diff --git a/paddle/fluid/inference/api/analysis_config.cc b/paddle/fluid/inference/api/analysis_config.cc
index 100ee0c9d37986829a7ddddbe6349d04fa679340..dd75f0d9a65404908667d873786160ddaa73fa57 100644
--- a/paddle/fluid/inference/api/analysis_config.cc
+++ b/paddle/fluid/inference/api/analysis_config.cc
@@ -46,7 +46,7 @@ contrib::AnalysisConfig::AnalysisConfig(const contrib::AnalysisConfig &other) {
   prog_file = other.prog_file;
   param_file = other.param_file;
   specify_input_name = other.specify_input_name;
-  cpu_num_threads_ = other.cpu_num_threads_;
+  cpu_math_library_num_threads_ = other.cpu_math_library_num_threads_;
   // fields from this.
   enable_ir_optim = other.enable_ir_optim;
   use_feed_fetch_ops = other.use_feed_fetch_ops;
@@ -73,6 +73,7 @@ contrib::AnalysisConfig::AnalysisConfig(contrib::AnalysisConfig &&other) {
   prog_file = other.prog_file;
   param_file = other.param_file;
   specify_input_name = other.specify_input_name;
+  cpu_math_library_num_threads_ = other.cpu_math_library_num_threads_;
   // fields from this.
   enable_ir_optim = other.enable_ir_optim;
   use_feed_fetch_ops = other.use_feed_fetch_ops;
diff --git a/paddle/fluid/inference/api/analysis_predictor.cc b/paddle/fluid/inference/api/analysis_predictor.cc
index 4633a75e5ec35f475d7c48051a4e67c1ab6ea8a7..c132ce326c6b22ea235e6fb8c570678cb54e22ef 100644
--- a/paddle/fluid/inference/api/analysis_predictor.cc
+++ b/paddle/fluid/inference/api/analysis_predictor.cc
@@ -66,7 +66,7 @@ bool AnalysisPredictor::Init(
 #endif
 
   // no matter with or without MKLDNN
-  paddle::platform::SetNumThreads(config_.GetCPUNumThreads());
+  paddle::platform::SetNumThreads(config_.cpu_math_library_num_threads());
 
   if (!PrepareScope(parent_scope)) {
     return false;
@@ -159,7 +159,7 @@ bool AnalysisPredictor::PrepareExecutor() {
   return true;
 }
 
-void AnalysisPredictor::SetMKLDNNThreadId(int tid) {
+void AnalysisPredictor::SetMkldnnThreadID(int tid) {
 #ifdef PADDLE_WITH_MKLDNN
   platform::set_cur_thread_id(tid);
 #else
diff --git a/paddle/fluid/inference/api/analysis_predictor.h b/paddle/fluid/inference/api/analysis_predictor.h
index 9191970a3ae0735a282746e3401ef96fa130d111..db57812bc3ba8e6d578e665524cb5749e6bfecd6 100644
--- a/paddle/fluid/inference/api/analysis_predictor.h
+++ b/paddle/fluid/inference/api/analysis_predictor.h
@@ -69,7 +69,7 @@ class AnalysisPredictor : public PaddlePredictor {
   framework::Scope *scope() { return scope_.get(); }
   framework::ProgramDesc &program() { return *inference_program_; }
 
-  void SetMKLDNNThreadId(int tid);
+  void SetMkldnnThreadID(int tid);
 
  protected:
   bool PrepareProgram(const std::shared_ptr<framework::ProgramDesc> &program);
diff --git a/paddle/fluid/inference/api/api_impl.cc b/paddle/fluid/inference/api/api_impl.cc
index c3d17edea43a326864343b88f470b7de28de84b3..66a8e513961d74b96a98b01393048112ded65482 100644
--- a/paddle/fluid/inference/api/api_impl.cc
+++ b/paddle/fluid/inference/api/api_impl.cc
@@ -75,7 +75,7 @@ bool NativePaddlePredictor::Init(
 #endif
 
