The following code snippet is a host-side timing routine around a kernel call (error handling is omitted):
float start = …;//getting the first time-stamp clEnqueueNDRangeKernel(g_cmd_queue, …); clFinish(g_cmd_queue);// to make sure the kernel completed float end = …;//getting the last time-stamp float time = (end-start);
In this example, host-side timing is implemented using the following functions:
- clEnqueueNDRangeKernel adds a kernel to a queue and immediately returns
- clFinish explicitly indicates the completion of kernel execution. You can also use clWaitForEvents.
Wrapping the Right Set of Operations
When using any host-side routine for evaluating performance of your kernel, ensure you wrapped the proper set of operations.
For example, avoid potentially costly and/or serializing routine, like:
- Including various printf calls
- File input or output operations
- and so on
Also profile kernel execution and data transferring separately by using OpenCL™ profiling events. Similarly, keep track of compilation and general initialization costs, like buffer creation separately from the actual execution flow.