Page 4 of 10 FirstFirst ... 23456 ... LastLast
Results 31 to 40 of 92

Thread: A few questions about video decode acceleration

  1. #31
    Join Date
    Nov 2007
    Posts
    1,353

    Default

    Quote Originally Posted by bridgman View Post
    I'm sure it is unintentional, but you are posting things I didn't say then calling me a liar for saying them.

    What I said (and please go back and check my posts if you have any doubts) was that licenced (aka certified) players check to see if they are running in a secure environment, and will not play (or will constrict the quality) if that secure environment is not present.

    Right now the certified players and secure environments only exist on Windows, at least for HD/BD. I did not say anything about not being able to play on Linux, in fact I said multiple times that the DRM hardware would *not* prevent you from being able to play protected content on Linux unless the player app and OS were working together to stop you.
    Ok so then the quewstion becomes how does this have anything at all to do with Linux? How does this mean that we need a closed driver? You said it yourself not me. You said that we need a closed driver to enable a secure environment. I didnt say that, you did. There really is only one way to understand that....

    If you dont have any DRM support enabled in the closed driver, then why do you use a secured environment as an argument that you need a closed driver?

  2. #32
    Join Date
    Oct 2007
    Posts
    370

    Default

    Honestly, if we took that kind of black/white approach we would not have been able to release 3d information either. What we do instead is put together a team of technical and legal experts then pick through the IP and try to draw a dotted line between "the stuff you need to write a good driver" and "the stuff that we can't release" so we can make everyone happy. For some of the blocks (2d) it's pretty easy. For others (3d) it's a lot harder but we were able to do it successfully.

    Video and power management are probably the hardest of all, but we're definitely going to release enough to make for a great user experience. I just don't know exactly where the line is going to be yet.
    why the f*** would power management be a problem?! who cares if you tell the world how to power down your chip?

    anyway, i am quite concerned about that. What are examples of such lines already taken with 3d, considered "cant release", but that you have "released enough for a good driver".

    Please bottom line it for me, which features does the chips have, which you to this date(or know about for later stuff), have been unable to give specs on? Even if good drivers providing a good user experience can be made, with less "features" documented, i'd sure like to know what it is that AMD ahs deemed itself unable to tell us how to use.

    the more i hear about the specs released and stuff, the more i get the feeling that the specs released isnt gonna be able to help create anything but a second class citizen feature wise(and no, i dont count DRM in as a feature.).
    Last edited by Redeeman; 06-07-2008 at 04:41 PM.

  3. #33
    Join Date
    May 2007
    Posts
    231

    Default

    Quote Originally Posted by Redeeman View Post
    why the f*** would power management be a problem?! who cares if you tell the world how to power down your chip?

    anyway, i am quite concerned about that. What are examples of such lines already taken with 3d, considered "cant release", but that you have "released enough for a good driver".

    Please bottom line it for me, which features does the chips have, which you to this date(or know about for later stuff), have been unable to give specs on? Even if good drivers providing a good user experience can be made, with less "features" documented, i'd sure like to know what it is that AMD ahs deemed itself unable to tell us how to use.

    the more i hear about the specs released and stuff, the more i get the feeling that the specs released isnt gonna be able to help create anything but a second class citizen feature wise(and no, i dont count DRM in as a feature.).
    Did you ever noticed that today industry focus is on power management ? Everywhere you see the paradigm of watt efficiency. The competition is now on delivering more computational power while consuming less watt. So obviously power management is sensitive, any trick AMD use can be an advantage over others constructors. And the world we leave in is just "cruel", if you ever tell your enemy what you do don't expect them to congratulate you on the cleverness of your solution but rather to copy or take advantage of this knowledge. I am not against emulations, as matter of fact this one of the things i love, it's just that sadly today you have to protect knowledge.

    On the 3d side i have fairly solid experience of radeon hw and i can tell you that if we ever want to achieve speed & functionalities parity with the closed source driver we better start founding a massive crew of engineers. The fact is that open source people are not genius neither more clever then the closed source engineers. It's just the same brand of human eating same kind of food and drinking same kind of beer

    In the end i am sure that the open source driver will be somewhere around 80%-90% of speed of the closed source one. And as we will limit the rendering to the refresh rate if the 10% gap is just frame you can't see then as a result we will be on pair with the closed one. For me this doesn't look like a 2 class citizen

    I think that AMD is mostly hidding stuff like performances registers which are helpfull only if you got this large crew of engineers i was talking about. And if you look at released spec you can often spot gap here and their and from context make wild guess and with little more effort find out what is missing.

