A struct to host thread-local cuda objects. More...
#include <context_gpu.h>
Friends | |
class | CUDAContext |
A struct to host thread-local cuda objects.
In Caffe2, each thread has its own non-default cuda stream as well as related objects such as cublas and curand handles. This is achieved by having the ThreadLocalCUDAObjects wrapper that takes care of allocating and deallocating these objects at the thread scope. This class is solely used inside CUDAContext and should not be used externally.
Definition at line 39 of file context_gpu.h.