Re: [radeon]Question about create ring BO in VRAM

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



2011/11/5 Alex Deucher <alexdeucher@xxxxxxxxx>:
> On Fri, Nov 4, 2011 at 10:26 AM, Chen Jie <chenj@xxxxxxxxxx> wrote:
>> Hi all,
>>
>> I tried to create/pin ring BO in VRAM instead of GTT to debug some
>> ring-related problems. After I did this, it rendered a black screen in
>> X (on a X86 RS780E board), but radeon.test passed.
>> 'ps aux' shows X uninterruptibly sleeps on radeon.
>>
>> Curious why this does not work?
>
> The tricky part is dealing with the HDP cache.  Access to vram via the
> PCI FB BAR goes through the HDP cache, you have to make sure it's
> flushed properly before the GPU starts using the data there.  To flush
> it, either read back from vram, or write 1 to the
> HDP_MEM_COHERENCY_FLUSH_CNTL register.  We generally don't recommend
> putting the ring in vram.
Get it, thanks.
After add HDP cache flush in r600_cp_commit(), it works fine.



Regards,
-- Chen Jie
_______________________________________________
dri-devel mailing list
dri-devel@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/dri-devel



[Index of Archives]     [Linux DRI Users]     [Linux Intel Graphics]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [XFree86]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux