On Tue, 2018-10-16 at 15:12 -0500, Jason Ekstrand wrote: > Suggested-by: Francisco Jerez <curroje...@riseup.net> > --- > src/intel/blorp/blorp_genX_exec.h | 9 +++++++++ > 1 file changed, 9 insertions(+) > > diff --git a/src/intel/blorp/blorp_genX_exec.h > b/src/intel/blorp/blorp_genX_exec.h > index 50341ab0ecf..30025cf4deb 100644 > --- a/src/intel/blorp/blorp_genX_exec.h > +++ b/src/intel/blorp/blorp_genX_exec.h > @@ -1628,6 +1628,15 @@ blorp_emit_gen8_hiz_op(struct blorp_batch *batch, > */ > blorp_emit_3dstate_multisample(batch, params); > > + /* According to the SKL PRM formula for WM_INT::ThreadDispatchEnable, the > + * 3DSTATE_WM::ForceThreadDispatchEnable field can force WM thread > dispatch > + * even when WM_HZ_OP is active. However, WM thread dispatch is normal > + * disabled for HiZ ops and it appears that force-enabling it can lead to > + * GPU hangs on at least Skylake. Since we don't know the current state > of > + * the 3DSTATE_WM packet, just emit a dummy one prior to 3DSTATE_WM_HZ_OP. > + */ > + blorp_emit(batch, GENX(3DSTATE_WM), wm); > + > /* If we can't alter the depth stencil config and multiple layers are > * involved, the HiZ op will fail. This is because the op requires that a > * new config is emitted for each additional layer.
This patch didn't apply cleanly on 18.2, so I've fixed the conflicts. You can check the fixed commit at https://gitlab.freedesktop.org/mesa/mesa/commit/14d61206eb5fc3b73a9eec686dc8423fe266286a J.A. _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
