FPGAs

Benefits to Modern Embedded Systems

Many real-time multicomputing problems are computationally challenging, requiring tens, or even hundreds of processors working in concert. Some of these difficult problems such as convolution, rebinning, backprojection, and synthetic aperture radar (SAR) signal formation and range/azimuth compression can be implemented in FPGAs with a 5:1 to 50:1 performance improvement over a single general-purpose microprocessor. High performance and dynamic reconfiguration are significant benefits FPGAs bring to modern embedded systems.

An Effective Solution

Certain characteristics of an algorithm may point to FPGAs as an effective solution. One indicator of suitability is low-bit arithmetic precision (fixed point). Another indicative characteristic is an algorithm that can be implemented in a highly parallel fashion. Moreover, algorithms that require repetitive, calculated memory access might be good candidates for an FPGA adjunct processor. Other characteristics favoring FPGAs include masking and thresholding; 2- or 4-bit, highly parallel logic operations; massive parallelization of integer arithmetic-logic units (ALUs); non-sequential memory access; and lookup table (LUT) functions.