[linux-audio-dev] XAP spec & PTAF comments [merge]

[Steve Harris]

On Sat, Feb 08, 2003 at 11:55:00 +0100, David Olofson wrote:
> On Saturday 08 February 2003 13.17, Steve Harris wrote:
> [...brachless clamp...]
> > Its not an instruction its just a bit of maths using fabs().
> 
> Yes, of course! I keep forgetting that fabs() is an FPU operation. :-) 
> (Life's not that nice with ints on most CPUs...)

Its not even an FPU op if you turn of the gcc optimisations, its just a
bitmask.
 
> If you want to make sure you *cannot* overload the CPU with the 
> current net, just have the host test it by turning all silent buffers 
> into cleared non-silent buffers.
> 
> Varying CPU load is not a problem in RT systems, but non-determinism 
> is. They may look confusingly similar from a practical POV, but 
> they're different things.

I suspect (but have no intention of finding out) that suddenly waking up a
large subnet will have large chace effects too, so it wont be a case of
just the CPU load varying.

- Steve