dimension = 2
ref.count = 0
*** error; expected ref.count=1

int main(int argc, char** argv)
{
    string err;
    try {
        cout << endl << "ReferenceCountTest" << endl;

        af::array a = af::constant(1, af::dim4(2, 2));
        cout << "dimension = " << a.dims().ndims() << endl;

        int refCount = 0;
        if (af_get_data_ref_count(&refCount, a.get())!=AF_SUCCESS)
            throw "af_get_data_ref_count failed";
        cout << "ref.count = " << refCount << endl;
        if (refCount!=1) throw "expected ref.count=1";

        return 0;
    }
    catch (const char* s) { err = s; }
    catch (af::exception& e) { err = e.what(); }
    catch (...) { err = "Unknown exception"; }
    cerr << endl
        << "*** error; " << err.c_str() << endl
        << endl;
    return -1;
}

Ubuntu 18.04 (EC2)
ArrayFire v3.9.0 (CPU, 64-bit Linux, build 1d03d07e)
[0] Intel: Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
GPU: Tesla T4, 15109 MiB, 450.142.00

$ clinfo
Number of platforms                               1
  Platform Name                                   NVIDIA CUDA
  Platform Vendor                                 NVIDIA Corporation
  Platform Version                                OpenCL 1.2 CUDA 11.0.228
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32
_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_creat
e_buffer cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_kernel_attribute_nv
  Platform Extensions function suffix             NV

  Platform Name                                   NVIDIA CUDA
Number of devices                                 1
  Device Name                                     Tesla T4
  Device Vendor                                   NVIDIA Corporation
  Device Vendor ID                                0x10de
  Device Version                                  OpenCL 1.2 CUDA
  Driver Version                                  450.142.00
  Device OpenCL C Version                         OpenCL C 1.2
  Device Type                                     GPU
  Device Topology (NV)                            PCI-E, 00:03.6
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               40
  Max clock frequency                             1590MHz
  Compute Capability (NV)                         7.5
  Device Partition                                (core)
    Max number of sub-devices                     1
    Supported partition types                     None
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x64
  Max work group size                             1024
  Preferred work group size multiple              32
  Warp size (NV)                                  32
  Preferred / native vector sizes
    char                                                 1 / 1
    short                                                1 / 1
    int                                                  1 / 1
    long                                                 1 / 1
    half                                                 0 / 0        (n/a)
    float                                                1 / 1
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (n/a)
  Single-precision Floating-point support         (core)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  Yes
  Double-precision Floating-point support         (cl_khr_fp64)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Address bits                                    64, Little-Endian
  Global memory size                              15843721216 (14.76GiB)
  Error Correction support                        Yes
  Max memory allocation                           3960930304 (3.689GiB)
  Unified memory for Host and Device              No
  Integrated memory (NV)                          No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       4096 bits (512 bytes)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        1310720 (1.25MiB)
  Global Memory cache line size                   128 bytes
  Image support                                   Yes
    Max number of samplers per kernel             32
    Max size for 1D images from buffer            268435456 pixels
    Max 1D or 2D image array size                 2048 images
    Max 2D image size                             32768x32768 pixels
    Max 3D image size                             16384x16384x16384 pixels
    Max number of read image args                 256
    Max number of write image args                32
  Local memory type                               Local
  Local memory size                               49152 (48KiB)
  Registers per block (NV)                        65536
  Max number of constant args                     9
  Max constant buffer size                        65536 (64KiB)
  Max size of kernel argument                     4352 (4.25KiB)
  Queue properties
    Out-of-order execution                        Yes
    Profiling                                     Yes
  Prefer user sync for interop                    No
  Profiling timer resolution                      1000ns
  Execution capabilities
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Kernel execution timeout (NV)                 No
  Concurrent copy and kernel execution (NV)       Yes
    Number of async copy engines                  3
  printf() buffer size                            1048576 (1024KiB)
  Built-in kernels
  Device Extensions                               cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32
_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_creat
e_buffer cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_kernel_attribute_nv

NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  No platform
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   No platform
  clCreateContext(NULL, ...) [default]            No platform
  clCreateContext(NULL, ...) [other]              Success [NV]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  No platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  No platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  Invalid device type for platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  No platform