Merge pull request #2595 from jacquesqiao/fix-multi-thread-train

fix MultiGradientMachine train and infer

paddle/gserver/gradientmachines/MultiGradientMachine.cpp

@@ -166,11 +166,21 @@ MultiGradientMachine::MultiGradientMachine(const ModelConfig& config,
 
   outArgStream_ = HPPL_STREAM_1;
 
+  start();
+}
+
+void MultiGradientMachine::start() {
   for (auto& thread : threads_) {
     thread->start();
   }
 }
 
+void MultiGradientMachine::finish() {
+  for (auto& thread : threads_) {
+    thread->stop();
+  }
+}
+
 std::vector<const std::vector<ParameterPtr>*>
 MultiGradientMachine::getSlaveParameters() {
   std::vector<const std::vector<ParameterPtr>*> vec;
@@ -326,12 +336,6 @@ void MultiGradientMachine::onPassEnd() {
   }
 }
 
-void MultiGradientMachine::finish() {
-  for (auto& thread : threads_) {
-    thread->stop();
-  }
-}
-
 Evaluator* MultiGradientMachine::makeEvaluator() const {
   return threads_[0]->getGradientMachine()->makeEvaluator();
 }
@@ -445,7 +449,7 @@ TrainerThread::TrainerThread(const ModelConfig& config,
 
   gradStream_ = HPPL_STREAM_2;
   valueStream_ = HPPL_STREAM_3;
-  stopping_ = false;
+  stopping_ = true;
   updateCounter_ = 0;
   parameterUpdated_ = false;
 }
@@ -453,6 +457,10 @@ TrainerThread::TrainerThread(const ModelConfig& config,
 TrainerThread::~TrainerThread() { stop(); }
 
 void TrainerThread::start() {
+  if (!stopping_) return;
+
+  stopping_ = false;
+
   gradientMachine_->start();
 
   computeThread_.reset(new std::thread([this]() { computeThread(); }));

paddle/gserver/gradientmachines/MultiGradientMachine.h

@@ -176,6 +176,10 @@ public:
 
   explicit MultiGradientMachine(const ModelConfig& config, bool useGpu);
 
+  virtual void start();
+
+  virtual void finish();
+
   virtual void prefetch(const std::vector<Argument>& inArgs);
 
   virtual void forward(const std::vector<Argument>& inArgs,
@@ -193,8 +197,6 @@ public:
 
   virtual void onPassEnd();
 
-  virtual void finish();
-
   virtual Evaluator* makeEvaluator() const;
 
   virtual void eval(Evaluator* evaluator) const;