  4. #34
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,418

    Default

    Quote Originally Posted by duby229 View Post
    Ok so then the quewstion becomes how does this have anything at all to do with Linux?
    I think the discussion started out talking about the DRM *hardware* we needed to provide that secure environment in Windows, and how the presence of some of the DRM bits made it harder to open up HW documentation which could be used to write an open source driver for Linux. It sorta morphed into a discussion about DRM software some time later.

    Quote Originally Posted by duby229 View Post
    How does this mean that we need a closed driver? You said it yourself not me. You said that we need a closed driver to enable a secure environment. I didnt say that, you did. There really is only one way to understand that....

    If you dont have any DRM support enabled in the closed driver, then why do you use a secured environment as an argument that you need a closed driver?
    I'm wondering if you are talking about a thread from a month or two ago. I did mention a secure environment and closed source there, but that was as a hypothetical, ie if Linux desktop market share grew to the point where many users were demanding HD/BD playback on a preloaded OEM system, then a legal solution would be required (the PC mfgs would insist on it), a licensed player would be required, and a secure environment would be needed to host the player. In that scenario I imagine we would need to implement some kind of secure environment, but right now the OS mechanisms aren't there to support it.

    Is that what you are talking about ? I think the context was actually hybrid drivers -- closed source 3d stack paired with open source display & modesetting etc...
    Last edited by bridgman; 06-07-2008 at 06:19 PM.

  5. #35
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,418

    Default

    Quote Originally Posted by glisse View Post
    Did you ever noticed that today industry focus is on power management ? Everywhere you see the paradigm of watt efficiency. The competition is now on delivering more computational power while consuming less watt. So obviously power management is sensitive, any trick AMD use can be an advantage over others constructors. And the world we leave in is just "cruel", if you ever tell your enemy what you do don't expect them to congratulate you on the cleverness of your solution but rather to copy or take advantage of this knowledge. I am not against emulations, as matter of fact this one of the things i love, it's just that sadly today you have to protect knowledge.
    Yep. I don't like it either but that is a reality we have to live with.

    The other problem with power management is that the transition from largely driver-controlled to largely hw-controlled power management was a rolling change midway through the 6xx family so there are more chip-to-chip differences than normal even documenting and validating the information is a big task.

    Again, I'm trying to send a message that "we may not be able to expose everything" but I think we will be able to expose enough to make for very happy users.

    Quote Originally Posted by glisse View Post
    On the 3d side i have fairly solid experience of radeon hw and i can tell you that if we ever want to achieve speed & functionalities parity with the closed source driver we better start founding a massive crew of engineers. The fact is that open source people are not genius neither more clever then the closed source engineers. It's just the same brand of human eating same kind of food and drinking same kind of beer
    Actually you guys frequently seem to have access to better beer than us, which is a constant source of aggravation.

    I still can't believe Chimay Blue was *on* *tap* in Brussels

    Quote Originally Posted by glisse View Post
    In the end i am sure that the open source driver will be somewhere around 80%-90% of speed of the closed source one. And as we will limit the rendering to the refresh rate if the 10% gap is just frame you can't see then as a result we will be on pair with the closed one. For me this doesn't look like a 2 class citizen
    It always bothers me a bit when people say "card A is better than card B because card B only runs my game at 177 frames per second

    Yep. I expect you guys will create a very elegant, efficient 3d driver which will perform very well. What I don't expect to see (and I doubt we can fund) is big lab full of people and systems constantly benchmarking and performance tuning drivers to keep the driver "positioned" ideally for the currently popular games and applications. That last bit of performance and compatibility is very expensive. The problem is that in the Windows world (and the Linux workstation world) that 20% performance delta makes the difference between sell and no-sell.

    Quote Originally Posted by glisse View Post
    I think that AMD is mostly hidding stuff like performances registers which are helpfull only if you got this large crew of engineers i was talking about. And if you look at released spec you can often spot gap here and their and from context make wild guess and with little more effort find out what is missing.
    Yep, and even there we want to open most of that up as well, just decided to hack it out of the initial docs so we didn't have to wait for going through the risk analysis. We opened up a lot of the performance and debug registers on 5xx (at least I think we did; I haven't actually gone through them in detail myself); we're mostly trying to hold back stuff related to things that might be useful for attacking DRM on a Windows system.
    Last edited by bridgman; 06-07-2008 at 06:23 PM.

