Results 1 to 8 of 8

Thread: Cedar Trail Coming Soon To Open GMA500 Driver

  1. #1
    Join Date
    Jan 2007
    Posts
    15,378

    Default Cedar Trail Coming Soon To Open GMA500 Driver

    Phoronix: Cedar Trail Coming Soon To Open GMA500 Driver

    While Intel's OSTC (Portland) team is busy at work on Intel Ivy Bridge Linux graphics support for this next-generation hardware due out by year's end, the same team doesn't play with Intel's Poulsbo or other graphics IP that isn't an in-house Intel creation and part of their open-source driver. It seems, however, that Alan Cox is personally working on early "Cedar Trail" support for the open-source GMA500 driver...

    http://www.phoronix.com/vr.php?view=OTYyNw

  2. #2
    Join Date
    Nov 2009
    Location
    Italy
    Posts
    984

    Default

    Awesome news, hopefully we will get something more than kernel mode settings.
    Intel is doing a damn good job nowadays, keep up the good work.

  3. #3
    Join Date
    Sep 2008
    Posts
    989

    Default

    Why doesn't Intel just terminate their stupid agreement with Proprietary Technologies' PowerVR and assign an internal team to miniaturizing the Intel GMA architecture to run on Atom?

    The inability to produce open source drivers for Linux due to the proprietary PowerVR "intellectual property" is really harming users and operating systems that want to take advantage of this hardware. It is something that is totally unbecoming of Intel, in light of their active participation of open source for Intel GMA (and the Linux kernel overall).

    It's good that Alan is working on this, but I don't think it will be enough that he alone is doing this. To get OpenGL 2.1 accel to the quality of r600g, we'd need a team of 5 or 6 people at least (just look at all the effort it takes to bring up a new Radeon or Fusion ASIC).

    I'd much rather see GMA-mini with the same form factor and TDP as the Atom+PowerVR chips are designed for, but with the PowerVR crap ripped out.

  4. #4
    Join Date
    Feb 2008
    Location
    Linuxland
    Posts
    5,264

    Default

    Intel tech already ran on Atom, remember 3150?

    Their better parts, HD2k and 3k, depend a lot on a powerful cpu, and that's likely why they haven't put one in an Atom.


    On the Tampere office speculation, I still have a hard time believing PowerVR would let Intel do that. My money is still on something Meego-related, perhaps the Meego phone from Intel.

  5. #5

    Default

    Quote Originally Posted by allquixotic View Post
    I'd much rather see GMA-mini with the same form factor and TDP as the Atom+PowerVR chips are designed for, but with the PowerVR crap ripped out.
    So you want the 5w version of the AMD Fusion APU then. Has both kinds of drivers, OSS and secret sauce, lower TDP and higher performance.

    http://www.engadget.com/2011/01/31/a...let-of-choice/

    This site ranks all laptop GPUs acording to how they stack up to the current fastest possible Crossfire/SLI laptop setup:

    The C-50's HD6250 comes in a 7% http://www.notebookcheck.net/AMD-Rad...0.40958.0.html

    While the Atom's GMA500 pulls in at only 1% http://www.notebookcheck.net/Intel-G...0.12614.0.html

  6. #6
    Join Date
    Jul 2008
    Location
    Berlin, Germany
    Posts
    847

    Default

    Intel's own GMA is not at all power efficient. It is much worse than AMD's Llano.
    AMD also made some strong claims about Llano's battery life while playing games, so we decided to test that, as well. We pulled up Battlefield: Bad Company 2 and left it running, full-screen, to see how long each laptop would last. The Llano test system's discrete GPU was disabled in the BIOS, so we were relying entirely on both processors' IGPs. Here's what we found.
    Source: http://techreport.com/articles.x/21099/7

  7. #7
    Join Date
    Oct 2006
    Posts
    14

    Default

    Quote Originally Posted by chithanh View Post
    Intel's own GMA is not at all power efficient. It is much worse than AMD's Llano.

    Source: http://techreport.com/articles.x/21099/7
    I got quite the opposite. The argument that AMD's GPU is more efficient seemed to hold true for laptops, but desktops with more detailed tests show a completely different story. I think the problem is with Intel paying less attention to 3D battery life, than the GPU being inefficient itself. Media playback, which they touted for having good power usage, did much better than Llano, like with Anand's review.

    It makes more sense to pay attention to battery life on video playback, that already got decent battery life, than 3D gaming on battery, which not only brings down performance compared to plugging it in, but the battery life is still pathetic even with big gains on Llano.

    http://translate.googleusercontent.c...EjwQ98X59BGqlQ

    Llano: extra 52W for graphics task
    Sandy Bridge: extra 32W

    Time to market is just as important and it will take some time for them to make power efficient graphics.
    Last edited by DavidC; 07-05-2011 at 06:33 PM.

  8. #8
    Join Date
    Jul 2008
    Location
    Berlin, Germany
    Posts
    847

    Default

    Quote Originally Posted by DavidC View Post
    I think the problem is with Intel paying less attention to 3D battery life, than the GPU being inefficient itself. Media playback, which they touted for having good power usage, did much better than Llano, like with Anand's review.
    If you read the techreport review, they found that with a similarly sized battery, Llano was on par with a single channel i5 2410M and beat a dual channel one in the Media playback test. Only in Web surfing, Intel was ahead by 30-50 min. Anandtech's review has drawn lots of commentary, and not all positive.

    Besides I don't think you get meaningful power consumption results from the 3DCenter figures (desktop not mobile, and a synthetic benchmark where Llano does much more work than Intel).

Posting Permissions

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