Re: [fluid-dev] problems with fluidsynth 1.1.6 on a raspberry pi

[David Henningsson]

On 11/19/2012 02:37 PM, Pedro Lopez-Cabanillas wrote:
> On Mon, Nov 19, 2012 at 1:05 PM, David Henningsson <address@hidden
> <mailto:address@hidden>> wrote:
>
>     Given that floats are faster on ARM devices (and probably older x86
>     devices as well), I think it makes sense to switch back to using
>     single point precision by default.
>
> I don't really care too much.

Ok, I'll change the default to float then.

>         Automatic denormals to zero doesn't prevent FP operations being
>         slower when
>         such numbers are involved. The problem is the larger CPU usage
>         if there are FP
>         exceptions, which happens in all CPUs except modern Intel
>         processors.
>
>
>     I'm trying to verify this theory,
>
>
> I'm not sure which part you don't buy: that there are still some
> problems with denormals or other FP exceptions in the DSP code? or that
> denormals are a problem in most architectures?  The former is pretty
> easy: the FPE check build option as I suggested. The latter is pretty
> well documented on the Net, I think.

I'm not convinced that this is a relevant performance hit. This could be 
either because denormal and/or FPU exception handling is not being so 
slow whenever this happens, or whether we don't get this often enough 
for it to relevant.

// David