Search:

Type: Posts; User: poonaatsoc

Search: Search took 0.00 seconds.

  1. Re: valgrind shows a lot of errors with leak check

    True. And the 195.xx drivers don't seem to reduce the valgrind errors and warnings too.
  2. Re: __constant args cause Segfault in the OpenCL library

    This is a bug in the 190.29 nvidia driver. The 195.30 beta solves it. Thanks all
  3. valgrind shows a lot of errors with leak check

    I a running nvidia's 190.29 OpenCL driver for linux. When I run my opencl program through valgrind for leak checks, valgrind throws a lot of errors. Apparently there seems to be a lot of leaks...
  4. Re: __constant args cause Segfault in the OpenCL library

    I haven't exceeded the limit. I am not crossing 1 kb of constant buffer size, let alone the min limit of 64 kb. Running it through gdb at times, makes clEnqueueNDRangeKernel throw errors. ...
  5. Re: __constant args cause Segfault in the OpenCL library

    Yes, it ocurs at clEnqueuenNDRangeKernel. I think I will contact the vendor. The driver is a beta release from nvidia. Thanks for replying affie
  6. Re: __constant args cause Segfault in the OpenCL library

    Actually I pasted the wrong definition. I had declared the non-pointers without any qualifiers since I wanted them to be private.

    "__kernel void Function(__global uint *offsets, __constant uint...
  7. __constant args cause Segfault in the OpenCL library

    I have kernel which is defined as



    Function(__constant uchar *buf, __constant ushort buflen, __constant uint m, __constant uchar *table, __constant uint *search_B2G, __global uint *mts,...
  8. Re: clBuildProgram crashes with varying kernel args

    I just checked my code and it looked like I was setting just a memory of size bytes instead of size + 1, for the code retrieved from the program source file. Changed it to size + 1 and it worked...
  9. clBuildProgram crashes with varying kernel args

    I have a kernel which I have defined by

    Filename: kernel.cl

    __kernel void ptop(__global int *a, __global int *b, __global int *c)
    {
    size_t global_id = get_global_id(0);

    ...
  10. Re: description for CL_MEM_USE_HOST_PTR on the use of host_ptr

    Ah Right. I mistook USE_HOST_PTR with COPY_HOST_PTR. It is quite clear and obvious now. Thank dbs2.
  11. description for CL_MEM_USE_HOST_PTR on the use of host_ptr

    For clCreateBuffer( ), the spec says that for CL_MEM_USE_HOST_PTR, if we supply host_ptr during the call to clCreateBuffer( ), the OpenCL implementation would use the memory bits used by host_ptr...
  12. Re: calling the same kernel object multiple times

    But won't this affect the kernel object, since the kernel arguments are associated with the kernel object.

    If I do a




    clSetKernelArg(kernel, 0, value1);...
  13. Re: Time of clReleaseMemObject : strange behaviour

    This is implementation defined, isn't it? I was considering the time spent on releasing the buffer objects. In cases, when you are in a loop and you have to call the kernel multiple times, isn't it...
  14. calling the same kernel object multiple times

    Can I call the same kernel object "search_kernel" multiple times in a loop, each time supplying different kernel arguments?

    For example -



    cl_mem args[32];
    cl_kernel search_kernel;
    ...
  15. completion of the kernel to retrieve buffer from device

    Hi,

    As I understand, clEnqueueNDRangeKernel(), enqueues the kernel and returns. If the kernel writes to a memory that I have to retrieve, I will have to wait for the kernel to complete before I...
  16. performance diff clEnqueueWriteBuffer vs clEnqueueMapBuffer

    Hi.

    Sorry for using shorthands in the topic title. The textbox seems to have a length limit.

    I have a buffer object, whose data contents are modified across kernel invocations(this memory...
  17. Assigning a number to a __global int *p and resolving it

    Thanks for taking time to read this. I have 2 kernels. To both these kernels I send the same 2 memory buffers as arguments, where each of the memory buffers have the size -> sizeof(int) * 10.
    ...
  18. Replies
    3
    Views
    3,904

    Re: Persistent storage on opencl GPU

    Yes. I think this would be the solution. Will try this out and get back here. Thanks for taking time on this.
  19. Replies
    3
    Views
    3,904

    Re: Persistent storage on opencl GPU

    A question related to this previous post of mine.

    When we set a kernel argument using clSetKernelArg(memory_object) and call the kernel multiple times using clEnqueueNDKernelRangeKernel( ), will...
  20. Replies
    3
    Views
    3,904

    Persistent storage on opencl GPU

    Sorry for the grammatical errors. Re-posting after correction

    Hi. Is there any way for the GPU to have persistent data storage(across kernel invocations), so that we don't have to repeatedly send...
Results 1 to 20 of 20