Re: [iiwusynth-devel] Bugs / optimization

[M. Nentwig]

Hello,

> ... So that was another argument to have only 1 type of interpolation.

Well, cutting away almost 50 % of the CPU overhead was just too
tempting...
But the user has to set it explicitly, the default is unchanged.

>
> BTW, thanks for the profiling. Do you have an idea how much the DSP
> takes in respect to the parameter initialization in iiwu_voice_write?

I don't have my sheet with notes with me at the moment, but I think it
was roughy a microsecond out of 5 (20 %). The numbers I listed are given
from memory, that's why the sum is more than 100 %.
I'll send more accurate results tomorrow. It was done before I started
changing the code, anyway.

> It would be great to use SSE for the interpolation. Only to bad that
you
> can't use SSE to calculate the sum of four floats at once as in
> sum(a0,a1,a2,a3).

Yes, I think you are right. Do you know how expensive an addition is,
compared to a multiplication? If it is about the same, we could process
four samples at a time and then do the respective additions in parallel
afterwards. Will require some comments, though :(

I have a suspicion, that calculating the phase is another minor
bottleneck. Maybe there are still some folks with old hardware out
there, but I'm tempted to use a 'long long' integer instead.

Cheers

Markus