Fractron 9000 -- an OpenCL fractal flame generator

Discussion in 'GPGPU Technology & Programming' started by fellix, Jun 29, 2010.

  1. fellix

    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,532
    Likes Received:
    485
    Location:
    Varna, Bulgaria
    More here
     
  2. homerdog

    homerdog donator of the year
    Legend Veteran Subscriber

    Joined:
    Jul 25, 2008
    Messages:
    6,288
    Likes Received:
    1,071
    Location:
    still camping with a mauler
    What version of OpenCL does it require?
     
  3. pcchen

    pcchen Moderator
    Moderator Veteran Subscriber

    Joined:
    Feb 6, 2002
    Messages:
    2,896
    Likes Received:
    394
    Location:
    Taiwan
    It seems to work with OpenCL 1.0. I can get it to run on my GTX 285. Unfortunately, it crashes on my Radeon 5850 (my own DeviceQuery program works so at least OpenCL works on it).
     
  4. fellix

    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,532
    Likes Received:
    485
    Location:
    Varna, Bulgaria
    Works fine on HD5780 and Stream SDK 2.1 here.
     
  5. pcchen

    pcchen Moderator
    Moderator Veteran Subscriber

    Joined:
    Feb 6, 2002
    Messages:
    2,896
    Likes Received:
    394
    Location:
    Taiwan
    I guess that's because GTX 285 now don't have to be part of the desktop to run OpenCL, and the program tries to run OpenCL on GTX 285 while it's being disabled so it's impossible to create a OpenGL context for it (or it's impossible to share data between the OpenCL device with the OpenGL device, which is the Radeon). Just my guess though :p

    [EDIT] It runs well after I disabled GTX 285 in the device manager.
     
  6. Andrew Lauritzen

    Moderator Veteran

    Joined:
    May 21, 2004
    Messages:
    2,526
    Likes Received:
    454
    Location:
    British Columbia, Canada
    Very cool! Curiously when you build up the iteration kernel for a given genome, do you fuse it together into one kernel when dealing with different function types (textually or some other way?) or do you simply iterate each function as a separate kernel?
     
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...