XvMC support

[popper]

are you sure it was on linux and not windows ?
because even right now, I can't play a DVD or a DVB stream on a powerpc G4 400mhz or a celeron coppermine 700mhz.

regarding your PowerPC G4 running linux, thats reasonably easy to pinpoint why it would seem slower, the simple fact is todate, PPC linux doesnt take any advantage of its core Altivec SIMD in the core PPC linux code,neglected is the word, infact shameful given the Altivecs power just sat there almost unused.

thats were the likes of Markos and his freevec Altivec optimised replacement code for the core comes in, he's now stated its his intension to expand his freevec work and make it to a full libc replacement so everyone can take advantage of the massive speed increases you can get with his optimised Altivec and related SIMD code.....

as a starting point you might take a look as his current libfreevec http://www.freevec.org/content/history_libfreevec and his benchmarking pages, very interesting....

and look for the VLC Altivec optimised code and apps too.

with these simple additions your going to get a massive boost in your video apps in your G4 linux if you take the time to include and help the projects grow....

http://www.freevec.org/

[popper]

way back in january 8th 2009 Bridgmen said:

Bridgmen said:"we are going to look into opening up UVD, I just can't make any commitments until we have actually gone through the investigation and it won't be quick. We have 6xx/7xx 3d code out now, so IMO the next priority should be basic power management. "


popper said:thats a shame, we are looking at months at the very least then!

Bridgeman said:For open source, yes, but I expect fglrx will have it sooner.

Bridgmen said:"I think the attraction of the [NV cuda] library is that it makes it easy to retrieve the decoded frame, while most of the decoder implementations supplied by HW vendors tend to only output to the screen simply because that was the main requirement.

We make a similar capability available to ISVs :

http://www.cyberlink.com/eng/press_room/view_1756.html
"

popper said:yep,that about covers it for basic needs it appears, your average dev and indeed Pro coders such as BetaBoy and the CoreAVC coders dont really need that much help once they have the right library and docs access it seems, BetaBoy said he wanted to support ATI UVD in CoreAVC and related apps but you dont give them or the open SW coders access to the ATI UVD.

Bridgmen said:"I suspect the library uses the DXVA framework in the NVidia drivers, so having DXVA die might be a bit inconvenient, but that's just a guess "

i think its just entry points into and out of the generic DSP "blackbox" they put on their cards/SOC chips TBO.....

popper said:i dont really see why ATI/AMD couldnt also make such as "blackbox" UVD available as a stop gap measure to help multi OS devs in the short term TBO...!

snip...

popper said:given the apparent potential long wait for anything ATI UVD related, perhaps its finally time to move over to NV cards for now as the only viable option for many people world wide today!, as CoreAVC have a linux library available and have released test HW assisted cuda/VS2 CoreAVC on windows that apparently gives it a massive (x2-x4) decoding boost, i dont know if it will be usable on linux X86 as yet though.

So Bridgmen, i was going to bump this way back in April given that would have already been been several months, but i thought id wait yet another few months to give you a lot more time to really get Something werth telling us how this "UVD" had passed all your internal reviews, and had now progressed to a usable post processing form, and how the team(s) had made some initial ATI "UVD" code drops to the likes of the FFMPEG and related projects.....:mad:

apparently Nothing has become public so far though, infact i cant see any form of official or even unofficial updates from you since i first asked you way back in january about getting at least a working "basic" API or even a somewhat useable initial working codebase for our "UVD" decoding/post processing use, if you have actually gone through the investigation and passed your review OC?, why is that?

the reason im bumping this crutial "UVD" usage point now is that http://www.phoronix.com/scan.php?page=news_item&px=NzM2OA
were it becomes clear (although you would'nt think so from the comments on its thread so far http://www.phoronix.com/news2forums.php?view=NzM2OA ) that Gwenolé Beauchesne is a/the only? developer working on various multimedia APIs and did a lot for the ASIC usability in FFMPEG etc with his code drops is now making use of a working "UVD" codebase.

along with that hidden crutial "UVD" working codebase, you could'nt decide what API was best do use and extend way back in january, it appears now an xvba-video package is available to some, and so you have now chosen the XVBA API as the current option to extend today!.

so whats happening please, will we FINALLY have something to make use of the "UVD" and perhaps at least some basic wrapper code and a form of this "UVD" xvba-video package to FINALLY USE the ATI "UVD" for frame accurate editing etc NOW...