  6. #36
    Join Date
    Nov 2007
    Posts
    1,353

    Default

    I just wanted say finally that I appreciate everything you guys are doing at ATi. The situation may not be ideal today, but it is certainly better now then it ever was in the past... I guess you could call me a bit of a zealot. I'm sorry for being so outspoken. I dont mean to offend anyone, and if that has happened I am truly sorry.

    I think that ATi is severely misguided in it's closed source efforts, but I want to say thank you from the bottom of my heart for your open source efforts. You could take it a bit further (alot further actually) if you wanted to, but what you have already done is toitally awesome....

    And you personally have been incredible.. How many other people do you know that would be willing to take this much badgering on an open forum? How many other people do you know that actually takes the time to talk with the community and help explain some of the difficult concepts of the industry? If anything we need more people like you in this industry.. ATi has already shown that they have what it takes to make a kick ass open source effort. They are in second gear now, but they need to hit the gas and switch to forth gear.

  7. #37
    Join Date
    Oct 2007
    Posts
    370

    Default

    "Did you ever noticed that today industry focus is on power management ? Everywhere you see the paradigm of watt efficiency. The competition is now on delivering more computational power while consuming less watt. So obviously power management is sensitive, any trick AMD use can be an advantage over others constructors"

    Im not asking for implementation details, im asking for how to issue GO_INTO_POWERSAVE().

    "In the end i am sure that the open source driver will be somewhere around 80%-90% of speed of the closed source one. And as we will limit the rendering to the refresh rate if the 10% gap is just frame you can't see then as a result we will be on pair with the closed one. For me this doesn't look like a 2 class citizen "
    This to me is not second class citizen either, however, i do consider not knowing about hardware features a second class citizen.

    "I think that AMD is mostly hidding stuff like performances registers which are helpfull only if you got this large crew of engineers i was talking about. And if you look at released spec you can often spot gap here and their and from context make wild guess and with little more effort find out what is missing."
    but why not release it then?



    "The problem is that in the Windows world (and the Linux workstation world) that 20% performance delta makes the difference between sell and no-sell."
    Dont mind me saying so, but i dont quite think you've done your research properly around what will give you most sales.

    First off, the "workstation" linux graphics market are an insanely very little part of what ati sells to linux users compared to desktops, and for "normal" linux users, that <=20% performance loss there MAY arise from us not having as big driver teams, doesent matter at all, even linux gamers wont mind, what they almost certainly would wish ALOT more, is that what little ressources AMD can devote to the free linux drivers, gets done, who knows, if 1-2 devs at AMD could work fulltime on the free drivers, it may close the gap to 10% or so, this would undoubtedly get you sold alot more pieces of hardware to linux users, than a few firegl cards(even despite the insane price they have, it should give more profit).

    And remember, performance isnt only about speed, but stability too, and this is where opensource outperforms the closed solutions by a factor 100000.

    You may well do speed benchmarks on your windows drivers, assuring your users of 10-20% more performance, but it comes at a price of about 1000 times more instability(dont deny it, you would be terrified if you were in a hospital, and the computer the doctors used to monitor your situation used fglrx) and THIS is a major factor.

  8. #38
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,418

    Default

    Quote Originally Posted by duby229 View Post
    I just wanted say finally that I appreciate everything you guys are doing at ATi. The situation may not be ideal today, but it is certainly better now then it ever was in the past... I guess you could call me a bit of a zealot. I'm sorry for being so outspoken. I dont mean to offend anyone, and if that has happened I am truly sorry.
    Thanks. I find this is the best way for me to learn. It's no fun if everyone agrees on everything

    Don't worry about pushing hard; it does help sometimes. I don't disagree with anything you are saying, but it sure would be nice if I could get a "workstation zealot" on the forum at the same time to argue the other side of the story so it didn't sound like I was just spouting ATI/AMD dogma.

    This is a tricky environment, and I think you do speak for most of the Linux users today, and I do understand that our closed source efforts are of very little interest to you (in fact are probably a constant source of irritation). There are a couple of transitions we need to get through before everyone will be happy though..

    1. We need to finish "catching up" on the open source drivers, to the point where we have decent 2d, 3d and video on all our shipping chips. At that point the focus can shift from "supporting the xxx chip" to "making the open source driver better".

    I don't think we'll quite be caught up before the next generation of GPUs starts shipping but it will be close; and we're already making plans for the next generation.

