Re: [linux-audio-dev] Software filter engines for high end audio and now DSP's

New Message Reply About this list Date view Thread view Subject view Author view Other groups

Subject: Re: [linux-audio-dev] Software filter engines for high end audio and now DSP's
From: Benno Senoner (sbenno_AT_gardena.net)
Date: ke helmi  16 2000 - 14:45:58 EST


On Wed, 16 Feb 2000, Frank J. Carmickle wrote:

>
> I was going to ask the question yesterday, is the Analog Devices SHARC
> chip, found on the Creamware Pulsar, going to be supported by any open
> source projects? I know we need to find some DSP's to do our processing.
> This looks like the best Candidate to me.
>
>
> FrankieC

I don't know, but some time ago I did some calculations about theoretical
comparison between a Pulsar and a dual Athlon at 700-800Mhz,
(even if the SMP motherboards aren't still available, but that will change
soon).

My conclusions are that such a SMP box is in the same performance
league as the Pulsar, but at a fraction of the cost plus giving you
much more flexibility.
For example on the Pulsar you have to squeeze all your data from/to
host through the PCI bus.
That includes HD recording, sending/receiving data from sources
different from the Scope hardware etc.

Even the producer of Protools is admitting the trend in shifting from
dedicated DSPs to native processing, or they wouldn't ship a native-only
solution (Basically a multi-channel soundcard with all the audio processing
done in software).

That is why I am still dreaming about an "audio operating system",
( MuCoS) which would provide an abstraction layer to run your
native audio processing components on top on a high performance OS.
(in this case Linux).

The only hurdles for useful native processing until now were:
- CPUs too slow , (this is changing because we are approaching the GHz
frequency range, plus CPUs are more and more equipped with DSP-like instructions
( MMX etc) which will speedup greatly the DSP processing.
- no useful host/plugin programming models until now
(as we see VST (and others) are widely accepted on the windows world,
and you can in fact do many things in software thus saving money and time)

But I try to stay away from proprietary APIs as usual
(no more M$ slaves, please :-) )
plus David Olofson is a bit disappointed from VST 2.0 any gave me the sense
like saying "is that all what one of the leading audio companies is able to
produce" :-)

PS: sorry for my offtopic posting, but I am a big "native-processing" advocate,
and just hate being locked to a company because of proprietary hardware add-ons
( DSP cards etc).
Just like one of you said: "I will not buy a soundcard anymore, where an
opensource driver and/or programming specs aren't available"

Benno.


New Message Reply About this list Date view Thread view Subject view Author view Other groups

This archive was generated by hypermail 2b28 : pe maalis 10 2000 - 07:23:27 EST