add Set/GetCPUNumThreads api

paddle/fluid/inference/api/analysis_config.cc

@@ -46,6 +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_;
   // fields from this.
   enable_ir_optim = other.enable_ir_optim;
   use_feed_fetch_ops = other.use_feed_fetch_ops;

paddle/fluid/inference/api/analysis_predictor.cc

@@ -35,7 +35,6 @@
 #include "paddle/fluid/platform/profiler.h"
 
 DECLARE_bool(profile);
-DECLARE_int32(paddle_num_threads);
 
 namespace paddle {
 
@@ -67,7 +66,7 @@ bool AnalysisPredictor::Init(
 #endif
 
   // no matter with or without MKLDNN
-  paddle::platform::SetNumThreads(FLAGS_paddle_num_threads);
+  paddle::platform::SetNumThreads(config_.GetCPUNumThreads());
 
   if (!PrepareScope(parent_scope)) {
     return false;

paddle/fluid/inference/api/api_impl.cc

@@ -28,7 +28,6 @@ limitations under the License. */
 #include "paddle/fluid/platform/profiler.h"
 
 DEFINE_bool(profile, false, "Turn on profiler for fluid");
-DECLARE_int32(paddle_num_threads);
 
 namespace paddle {
 namespace {
@@ -76,7 +75,7 @@ bool NativePaddlePredictor::Init(
 #endif
 
   // no matter with or without MKLDNN
-  paddle::platform::SetNumThreads(FLAGS_paddle_num_threads);
+  paddle::platform::SetNumThreads(config_.GetCPUNumThreads());
 
   if (config_.use_gpu) {
     place_ = paddle::platform::CUDAPlace(config_.device);

paddle/fluid/inference/api/paddle_api.h

@@ -186,6 +186,15 @@ struct NativeConfig : public PaddlePredictor::Config {
   // Specify the variable's name of each input if input tensors don't follow the
   // `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;
+  }
+  int GetCPUNumThreads() const { return cpu_num_threads_; }
+
+ protected:
+  int cpu_num_threads_{1};  // number of cpu threads for each instance.
 };
 
 // A factory to help create different predictors.

paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc

@@ -27,6 +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);
 }
 
 void SetInput(std::vector<std::vector<PaddleTensor>> *inputs) {

paddle/fluid/inference/tests/api/config_printer.h

@@ -53,6 +53,8 @@ std::ostream &operator<<(std::ostream &os, const NativeConfig &config) {
   os << GenSpaces(num_spaces) << "param_file: " << config.param_file << "\n";
   os << GenSpaces(num_spaces)
      << "specify_input_name: " << config.specify_input_name << "\n";
+  os << GenSpaces(num_spaces)
+     << "cpu_num_threads: " << config.GetCPUNumThreads() << "\n";
   num_spaces--;
   os << GenSpaces(num_spaces) << "}\n";
   return os;

paddle/fluid/inference/tests/api/tester_helper.h

@@ -42,6 +42,7 @@ DEFINE_bool(use_analysis, true,
             "Running the inference program in analysis mode.");
 
 DECLARE_bool(profile);
+DECLARE_int32(paddle_num_threads);
 
 namespace paddle {
 namespace inference {

paddle/fluid/operators/math/fc_compute.h

@@ -17,8 +17,6 @@ limitations under the License. */
 #include "paddle/fluid/operators/math/blas.h"
 #include "paddle/fluid/operators/math/jit_kernel.h"
 
-DECLARE_int32(paddle_num_threads);
-
 namespace paddle {
 namespace operators {
 namespace math {
@@ -43,7 +41,7 @@ inline void FCCompute(const BlasT<DeviceContext, T>& blas, const int M,
                            .template Get<jitkernel::VAddKernel<T>>(N);
 
 #ifdef PADDLE_WITH_MKLML
-#pragma omp parallel for if (FLAGS_paddle_num_threads > 1)
+#pragma omp parallel for
 #endif
     for (int i = 0; i < M; i++) {
       T* dst = Y + i * N;

paddle/fluid/platform/cpu_helper.cc

@@ -41,7 +41,7 @@ void SetNumThreads(int num_threads) {
 #elif defined(PADDLE_WITH_MKLML)
   int real_num_threads = num_threads > 1 ? num_threads : 1;
   platform::dynload::MKL_Set_Num_Threads(real_num_threads);
-  omp_set_num_threads(num_threads);
+  omp_set_num_threads(real_num_threads);
 #else
   PADDLE_ENFORCE(false, "To be implemented.");
 #endif