[bridgman]

So Bridgmen, i was going to bump this way back in April given that would have already been been several months,

Jan to April is "several months" ? Are we talking about Internet Time here ?

but i thought id wait yet another few months to give you a lot more time to really get Something werth telling us how this "UVD" had passed all your internal reviews, and had now progressed to a usable post processing form, and how the team(s) had made some initial ATI "UVD" code drops to the likes of the FFMPEG and related projects.....:mad:

No, we're still working on 3D and power management. I told you that investigation of UVD for open source wouldn't be quick. When we get there I'll tell you, don't worry...

apparently Nothing has become public so far though, infact i cant see any form of official or even unofficial updates from you since i first asked you way back in january about getting at least a working "basic" API or even a somewhat useable initial working codebase for our "UVD" decoding/post processing use, if you have actually gone through the investigation and passed your review OC?, why is that?

Because there's nothing much to announce. Again, I told you this wouldn't be quick.

the reason im bumping this crutial "UVD" usage point now is that http://www.phoronix.com/scan.php?page=news_item&px=NzM2OA
were it becomes clear (although you would'nt think so from the comments on its thread so far http://www.phoronix.com/news2forums.php?view=NzM2OA ) that Gwenolé Beauchesne is a/the only? developer working on various multimedia APIs and did a lot for the ASIC usability in FFMPEG etc with his code drops is now making use of a working "UVD" codebase.

XvBA has been available for embedded applications for a while. What is being working on now is something that can be used in a general purpose PC.

along with that hidden crutial "UVD" working codebase, you could'nt decide what API was best do use and extend way back in january, it appears now an xvba-video package is available to some, and so you have now chosen the XVBA API as the current option to extend today!.

You might be mixing the open and closed source discussions. The fglrx implementation was always going to be XvBA; what we weren't sure of was what API to use for open source drivers.

so whats happening please, will we FINALLY have something to make use of the "UVD" and perhaps at least some basic wrapper code and a form of this "UVD" xvba-video package to FINALLY USE the ATI "UVD" for frame accurate editing etc NOW...

NOW ? No.

What I said in January still holds. It won't be quick, and I think you'll see something on fglrx before the open drivers.

[popper]

being its now in the 3rd finantial quarter since then, i would have thought that more than covered my "we are looking at months at the very least then!" it seems.

were i reasonably consider "a few"/several "months" being a finantial quarter, but no matter...

but thanks for the update anyway, can i/we at least take it after half a year, without making any commitments on your part OC, you have at least gone through the investigation and finished the UVD review?, or at least near the end!

[bridgman]

being its now in the 3rd finantial quarter since then, i would have thought that more than covered my "we are looking at months at the very least then!" it seems.

January is first quarter, July is third quarter. That's a two quarter difference, not three. That said, it still covers "months" just fine.

If you are trying to get me to say that UVD support in fglrx has taken longer than I guessed in January, I have no problem saying that.

were i reasonably consider "a few"/several "months" being a finantial quarter, but no matter...

I agree completely that "a few" corresponds nicely to a financial quarter, but you used "several" which is generally considered to be bigger than "a few".

but thanks for the update anyway, can i/we at least take it after half a year, without making any commitments on your part OC, you have at least gone through the investigation and finished the UVD review?, or at least near the end!

No, we're still working on 3D and power management. I said it wouldn't be quick.

