Jason Ekstrand <ja...@jlekstrand.net> writes:

> You've got me almost convinced as well.  Thanks for the diagrams!  I think
> instead of adding 1 perhaps what we want is
>
> max2(sample_interval_ns, gpu_tick_ns + monotonic_tick_ns)
>
> Where monotonic_tick_ns is maybe as low as 1.  Am I following you correctly?

Not quite; I was thinking that because the sample_interval_ns is
measured by sampling the monotonic clock twice, the actual interval can
be up to 1 tick longer, so

max2(sample_interval_ns + monotonic_tick_ns, gpu_tick_ns)

The gpu_tick_ns is computed, not measured, and so accurately reflects
the maximum deviation in the measurements.

-- 
-keith

Attachment: signature.asc
Description: PGP signature

_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev

Reply via email to