Type: Posts; User: sean.settle

Page 1 of 5 1 2 3 4

Search: Search took 0.00 seconds.

  1. Replies

    Re: Reverse (.rev) Vector Components

    Reversing built-in vector types using shuffles and swizzles are explicit, but not readily portable for different vector lengths because function overloading in not included in the OpenCL C kernel...
  2. Re: OpenCL 1.2 Specification Update Feedback Thread

    I see, thanks again!

    Oh, and I didn't catch the extension part because the link is still OpenCL 1.2 Extensions Specification (revision 15, released November 15, 2011), although it has actually...
  3. Replies

    Re: opencl sobel filter and theory

    Take a look at the Sobel Filter for some accessible background info, and at Image Convolution for more details about optimizing the kernel in OpenCL.
  4. Re: OpenCL 1.2 Specification Update Feedback Thread

    Thanks Affie,

    So my initial intuition was correct. However, I still don't see the use for the buffer/array image types. I can't tell how they're different than the regular 1D, 2D, and 3D types....
  5. Re: OpenCL 1.2 Specification Update Feedback Thread

    Hi, I don't know exactly if this pertains to the original or updated 1.2 specification. It may be just me, but I'm a bit confused about the definitions of the various image objects in section 5.3.1...
  6. Replies

    Re: unknown type name kernel in opencl

    Change "_kernel" to "__kernel" or "kernel", and similarly for "_global".
  7. Replies

    Re: pointer type conversion

    It is my understanding that OpenCL does not allow indexing into built-in vector types using pointers. If you wish to accomplish this you should use *.hi, *.lo, etc. I believe the reason for this is...
  8. Replies

    Re: unknown type name kernel in opencl

    It seems that you have one too few (or many) underscores in your attributes, e.g., __kernel or kernel. Please check that you use either two or no underscores first.
  9. Re: Regular question about dual gpu on single board

    Given that the 5970 and 6990 were dual GPU graphics cards seen by OpenCL as two GPU devices each with one half the total advertised memory, I would say that will also be the case for the 7990. You...
  10. Do host allocated buffers need to be manually deallocated?

    If a buffer is created with CL_MEM_ALLOC_HOST_PTR, does that buffer have to be manually deallocated, or is that automatically done inside of clReleaseMemObject when its counter reaches zero? ...
  11. Multiple devices and CL_DEVICE_MEM_BASE_ADDR_ALIGN

    Are there any assumptions I can make about CL_DEVICE_MEM_BASE_ADDR_ALIGN? Without any additional information, if I have to program for multiple devices within a context then I have to ensure things...
  12. Replies


    I have a use case for a get_group_offset function. Suppose you wish to program some reduction algorithm using multiple devices. One option is to use implicit buffer transfers using a subbuffer for...
  13. Replies

    Reverse (.rev) Vector Components

    I ran into a case where it would be really useful to reverse the vector components. To create fully compliant BLAS functions, one must account for when the steps between elements (e.g., incx), are...
  14. Re: Sum Vector Components in OpenCL (SSE-like)

    I've been wondering also why there's no built-in sum function in the OpenCL specification, but maybe that's because a compiler could generate it from optimizing the built-in dot function, e.g., sum =...
  15. Re: unresolved external symbol clIcdGetPlatformIDsKHR...

    The platform supports the cl_khr_icd extension, although I don't see it listed under any of the device extensions. Since this function is called on the host side it should work, right?
  16. Replies

    Re: Error - 52 with clEnqueueNDRangeKernel

    Are those typos in your clSetKernelArg, the ordering is really 0, 1, 2, 3, not 0, 1, 1, 1?
  17. Replies

    Re: Error - 52 with clEnqueueNDRangeKernel

    The error message hints at performing clSetKernelArg(), did you do that correctly?
  18. Re: unresolved external symbol clIcdGetPlatformIDsKHR...

    Thank you for pointing that out; however I still get the same error even after including that extension enable line at the beginning or end of the header include section.

    Any other suggestions?
  19. Re: One cl_context includes devices from different cl_platfo

    In my opinion the restriction is due to vendors having little or no apparent financial incentive to implement that level of interoperability relative to the support it would require. Efficiently...
  20. Re: Where/how to add kernel source code--*.cl--to a VS2010 p

    I don't want to include the kernel source inside the binary, but load the kernel source from a file when executing the binary. The problem is that when I add the kernel source to the project using...
  21. Re: Where/how to add kernel source code--*.cl--to a VS2010 p

    I'm glad I'm not the only one that was shocked by their response. I find the Khronos forums to be way more kind and helpful :).

    Normally I just use gcc and a Makefile to compile my OpenCL...
  22. unresolved external symbol clIcdGetPlatformIDsKHR...

    I originally posted this on the AMD OpenCL forum, but since I wasn't getting any replies and this may be more related to a misunderstanding of mine with the OpenCL spec than my usage of the AMD APP...
  23. Where/how to add kernel source code--*.cl--to a VS2010 proj.

    Where/how is the best place/way to add OpenCL kernel source code to a C++ Win32 console project in Visual Studio 2010? I want to edit the kernel source code in VS2010 and then when I compile (Debug...
  24. Replies

    Re: Predefined Macros: device type

    If a kernel is allowed to be shifted between different basic hardware architectures then it would be helpful to provide a function that hints/dictates which parts of the kernel code should be...
  25. Re: can host determine number of workgroups? related to redu

    The developer generally knows the number of work-groups when they enqueue a kernel and specify the global and local sizes; for each dimension its global[i]/local[i], and take the product of those if...
Results 1 to 25 of 120
Page 1 of 5 1 2 3 4