On Mon, Sep 12, 2011 at 9:57 AM, Ilija Hadzic <ihadzic at research.bell-labs.com> wrote: > > Related to this question, one thing that I noticed is that in some > instances, I would not see any interrupts at all. Instead, all signaled > fences would be taken care of next time somebody waits on one them (through > radeon_fence_wait, radeon_fence_signaled, radeon_fence_poll_locked call > sequence -- the last function has the loop that marks all fences signaled > that should be). > > Is that also expected behavior ? > > -- Ilija
Yes we enable interrupt only if fence we are waiting for is not signaled, this avoid cpu waking for no good reasons, and thus allow cpu to go into sleep state. Cheers, Jerome
