Pinpointing OpenCL segmentation fault

I would like to test my Intel Graphic HD 530 with an OpenCL code. To do that, I used the vecAdd example along with the following compilation and run command

    $ cc vecAdd.c -o vecAdd.out -lOpenCL -lm
    In file included from /usr/include/CL/cl.h:32,
                     from /usr/include/CL/opencl.h:38,
                     from vecAdd.c:4:
    /usr/include/CL/cl_version.h:34:9: note: #pragma message: cl_version.h: CL_TARGET_OPENCL_VERSION is not defined. Defaulting to 220 (OpenCL 2.2)
       34 | #pragma message("cl_version.h: CL_TARGET_OPENCL_VERSION is not defined. Defaulting to 220 (OpenCL 2.2)")
          |         ^~~~~~~
    vecAdd.c: In function ‘main’:
    vecAdd.c:82:5: warning: ‘clCreateCommandQueue’ is deprecated [-Wdeprecated-declarations]
       82 |     queue = clCreateCommandQueue(context, device_id, 0, &err);
          |     ^~~~~
    In file included from /usr/include/CL/opencl.h:38,
                     from vecAdd.c:4:
    /usr/include/CL/cl.h:1781:1: note: declared here
     1781 | clCreateCommandQueue(cl_context                     context,
          | ^~~~~~~~~~~~~~~~~~~~
    $ ./vecAdd.out 
    Segmentation fault (core dumped)

I am not able to find the cause of that segmentation fault. In fact, I am not sure whether there is a problem with the code or it is not possible to offload the kernel on the device. Any idea how to pinpoint the problem?

P.S: More information about the device

    $ sudo lshw -numeric -C display
           description: VGA compatible controller
           product: HD Graphics 530 [8086:1912]
           vendor: Intel Corporation [8086]

This topic was automatically closed 183 days after the last reply. New replies are no longer allowed.