denormal floats (was Re: [linux-audio-dev] XAP spec - early scribbles)

David Olofson david at
Thu Feb 6 19:04:00 UTC 2003

On Friday 07 February 2003 01.22, Simon Jenkins wrote:
> (IIRC:)
> If a plugin has got denormals coming out of its outputs, its pretty
> certain that its got them circulating around an internal feedback
> loop also, since thats where denormals generally come from.
> Killing denormals at the plugin output will stop them propogating
> through subsequent plugins, but do nothing to stop them propogating
> around inside the plugin that's generating them. In fact a plugin
> can have denormals circulating around inside it *without* producing
> denormals at its output.
> (IMHO:)
> Denormals need to be detected and killed in the feedback paths that
> generate them. These paths are inside the plugins, not between
> them, so its something the plugin author has got to get right, not
> something the API/host can effectively deal with.

This makes a *lot* of sense to me.

I say we should make it as simple as strongly recommending that 
plugins with algorithms that tend to generate denormals easily, 
should deal with it in a suitable way. Sounds both better and easier 
to me.

//David Olofson - Programmer, Composer, Open Source Advocate

.- The Return of Audiality! --------------------------------.
| Free/Open Source Audio Engine for use in Games or Studio. |
| RT and off-line synth. Scripting. Sample accurate timing. |
`---------------------------> -'
   --- --- ---

More information about the Linux-audio-dev mailing list