Merge pull request #12005 from reyoung/feature/fix_data_balance_on_one_gpu

Fix data balance on single GPU

paddle/fluid/framework/details/build_strategy.h

@@ -34,7 +34,7 @@ struct BuildStrategy {
 
   std::string debug_graphviz_path_{""};
 
-  bool enable_data_balance_{true};
+  bool enable_data_balance_{false};
 };
 
 }  // namespace details

paddle/fluid/framework/details/data_balance_op_handle.cc

@@ -86,9 +86,9 @@ std::vector<std::array<int, 3>> DataBalanceOpHandle::GetBalancePlan(
 }
 
 void DataBalanceOpHandle::RunImpl() {
-  if (places_.size() == 1) {
-    return;
-  }
+  PADDLE_ENFORCE_GT(places_.size(), 1,
+                    "Data balance can only be enabled when the number of "
+                    "places to run larger than 1.");
   auto in_var_handles = DynamicCast<VarHandle>(inputs_);
   auto out_var_handles = DynamicCast<VarHandle>(outputs_);
   PADDLE_ENFORCE(in_var_handles.size() % places_.size() == 0);

paddle/fluid/framework/details/multi_devices_graph_builder.cc

@@ -59,6 +59,11 @@ MultiDevSSAGraphBuilder::MultiDevSSAGraphBuilder(
     grad_names_.insert(GradVarName(p));
   }
   balance_vars_.resize(places_.size(), 0);
+  if (strategy_.enable_data_balance_ && places_.size() == 1) {
+    LOG(WARNING) << "It is no need to enable data balance when there is only "
+                    "one place. enable_data_balance is set to False.";
+    strategy_.enable_data_balance_ = false;
+  }
 }
 
 void MultiDevSSAGraphBuilder::CreateOpHandleIOs(SSAGraph *result,

paddle/fluid/operators/read_op.cc

@@ -92,9 +92,13 @@ class ReadOpMaker : public framework::OpProtoAndCheckerMaker {
   void Make() override {
     AddInput("Reader", "(ReaderHolder) The executed reader.");
     AddOutput("Out", "(LoDTensor) The output data.").AsDuplicable();
-    AddAttr<bool>("throw_eof_exp",
+    AddAttr<bool>(
+        "throw_eof_exp",
         "If set true, an exception will be thrown when the Reader "
-                  "yields empty (which means there is no next data).")
+        "yields empty (which means there is no next data).\n"
+        "NOTES: This flag must be true always. It will be set to false"
+        " only when the data-balance is enabled in ParallelExecutor"
+        " and it is set by ParallelExecutor instance, not users.")
         .SetDefault(true);
     AddComment(R"DOC(
       Read Operator

python/paddle/fluid/tests/unittests/test_data_balance.py

@@ -103,8 +103,12 @@ class TestDataBalance(unittest.TestCase):
             exe = fluid.Executor(place)
             exe.run(startup_prog)
 
+            build_strategy = fluid.BuildStrategy()
+            build_strategy.enable_data_balance = True
             parallel_exe = fluid.ParallelExecutor(
-                use_cuda=self.use_cuda, main_program=main_prog)
+                use_cuda=self.use_cuda,
+                main_program=main_prog,
+                build_strategy=build_strategy)
 
             if (parallel_exe.device_count > self.batch_size):
                 print("WARNING: Unittest TestDataBalance skipped. \
@@ -145,9 +149,12 @@ class TestDataBalance(unittest.TestCase):
             place = fluid.CUDAPlace(0) if self.use_cuda else fluid.CPUPlace()
             exe = fluid.Executor(place)
             exe.run(startup_prog)
-
+            build_strategy = fluid.BuildStrategy()
+            build_strategy.enable_data_balance = True
             parallel_exe = fluid.ParallelExecutor(
-                use_cuda=self.use_cuda, main_program=main_prog)
+                use_cuda=self.use_cuda,
+                main_program=main_prog,
+                build_strategy=build_strategy)
 
             if (parallel_exe.device_count > self.batch_size):
                 print("WARNING: Unittest TestDataBalance skipped. \