Hi!, On vie, 2015-03-13 at 10:42 -0700, Matt Turner wrote: > On Fri, Mar 13, 2015 at 3:41 AM, Antia Puentes <apuen...@igalia.com> wrote: > > IvyBridge and Haswell PRM say that the JIP should be emitted > > with type W but we were using UD. The previous implementation > > did not show adverse effects, however changing the type to > > D caused a GPU hang, see bug 84557; IMHO it is safer to > > follow the specification thoroughly. > > --- > > The change seems fine to me, though changing the type to D never > seemed like the thing that was actually causing the hang. It seemed > much more likely that allowing the ELSE and ENDIF instructions to be > compacted violated some assumption in our code and we misaligned some > jump target by 8-bytes. > > I should investigate more. > > I'd probably remove the "however changing the type to D caused a GPU > hang, see bug 84557" comment from the commit.
I will remove the comment. > Reviewed-by: Matt Turner <matts...@gmail.com> Thanks for reviewing! _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
