2013: A Good Year For Open-Source AMD?

[ChrisXY]

ok then in "video playback" and "power-management" the spec and AMD support is a lie...

There's still a little difference in "good enaugh so it works, but not as good as it possibly could" and "a lie".

[curaga]

Don't think we were talking about turning UVD off -- I was talking about decoding video with it.

Of course I meant "UVD and other unused blocks on the card", but didn't quite phrase that right.

[airlied]

If reverse engineering the FGLRX is more useful than using specs from AMD then the hole support from AMD is a lie?

or maybe i didn't understand you here.

yeah you didn't understand because I never said it in a general way. We just know in some cases that fglrx uses the hw in ways that the docs don't/won't cover, e.g. UVD. In most cases this isn't true, and its fine to never RE fglrx, because the docs are fine.

So really in most cases I wouldn't dream of RE'ing fglrx since we have good enough docs/access to engineers.

[smitty3268]

@bridgman
is there still work being done for the UVD ???

Yes, although we're not at the point where I can say anything more encouraging than before about chances of exposing the HW.

What about the video encoder that the new chips have?

I'm not particularly in a hurry to get support for it, I'm just wondering if it's a minefield of patents/lawyers as well, or if you think that would be easier than decoding through UVD.

[smitty3268]

Can you share with us _why_ this turns out to be problematic?
I think it's obvious for the UVD blocks - but for the PM bits?

Nope. Same goes for all of the programming info...

[Hamish Wilson]

Just to add some common decency and politeness to this thread: I wish to offer my thanks to bridgman, agd5f, airlie, and everyone else who is working on improving these drivers. If it was not for your hard work we would not have anything to talk about here at all, and everyone should be grateful. I at least appreciate your efforts.

Now, was that so hard everyone?

[DanL]

well the clue is to call a opponent with dissenting opinions a "Contrarian Troll" is the first step to be the Contrarian Troll

...

Accusing the accusers. When confronted with their trolling, trolls immediately respond that it is the accusers who are trolls.

You made my day. Thanks.

[bridgman]

@bridgman
is there still work being done for the UVD ???

Yes, although we're not at the point where I can say anything more encouraging than before about chances of exposing the HW.

[89c51]

@bridgman


is there still work being done for the UVD ???

[airlied]

I think many people (like me) who say they would like better power management aren't even talking about automatically adjusting power levels to "match the user's needs". It's still that on "low" power level my HD 6550M drains more power than catalyst by default. (Last time I tried "low" it sometimes crashed so I used "mid" since then which seems to be exactly the same but at least appeared to be more stable).

What I personally think should be the priority in power management is bringing the card down to the minimum power drain possible for the "low" profile.

 % sudo su -c "echo low > /sys/class/drm/card0/device/power_profile"
 % cat /sys/kernel/debug/dri/0/radeon_pm_info
default engine clock: 600000 kHz
current engine clock: 299970 kHz
default memory clock: 800000 kHz
current memory clock: 299950 kHz
voltage: 900 mV
PCIE lanes: 16
 % sudo su -c "echo mid > /sys/class/drm/card0/device/power_profile"
 % cat /sys/kernel/debug/dri/0/radeon_pm_info
default engine clock: 600000 kHz
current engine clock: 299970 kHz
default memory clock: 800000 kHz
current memory clock: 299950 kHz
voltage: 900 mV
PCIE lanes: 16

Yeah I suspect there are block on the gpu that fglrx powers off dynamically to get even lower than the min one.

I'm not sure, if anyone was going to work on power saving I'd recommend the nouveau approach and reverse engineer fglrx rather than talking to AMD, and definitely try not be covered by an NDA.

While improving the current code might be worth it for a while, its suboptimal in the long term, and reverse engineering fglrx would probably produce a much more useful benefit.

Dave.