Pre Merge pull request !600 from gengchao/baby5

ge/graph/load/new_model_manager/davinci_model.cc

@@ -2186,8 +2186,9 @@ Status DavinciModel::CopyInputData(const InputData &input_data, bool device_data
   const std::vector<DataBuffer> &blobs = input_data.blobs;
   for (const auto &data : new_input_data_info_) {
     if (data.first >= blobs.size()) {
-      GELOGE(FAILED, "Blobs not match: blobs=%zu, tensor=%zu, index=%u, size=%ld", blobs.size(),
-             new_input_data_info_.size(), data.first, data.second.GetDataInfo().at(0).first);
+      GELOGE(FAILED, "Blobs not match: blobs=%zu, tensor=%zu, index=%u, size=%ld, op_name(%s)", blobs.size(),
+             new_input_data_info_.size(), data.first, data.second.GetDataInfo().at(0).first,
+             data.second.GetOpName().c_str());
       return FAILED;
     }
 
@@ -2198,13 +2199,14 @@ Status DavinciModel::CopyInputData(const InputData &input_data, bool device_data
     }
     uint64_t data_size = data.second.GetDataSize();
     GE_CHK_BOOL_RET_STATUS(data_size >= data_buf.length, PARAM_INVALID,
-                           "input data size(%lu) does not match model required size(%lu), ret failed.", data_buf.length,
-                           data_size);
+                           "input data size(%lu) does not match model required size(%lu), op_name(%s) ret failed.",
+                           data_buf.length, data_size, data.second.GetOpName().c_str());
     void *mem_addr = data.second.GetBasicAddr();
     void *data_buf_addr = reinterpret_cast<void *>(reinterpret_cast<uintptr_t>(data_buf.data));
     uint64_t data_buf_length = data_buf.length;
-    GELOGI("CopyPlainData memcpy graph_%u type[F] input[%u] dst[%p] src[%p] mem_size[%lu] datasize[%lu]",
-           runtime_param_.graph_id, data.first, mem_addr, data_buf_addr, data_size, data_buf_length);
+    GELOGI("CopyPlainData memcpy graph_%u type[F] input[%s] rank[%u] dst[%p] src[%p] mem_size[%lu] datasize[%lu]",
+           runtime_param_.graph_id, data.second.GetOpName().c_str(), data.first, mem_addr, data_buf_addr, data_size,
+           data_buf_length);
     GE_CHK_RT_RET(rtMemcpy(mem_addr, data_size, data_buf_addr, data_buf_length, kind));
   }
 
@@ -3445,7 +3447,7 @@ Status DavinciModel::UpdateIoTaskArgs(const std::map<uint32_t, ZeroCopyOffset> &
     }
 
     if (!CheckInputAndModelSize(buffer.length, data.second.GetDataSize(), is_dynamic)) {
-      GELOGE(FAILED, "Check input size and model size failed");
+      GELOGE(FAILED, "Check input size and model size failed, op[%s]", data.second.GetOpName().c_str());
       return FAILED;
     }
 

ge/graph/load/new_model_manager/zero_copy_offset.cc

@@ -35,6 +35,7 @@ Status ZeroCopyOffset::InitInputDataInfo(int64_t output_size, void *virtual_addr
   GELOGI("[ZCPY] Start to InitInputDataInfo of %s, total_data_size is %ld, virtual_addr is %p",
          op_desc->GetName().c_str(), output_size, virtual_addr);
   basic_addr_ = virtual_addr;
+  op_name_ = op_desc->GetName();
   (void)ge::AttrUtils::GetListInt(op_desc, ATTR_ZERO_COPY_BASIC_OFFSET, zero_copy_basic_offset_);
   (void)ge::AttrUtils::GetListInt(op_desc, ATTR_ZERO_COPY_RELATIVE_OFFSET, zero_copy_relative_offset_);
   GE_CHK_BOOL_EXEC(zero_copy_basic_offset_.size() == zero_copy_relative_offset_.size(), return PARAM_INVALID,
@@ -82,6 +83,7 @@ Status ZeroCopyOffset::InitOutputDataInfo(const vector<int64_t> &input_size_list
   GELOGD("Tensor data size: GetSize=%ld, GetTensorSizeInBytes=%ld", input_size_list[idx], size);
 
   basic_addr_ = virtual_addr_list[idx];
+  op_name_ = op_desc->GetName();
   (void)ge::AttrUtils::GetListInt(op_desc, ATTR_ZERO_COPY_BASIC_OFFSET, zero_copy_basic_offset_);
   (void)ge::AttrUtils::GetListInt(op_desc, ATTR_ZERO_COPY_RELATIVE_OFFSET, zero_copy_relative_offset_);
   GE_CHK_BOOL_EXEC(zero_copy_basic_offset_.size() == zero_copy_relative_offset_.size(), return PARAM_INVALID,

