cudaEvent

cuda 计算kernel执行时间：

cudaEvent_t start, stop;
cudaEventCreate(&start);
cudaEventCreate(&stop);
// record start event on the default stream
cudaEventRecord(start);
// execute kernel
interesting_kernel<<>>(arguments);
// record stop event on the default stream
cudaEventRecord(stop);
// wait until the stop event completes
cudaEventSynchronize(stop);
// calculate the elapsed time between two events
float time;
cudaEventElapsedTime(&time, start, stop);

cout<<"Time is "< // clean up the two events
cudaEventDestroy(start);
cudaEventDestroy(stop);