Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into...

Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add-async_sparse_param_update_recorder
test=develop

paddle/fluid/framework/ir/graph_helper.cc

@@ -31,8 +31,8 @@ namespace paddle {
 namespace framework {
 namespace ir {
 namespace {
-void SortHelper(
-    const std::map<ir::Node *, std::unordered_set<ir::Node *>> &adj_list,
+void SortHelper(const std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>,
+                               ir::NodeComp> &adj_list,
                 ir::Node *node, std::unordered_set<ir::Node *> *visited,
                 std::vector<ir::Node *> *ret) {
   visited->insert(node);
@@ -50,7 +50,8 @@ void SortHelper(
 
 bool HasCircleHelper(
     ir::Node *node,
-    const std::map<ir::Node *, std::unordered_set<ir::Node *>> &adj_list,
+    const std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>, ir::NodeComp>
+        &adj_list,
     std::unordered_set<ir::Node *> *visited,
     std::unordered_set<ir::Node *> *in_trace,
     std::vector<std::vector<ir::Node *>> *circles) {
@@ -84,7 +85,8 @@ bool HasCircleHelper(
 }
 
 bool HasCircleInternal(
-    const std::map<ir::Node *, std::unordered_set<ir::Node *>> &adj_list,
+    const std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>, ir::NodeComp>
+        &adj_list,
     std::vector<std::vector<ir::Node *>> *circles) {
   std::unordered_set<ir::Node *> visited;
   std::unordered_set<ir::Node *> in_trace;
@@ -107,8 +109,8 @@ bool FindCircleSubGraph(const Graph &graph,
 }
 
 std::vector<ir::Node *> TopologySortOperations(const Graph &graph) {
-  std::map<ir::Node *, std::unordered_set<ir::Node *>> adj_list =
-      BuildOperationAdjList(graph);
+  std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>, ir::NodeComp>
+      adj_list = BuildOperationAdjList(graph);
   PADDLE_ENFORCE(!HasCircleInternal(adj_list, nullptr));
   std::unordered_set<ir::Node *> visited;
   std::vector<ir::Node *> ret;
@@ -117,34 +119,30 @@ std::vector<ir::Node *> TopologySortOperations(const Graph &graph) {
       SortHelper(adj_list, adj.first, &visited, &ret);
     }
   }
+
   return ret;
 }
 
 // Build operator inlink edge table.
-std::map<ir::Node *, std::unordered_set<ir::Node *>> BuildOperationAdjList(
-    const Graph &graph) {
-  std::map<ir::Node *, std::unordered_set<ir::Node *>> adj_list;
+std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>, ir::NodeComp>
+BuildOperationAdjList(const Graph &graph) {
+  std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>, ir::NodeComp>
+      adj_list;
 
   for (auto &n : graph.Nodes()) {
     if (!n->IsOp()) continue;
     if (adj_list.find(n) == adj_list.end()) {
-      adj_list[n] = std::unordered_set<ir::Node *>();
+      adj_list[n] = std::set<ir::Node *, ir::NodeComp>();
     }
-    std::vector<ir::Node *> nodes;
     for (auto &var : n->inputs) {
       for (auto &adj_n : var->inputs) {
         PADDLE_ENFORCE(adj_n->NodeType() == ir::Node::Type::kOperation);
         VLOG(4) << "adj " << adj_n->Name() << reinterpret_cast<void *>(adj_n)
                 << " -> " << n->Name() << reinterpret_cast<void *>(n)
                 << "  via " << var->Name() << reinterpret_cast<void *>(var);
-        nodes.push_back(adj_n);
+        adj_list[n].insert(adj_n);
       }
     }
-    std::sort(nodes.begin(), nodes.end(), [](ir::Node *node1, ir::Node *node2) {
-      return node1->id() > node2->id();
-    });
-    adj_list[n].insert(std::make_move_iterator(nodes.begin()),
-                       std::make_move_iterator(nodes.end()));
   }
   return adj_list;
 }

paddle/fluid/framework/ir/graph_helper.h

@@ -16,6 +16,7 @@ limitations under the License. */
 
 #include <map>
 #include <memory>
+#include <set>
 #include <vector>
 
 #include "paddle/fluid/framework/ir/graph.h"
@@ -25,6 +26,13 @@ namespace paddle {
 namespace framework {
 namespace ir {
 
+// Compare nodes via node id.
+struct NodeComp {
+  bool operator()(ir::Node *const &node1, ir::Node *const &node2) const {
+    return node1->id() < node2->id();
+  }
+};
+
 // Test if the graph contains circle.
 bool HasCircle(const Graph &graph);
 
@@ -57,8 +65,8 @@ std::vector<Node *> TopologyVarientSort(const Graph &graph, SortKind sort_kind);
 void CleanIndividualNodes(Graph *graph);
 
 // Build an adjacency list of operations for the `graph`.
-std::map<ir::Node *, std::unordered_set<ir::Node *>> BuildOperationAdjList(
-    const Graph &graph);
+std::map<ir::Node *, std::set<ir::Node *, ir::NodeComp>, ir::NodeComp>
+BuildOperationAdjList(const Graph &graph);
 
 template <typename T>
 std::vector<T *> FilterByNodeWrapper(const Graph &graph) {

paddle/fluid/inference/tests/api/analyzer_transformer_tester.cc

@@ -214,28 +214,23 @@ TEST(Analyzer_Transformer, fuse_statis) {
 }
 
 // Compare result of NativeConfig and AnalysisConfig
-// void compare(bool use_mkldnn = false) {
-//   AnalysisConfig cfg;
-//   SetConfig(&cfg);
-//   if (use_mkldnn) {
-//     cfg.EnableMKLDNN();
-//   }
-//
-//   std::vector<std::vector<PaddleTensor>> input_slots_all;
-//   SetInput(&input_slots_all);
-//   CompareNativeAndAnalysis(
-//       reinterpret_cast<const PaddlePredictor::Config *>(&cfg),
-//       input_slots_all);
-// }
-
-// TODO(yihuaxu):
-//    Disable compare and compare_mkldnn temporary, see
-//    https://github.com/paddlePaddle/Paddle/issues/16316 for details.
-// TEST(Analyzer_Transformer, compare) { compare(); }
-// #ifdef PADDLE_WITH_MKLDNN
-// TEST(Analyzer_Transformer, compare_mkldnn) { compare(true /* use_mkldnn */);
-// }
-// #endif
+void compare(bool use_mkldnn = false) {
+  AnalysisConfig cfg;
+  SetConfig(&cfg);
+  if (use_mkldnn) {
+    cfg.EnableMKLDNN();
+  }
+
+  std::vector<std::vector<PaddleTensor>> input_slots_all;
+  SetInput(&input_slots_all);
+  CompareNativeAndAnalysis(
+      reinterpret_cast<const PaddlePredictor::Config *>(&cfg), input_slots_all);
+}
+
+TEST(Analyzer_Transformer, compare) { compare(); }
+#ifdef PADDLE_WITH_MKLDNN
+TEST(Analyzer_Transformer, compare_mkldnn) { compare(true /* use_mkldnn */); }
+#endif
 
 }  // namespace inference
 }  // namespace paddle

paddle/fluid/op_use_default_grad_op_maker.spec

@@ -29,6 +29,8 @@ pool3d
 prelu
 quantize
 rank_loss
+reduce_all
+reduce_any
 reduce_max
 reduce_mean
 reduce_min