有谁知道以下用法cudaSetDevice
是否正确?我想随时在任何主机线程中重复调用在不同设备上创建的资源;有没有办法在 CUDA 中做到这一点?
cudaSetDevice(0);
/...create cuda streams and do some memory allocation on gpu.../
cudaSetDevice(1);
/...create cuda streams and do some memory allocation on gpu.../
#pragma omp parallel num_threads(2)
{
int omp_threadID=omp_get_thread_num();
....
if (omp_threadID==0)
{
cudaSetDevice(0);
/...calling streams/memory created on device 0.../
}
else
{
cudaSetDevice(1);
/...calling streams/memory created on device 1.../
};
};