Apply mutex only to shared layers and fix NVCC warning

diff --git a/include/caffe/layer.hpp b/include/caffe/layer.hpp
index d82197a..a0d1d4e 100644 (file)
--- a/include/caffe/layer.hpp
+++ b/include/caffe/layer.hpp
@@ -1,7 +1,6 @@
 #ifndef CAFFE_LAYER_H_
 #define CAFFE_LAYER_H_
 
-#include <boost/thread.hpp>
 #include <algorithm>
 #include <string>
 #include <vector>
@@ -12,6 +11,12 @@
 #include "caffe/proto/caffe.pb.h"
 #include "caffe/util/device_alternate.hpp"
 
+/**
+ Forward declare boost::thread instead of including boost/thread.hpp
+ to avoid a boost/NVCC issues (#1009, #1010) on OSX.
+ */
+namespace boost { class mutex; }
+
 namespace caffe {
 
 /**
@@ -33,7 +38,7 @@ class Layer {
    * layer.
    */
   explicit Layer(const LayerParameter& param)
-    : layer_param_(param) {
+    : layer_param_(param), is_shared_(false) {
       // Set phase and copy blobs (if there are any).
       phase_ = param.phase();
       if (layer_param_.blobs_size() > 0) {
@@ -61,6 +66,7 @@ class Layer {
    */
   void SetUp(const vector<Blob<Dtype>*>& bottom,
       const vector<Blob<Dtype>*>& top) {
+    InitMutex();
     CheckBlobCounts(bottom, top);
     LayerSetUp(bottom, top);
     Reshape(bottom, top);
@@ -94,6 +100,22 @@ class Layer {
    */
   virtual inline bool ShareInParallel() const { return false; }
 
+  /** @brief Return whether this layer is actually shared by other nets.
+   *         If ShareInParallel() is true and using more than one GPU and the
+   *         net has TRAIN phase, then this function is expected return true.
+   */
+  inline bool IsShared() const { return is_shared_; }
+
+  /** @brief Set whether this layer is actually shared by other nets
+   *         If ShareInParallel() is true and using more than one GPU and the
+   *         net has TRAIN phase, then is_shared should be set true.
+   */
+  inline void SetShared(bool is_shared) {
+    CHECK(ShareInParallel() || !is_shared)
+        << type() << "Layer does not support sharing.";
+    is_shared_ = is_shared;
+  }
+
   /**
    * @brief Adjust the shapes of top blobs and internal buffers to accommodate
    *        the shapes of the bottom blobs.
@@ -406,8 +428,18 @@ class Layer {
   }
 
  private:
-  // mutex to lock layer to ensure sequential forward
-  boost::mutex forward_mutex_;
+  /** Whether this layer is actually shared by other nets*/
+  bool is_shared_;
+
+  /** The mutex for sequential forward if this layer is shared */
+  shared_ptr<boost::mutex> forward_mutex_;
+
+  /** Initialize forward_mutex_ */
+  void InitMutex();
+  /** Lock forward_mutex_ if this layer is shared */
+  void Lock();
+  /** Unlock forward_mutex_ if this layer is shared */
+  void Unlock();
 
   DISABLE_COPY_AND_ASSIGN(Layer);
 };  // class Layer
@@ -419,7 +451,7 @@ template <typename Dtype>
 inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom,
     const vector<Blob<Dtype>*>& top) {
   // Lock during forward to ensure sequential forward
-  boost::mutex::scoped_lock lock(forward_mutex_);
+  Lock();
   Dtype loss = 0;
   Reshape(bottom, top);
   switch (Caffe::mode()) {
@@ -450,6 +482,7 @@ inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom,
   default:
     LOG(FATAL) << "Unknown caffe mode.";
   }
+  Unlock();
   return loss;
 }
 

diff --git a/src/caffe/layer.cpp b/src/caffe/layer.cpp
new file mode 100644 (file)
index 0000000..3b91289
--- /dev/null
+++ b/src/caffe/layer.cpp
@@ -0,0 +1,27 @@
+#include <boost/thread.hpp>
+#include "caffe/layer.hpp"
+
+namespace caffe {
+
+template <typename Dtype>
+void Layer<Dtype>::InitMutex() {
+  forward_mutex_.reset(new boost::mutex());
+}
+
+template <typename Dtype>
+void Layer<Dtype>::Lock() {
+  if (IsShared()) {
+    forward_mutex_->lock();
+  }
+}
+
+template <typename Dtype>
+void Layer<Dtype>::Unlock() {
+  if (IsShared()) {
+    forward_mutex_->unlock();
+  }
+}
+
+INSTANTIATE_CLASS(Layer);
+
+}  // namespace caffe

diff --git a/src/caffe/net.cpp b/src/caffe/net.cpp
index 14f8385..7f5bdf7 100644 (file)
--- a/src/caffe/net.cpp
+++ b/src/caffe/net.cpp
@@ -84,7 +84,7 @@ void Net<Dtype>::Init(const NetParameter& in_param) {
   bottom_need_backward_.resize(param.layer_size());
   for (int layer_id = 0; layer_id < param.layer_size(); ++layer_id) {
     // For non-root solvers, whether this layer is shared from root_net_.
-    bool is_shared_layer = !Caffe::root_solver()
+    bool share_from_root = !Caffe::root_solver()
         && root_net_->layers_[layer_id]->ShareInParallel();
     // Inherit phase from net if unset.
     if (!param.layer(layer_id).has_phase()) {
@@ -98,9 +98,10 @@ void Net<Dtype>::Init(const NetParameter& in_param) {
           << "propagate_down param must be specified "
           << "either 0 or bottom_size times ";
     }
-    if (is_shared_layer) {
+    if (share_from_root) {
       LOG(INFO) << "Sharing layer " << layer_param.name() << " from root net";
       layers_.push_back(root_net_->layers_[layer_id]);
+      layers_[layer_id]->SetShared(true);
     } else {
       layers_.push_back(LayerRegistry<Dtype>::CreateLayer(layer_param));
     }
@@ -137,7 +138,7 @@ void Net<Dtype>::Init(const NetParameter& in_param) {
       }
     }
     // After this layer is connected, set it up.
-    if (is_shared_layer) {
+    if (share_from_root) {
       // Set up size of top blobs using root_net_
       const vector<Blob<Dtype>*>& base_top = root_net_->top_vecs_[layer_id];
       const vector<Blob<Dtype>*>& this_top = this->top_vecs_[layer_id];