[Intel-gfx] [PATCH] Revert "drm/i915: Kill GTT mappings when moving from GTT domain"

Eric Anholt eric at anholt.net
Fri Jun 17 21:06:54 CEST 2011


On Wed, 15 Jun 2011 17:03:58 +0100, Chris Wilson <chris at chris-wilson.co.uk> wrote:
> On Wed, 15 Jun 2011 08:08:59 -0700, Eric Anholt <eric at anholt.net> wrote:
> > On Wed, 15 Jun 2011 10:39:06 +0100, Chris Wilson <chris at chris-wilson.co.uk> wrote:
> > > For the record, on my SugarBay, this patch on top of drm-intel-fixes and
> > > mesa.git + your instruction streaming, regresses cairo-xlib 4.5s to 4.7s
> > > (4%, with a claim of .1% stddev) and improves cairo-gl from 21.5s to 20.1s
> > > (6.5%, with a claim of .5% stddev) for the firefox-talos-gfx. [This is a
> > > system that can do under 2s for cairo-xlib using vmap and the perf
> > > patches I posted before.]
> > > -Chris
> > 
> > I was testing with semaphores enabled on the LLC series.  I'm curious
> > how this revert could possibly regress cairo-xlib, though -- that seems
> > very strange.
> 
> Moving back to LLC+semaphores (2.6.39-rc2+), firefox-talos-gfx:
> xlib: 4.473
> gl:  20.753
> 
> applying the patch:
> xlib: 4.472
> gl:  20.824
> 
> I'm just not reproducing the same issue you are seeing. Are you using a
> standard distro Kconfig, or if not, can you send me yours?
> -Chris

http://people.freedesktop.org/~anholt/dotconfig

Pushed my kernel tree to "gtt-revert" branch.

Fresh set of numbers on two fresh boots, just about as identical testing
environments as I could produce:

(without revert)
anholt at eliezer:src/cairo/perf% cat /home/anholt/cairogl-before
21791099815
21677090234
22060471069
22049244399
21721362892
21966143347

(with revert)
anholt at eliezer:src/cairo/perf% cat /home/anholt/cairogl-after 
19162606198
19127697366
19462253708
19172535715
19339999910
19221539215

anholt at eliezer:src/cairo/perf% ministat ~/cairogl-before ~/cairogl-after
x /home/anholt/cairogl-before
+ /home/anholt/cairogl-after
+------------------------------------------------------------------------------+
| +                                                                           x|
|++ +  +  +                                                         xx x    x x|
||__A___|                                                            |___A__M_||
+------------------------------------------------------------------------------+
    N           Min           Max        Median           Avg        Stddev
x   6  2.167709e+10 2.2060471e+10 2.1966143e+10 2.1877569e+10 1.6902073e+08
+   6 1.9127697e+10 1.9462254e+10 1.9221539e+10 1.9247772e+10 1.2847426e+08
Difference at 95.0% confidence
	-2.6298e+09 +/- 1.93108e+08
	-12.0205% +/- 0.882677%
	(Student's t, pooled s = 1.50123e+08)
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 197 bytes
Desc: not available
URL: <http://lists.freedesktop.org/archives/intel-gfx/attachments/20110617/f26e5511/attachment.sig>


More information about the Intel-gfx mailing list