Announcement

Collapse
No announcement yet.

"Ask ATI" dev thread

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

  • bridgman
    replied
    I don't think we ever supported >2 displays per card, unless some of the displays were showing the same image. AFAIK the Evergreen series are the first ATI products to support >2 independent displays per GPU.

    Or are you talking about a dual-GPU card such as one of the FireMV products ?

    Leave a comment:


  • myeyespy
    replied
    when might 2+ monitors be supported?

    Any ideas when 2+ monitors per card might be supported? I currently have 4 x Nvidia 6600gt and I am dying to make the switch and upgrade my monitor setup..

    No interest in eyefinity single desktop, just "old" "normal" style 2+ support per card

    Leave a comment:


  • bridgman
    replied
    Dandel:

    There is work being done to provide a run-time install of OpenCL independent of the development kit, but I don't know the schedule.

    Emergence:

    I would not have expected 10.6 to have any effect on the tearing you mentioned. The 10.6 release was the first time we turned on the new 2D code by default and it is still being worked on. The point I made about the new 2D code was not that it would "magically fix everything" but that putting a lot of work into building a tear-free infrastructure around the old accel code would not be a good use of time because we would have ended up tossing much of it when we switched to the new accel architecture anyways.

    Prescience500:

    Yes, but it would be in line with the work that has been done so far, ie opening up more of the code which interfaces to the rest of the system, not opening up the core.

    Leave a comment:


  • Prescience500
    replied
    Is there any hope or plans to further open your divers as of this point in time?

    Leave a comment:


  • emergence
    replied
    AMD/ATI linux devs, there is a bug related to the drivers regarding tearing. The bug still exists with catalyst 10.6. Any ideas as to when it will be resolved?

    The bug was opened 1.5+ years ago:
    https://bugs.launchpad.net/ubuntu/+s...er/+bug/303697

    The last message in that bug report confirms that this is a driver issue:

    Here is what I have found since I first reporting my problem. It turns out this is a Catalyst Driver issue. On a different computer running Ubuntu 10.04 and with a Radeon HD 4890 I was able to get solid graphics performance with no screen tearing using the latest open source ati driver. However, on the same machine with 10.04 and the Catalyst driver, I am seeing screen tearing.

    Just to recap my other machine has a Radeon HD 5870 and I am seeing tearing with the Catalyst driver. Unfortunately, however, the open source ati driver does not currently support the Evergreen series of GPUs, so I am stuck with this pitiful driver. I am now hopeful that my problems will be solved later this year when 5xxx series cards are supported in the open source graphics stack.

    I'm looking forward to Ubuntu 10.10 and beyond. I think this problem won't be fixed until that time and any future AMD/ATI GPUs I would advise staying away from until the open source driver can support them out of the box. It is my understanding that this screen tearing issue is rooted in something fundamental to the proprietary Catalyst driver and is not going away any time soon.
    I myself have an HD5850 and with compiz and metacity I'm getting tearing when dragging windows. My previous post alluded to this same issue and was told that 2D rendering was being rewritten. Catalyst 10.6 has not resolved my issue.

    Leave a comment:


  • Dandel
    replied
    I'm actually wondering approximately how long it will be for the OpenCL headers and libraries will be bundled with the linux drivers package, without having to download, install and configure Stream sdk.

    Leave a comment:


  • phoen1x
    replied
    please fix it

    Could someone from amd/ati check these two bugs http://ati.cchtml.com/show_bug.cgi?id=1700 and http://ati.cchtml.com/show_bug.cgi?id=1794 ? Driver works fine with that chipset in windows. And this is not kernel or whatever issue, it is driver issue since 9.9 version. Catalyst 9.8 and older versions like 9.4 work fine.

    Leave a comment:


  • mitch074
    replied
    Originally posted by d2kx View Post
    Go and try it.
    It does solve the slow workspace switching problem. Yay!

    Leave a comment:


  • d2kx
    replied
    Originally posted by mitch074 View Post
    If 10.6's new code base solves THAT, I can't wait to try it
    Go and try it.

    Leave a comment:


  • mitch074
    replied
    Thank you for the explanation Bridgeman: I remember seeing something about that at the time, yes.

    Could it also be the reason why switching workspace is so slow with fglrx? I have a 1-5s delay switching to a workspace that contains open windows (the more windows, the longer the delay).

    If 10.6's new code base solves THAT, I can't wait to try it

    Leave a comment:

Working...
X