Re: New subsystem for acceleration devices

[Oded Gabbay]

On Tue, Aug 2, 2022 at 8:25 PM Jiho Chu <jiho.chu@xxxxxxxxxxx> wrote:
>
> On Sun, 31 Jul 2022 14:45:34 +0300
> Oded Gabbay <oded.gabbay@xxxxxxxxx> wrote:
>
> > Hi,
> > Greg and I talked a couple of months ago about preparing a new accel
> > subsystem for compute/acceleration devices that are not GPUs and I
> > think your drivers that you are now trying to upstream fit it as well.
> >
> > Would you be open/interested in migrating your drivers to this new subsystem ?
> >
> > Because there were no outstanding candidates, I have done so far only
> > a basic and partial implementation of the infrastructure for this
> > subsystem, but if you are willing to join I believe I can finish it
> > rather quickly.
> >
> > At start, the new subsystem will provide only a common device
> > character (e.g. /dev/acX) so everyone will do open/close/ioctl on the
> > same device character. Also sysfs/debugfs entries will be under that
> > device and maybe an IOCTL to retrieve information.
> >
> > In the future I plan to move some of habanalabs driver's code into the
> > subsystem itself, for common tasks such as memory management, dma
> > memory allocation, etc.
> >
> > Of course, you will be able to add your own IOCTLs as you see fit.
> > There will be a range of IOCTLs which are device-specific (similar to
> > drm).
> >
> > wdyt ?
> >
> > Thanks,
> > Oded
> >
>
> Hi, Oded.
> Thanks for sharing your idea. And I'm really positive on the subsystem for ai acceleration devices.
>
> Samsung NPU driver is trying to upstream now, so I wonder new subsystem can cover all of the operations.
> I'll appreciate if you share the code when you ready, so I can figure out our driver can be migrated.
I'm working on it.
I'm also preparing a small demo driver so you will be able to better
understand how to integrate a driver with this subsystem.
I believe I will be able to post the link during the weekend.

Oded

>
> Sincerely,
> Jiho Chu
>
>
>
>
>