Re: Denormals
Posted: Thu Sep 18, 2014 11:47 pm
The CPU usage of the denormal remover are relatively small (one comaprison, two "and" operations one writing to value...around 7 cycles).tester wrote:Will/would such portion of code change something (CPU usage) in (where in the design where? input?) zdf filters posted somewhere here?
You should put it in the feedback of the algorithm. just in front of the link that loops backward.