[hpsdr] DttSP ovsv.c possible optimization?

Frank Brickle brickle at pobox.com
Mon Aug 13 11:17:14 PDT 2007


Chris Albertson wrote:

> This was a very expensive system but now only could make FFT/FFT-1
> chips using an FPGA.  After doing this a ham=style SDR could be run
> with even a low-end micro controller. Simply pre-store all the filters
> The linear nature of the FFT really does mean you can but
> __everything__ into just that one step.

There are a lot of nonlinearities in a full-up SDR. Some of them are 
analytic, which means they can be computed by table lookup or short 
series expansion. Some of the most important ones like AGC are not; they 
depend on conditional code execution at runtime.

It's also important for a processor to have a sufficiently rich 
structure to support robust multithreading. One reason to prefer the 
TMS320C67xx series is its native software support for embedding in a 
complex operating environment in that way.

73
Frank
AB2KT/VE7

 1187029034.0


More information about the Hpsdr mailing list