Matched Filter Computation on FPGA, Cell and GPU
Los Alamos Nat. Lab., Los Alamos
Field-Programmable Custom Computing Machines, 2007. FCCM 2007. 15th Annual IEEE Symposium on In Field-Programmable Custom Computing Machines, 2007. FCCM 2007. 15th Annual IEEE Symposium on (25 April 2007), pp. 207-218.
@conference{baker2007matched,
title={Matched filter computation on FPGA, Cell and GPU},
author={Baker, Z.K. and Gokhale, M.B. and Tripp, J.L.},
booktitle={Field-Programmable Custom Computing Machines, 2007. FCCM 2007. 15th Annual IEEE Symposium on},
pages={207–218},
year={2007},
organization={IEEE}
}
The matched filter is an important kernel in the processing of hyperspectral data. The filter enables researchers to sift useful data from instruments that span large frequency bands and can produce Gigabytes of data in seconds. In this work, we evaluate the performance of a matched filter algorithm implementation on an FPGA-accelerated co-processor (Cray XD-1), the IBM Cell microprocessor, and the NVIDIA GeForce 7900 GTX GPU graphics card. We provide extensive discussion of the challenges and opportunities afforded by each platform. In particular, we explore the problems of partitioning the filter most efficiently between the host CPU and the co-processor. Using our results, we derive several performance metrics that provide the optimal solution for a variety of application situations.
October 28, 2010 by hgpu
