cuda计时⌛️

可参考nvidia官方文档：

http://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__EVENT.html#group__CUDART__EVENT_1g40159125411db92c835edb46a0989cd6

__host__ ​ cudaError_t cudaEventElapsedTime ( float*  ms,  cudaEvent_t  start,  cudaEvent_t  end )

Computes the elapsed time between events.

Parameters

ms

- Time between  start and  end in ms

start

- Starting event

end

- Ending event

// create two events
cudaEvent_t start, stop;
cudaEventCreate(&start);
cudaEventCreate(&stop);
// record start event on the default stream
cudaEventRecord(start);
// execute kernel
kernel<<<grid, block>>>(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);
// clean up the two events
cudaEventDestroy(start);
cudaEventDestroy(stop);