On Thu, 4 Dec 2014 12:21:01 +0100
Daniel Vetter wrote:
> On Wed, Dec 03, 2014 at 11:49:06AM -0800, Jesse Barnes wrote:
> > Expose an ioctl to create Android fences based on the Android sync point
> > infrastructure (which in turn is based on DMA-buf fences). Just a
> > sketch at this point, no t
On Wed, Dec 03, 2014 at 11:49:06AM -0800, Jesse Barnes wrote:
> Expose an ioctl to create Android fences based on the Android sync point
> infrastructure (which in turn is based on DMA-buf fences). Just a
> sketch at this point, no testing has been done.
>
> There are a couple of goals here:
>
On Thu, Dec 04, 2014 at 08:10:22AM +, Chris Wilson wrote:
> If I understand correctly, the fence timeline are indeed per-ring, but
> here you set them up (and name them) on a per-engine basis.
On reflection, the timeline are per-fd, so using the engine name is not
confusing after all.
-Chris
On Wed, Dec 03, 2014 at 11:49:06AM -0800, Jesse Barnes wrote:
> Expose an ioctl to create Android fences based on the Android sync point
> infrastructure (which in turn is based on DMA-buf fences). Just a
> sketch at this point, no testing has been done.
>
> There are a couple of goals here:
>
On 03-12-14 20:49, Jesse Barnes wrote:
> Expose an ioctl to create Android fences based on the Android sync point
> infrastructure (which in turn is based on DMA-buf fences). Just a
> sketch at this point, no testing has been done.
>
> There are a couple of goals here:
> 1) allow applications
Expose an ioctl to create Android fences based on the Android sync point
infrastructure (which in turn is based on DMA-buf fences). Just a
sketch at this point, no testing has been done.
There are a couple of goals here:
1) allow applications and libraries to create fences without an
assoc