Function printDevProp

ngscuda/cuda_ngstd.cpp:13–40

Print device properties

  // Print device properties
  void printDevProp(cudaDeviceProp devProp, int device_id)
  {
    int clock_rate, kernel_exec_timeout, device_overlap;
    cudaDeviceGetAttribute(&clock_rate, cudaDevAttrClockRate, device_id);
    cudaDeviceGetAttribute(&kernel_exec_timeout, cudaDevAttrKernelExecTimeout, device_id);
    cudaDeviceGetAttribute(&device_overlap, cudaDevAttrConcurrentManagedAccess, device_id);

    printf("Major revision number:         %d\n",  devProp.major);
    printf("Minor revision number:         %d\n",  devProp.minor);
    printf("Name:                          %s\n",  devProp.name);
    printf("Total global memory:           %lu\n",  devProp.totalGlobalMem);
    printf("Total shared memory per block: %lu\n",  devProp.sharedMemPerBlock);
    printf("Total registers per block:     %d\n",  devProp.regsPerBlock);
    printf("Warp size:                     %d\n",  devProp.warpSize);
    printf("Maximum memory pitch:          %lu\n",  devProp.memPitch);
    printf("Maximum threads per block:     %d\n",  devProp.maxThreadsPerBlock);
    for (int i = 0; i < 3; ++i)
      printf("Maximum dimension %d of block:  %d\n", i, devProp.maxThreadsDim[i]);
    for (int i = 0; i < 3; ++i)
      printf("Maximum dimension %d of grid:   %d\n", i, devProp.maxGridSize[i]);
    printf("Clock rate:                    %d\n",  clock_rate);
    printf("Total constant memory:         %lu\n",  devProp.totalConstMem);
    printf("Texture alignment:             %lu\n",  devProp.textureAlignment);
    printf("Concurrent copy and execution: %s\n",  (device_overlap ? "Yes" : "No"));
    printf("Number of multiprocessors:     %d\n",  devProp.multiProcessorCount);
    printf("Kernel execution timeout:      %s\n",  (kernel_exec_timeout ? "Yes" : "No"));
    return;
  }


  void InitCUDA (int verbose)