ge/graph/load/new_model_manager/zero_copy_offset.h

@@ -66,9 +66,12 @@ class ZeroCopyOffset {
   int64_t GetDataSize() const { return data_size_; }
   // value of *outside_addrs_ from davinci_model
   std::vector<std::map<const void *, std::vector<void *>>> &GetOutsideAddrs() { return outside_addrs_; }
+  // name of op
+  std::string GetOpName() const {return op_name_};
 
  private:
   void *basic_addr_ = nullptr;
+  std::string op_name_;
   uint32_t data_count_ = 0;
   std::vector<std::pair<int64_t, void *>> data_info_;
   vector<int64_t> relative_offset_;

ge/graph/partition/graph_partition.cc

@@ -614,32 +614,32 @@ Status ge::GraphPartitioner::AddPartitionsToGraphNode(vector<ge::SubGraphInfoPtr
     }
     // flush parent node of subgraph
     sub_graph->SetParentNode(compute_graph->GetParentNode());
-    (void) AttrUtils::SetStr(*sub_graph, ATTR_NAME_PARENT_GRAPH_NAME, compute_graph->GetName());
-      auto sgi = MakeShared<SubGraphInfo>();
-      if (sgi == nullptr) {
-        GELOGE(GE_GRAPH_PARAM_NULLPTR, "[GraphPartitioner]: MakeShared sub graph info failed.");
-        return FAILED;
-      }
-      // set engine name
-      sgi->SetEngineName(engine_name);
-      // set stream label
-      string sub_graph_stream;
-      if (AttrUtils::GetStr(sub_graph->GetDirectNode().at(0)->GetOpDesc(), ATTR_NAME_STREAM_LABEL, sub_graph_stream)) {
-        sgi->SetStreamLabel(sub_graph_stream);
-      }
-      /// for now inputFlag is the same before and after partition. It should
-      /// be changed according to the real partition
-      std::vector<bool> sub_graph_input(graph_info_.input_size_, true);
-      std::vector<bool> sub_graph_output(graph_info_.output_size_, true);
-      sgi->SetSubGraph(sub_graph);
-      sgi->SetOutputFlag(sub_graph_output);
-      sgi->SetInputFlag(sub_graph_input);
-      sgi->SetOutputContext(graph_info_.output_name_);
-      AddEndPldInformationToSubGraphInfo(sgi);
-      GELOGI("[GraphPartitioner]: subGraph engine name is %s, graph name is %s, stream label is %s",
-             engine_name.c_str(),
-             sub_graph->GetName().c_str(),
-             sgi->GetStreamLabel().empty() ? "null" : sgi->GetStreamLabel().c_str());
+    (void)AttrUtils::SetStr(*sub_graph, ATTR_NAME_PARENT_GRAPH_NAME, compute_graph->GetName());
+    GELOGD("set attr success. subgraph(%s) with parent graph(%s)", sub_graph->GetName().c_str(),
+           compute_graph->GetName().c_str())
+    auto sgi = MakeShared<SubGraphInfo>();
+    if (sgi == nullptr) {
+      GELOGE(GE_GRAPH_PARAM_NULLPTR, "[GraphPartitioner]: MakeShared sub graph info failed.");
+      return FAILED;
+    }
+    // set engine name
+    sgi->SetEngineName(engine_name);
+    // set stream label
+    string sub_graph_stream;
+    if (AttrUtils::GetStr(sub_graph->GetDirectNode().at(0)->GetOpDesc(), ATTR_NAME_STREAM_LABEL, sub_graph_stream)) {
+      sgi->SetStreamLabel(sub_graph_stream);
+    }
+    /// for now inputFlag is the same before and after partition. It should
+    /// be changed according to the real partition
+    std::vector<bool> sub_graph_input(graph_info_.input_size_, true);
+    std::vector<bool> sub_graph_output(graph_info_.output_size_, true);
+    sgi->SetSubGraph(sub_graph);
+    sgi->SetOutputFlag(sub_graph_output);
+    sgi->SetInputFlag(sub_graph_input);
+    sgi->SetOutputContext(graph_info_.output_name_);
+    AddEndPldInformationToSubGraphInfo(sgi);
+    GELOGI("[GraphPartitioner]: subGraph engine name is %s, graph name is %s, stream label is %s", engine_name.c_str(),
+           sub_graph->GetName().c_str(), sgi->GetStreamLabel().empty() ? "null" : sgi->GetStreamLabel().c_str());
     if (engine_name != input_subgraph_name) {  // do not add Data subGraph into SubGraphInfo
       output_subgraphs.push_back(sgi);
     } else {