cudaEvent_t cuda 计算kernel执行时间

cuda 计算kernel执行时间：

#include <iostream>
using namespace std;

__global__ void kernel()
{
    //printf("kkeerrnneell\n");

}

int main(){


    cudaEvent_t start, stop;
	cudaEventCreate(&start);
	cudaEventCreate(&stop);
	// record start event on the default stream
	cudaEventRecord(start);
	
	
	
	// execute kernel
	for(int i=0; i<1000000; i++)
	kernel<<<1,1>>>();
	
	
	
	// 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 "<<time<<endl;
	// clean up the two events
	cudaEventDestroy(start);
	cudaEventDestroy(stop);

    

    return 0;
}