Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

AMD OpenCL multi-core CPU demo at Siggraph Asia 2008

Loading...

Sign in or sign up now!
67,795
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Feb 3, 2009

The first public demonstration of OpenCL functionality was by AMD's FirePro / Firestream team at Siggraph Asia 2008. The particle & fluid simulation shows how OpenCL can extract high performance parallel computing out of GPUs, DSPs and multicore CPUs. Basically the idea is that you can write up your core computational code in OpenCL and suddenly you scale to whatever processors are available. Initially the demo only uses one core of a Dragon-based system (quad-core Phenom II). As the additional cores are enabled the simulation compute time is cut in half!

Category:

Science & Technology

Tags:

License:

Standard YouTube License

  • likes, 5 dislikes

Link to this comment:

Share to:

Uploader Comments (fireuser3d)

  • This is is a demo using the CPU only - that is the beauty of OpenCL - it scales to whatever is available - CPU, GPU, DSP, Larabee... This demo using a multi-core CPU really shows off this scaling and that was the goal (and to be the first public example of OpenCL). Now we just need to see software developers work with AMD to take advantage of the OpenCL drivers

Top Comments

  • is this demo downloadable?

  • I think it runs on both after reading the wiki page for opencl

see all

All Comments (37)

Sign In or Sign Up now to post a comment!
  • @niinja2

    Yeah you could try luxrender it's a ray tracing program that uses opencl and I think runs on GPU and multiple cores.

    

  • @thepantherx12

    to bad , do you know any other easy demos that could test the power of multicore cpu or gpu?

  • @niinja2

    This version of powder toy isn't available.

  • @niinja2 Why ask me? I haven't a clue what program you're talking about, but the OpenCL implementation I mentioned should be at developer.amd.com/gpu/AMDAPPSD­K/ ... As for the demo in the video, which I don't know where to find, it presumably has some hotkey to change the number of cores used to demonstrate the speedup. If a GPU-accelerated program shows as using one core, it's probably just wasting CPU time polling the GPU (which does the work).

  • @0LoneTech

    do i need any other software to run this program with all 4 cores? because my cpu uses only 25% of his capacity.

  • Like EnigmaSand. But BETTER.

  • where can u get the powder toy :)

  • @sonofhendrix AMD have published their OpenCL implementation (ATI Stream SDK), and it supports both their ATI GPUs and CPUs (where non-AMD models are not officially "supported"). nVidia also have an OpenCL implementation for their graphics drivers, but it is wasteful with CPU. CUDA is fairly mature, but OpenCL is far more portable.

  • @shartep Err incase you havent realized this is from AMD meaning you cant download it. Best bet is to get Nvidia and you will have thousonds of free CUDA demos.

  • @sonofhendrix

    1/10

Loading...
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more