (efficiency and effectiveness)

General Terms:
Performance

Keywords:
FPGA, efficiency, filtering