Yeah, I imagine with no kernel doing timeslicing, Pd would literally have all
of the CPU time, and the audio output to the hardware happen more often than
every 64 samples.
.hc
On Apr 2, 2012, at 11:31 AM, Miller Puckette wrote:
> It should be possible but Pd needs stuff like open(), read(),
It should be possible but Pd needs stuff like open(), read(), and write()
for files, so it's necessary to make a small library to either carry out
or somehow fake those operations.
The great advantage of running Pd on a DSP is that you can probably get audio
latencies down much further than on a P
Hey Damian,
The gluiph was just that, it ran Pd directly on a DSP:
http://www.nime.org/proceedings/2003/nime2003_180.pdf
Depending on your skills, it could be easier to run a über-stripped OS like I
did on the Palm Pilots, which ran Pd tho they had 32megs of RAM. There wasn't
much more than t
hi alls,
i'm investigating possibilities for a general purpose audio hardware device
based on a DSP chip.
i know about Pd-anywhere and Hans-Christoph Steiner's efforts to get Pd to run
on older devices. this is not my goal here as i'd like to avoid having to load
an entire operating system,