[LAU] multiJACK patch management: the first glimmerings of success

[Alexandre DENIS]

On Thu, 7 Apr 2016 01:57:07 +0200
Robin Gareus <robin at gareus.org> wrote:

> How would that effectively differ from running at twice the
> buffersize?
> 
> That approach just moves the load to two CPU cores. If those two cores
> can produce the result in a given time, a single core can do the same
> with twice the buffersize. Identical total latency.

With twice the buffer size, one core has twice as much work to do in
twice as much time, which basically doesn't change the DSP load (but
there are less context switches, etc.)

With a decoupling buffer between stages of the pipeline, the load is
spread on cores, so DSP load is theoretically halved. I agree that from
the user point of view, latency is doubled as if buffer size would have
been doubled, but more DSP power is available.

-a.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 473 bytes
Desc: OpenPGP digital signature
URL: <http://lists.linuxaudio.org/pipermail/linux-audio-user/attachments/20160407/f7203655/attachment.pgp>