Subject: Re: [linux-audio-dev] LADSPA hard_rt_capable
From: Steve Harris (S.W.Harris_AT_ecs.soton.ac.uk)
Date: Mon Dec 11 2000 - 16:36:28 EET
On Mon, Dec 11, 2000 at 04:48:30PM +0100, Benno Senoner wrote:
> I think if a plugin architecture supplies estimates about CPU consumption,
> then it should provide both the CPU usage of the DSP algorithm and parameter
> recalculation.
> That way the host app could figure out quite precisely if the CPU can
> tolerate the DSP load and/or heavy parameter changes.
That sonds very cool, but I think its a bit over the top for LADSPA. You
would proably want the host (or meta host) to do the calculations
automatically though, as the cost varies wildly with compiler and
architecture. It should be quite easy to automate.
> Steve, I was wondering if you measured the CPU consumption of some
> of these problematic parameter recalculation functions.
> I mean: assuming you've got a 400-800Mhz CPU, would some of these recalculation
> functions cause audio disruptions (runnnig with 3-5msec latencies) in the case
> of the parameter changing during each iteration ?
I haven't actually, but I've tried to make sure that all my recalculations
take < 1 ms or so on a reasonable machine, but its mostly educated
guesswork at the moment. Paul B-D might be able to answer this as he's
used some of my plugins in realtime.
I plan to try some tests to see exactly how expensive each recalc. is
(which I can do just by changing the chunk size, I think ecasound can do
this). Its a bit more tricky for plugins that do parameter watching
though.
- Steve
This archive was generated by hypermail 2b28 : Mon Dec 11 2000 - 17:24:02 EET