[LAU] benchmarking your audio system

[James Morris]

On 23 October 2010 07:43, david <gnome at hawaii.rr.com> wrote:
> Joan Quintana wrote:
>>
>> I had the idea in mind to test my machine (and trying to benchmark the
>> tests), loading the session with a chain of JACK clients, in order to know
>> the limits of my system and in what conditions the system is stressed, and
>> when I would have more chances of XRUNS.
>>
>> The chain would be something like this.
>>
>> *playing a midi file with Rosegarden (a midifile full of tracks)
>> *fluidsynth as a soft synth, loading a heavy soundfont.
>> *JACK RACK for LADSPA effects (load several processor consuming effects)
>> *recording the session into Ardour, at the same time that monitoring the
>> output to the speakers
>>
>> Meanwhile I will monitor the system performance (processor & RAM). (I
>> thing that Conky System Monitor would do the task of saving a log file for
>> later parsing). I don't know if it is possible to fetch the number of XRuns
>> from a file or log.
>>
>> Questions:
>> -how can I stress even more this test?
>
> While it's doing all that, fire up some complex synthesizer patches in Pure
> Data or csound or AmSynth or AMS or Zyn or some other synthesizer that does
> a lot of processing to generate its sound. Synthesizer patches that generate
> their own changing sounds would be great. Alsa Modular Synthesizer has a
> living_phaser patch and probably other patches that do that.
>
> Or you could download and install the trial version of the Bibble photo
> processing program <http://www.bibblelabs.com/>. It is one of the most
> processor and memory intensive programs I've ever encountered. Install it,
> do some basic processing of an entire directory of large images, then have
> it batch process the images ...
>
> Another thought: add a Windows audio app running under WINE or on a virtual
> machine running Windows.
>
> Oh, and install XFractint and have it do a deep zoom somewhere into the
> Mandelbrot set.

try MDZ - mandelbrot deep zoom, it uses the MPFR math library to go
beyond long-double precision to as deep as you have patience for. by
default for some peculiar reason it also uses 64 threads. makes the
system very unresponsive i promise.

http://jwm-art.net/mdz/


-- 
_
: http://jwm-art.net/
-audio/image/text/code