On 30/06/16 14:34, Chris Wilson wrote:
On Thu, Jun 30, 2016 at 02:27:55PM +0100, Tvrtko Ursulin wrote:
On 30/06/16 12:30, Chris Wilson wrote:
By using the out-of-line intel_wait_for_register() not only do we can
efficiency from using the hybrid wait_for() contained within, but we
avoid code bloat from the numerous inlined loops:
text data bss dec hex filename
1078551 4557 416 1083524 108884 drivers/gpu/drm/i915/i915.ko
1070775 4557 416 1075748 106a24 drivers/gpu/drm/i915/i915.ko
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Read it all and did not spot any errors.
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
I think I will split this patch into per-file changes just to help
bisection, just in case. I just wanted to share how big an impact this
is. (There are still more we can do mostly for vlv sidebands.)
Certainly would not harm, although for bisection it is mostly already
naturally split by platforms and features.
Mind if I keep your r-b tag on splitting?
Don't mind. Certainly prefer that to re-reading it! :D
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
