PS3 Linux: Cell optimized graphics library

Discussion in 'CellPerformance@B3D' started by Shifty Geezer, Mar 14, 2007.

  1. Turok

    Regular

    Joined:
    Dec 24, 2006
    Messages:
    330
    Likes Received:
    0
    I'm not familiar with Mesa, but is it anything like OGRE?
     
  2. Todd33

    Veteran Banned

    Joined:
    Jan 22, 2007
    Messages:
    1,066
    Likes Received:
    7
    Location:
    CA
    I don't think there is any port of the VTK code itself, but if you use the ported MESA for the opengl then the VTK render window, which is opengl, should be much faster than a regular CPU. I have a little app that uses the software based vtkVolumeRayCastMapper class for 3D volume rendering. It would interesting to build it on the PS3 and see how fsat it is compared to my dual Xeon at work.
     
  3. zed

    zed
    Veteran

    Joined:
    Dec 16, 2005
    Messages:
    4,442
    Likes Received:
    629
    no orge is a rendering engine i believe
    mesa is a 100% software opengl implementation
    ie (under windows) it replaces opengl32.dll thus all gl calls get done with the mesa opengl.
    normally when u make gl calls they go from opengl32.dll -> (the card markers dll) eg with nvidia its nvoglnt.dll (which does the drawing)
    (there was hardware support in the old days on voodoo cards IIRC) more info at www.mesa3d.org
     
  4. patsu

    Legend

    Joined:
    Jun 25, 2005
    Messages:
    27,614
    Likes Received:
    60
    I emailed Terrasoft to request for more info about the optimized Mesa run-time. Also gave them the URL to this thread. Hopefully we will see some response from them.

    Meanwhile (not sure if it has been posted before) I also found this:
    http://forums.ps2dev.org/viewtopic.php?t=7209
    The hardworking members at ps2dev created some simple example based on the vsync sample source code in Cell SDK 1.1 (I think).
     
  5. patsu

    Legend

    Joined:
    Jun 25, 2005
    Messages:
    27,614
    Likes Received:
    60
    Kai replied via Email. Apparently, the optimized Mesa library is available in the HPC Consortium wiki (opened to members only). They are in the process of doing a public interface for the wiki. Once that's done, we should be able to get our little hands on the new Mesa library.
     
  6. ihamoitc2005

    Veteran

    Joined:
    Sep 21, 2005
    Messages:
    1,181
    Likes Received:
    15
    720p

    Or 720P at 26fps no? But how many SPE do they use for this and how much is AA?
     
  7. popper

    Newcomer

    Joined:
    Jul 22, 2006
    Messages:
    69
    Likes Received:
    3
    were is the WIKI


    has anyone found it yet?:shock:
     
  8. popper

    Newcomer

    Joined:
    Jul 22, 2006
    Messages:
    69
    Likes Received:
    3

    well Lu_Zero has done LOTS of PPC, Altivec and SPU work for everyones use, perhaps people should go and help him in his good work and we might get somewere far faster...
    http://planet.gentoo.org/developers/lu_zero

    http://search.virginmedia.com/results/?channel=homepage&q=Lu_zero+altivec&cr=
    http://search.virginmedia.com/results/index.php?channel=other&q=Lu_zero+spu&cr=

    http://forums.ps2dev.org/viewtopic.php?t=7180&sid=0a2e4129305935f0705e4790832e29a6
     
    #28 popper, Apr 11, 2007
    Last edited by a moderator: Apr 11, 2007
  9. popper

    Newcomer

    Joined:
    Jul 22, 2006
    Messages:
    69
    Likes Received:
    3
    no sign of it appearing yet then patsu, i wonder if the source is there too,we might even get a working SDL svn like https://ssl.keshi.org/projects/ps3/trac.fcgi/browser/SDL/trunk Keshi started but never did anything else .
     
  10. Titanio

    Legend

    Joined:
    Dec 1, 2004
    Messages:
    5,670
    Likes Received:
    51
    I managed to get some more info out of Terrasoft on this. It looks like some of our assumptions were off-base..

    First off, most importantly, the relative performance figures (7x the framerate, 80x the fragment rate) are comparing performance of their technique implemented with Rapidmind versus without Rapidmind. The idea of the project was to implement a system that takes OpenGL fragment shaders and turns the interpreter for them into a compiler that compiles them into SPE code, and offloads that code to the SPEs. They implemented it with and without Rapidmind, and the relative performance figures shown are comparing those implementations - not MESA's speed before and after. The figures by no means reflect the performance you would get in the general case going to this new version of MESA, not by a long shot. It wouldn't accelerate something like Q3 on the system since it's just addressing fragment shaders (which Q3 doesn't use)..and for apps using fragment shaders it would just make them go from being really really really slow to really really slow :p Their system also doesn't yet allow all operations in the fragment shaders, there are still some holes to be filled. In absolute terms it's all still quite slow apparently, they still have a lot of work to do to make this part run well, and comprehensively.

    The guys working on this at the hack-a-thon haven't had a chance to get back into it since then either, so it's hard to tell if it's an on-going concern on their part or not. But it is something they think would require a lot more work if it were to be a generally accelerated version of MESA.
     
  11. one

    one Unruly Member
    Veteran

    Joined:
    Jul 26, 2004
    Messages:
    4,823
    Likes Received:
    153
    Location:
    Minato-ku, Tokyo
    As long as Rapidmind is proprietary, it's not very likely MESA optimized for it appear in the open source world...
     
Loading...

Share This Page

  • About Us

    Beyond3D has been around for over a decade and prides itself on being the best place on the web for in-depth, technically-driven discussion and analysis of 3D graphics hardware. If you love pixels and transistors, you've come to the right place!

    Beyond3D is proudly published by GPU Tools Ltd.
Loading...