Type: Posts; User: affie

Page 1 of 5 1 2 3 4

Search: Search took 0.00 seconds.

  1. Replies

    The 24-bit depth / stencil format is supported as...

    The 24-bit depth / stencil format is supported as an optional extension. These are described in the OpenCL 2.0 extension specification (refer to section 9.11)
  2. Replies

    Writes to 3D images is a core feature in OpenCL...

    Writes to 3D images is a core feature in OpenCL 2.0. This looks like a bug in the reference pages.
  3. Replies

    Re: Kernel improvement?

    Local memory can be helpful if one or more work-items are reading from a location in global memory multiple times. In the specific example you posted it is not clear if it will help as the OpenCL...
  4. Re: Race condition between clEnqueue* and clSetEventCallback

    There is no race condition. The spec states that for clSetEventCallback, the registered
    callback function will be called when the execution status of command associated with event
    changes to an...
  5. Replies

    Re: 3-D vs 1-D Global worksapce

    This seems like a bug in the OpenCL implementation you are running on. Suggest you contact the vendor and file a bug.
  6. Re: how to create and init gpu memory buff to be all 0s

    You can also use clEnqueueFillBuffer to fill the buffer with a pattern which in your case will be 0s.
  7. Replies

    Re: OpenCL 1.2 2D image array

    The addressing & filter mode specified in the sampler only get applied to the x and y dimensions of a 2D image array. The z dimension (for a 2D image array) is only clamped and no filtering is...
  8. Re: OpenCL 1.2 Specification Update Feedback Thread

    Are you referring to the cl_khr_image2d_from_buffer extension that was just added as an extension to 1.2? When you create an image, the GPU stores this in an opaque layout which means you cannot...
  9. Re: OpenCL 1.2 Specification Update Feedback Thread

    The device (typically GPUs) will store the image data in an opaque format. The linear layout that is being described in the spec is referring to how the image data is laid out in the memory pointed...
  10. Re: Do host allocated buffers need to be manually deallocate

    The buffer does not have to be manually deallocated. All you need to is release the buffer using clReleaseMemObject. When the cl_mem object is released by the OpenCL implementation the allocated...
  11. Replies

    Re: Using a buffer on multiple devices.

    Just wanted to confirm that when you enqueue kernel to device 2 that does not modify B or E, you do not use the event that refers to kernel enqueued to device 1 (that does not modify B or C) in the...
  12. Replies

    Re: OSX Lion 10.7.4 update broke my kernel

    Please file a bug to Apple with a test case.
  13. Re: Allocate array in a kernel of length known only at runti

    One option is to create the temporary array that is the same size as arr being used inside the kernel as a cl_mem object i.e. using clCreateBuffer and pass it also as an argument to kernel.
  14. Re: [OS X, CoreImage]How to bind a CIImage to an openCL imag

    I would recommend the following:

    1) First of all, you need to create a CL context from a CGLShareGroup. You can get the CGLShareGroup by doing:

    CGLShareGroupObj sharegroup =...
  15. Replies

    Re: Predefined Macros: device type

    Can't you do this by defining your own macro which is passed in the options argument to clBuildProgram? It does mean that you now need to call clBuildProgram separately for devices of different...
  16. Replies

    Re: Built-in Functions: Work-Item Functions

    CL_KERNEL_WORK_GROUP_SIZE_MULTIPLE is supposed to be a performance hint to make sure that the local workgroup size specified to clEnqueueNDRangeKernel is a multiple of this value.

    To do what you...
  17. Re: OpenCL/OpenGL Problems: clEnqueue{Acquire|Release}GLObje

    I'm assuming you created the CL image from GL texture using clCreateFromGLTexture{2D|3D} API. clEnqueueAcquireGLObjects / clEnqueueReleaseGLObjects should not do a copy if both CL & GL are on the...
  18. Replies

    Re: clBuildProgram pfn_notify

    The pfn_notify function you specified will be called when the program build has finished. You can then query the build status to see if the program was built successfully or not.
  19. Replies

    Re: OpenCL Language Clarification

    Intel is correct here. Section 6.3, item g states that "The logical operators and (&&), or (||) operate on all scalar and vector built-in types except the built-in scalar and vector float types".
  20. Re: Is there a way to GL render 3d data directly from CL mem

    Refer to section 9.7 of the 1.1 spec which describes how to create a CL context for sharing with GL. You can pass a GLcontext or a sharegroup (on Mac OS X) to cl_context_properties argument in...
  21. Replies

    Re: Early returns and barriers inside the kernel

    You could pad the buffers appropriately and this solution works. If you decide you do not want to pad then the code would need to be something like:

    if (get_global_id(0) < n)
  22. Replies

    Re: Atomic operations in OpenCL 1.0

    The cl_khr_local_int32_***_atomics extensions are not exported and therefore atomic operations to local memory are not supported. The GeForce 9600M GT does not support atomic operations to local...
  23. Replies

    Re: global work offset in OpenCL 1.1

    Refer to section 3.2 (specifically the following equation on page 24) of the 1.1 spec:

    Given a global ID and the work-group size, the work-group ID for a work-item is computed as:
    (wx, wy) = (...
  24. Re: Undefined reference errors with image2d functions

    There is also an error with the values in the sampler that you are using with read_imagei.
    The sampler you are using with read_imagei in your kernel is defined to be: (CLK_NORMALIZED_COORDS_TRUE |...
  25. Replies

    Re: Correct way to declare a global sampler_t

    I've posted my comments in the bugzilla. Will update once the WG discusses and makes a decision.
Results 1 to 25 of 105
Page 1 of 5 1 2 3 4
Proudly hosted by Digital Ocean