Merge pull request #16116 from NHZlX/anakin_merge_develop

add trt update for this branch

Author: NHZlX

Dockerfile

@@ -75,8 +75,9 @@ RUN curl -s -q https://glide.sh/get | sh
 #    and its size is only one-third of the official one.
 # 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle.
 #    See https://github.com/PaddlePaddle/Paddle/issues/10129 for details.
-RUN wget -qO- http://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
-    tar -xz -C /usr/local && \
+
+RUN wget -q https://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.1.6-ubuntu14.04.x86_64-gnu.cuda.8.0.cudnn7.0.tar.gz --no-check-certificate && \
+    tar -zxf TensorRT-4.0.1.6-ubuntu14.04.x86_64-gnu.cuda.8.0.cudnn7.0.tar.gz -C /usr/local && \
     cp -rf /usr/local/TensorRT/include /usr && \
     cp -rf /usr/local/TensorRT/lib /usr
 

paddle/fluid/framework/ir/fuse_pass_base.h

@@ -14,6 +14,7 @@
 
 #pragma once
 
+#include <string>
 #include "paddle/fluid/framework/ir/graph.h"
 #include "paddle/fluid/framework/ir/pass.h"
 #include "paddle/fluid/framework/scope.h"
@@ -24,6 +25,10 @@ namespace ir {
 
 static const char kParamScopeAttr[] = "__param_scope__";
 static const char kFuseStatisAttr[] = "__fuse_statis__";
+// When we use trt or other third_party lib, the parameters are managed by
+// the lib, but not the fluid. So we need to record them to avoid duplicate
+// allocation.
+static const char kRepetitiveParamAttr[] = "__repetitive_param__";
 
 enum FuseOptions {
   DO_NOT_FUSE,  // fusing will not be done

paddle/fluid/inference/analysis/argument.h

@@ -23,8 +23,12 @@
 
 #pragma once
 
+#include <memory>
 #include <string>
+#include <unordered_map>
+#include <unordered_set>
 #include <vector>
+
 #include "paddle/fluid/framework/ir/graph.h"
 #include "paddle/fluid/framework/program_desc.h"
 #include "paddle/fluid/framework/scope.h"
@@ -133,6 +137,8 @@ struct Argument {
   DECL_ARGUMENT_FIELD(tensorrt_min_subgraph_size, TensorRtMinSubgraphSize, int);
   DECL_ARGUMENT_FIELD(tensorrt_precision_mode, TensorRtPrecisionMode,
                       AnalysisConfig::Precision);
+  DECL_ARGUMENT_FIELD(tensorrt_use_static_engine, TensorRtUseStaticEngine,
+                      bool);
 
   // Memory optimized related.
   DECL_ARGUMENT_FIELD(enable_memory_optim, EnableMemoryOptim, bool);

paddle/fluid/inference/analysis/helper.h

@@ -17,10 +17,12 @@ limitations under the License. */
 #include <sys/stat.h>
 #include <cstdio>
 #include <fstream>
+#include <memory>
 #include <set>
 #include <string>
 #include <typeindex>
 #include <unordered_map>
+#include <utility>
 #include <vector>
 
 #include "paddle/fluid/framework/framework.pb.h"
@@ -217,6 +219,35 @@ static std::string GetTrtCalibTableData(const std::string &model_opt_cache_dir,
   return "";
 }
 
+static std::string GetTrtEngineSerializedPath(const std::string &model_root,
+                                              const std::string &engine_key) {
+  return model_root + "/trt_serialized_" + engine_key;
+}
+
+static std::string GetTrtEngineSerializedData(
+    const std::string &model_opt_cache_dir, const std::string &engine_key) {
+  std::string trt_serialized_path =
+      GetTrtEngineSerializedPath(model_opt_cache_dir, engine_key);
+  if (FileExists(trt_serialized_path)) {
+    VLOG(3) << "Trt serialized file: " << trt_serialized_path
+            << "is found here";
+    std::ifstream infile(trt_serialized_path, std::ios::in);
+    std::stringstream buffer;
+    buffer << infile.rdbuf();
+    std::string trt_engine_serialized_data(buffer.str());
+    return trt_engine_serialized_data;
+  }
+  return "";
+}
+
+static void SaveTrtEngineSerializedDataToFile(
+    const std::string &trt_serialized_path,
+    const std::string &engine_serialized_data) {
+  std::ofstream outfile(trt_serialized_path);
+  outfile << engine_serialized_data;
+  outfile.close();
+}
+
 }  // namespace analysis
 }  // namespace inference
 }  // namespace paddle

paddle/fluid/inference/analysis/ir_pass_manager.cc

@@ -89,6 +89,9 @@ void IRPassManager::CreatePasses(Argument *argument,
       pass->Set(
           "model_opt_cache_dir",
           new std::string(GetOrCreateModelOptCacheDir(model_opt_cache_dir)));
+      pass->Set("gpu_device_id", new int(argument->gpu_device_id()));
+      pass->Set("use_static_engine",
+                new bool(argument->tensorrt_use_static_engine()));
     }
 
     pre_pass = pass_name;

paddle/fluid/inference/analysis/ir_pass_manager.h

@@ -22,7 +22,10 @@
 
 #pragma once
 
+#include <memory>
 #include <string>
+#include <unordered_set>
+#include <utility>
 #include <vector>
 #include "paddle/fluid/framework/ir/graph.h"
 #include "paddle/fluid/framework/ir/pass.h"