Re: [PATCH] drm/i915: Optimize the i915_gem_gtt_finish_object function

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



So the code should stay the way it is originally and assume GPU idling is always needed?
- Armin

-----Original Message-----
From: Chris Wilson [mailto:chris@xxxxxxxxxxxxxxxxxx] 
Sent: Friday, July 11, 2014 10:37 AM
To: Reese, Armin C
Cc: intel-gfx@xxxxxxxxxxxxxxxxxxxxx
Subject: Re:  [PATCH] drm/i915: Optimize the i915_gem_gtt_finish_object function

On Fri, Jul 11, 2014 at 05:29:48PM +0000, Reese, Armin C wrote:
> Originally, the function always executes do_idling() followed by undo_idling() regardless of whether obj->has_dma_mapping is TRUE or not.  This change idles the GPU only if needed.
> 
> However, if the intention of the function is to ALWAYS idle the GPU, then my change is a mistake.

Ah yes. It is unclear whether the workaround also needs to be applied for stolen objects, but it is best to presume that it is.
-Chris

--
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]
  Powered by Linux