<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#FFFFFF">
Hi Dave,<br>
<br>
As the attached, our Vulkan team is verifying it.<br>
<br>
Thanks,<br>
David Zhou<br>
<br>
<div class="moz-cite-prefix">On 2016年12月01日 13:44, Dave Airlie
wrote:<br>
</div>
<blockquote
cite="mid:CAPM=9tz2Qv0DXp-Tpfb38b81G1Gbs0MyM4KvUcvj5m+sp3dhoQ@mail.gmail.com"
type="cite">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<p dir="ltr">On 1 Dec. 2016 15:22, "zhoucm1" <<a
moz-do-not-send="true" href="mailto:david1.zhou@amd.com">david1.zhou@amd.com</a>>
wrote:<br>
><br>
> Yes, the old implementation which is already in upstream
libdrm is out of data, there isn't other user, so we want to
drop it when new semaphore is verified OK.</p>
<p dir="ltr">Could you post some patches for the new one?
Otherwise I'll have to write one for radv.</p>
<p dir="ltr">Dave.<br>
><br>
> Thanks,<br>
> David Zhou<br>
><br>
><br>
> On 2016年12月01日 10:36, Mao, David wrote:<br>
>><br>
>> Hi Dave,<br>
>> i believe your first attempt is correct.<br>
>> The export/import semaphore needs refine of the
semaphore implementation.<br>
>> We are working on that.<br>
>><br>
>> Thanks.<br>
>> Best Regards,<br>
>> David<br>
>>><br>
>>> On 1 Dec 2016, at 10:12 AM, Dave Airlie <<a
moz-do-not-send="true" href="mailto:airlied@gmail.com">airlied@gmail.com</a>>
wrote:<br>
>>><br>
>>> Hey all,<br>
>>><br>
>>> So I've started adding semaphore support to radv
but I'm not really<br>
>>> sure what the API to the semaphore code is.<br>
>>><br>
>>> the Vulkan API is you get a command submission of a
number of submit<br>
>>> units which have a 0-n wait semaphore, 0-n command
buffers and 0-n<br>
>>> signal semaphores.<br>
>>><br>
>>> Now I'm not sure how I should use the APIs with
those.<br>
>>><br>
>>> My first attempt is<br>
>>><br>
>>> call amdgpu_cs_wait_semaphore on all the wait ones,
call the cs submit<br>
>>> API, then call the amdgpu_cs_signal_semaphore on
all the signal ones?<br>
>>><br>
>>> or should I be up front calling wait/signal then
submitting the command streams?<br>
>>><br>
>>> Also upcoming work requires possibly sharing
semaphores between<br>
>>> processes, is there any indication how this might
be made work with<br>
>>> the libdrm_amdgpu semaphore implementation?<br>
>>><br>
>>> Thanks,<br>
>>> Dave.<br>
>>> _______________________________________________<br>
>>> amd-gfx mailing list<br>
>>> <a moz-do-not-send="true"
href="mailto:amd-gfx@lists.freedesktop.org">amd-gfx@lists.freedesktop.org</a><br>
>>> <a moz-do-not-send="true"
href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br>
>><br>
>> _______________________________________________<br>
>> amd-gfx mailing list<br>
>> <a moz-do-not-send="true"
href="mailto:amd-gfx@lists.freedesktop.org">amd-gfx@lists.freedesktop.org</a><br>
>> <a moz-do-not-send="true"
href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br>
><br>
></p>
</blockquote>
<br>
</body>
</html>