[Intel-gfx] [PATCH 1/2] split render engine batch buffer and BLT engine

Chris Wilson chris at chris-wilson.co.uk
Tue Oct 26 11:13:24 CEST 2010


On Tue, 26 Oct 2010 16:23:24 +0800, "Zou, Nanhai" <nanhai.zou at intel.com> wrote:
> 	I do not quite understand your point.
> How can we mix blitter command with render command in a batch buffer?

We can't. We also can't mix render targets/sources between concurrent
batch buffers either, at the moment. (I'd much rather finish the kernel
synchronisation before teaching X how to synchronise a pair of
interdependent concurrent batch buffers).  So in order to get any
synchronisation between the rings you have to flush the BLT batch when
starting a RENDER operation (if that operation accesses a BLT buffer and
vice versa).  Hence why I think that a single, modal batch buffer will be
no less efficient than maintaining a pair (or more) concurrent batch
buffers. X's request model means that we will process many sequential ops
from a single client in a single pass which will intermix BLT/RENDER
commands (or just use RENDER predominantly). I do not foresee X attaining
any great level of parallelism between the rings.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre



More information about the Intel-gfx mailing list