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. Reviewed-by: Matt Turner <matts...@gmail.com> _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
