Announcement

Collapse
No announcement yet.

X.Org Server To See More API/ABI Breakage

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • #41
    Originally posted by liam View Post
    Clearly we have a bit of a communication problem here
    Maybe, maybe not.. When you asserted that KP is leaning towards a performance boost, i don't see that at all;

    Originally posted by Liam
    Fair enough that he didn't say it would definitely improve performance, but the fact that Keith Packard even said it makes it *more than a little likely* to be the case.
    KP did NOT say it was 'more than a little likely'. he said there could be a performance boost. he also said it more likely that it wouldn't even be something imperceptible. And as dave pointed out. His statements seem somewhat in contradiction ~ which is better than what i said of them being 'ambiguous / foggy '. I also tend to agree that it sounds like marketing and hype ~ since there isn't a way at this point to back up that claim.

    Originally posted by Liam
    I don't feel like I misrepresented KP. What I said is technically true. KP, being paraphrased, thinks there could be a performance increase, and I gave the reasoning, which was consistent with what the quote says. The only sticking point is that I failed to specify that it wasn't a certainty, but I did specify that any improvements would likely be minor (whether or not that is a "real performance boost" doesn't matter).
    Does that make sense?
    But i think you are misrepresenting what he is saying and i don't think it is consistent with KPs comment. I think i have a reasonable grasp on the english language (which is my native tongue), and from reading what he said - i didn't come to the same conclusion (as you). Maybe i am wrong, but it really didn't come across that he thinks there (more than likely) will be some sort of tangible performance boost, it sounded like nothing more than a possibility (with no data to support it, which is (obviously) in itself very problematic). One always needs data/facts to back up claims, without it the claim is nothing more than a belief / hunch / faith / etc. I mean if i told you i was psychic ~ you would want proof of it. You wouldn't just accept that i am psychic because i said so. Which goes back to one of my first statements;

    "I will believe it, when i see it".

    Originally posted by Arlied
    wayland won't magically speed-up X rendering, the same operations happen. In fact something like SNA would speed it up a lot more than wayland, since it actually tries to accelerate X rendering, where wayland does nothing different wrt X rendering really vs having a compositing manager running on X now.
    This is what i thought Dave was implying with the 'magic bullet' statement. I didn't think he was talking about things like cairo. I thought he was talking about X acceleration in wayland. So i think this may have also been a point of miscommunication between us.

    and by the way Liam. I do quite enjoy our interactions, even when you and i may disagree on something or have different ideas ~ we always keep our conversations clean and civil, which is nice.

    cheerz

    Comment


    • #42
      Originally posted by airlied View Post
      In fact something like SNA would speed it up a lot more than wayland, since it actually tries to accelerate X rendering, where wayland does nothing different wrt X rendering really vs having a compositing manager running on X now.
      SNA is only for Intel / Sandy Bridge only or can be used for AMD, Nvidia, etc too?

      Comment


      • #43
        Originally posted by airlied View Post
        It was a reply to uid313's comment not yours. He made a fanboi comment, and I corrected him.

        If I paraphrased Keith as "An possibly imperceptible performance boost", seems like a contradiction in terms to me.

        The thing you might have a couple context switches, but you might also have a few more introduced elsewhere like the input paths, the latency might go up as well as the throughput.

        Keith was engaging in a bit of marketing really, since no measurements are possible at this point. I generally prefer my performance boosts to come with a measureable difference, and I don't mean gtkperf gets faster, since nobody has ever correlated that with a real world difference.

        wayland won't magically speed-up X rendering, the same operations happen. In fact something like SNA would speed it up a lot more than wayland, since it actually tries to accelerate X rendering, where wayland does nothing different wrt X rendering really vs having a compositing manager running on X now.

        Dave.
        I had a feeling you were responding to the seeming fanboi comment and, I imagine, you encounter that sort of thing a lot. As I think I said, my only concern was that what you said seemed to be contradicting something I'd read recently (Keith's comment). Now, while I would argue that performance boosts need not be perceptible, they at least need be measurable but I wasn't aware that Keith was speaking from a marketing perspective. That clears things up a bit and helps me to understand your comment.
        I, too have been wondering about the effect Wayland's input handling would have with the X clients but I've not read much about that, so I could easily see that negating at least some of the gains Wayland provides X clients on the display side.
        Lastly, I reiterate that I understand there is no magic going on. I repeat, though I haven't looked behind the curtain, I believe there IS a normal person there!
        The advantages Wayland provides X clients is simply fewer context switches (though only possibly, as I agreed earlier, we'll have to see how things work out) and synchronization guarantees (though we have those with a modern, desktop that is handled by an opengl library like clutter in combination with dri clients).
        If I am mistaken in any of this, feel free to correct me b/c I'd much rather be publicly corrected than to privately hold false notions.
        Best/Liam

        Comment

        Working...
        X