Honestly, if/when we have something to announce you *will* hear about it, I promise :D

[popper]

"If you are trying to get me to say that UVD support in fglrx has taken longer than I guessed in January, I have no problem saying that."

not in the lease Bridgeman, dont take it like that, you are one of the good guys, and i welcome all your feedback to the community, and you do listen to us, and feed that back inhouse, and thats key, and a good thing.

its just yet again im on the lookout for yet another HD Video upgrade for a beagleboard and Genesi board, both considered embedded applications , but they are also a general purpose PC able to run a generic linux too and FFMPEG and other AVC related code ;)

[mirak63]

ati is just ruining it's reputation

just don't say there will be support when there is no timeline and anything
it's almost like ati lied
you can say what you want about how it was anounced but what matters is the image that will stay in people mind.
And for me as a user it's pretty bad ...

[Zajec]

ati is just ruining it's reputation

just don't say there will be support when there is no timeline and anything
it's almost like ati lied
you can say what you want about how it was anounced but what matters is the image that will stay in people mind.
And for me as a user it's pretty bad ...I think you just can't read that right. You have clear message: SOMETIME, NOT SOON. It really means you shouldn't have any expectations about that, and you can wait years for that to appear. Just take it as I said.

Would you prefer AMD to not even mention open source UVD? Now we at least know it's possible (could be not, because of some patents).

I'm happy with informations from Bridgman and I'm not frustrated. I just don't belive in more than he wrote.

[mirak63]

at the time I bought a hd4850 ATI was claiming linux support, and also UVD support was announced.

now we know what it was worth

It's not about bridgman here, however I think the less ati talks about things that ati can't support right now or officialy at some point, the less arm it will do for ati image.

And probably phoronix didn't do anygood by anouncing stuffs based on the fact some lib was seen in some binary

[Zajec]

at the time I bought a hd4850 ATI was claiming linux support, and also UVD support was announced.

now we know what it was worth

It's not about bridgman here, however I think the less ati talks about things that ati can't support right now or officialy at some point, the less arm it will do for ati image.

And probably phoronix didn't do anygood by anouncing stuffs based on the fact some lib was seen in some binaryThat explains your disappointment, but as you noticed by yourself, that has nothing to Bridgman's information. Where did you read this UVD announcement actually?

[bridgman]

That explains your disappointment, but as you noticed by yourself, that has nothing to Bridgman's information. Where did you read this UVD announcement actually?

I would like a copy as well, please ;)

The only UVD-related announcement we made was the statement that we did *not* (and I stress *not*) plan to open up UVD, however I did commit to looking into whether it was possible after we had the other core functionality in place.

On the fglrx side, Michael drew some perfectly reasonable conclusions from what he saw in the driver binaries and heard from his contacts around the industry; even if things didn't work out that way this time in general his guesses are quite good.

If you're saying that we should have hidden the work-in-process XvBA code better so that people would not speculate maybe that's fair. If you're saying that we should have taken legal action to stop people from publicly speculating, that's not the way we like to do things.

[duby229]

If you're saying that we should have hidden the work-in-process XvBA code better so that people would not speculate maybe that's fair. If you're saying that we should have taken legal action to stop people from publicly speculating, that's not the way we like to do things.

He might be saying that, but I'm definitely not. I think the work in progress code should be made available in a public git so that we can --see-- what work is being done. This is the only way to make it fair. If we could see the code then there wouldnt be any speculation.

[pingufunkybeat]

The fglrx drivers are not open-source, so putting the code in a public git is not really an option.

[Kano]

The lib is there, just not the headers. What would be hidden in the headers?!

[Ex-Cyber]

The lib is there, just not the headers. What would be hidden in the headers?!An implicit commitment to continue supporting the interface?

[duby229]

The fglrx drivers are not open-source, so putting the code in a public git is not really an option.

And that is exactly what the problem is. Putting that code in the public under an open source agreement would solve this issue once and for all.

[bridgman]

Sure, but if we could do that then we would have already released the information to the open source development community.

[duby229]

I understand completely. I can only wish that the right thing be done, but just like with everything else there is always some excuse as to why it cant be done. Its OK though, maybe someday when the content industry fails they'll realize they've been doing it all wrong, and give you guys the opportunity to finally document the technology they've been trying to push all along.