Add comments for CUDA Device Context Allocator related stuff (#19809)

paddle/fluid/memory/allocation/cuda_device_context_allocation.h

@@ -20,6 +20,12 @@ namespace paddle {
 namespace memory {
 namespace allocation {
 
+/**
+ * CUDADeviceContextAllocation is a wrapper of the underbeneath allocation.
+ * CUDADeviceContextAllocation adds a CUDA stream callback for the underbeneath
+ * allocation so that CUDADeviceContextAllocation can be used in a CUDA stream
+ * which deletes allocation in the callback.
+ */
 class CUDADeviceContextAllocation : public Allocation {
  public:
   explicit CUDADeviceContextAllocation(AllocationPtr allocation);

paddle/fluid/memory/allocation/cuda_device_context_allocator.h

@@ -24,6 +24,12 @@ namespace paddle {
 namespace memory {
 namespace allocation {
 
+/**
+ * CUDADeviceContextAllocator will allocate a CUDADeviceContextAllocation
+ * after waiting for a self-created event on the default stream. It does so to
+ * let the non-default stream be able to allocate GPU memory which will be
+ * released by stream callback
+ */
 class CUDADeviceContextAllocator : public Allocator {
  public:
   explicit CUDADeviceContextAllocator(platform::CUDAPlace place,

paddle/fluid/memory/allocation/cuda_device_context_allocator_pool.h

@@ -24,6 +24,13 @@ namespace paddle {
 namespace memory {
 namespace allocation {
 
+/**
+ * CUDADeviceContextAllocatorPool is a singletion stores mapping from
+ * CUDAPlace(s) to std::shared_ptr<CUDADeviceContextAllocator>. When a
+ * CUDADeviceContext's compute stream isn't default stream, it can call this
+ * class to allocate GPU memory which will be released by a callback after
+ * stream execution.
+ */
 class CUDADeviceContextAllocatorPool {
  public:
   static CUDADeviceContextAllocatorPool &Instance();