Faculty of Engineering and Natural Sciences
Field Programmable Gate Array (FPGA) Based Evaluation of
Low Density Parity Check (LDPC) Codes
Prof. Vijayakumar Bhagavatula
Dept. of Electrical and Computer Eng. Carnegie Mellon University
We all have come to enjoy constantly-increasing hard disk drive (HDD) capacities. Maintaining such storage density increases will require the use of advanced codes such as low-density parity-check (LDPC) codes. While LDPC codes have shown superior error correcting performance in a variety of data storage system simulations, the theory for LDPC codes is not well developed and we do not completely know the error correcting behavior for many LDPC codes. For example, many LDPC codes exhibit error floor, i.e., the phenomenon where bit error rate (BER) does not decrease much with increasing SNR. Another aspect of importance in data storage applications is the data rate --- for this reason, LDPC codes with hardware-friendly structure are important. Also, software implementations of LDPC decoding are too slow to achieve the very low BERs (about 10-10) that are of interest. To address these issues, we have implemented on a field programmable gate array (FPGA) platform a magnetic recording model that includes realistic impairments, soft output Viterbi algorithm (SOVA), LDPC encoder and decoder. This talk will provide the motivation for and the details of our FPGA LDPC channel implementation as well some sample results from the use of this FPGA platform.
Vijayakumar Bhagavatula received his Ph.D. in Electrical Engineering from Carnegie Mellon University (CMU), Pittsburgh and since 1982, he has been a faculty member in the Electrical and Computer Engineering (ECE) Department at CMU where he is now a Professor. He served as the Associate Head of the ECE Department from 1994 to 1996 and as its Acting Department Head during 2004-2005. In 2003, he received the Eta Kappa Nu Most Outstanding Teacher award in ECE Department at Carnegie Mellon University. Professor Kumar's research interests include Pattern Recognition (for automatic target recognition and biometrics applications) and Coding and Signal Processing for Data Storage Systems and for Digital Communications. He has authored or co-authored about 400 technical papers and one book entitled Correlation Pattern Recognition. He served as a Topical Editor for the Information Processing division of Applied Optics. Professor Kumar is a member of Sigma Xi, a senior member of IEEE, a Fellow of SPIE - The International Society of Optical Engineering, and a Fellow of Optical Society of America (OSA). He is listed in Marquis’ Who’s Who in the World and in the American Men and Women of Sciences.
September 14, 2006, 14:40, FENS G032