Re: [fluid-dev] High DSP load

[Pedro Lopez-Cabanillas]

On Saturday, October 24, 2009, address@hidden wrote:
> Quoting Pedro Lopez-Cabanillas <address@hidden>:
> > What about adding a call to jack_cpu_load() in fluid_jack.c, and logging
> > the results?
>
> Good idea.  Just did that, ran some tests, saved the output numbers to
> files and graphed the results from both versions using gnuplot:
> plot "FluidSynth-1.1.0.txt" with lines, "FluidSynth-1.0.9.txt" with lines
>
> http://resonance.org/~josh/FluidSynth-AutumnLeaves-graph.png
>
> Very little difference in my case.  In fact 1.0.9 spikes higher than
> 1.1.0 for that test on my system.

Sorry, my mistake. I was compiling 1.1.0 in debug mode, comparing it with an 
optimized 1.0.9 build. After disabling debug, the results are pretty much the 
same as yours. I've repeated the tests in two test machines and here are the 
plots, using the same song and SoundFont:

http://plcl.users.sourceforge.net/fluid/AMDK7-FluidSynth-AutumLeaves.png
test machine: AMD Athlon XP 2800+ Speed: 2 GHz
with jackdmp 1.9.2

http://plcl.users.sourceforge.net/fluid/Core2-FluidSynth-AutumLeaves.png
test machine: Intel Core2Duo T7200 Speed: 2 GHz
with jackd 0.109.2

>
> Here is the code fragment I added at the top of
> fluid_jack_audio_driver_process() in fluid_jack.c:
>
>    static int stats_frame_counter = 0;
>    float cpuload;
>
>    stats_frame_counter += nframes;
>
>    if (stats_frame_counter > 48000)
>    {
>      cpuload = jack_cpu_load (dev->client);
>      printf ("%0.3f\n", cpuload);
>      stats_frame_counter = 0;
>    }

Regards,
Pedro