[Dygraph] Refactoring of reducer in DataParallel (#40389)

* refactor reducer * modify cmakelists * solve conflicts * rename group and update process_group * fix bugs of ProcessGroupNCCL * modify for CIs * refactoring reducer

Author: haohongxiang

paddle/fluid/distributed/collective/CMakeLists.txt

@@ -1,8 +1,9 @@
 cc_library(processgroup SRCS ProcessGroup.cc DEPS phi phi_api eager_api)
+cc_library(eager_reducer SRCS reducer.cc DEPS eager_api processgroup phi phi_api)
+
 if (WITH_DISTRIBUTE)
  cc_library(processgroup_gloo SRCS ProcessGroupGloo.cc DEPS phi phi_api eager_api gloo_wrapper)
 endif()
-cc_library(eager_reducer SRCS reducer.cc DEPS eager_api processgroup)
 
 if(WITH_NCCL)
  cc_library(processgroup_nccl SRCS ProcessGroupNCCL.cc DEPS place cuda_stream enforce collective_helper device_context phi phi_api eager_api)

paddle/fluid/distributed/collective/ProcessGroupNCCL.cc

@@ -88,8 +88,8 @@ void SyncDefaultStream(
  for (size_t i = 0; i < places.size(); ++i) {
  auto* default_ctx = static_cast<platform::CUDADeviceContext*>(
  platform::DeviceContextPool::Instance().Get(places[i]));
- ncclEvents[i].Record(*dev_ctx[i]);
- ncclEvents[i].Block(*default_ctx);
+ ncclEvents[i].Record(*default_ctx);
+ ncclEvents[i].Block(*dev_ctx[i]);
  }
 }