Discovering Platforms and Devices

In OpenCL, all work must be associated with a platform+device. This is a little different from CUDA in that with CUDA, you are handed a default device, and only if you go around playing with cudaSetDevice or the device contexts with the driver API can you get access to more than that one device. OpenCL, on the other hand, adds some burden up front in initializing the devices in exchange for the programmer having more control over what platforms/devices are being used and probably more readable+safe code in that everything is stated explicitly.

The two functions that I have found which seem to be most useful in doing this are clGetPlatformIDs and clGetDeviceIDs. These functions allow you to retrieve identifiers for platforms and devices, as well as the number of platforms/devices available. To illustrate this, let's start with some sample code I just wrote:


int main(void) { // Detect how many platforms there are and retrieve platform ids for each cl_int err; cl_uint num_platforms; err = clGetPlatformIDs(0, NULL, &num_platforms); checkErr(err, "clGetPlatformIDs(0,NULL,&num_platforms)"); std::cout<<"Detected "<<num_platforms<<" platforms"<<std::endl; if(num_platforms == 0) { std::cout<<"Unable to find a valid OpenCL platform"<<std::endl; exit(-1); } cl_platform_id *platforms = (cl_platform_id *)malloc(sizeof(cl_platform_id) * num_platforms) err = clGetPlatformIDs(num_platforms, platforms, NULL); checkErr(err, "clGetPlatformIDs(num_platforms, platforms, NULL)"); return 0; }

This code discovers how many platforms there are, and there fetches platform identifiers for each platform into the platforms array (clGetPlatformIDs). A similar process can be done for devices on a single platform:

int main(void) { // Detect how many platforms there are and retrieve platform ids for each cl_int err; cl_uint num_platforms; err = clGetPlatformIDs(0, NULL, &num_platforms); checkErr(err, "clGetPlatformIDs(0,NULL,&num_platforms)"); std::cout<<"Detected "<<num_platforms<<" platforms"<<std::endl; if(num_platforms == 0) { std::cout<<"Unable to find a valid OpenCL platform"<<std::endl; exit(-1); } cl_platform_id *platforms = (cl_platform_id *)malloc(sizeof(cl_platform_id) * num_platforms); err = clGetPlatformIDs(num_platforms, platforms, NULL); checkErr(err, "clGetPlatformIDs(num_platforms, platforms, NULL)"); cl_platform_id platform = platforms[0]; cl_device_id device; cl_uint num_gpu_devices, num_cpu_devices; err = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 0, NULL, &num_gpu_devices); checkErr(err, "GPU clgetDeviceIDs(&num_devices)"); err = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, 0, NULL, &num_cpu_devices); checkErr(err, "CPU clgetDeviceIDs(&num_devices)"); std::cout<<"Detected "<<num_gpu_devices<<" GPU device(s) and "<<num_cpu_devices<<" CPU device(s) attached to platform 0"<<std::endl; if(num_gpu_devices == 0 || num_cpu_devices == 0) { std::cout<<"Insufficient OpenCL devices found for platform 0"<<std::endl; exit(-1); } err = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 1, &device, NULL); return 0; }

With this code, we can now retrieve information on all platforms, and the devices associated with those platforms (depending on what platform is set to) (clGetDeviceIDs). To build this code, place it in a .cpp file and compile using:

g++ -I${AMDAPPSDKROOT}/include -L${AMDAPPSDKROOT}/lib/x86_64 opencl.cpp -lOpenCL

where AMDAPPSDKROOT is the top directory where the OpenCL SDK is. x86_64 may need to be changed to x86 depending on your platform.