On Mon, Apr 08, 2013 at 09:23:55AM +0200, Daniel Vetter wrote:
> With this at least the y-tiled test reliably fails on my machines, but
> x-tiled still passes on some. More ideas to tune this highly welcome.
>
> v2: Fill cpu caches with data for each newly allocated bo. This seems
> to do the tric
With this at least the y-tiled test reliably fails on my machines, but
x-tiled still passes on some. More ideas to tune this highly welcome.
v2: Fill cpu caches with data for each newly allocated bo. This seems
to do the trick on my snb here _really_ reliably. So apparently the
backsnoop for llc g
On Sun, Apr 7, 2013 at 7:21 PM, Daniel Vetter wrote:
> With this at least the y-tiled test reliably fails on my machines, but
> x-tiled still passes on some. More ideas to tune this highly welcome.
>
> Signed-off-by: Daniel Vetter
Correction: Y-tiled still seems to not fail on my snb mobile gt2.
With this at least the y-tiled test reliably fails on my machines, but
x-tiled still passes on some. More ideas to tune this highly welcome.
Signed-off-by: Daniel Vetter
---
tests/gem_fence_thrash.c | 12 ++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/tests/gem_fen
