Quoting Mika Kuoppala (2019-02-08 09:31:48)
> Chris Wilson writes:
>
> > When declaring the GPU wedged, we do need to hit the GPU with the reset
> > hammer so that its state matches our presumed state during cleanup. If
> > the reset fails, it fails, and we may be unhappy but wedged. However, if
Chris Wilson writes:
> When declaring the GPU wedged, we do need to hit the GPU with the reset
> hammer so that its state matches our presumed state during cleanup. If
> the reset fails, it fails, and we may be unhappy but wedged. However, if
> we are testing our wedge/unwedged handling, the desy
When declaring the GPU wedged, we do need to hit the GPU with the reset
hammer so that its state matches our presumed state during cleanup. If
the reset fails, it fails, and we may be unhappy but wedged. However, if
we are testing our wedge/unwedged handling, the desync carries over into
the next t
When declaring the GPU wedged, we do need to hit the GPU with the reset
hammer so that its state matches our presumed state during cleanup. If
the reset fails, it fails, and we may be unhappy but wedged. However, if
we are testing our wedge/unwedged handling, the desync carries over into
the next t
