[Intel-gfx] [PATCH] drm/i915: Support to create uncached user mapping for a Gem object

[Chris Wilson]

On Thu, Oct 23, 2014 at 12:56:46PM +0100, Chris Wilson wrote:
> On Thu, Oct 23, 2014 at 04:03:56PM +0530, akash.goel at intel.com wrote:
> > From: Akash Goel <akash.goel at intel.com>
> > 
> 
> > This is for improving the CPU write operation performance, as with such
> > mapping, writes are almost 50% faster than with mmap_gtt. Also it avoids the
> 
> I doubt it is the actual write that is faster. For example,
> 
>    gtt       wc    Operation
> --------  ------   ---------
> 424000.0    1.30   ShmPutImage 10x10 square 
>  29500.0    1.42   ShmPutImage 100x100 square 
>   1510.0    0.95   ShmPutImage 500x500 square 

Oops, bugs beware. I wasn't calling the ioctl correctly.
Having re-run the test, I now get:

   gtt       wc    Operation
--------  ------   ---------
424000.0    1.30   ShmPutImage 10x10 square 
 29500.0    1.44   ShmPutImage 100x100 square 
  1510.0    1.38   ShmPutImage 500x500 square 

Supporting your claims. Very nice.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre