Signalling change
1 min read
FPGAs are becoming more applicable in signal processing applications. By Edward Young and Paul Moakes.
If you were designing a high performance signal processing solution five years ago, selecting the processor was easy: dsps were clearly best. This was reflected in the wide choice of dsp based boards available from subsystem vendors.
Times have changed and fpgas have become increasingly attractive, with devices targeted at dsp applications and much improved development tools. Choosing between fpgas, dsps or a hybrid system today is not obvious, but a number of factors can help engineers make the right choice.
High performance dsps continue to develop with faster clock speeds and multicore solutions. Whilst experienced developers have built up a wealth of field proven application code to run on dsp cores, the dsp is not particularly well suited to parallel processing: multiple devices can be required for tasks which take only a fraction of the logic elements of an fpga. Conversely, fpgas are ill suited to processing sequential conditional data and the ever changing protocols of emerging standards make the dsp route attractive for some data processing: algorithms can be implemented readily in an accessible language, such as C.
