我使用CUDA流实现了以下类
class CudaStreams
{
private:
int nStreams_;
cudaStream_t* streams_;
cudaStream_t active_stream_;
public:
// default constructor
CudaStreams() { }
// streams initialization
void InitStreams(const int nStreams = 1) {
nStreams_ = nStreams;
// allocate and initialize an array of stream handles
streams_ = (cudaStream_t*) malloc(nStreams_*sizeof(cudaStream_t));
for(int i = 0; i < nStreams_; i++) CudaSafeCall(cudaStreamCreate(&(streams_[i])));
active_stream_ = streams_[0];}
// default destructor
~CudaStreams() {
for(int i = 0; i<nStreams_; i++) CudaSafeCall(cudaStreamDestroy(streams_[i])); }
};
Run Code Online (Sandbox Code Playgroud)
如果我现在运行这个简单的代码
void main( int argc, char** argv)
{
streams.InitStreams(1);
streams.~CudaStreams(); …Run Code Online (Sandbox Code Playgroud)