[Intel-gfx] [intel-gfx][PATCH] intel: add a new interface drm_intel_bo_alloc_direct
daniel at ffwll.ch
Tue Jun 1 11:58:55 PDT 2010
On Tue, Jun 01, 2010 at 05:17:45PM +0800, Xiang, Haihao wrote:
> On Fri, 2010-05-28 at 22:04 +0800, Daniel Vetter wrote:
> > On Tue, May 25, 2010 at 01:06:50PM +0800, Xiang, Haihao wrote:
> > > This interface is the same as drm_intel_bo_alloc except the allocated
> > > size isn't rounded up, so it bypasses the cache bucket.
> > >
> > > The size of the BO created by drm_intel_bo_alloc for a 1920x800,4:2:0 YUV
> > > planar surface is 4M, it is about 2.2M if using drm_intel_bo_alloc_direct.
> > Have you tried either Chris Wilson's or my fair-lru eviction patches? They
> > should help quite a lot, especially for many big objects of exactly the
> > same size like libva uses.
> Get the following errors when applying your fair-lru eviction patches
> Applying: drm/i915: prepare for fair lru eviction
> error: patch failed: drivers/gpu/drm/i915/i915_gem.c:2203
> error: drivers/gpu/drm/i915/i915_gem.c: patch does not apply
> I am using drm-intel-next branch.
Kinda expected - the patch series was against drm-intel-next before your
bsd ring stuff was merged ;) So either fixup the conflicts yourself
(conflicts are probably just due to the bsd merge, so you already know the
code) or prod Chris Wilson into implementing his single-scan patch for
i915 atop my generic fair-lru drm patches. Or simply wait till I get
around to rebase this stuff. But don't hold your breath, that won't happen
soon, unfortunately. Too busy atm.
Mail: daniel at ffwll.ch
Mobile: +41 (0)79 365 57 48
More information about the Intel-gfx