    The open source community is not big but there are some *really* good people working on the drivers. You know who you are

    2. We need our customers to bump around until they are using the driver which is most appropriate for their needs.

    Right now I cringe when I see people who really should be using the open source driver bang their heads against fglrx every month, and people who should be using fglrx stuck using an open source driver because of some distro or installer quirk.

    I think this should all shake out over the next few months and I'm hoping to see a big jump in the "happy user index".
    Last edited by bridgman; 06-07-2008 at 07:53 PM.

  9. #39
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,418

    Default

    Quote Originally Posted by Redeeman View Post
    Im not asking for implementation details, im asking for how to issue GO_INTO_POWERSAVE().
    If you mean "use less power but don't run as fast", that's no problem and I'm sure we will be able to release that. What I'm not so sure about is releasing enough information to match what our closed source driver can do, using Windows for a reference because we're still turning on PowerPlay in the Linux driver bit by bit.

    PowerPlay is maybe two orders of magnitude more complex than just going into low power mode, and it is woven all through every part of the driver. You can a fair bit of the power savings with a simple GO_INTO_POWERSAVE() but that won't be enough to match what the closed source driver can do.

    Quote Originally Posted by Redeeman View Post
    but why not release it (full performance info) then?
    Simple. We had to choose between releasing most of the information quickly or all of the information a lot later. We figured that getting 95% of the informnation out quickly was best; we do expect to go back and fill in gaps.

    Quote Originally Posted by Redeeman View Post
    Dont mind me saying so, but i dont quite think you've done your research properly around what will give you most sales. First off, the "workstation" linux graphics market are an insanely very little part of what ati sells to linux users compared to desktops, and for "normal" linux users, that <=20% performance loss there MAY arise from us not having as big driver teams, doesent matter at all, even linux gamers wont mind, what they almost certainly would wish ALOT more, is that what little ressources AMD can devote to the free linux drivers, gets done, who knows, if 1-2 devs at AMD could work fulltime on the free drivers, it may close the gap to 10% or so, this would undoubtedly get you sold alot more pieces of hardware to linux users, than a few firegl cards(even despite the insane price they have, it should give more profit).
    Actually Linux market penetration seems to be a lot higher in workstation than in consumer desktop; not quite midway between consumer desktop and server but enough that workstation is much more significant than you might think.

    Quote Originally Posted by Redeeman View Post
    And remember, performance isnt only about speed, but stability too, and this is where opensource outperforms the closed solutions by a factor 100000.
    This is hotly debated. Stability seems to be a function of complexity and resources available, ie one reason the open source drivers appear more stable is that they don't try to do as much. As we complete the move from largely Linux-specific code to largely common code I think you will see most of the remaining stability issues go away.

    Quote Originally Posted by Redeeman View Post
    You may well do speed benchmarks on your windows drivers, assuring your users of 10-20% more performance, but it comes at a price of about 1000 times more instability(dont deny it, you would be terrified if you were in a hospital, and the computer the doctors used to monitor your situation used fglrx) and THIS is a major factor.
    Are you actually seeing that today ? Most of the issues I have seen are primarily related to bits of functionality which were lost or changed during the transition from the old OpenGL code base to the new one. If you take AGP systems out of the equation (AGP brings a host of other stability challenges) the new driver *seems* to be pretty stable today.

    One important point here -- if the driver simply doesn't start up on a specific configuration I would not call that a stability issue, would you ?
    Last edited by bridgman; 06-07-2008 at 07:23 PM.

  10. #40
    Join Date
    Oct 2007
    Posts
    370

    Default

    but the thing about "workstation zealots" is, if you consider linux users a small minority, the workstation users in that minority, is an extremely TIINNNYY minority, and even they will be best served with the open drivers, whether they know it or not
    (thats right, when fglrx doesent even set proper resolution, and highly paid engineers sits mangling with xorg.conf and crap, that really costs, much more than a few percent in speed).

    As for fglrx, i consider it to be largely useless in its current state. As i see it right now, you can NOT go out, purchase a given ati card, and be reasonably certain it will work. Sure, at some point it will work with the free drivers, which is good, but if one is shopping for a card right now, it HAS to be an old one, or an nvidia one, there is no other way, if one wants 3d - which again points in the direction of - THE FREE DRIVERS! they are simply needed, as its abundantly apparent that amd is unable to provider working closed drivers.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •