Re: Limitations with v2 port implementation

On Apr 08, 2015, at 10:06, Sylvain Joyeux <[email protected]> wrote:

>> Agreed, but it doesn=92t solve the performance issue.
> =

> Definitely not :(.
> =

> Just for benchmarking sake, have you done some profiling ? Or have you
> tried using a lock policy instead of lock-free. Lock-free is nice, but
> it looks nasty from an instruction cache p.o.v.
> =

> Sylvain

Benchmarking as in timing port writes? That=92s where that 450% slow down c=
omes from - we timed the function that writes the port data.

We=92ve not looked at the effect of different lock policies, but I=92m very=
 reluctant to start making those kind of changes unless really necessary. A=
nd in all honesty that feels like a solution to a solution. The performance=
 issue is fundamentally driven by the 1-to-N fanout from output ports to in=
put ports. Certainly the locking solution may/will improve performance, but=
 the fundamental issue remains.

Sigh =85 I suspect that there=92s no good *and* easy answer here.

Cheers
S
-- =

Orocos-Dev mailing list
[email protected]
http://lists.mech.kuleuven.be/mailman/listinfo/orocos-dev