[Kunlun]fix multi xpu dygraph hang, test=kunlun (PaddlePaddle#32662) (P…

…addlePaddle#32696)
sandyhouse · May 1, 2021 · 2c1ed9b · 2c1ed9b
1 parent 09adf20
commit 2c1ed9b
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/paddle/fluid/imperative/reducer.cc b/paddle/fluid/imperative/reducer.cc
@@ -762,10 +762,11 @@ void Reducer::MarkGroupReady(size_t group_index) {
     // TODO(liuyuhui): Add try catch to deal with exception later,
     // otherwise the main thread will continue to run when an exception is
     // thrown in comm_pool_.
-    comm_pool_->enqueue([&] {
+    auto next_group = next_group_;
+    comm_pool_->enqueue([this, run_order, next_group, &group] {
       auto dev_id = BOOST_GET_CONST(platform::XPUPlace, place_).device;
       platform::SetXPUDeviceId(dev_id);
-      FusedAllReduceSchedule(run_order, group, next_group_);
+      FusedAllReduceSchedule(run_order, group, next_group);
       {
         std::lock_guard<std::mutex> lock(mutex_);
         comm_op_count_ -= 1;  // lock