   // no matter with or without MKLDNN
-  paddle::platform::SetNumThreads(config_.GetCPUNumThreads());
+  paddle::platform::SetNumThreads(config_.cpu_math_library_num_threads());
 
   if (config_.use_gpu) {
     place_ = paddle::platform::CUDAPlace(config_.device);
diff --git a/paddle/fluid/inference/api/paddle_api.h b/paddle/fluid/inference/api/paddle_api.h
index b7f7781d064814a07dc666a21823c2799c3ffaf9..1513a4b3b4f6620aa8bf53e082afa203af15ca13 100644
--- a/paddle/fluid/inference/api/paddle_api.h
+++ b/paddle/fluid/inference/api/paddle_api.h
@@ -187,14 +187,18 @@ struct NativeConfig : public PaddlePredictor::Config {
   // `feeds` and `fetches` of the phase `save_inference_model`.
   bool specify_input_name{false};
 
-  // Set and get the number of cpu threads.
-  void SetCPUNumThreads(int cpu_num_threads) {
-    cpu_num_threads_ = cpu_num_threads;
+  // Set and get the number of cpu math library threads.
+  void SetCpuMathLibraryNumThreads(int cpu_math_library_num_threads) {
+    cpu_math_library_num_threads_ = cpu_math_library_num_threads;
+  }
+  int cpu_math_library_num_threads() const {
+    return cpu_math_library_num_threads_;
   }
-  int GetCPUNumThreads() const { return cpu_num_threads_; }
 
  protected:
-  int cpu_num_threads_{1};  // number of cpu threads for each instance.
+  // number of cpu math library (such as MKL, OpenBlas) threads for each
+  // instance.
+  int cpu_math_library_num_threads_{1};
 };
 
 // A factory to help create different predictors.
diff --git a/paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc b/paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
index 308a794ca3d1a696ee02382e2b4fd3eae768be11..abc63577b7913a3c9de7d6c16d8ac3e85ffd7c3c 100644
--- a/paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
+++ b/paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
@@ -27,7 +27,7 @@ void SetConfig(AnalysisConfig *cfg) {
   cfg->device = 0;
   cfg->enable_ir_optim = true;
   cfg->specify_input_name = true;
-  cfg->SetCPUNumThreads(FLAGS_paddle_num_threads);
+  cfg->SetCpuMathLibraryNumThreads(FLAGS_paddle_num_threads);
 }
 
 void SetInput(std::vector<std::vector<PaddleTensor>> *inputs) {
diff --git a/paddle/fluid/inference/tests/api/config_printer.h b/paddle/fluid/inference/tests/api/config_printer.h
index a803f5b3f4166e7ef68a425bd2ce24a4ad42cbda..4231eef7220735d0b80eb1adc951c55ff7378f1b 100644
--- a/paddle/fluid/inference/tests/api/config_printer.h
+++ b/paddle/fluid/inference/tests/api/config_printer.h
@@ -54,7 +54,7 @@ std::ostream &operator<<(std::ostream &os, const NativeConfig &config) {
   os << GenSpaces(num_spaces)
      << "specify_input_name: " << config.specify_input_name << "\n";
   os << GenSpaces(num_spaces)
-     << "cpu_num_threads: " << config.GetCPUNumThreads() << "\n";
+     << "cpu_num_threads: " << config.cpu_math_library_num_threads() << "\n";
   num_spaces--;
   os << GenSpaces(num_spaces) << "}\n";
   return os;
diff --git a/paddle/fluid/inference/tests/api/tester_helper.h b/paddle/fluid/inference/tests/api/tester_helper.h
index d21567ac197587473684092f6cb12b059e0b1871..1dc16784067836f173c9c0e0bc30f10c98435ed7 100644
--- a/paddle/fluid/inference/tests/api/tester_helper.h
+++ b/paddle/fluid/inference/tests/api/tester_helper.h
@@ -221,7 +221,7 @@ void TestMultiThreadPrediction(
 #ifdef PADDLE_WITH_MKLDNN
       if (use_analysis) {
         static_cast<AnalysisPredictor *>(predictor.get())
-            ->SetMKLDNNThreadId(static_cast<int>(tid) + 1);
+            ->SetMkldnnThreadID(static_cast<int>(tid) + 1);
       }
 #endif