Search:

Type: Posts; User: clint3112

Page 1 of 7 1 2 3 4

Search: Search took 0.00 seconds.

  1. Replies
    4
    Views
    1,425

    I used this to automatically start multiple...

    I used this to automatically start multiple kernels when the problem size will be larger than the flops the gpu can achieve in 2 seconds. This will make shure the windows watchdog will never get...
  2. Replies
    4
    Views
    1,425

    Thanks for your reply. This was just a quick shot...

    Thanks for your reply. This was just a quick shot from my mind. In my code i am checking for the correct division into LWG sizes.
    My syncproblem has been solved. I missed an iteration in the for...
  3. Replies
    4
    Views
    1,425

    Subdividing gloabl Workgoup Size

    Hi,

    i try to automatically subdivide my global workgroup size (gws) into smaller pieces using the GW offset.
    Here an example:


    size_t szGWS[3] = {1024,1024,1};
    size_t szLWS[3] = {256,1,1};...
  4. Just pass the start adress and for the 3x3 matrix...

    Just pass the start adress and for the 3x3 matrix 9*sizeof(float) as size of your data.
  5. &h_z.at(0) is the same as float foo[n]; &foo[0];...

    &h_z.at(0) is the same as float foo[n]; &foo[0]; So yiu dont need to copy anything. Just have to pass that adress to the enque call.
  6. Your access to the local variables seems to be...

    Your access to the local variables seems to be incorrect. you arent synchronizing the access and all threads of your local workgroup access the same variable. so t1 till write maxZ, t2 will write...
  7. are you shure that the reference to the...

    are you shure that the reference to the std::vector will give you a data array of floats? this would mean that &h_x is the same as a float[dims]
  8. You can keep your Data in the global memory on...

    You can keep your Data in the global memory on your device.
    1. create Buffer on GPU
    2. fill Buffer from CPU
    3. run Kernel 1 on that Buffer
    4. run Kernel 2 on that Buffer
    5. Read Buffer to CPU
    ...
  9. Replies
    2
    Views
    561

    I think the only way to make shure your driver...

    I think the only way to make shure your driver will not crash is to determine the approximate flops you can achieve and split your problem in dimensions that fit these values plus an extra backup...
  10. Replies
    4
    Views
    870

    timing outside on openCL only makes sense when...

    timing outside on openCL only makes sense when you have blocking calls. if you only want to see the time your kernel runs have a look at the timing events of the Kernel
  11. Replies
    5
    Views
    1,123

    he cant find simpleCL.h Thats why all the rest...

    he cant find simpleCL.h
    Thats why all the rest went wrong. have you set your include path correctly?
  12. Replies
    2
    Views
    1,417

    I don't think you can easily compare that. OpenCL...

    I don't think you can easily compare that. OpenCL code will be compiled to the same binary code as cude on an NVidia GPU. So it should be the same performance when you get your code tweaked...
  13. Replies
    1
    Views
    931

    It's been a long time since i tried (and failed)...

    It's been a long time since i tried (and failed) to debug my OpenCL code that way. But didn't they say you need to have 2 GPU's to debug?
    I've tried it for 2 weeks to get gDebugger running and...
  14. Replies
    4
    Views
    1,077

    This Function will give you the thread ID and...

    This Function will give you the thread ID and should be [0;get_global_size()-1] on all devices. if thats not the case, your openCL impelementation is not valid and the hardwaremanufactor who provides...
  15. Are there 2 Graphics Device in Use? Have you...

    Are there 2 Graphics Device in Use? Have you created GL an CL on the same device correctly?
  16. Hi there, on NVidia hardware this can also be...

    Hi there,

    on NVidia hardware this can also be cause by when the device is lost


    Found in
  17. Maybe your code is limited by the number of...

    Maybe your code is limited by the number of registers or memory bandwidth. In that case you would not benefit from more workitems because your problem is still splitted to the same low number of...
  18. looks fine as i can see. Memory for your image...

    looks fine as i can see.

    Memory for your image is set on the host correctly without any errors?
  19. It would be helpful to see the image definition...

    It would be helpful to see the image definition and your sampler definition. Without that i can't tell you where you have your problems
  20. Replies
    5
    Views
    1,480

    hmm, this shouldn't work i think. but the...

    hmm, this shouldn't work i think. but the compiler will not complain because he can't know that you are passing invalid arguments. The buffer definition mustn't be Read_Only
  21. Replies
    2
    Views
    1,157

    One pixel in the image is just one float becuase...

    One pixel in the image is just one float becuase image Format is float and Order is CL_R. So every Pixel you read has just this one float value. To pass a valid array just insert a normal float array...
  22. Replies
    5
    Views
    1,480

    If the Buffer really is a Read Only Buffer, this...

    If the Buffer really is a Read Only Buffer, this should not work. If it is only defined as const in that function this may work. Is it a local funktion in the kernel or the kernelfunction itself?
  23. Hi Duy, i think multiple NVidia Devices could...

    Hi Duy,

    i think multiple NVidia Devices could get a speedup by crossfire and can share memory faster than. I dont know how APU Memory is shared on Intel so that might be a bottleneck....
  24. Hi duy, it is possible to spread out you Problem...

    Hi duy, it is possible to spread out you Problem across all devices on One platform automatically. So i think you might be able to spread it across the whole Intel platform by creating both devices...
  25. Thanks for the Tip, great presentaion

    Thanks for the Tip, great presentaion
Results 1 to 25 of 164
Page 1 of 7 1 2 3 4