Search:

Type: Posts; User: FirmiDerac

Search: Search took 0.00 seconds.

  1. Re: Slow MD-program. My cpu runs it faster than my GPU

    I actully think I might have figured out the problem, but I am not sure on how to solve it though. The thing is that in one of my kernels you got the following when adding the velocity:


    ...
  2. Re: Slow MD-program. My cpu runs it faster than my GPU

    Since the program gives errenous results with the GPU only it should be something wrong with the concurrency. I thought that maybe openCL started moving atoms before I had finished calculated their...
  3. Re: when to use get_global id and get_local id in opencl?

    if you are in the first work item get_global_id(0) will return 0. If you are in the second work item get_global_id(0) will return 1 and so on. The 0 stand for the dimension.
  4. Re: when to use get_global id and get_local id in opencl?

    Is it correct to assume that the kernel will be run global_work_size times regardless of local worksizes and etc?
  5. Re: Slow MD-program. My cpu runs it faster than my GPU

    Also, when you calculate it with the CPU only, you get the right result regardless of what your local work size is...

    (btw, how do you edit your posts?)
  6. Re: Slow MD-program. My cpu runs it faster than my GPU

    When I change local work size from 1 to higher numbers e.g. 64 my program finishes about 20 times faster but it doesn't calculate it correctly (it diverges and it seems that you don't calculate...
  7. Slow MD-program. My cpu runs it faster than my GPU

    Hi, I really need some help with this thing. I would really like some pointers on what to do to make this thing faster. Since the CPU (intel i5 2500K) runs it faster than my radeon 6780 it feels like...
Results 1 to 7 of 7