Profiling Operations Using OpenCL™ Profiling Events
The following code snippet measures kernel execution using OpenCL™ profiling events (error handling is omitted):
g_cmd_queue = clCreateCommandQueue(…CL_QUEUE_PROFILING_ENABLE, NULL); clEnqueueNDRangeKernel(g_cmd_queue,…, &perf_event); clWaitForEvents(1, &perf_event); cl_ulong start = 0, end = 0; clGetEventProfilingInfo(perf_event, CL_PROFILING_COMMAND_START, sizeof(cl_ulong), &start, NULL); clGetEventProfilingInfo(perf_event, CL_PROFILING_COMMAND_END, sizeof(cl_ulong), &end, NULL); //END-START gives you hints on kind of “pure HW execution time” //the resolution of the events is 1e-09 sec g_NDRangePureExecTimeMs = (cl_double)(end - start)*(cl_double)(1e-06);
Important caveats:
- The queue should be enabled for profiling (CL_QUEUE_PROFILING_ENABLEproperty) at the time of creation.
- You need to explicitly synchronize the operation usingclFinish()orclWaitForEvents. The reason is that device time counters for the profiled command, are associated with the specified event.
This way you can profile operations on both Memory Objects and Kernels. Refer to the OpenCL™ 1.2 Specification for the detailed description of profiling events.
Note
The host-side wall-clock time might return different results. For the CPU the difference is typically negligible.
See Also
The OpenCL™ 1.2 Specification at http://www.khronos.org/registry/cl/specs/opencl-1.2.pdf