[Intel-gfx] Fencing on the i915
chris at chris-wilson.co.uk
Mon Feb 9 23:49:41 CET 2009
On Mon, 2009-02-09 at 11:06 -0800, Jesse Barnes wrote:
> Seems reasonable; I don't think removing the fence register will do anything
> special, so waiting for the rendering to finish seems like a good idea.
Actually this chunk is now a no-op as we explicitly wait for rendering
and flushing of all i915 fenced buffers and so at that point we will
only be handling an inactive buffer.
More information about the Intel-gfx