optimize performace (#363)

src/metric/multiclass_metric.hpp

@@ -100,7 +100,7 @@ class MultiErrorMetric: public MulticlassMetric<MultiErrorMetric> {
 public:
   explicit MultiErrorMetric(const MetricConfig& config) :MulticlassMetric<MultiErrorMetric>(config) {}
 
-  inline static double LossOnPoint(float label, std::vector<double> score) {
+  inline static double LossOnPoint(float label, std::vector<double>& score) {
     size_t k = static_cast<size_t>(label);
     for (size_t i = 0; i < score.size(); ++i){
         if (i != k && score[i] >= score[k]) {
@@ -120,7 +120,7 @@ class MultiLoglossMetric: public MulticlassMetric<MultiLoglossMetric> {
 public:
   explicit MultiLoglossMetric(const MetricConfig& config) :MulticlassMetric<MultiLoglossMetric>(config) {}
 
-  inline static double LossOnPoint(float label, std::vector<double> score) {
+  inline static double LossOnPoint(float label, std::vector<double>& score) {
     size_t k = static_cast<size_t>(label);
     Common::Softmax(&score);
     if (score[k] > kEpsilon) {

src/objective/multiclass_objective.hpp

@@ -48,9 +48,10 @@ public:
 
   void GetGradients(const double* score, score_t* gradients, score_t* hessians) const override {
     if (weights_ == nullptr) {
-      #pragma omp parallel for schedule(static)
+      std::vector<double> rec;
+      #pragma omp parallel for schedule(static) private(rec)
       for (data_size_t i = 0; i < num_data_; ++i) {
-        std::vector<double> rec(num_class_);
+        rec.resize(num_class_);
         for (int k = 0; k < num_class_; ++k){
           size_t idx = static_cast<size_t>(num_data_) * k + i;
           rec[k] = static_cast<double>(score[idx]);
@@ -69,9 +70,10 @@ public:
         }
       }
     } else {
-      #pragma omp parallel for schedule(static)
+      std::vector<double> rec;
+      #pragma omp parallel for schedule(static) private(rec)
       for (data_size_t i = 0; i < num_data_; ++i) {
-        std::vector<double> rec(num_class_);
+        rec.resize(num_class_);
         for (int k = 0; k < num_class_; ++k){
           size_t idx = static_cast<size_t>(num_data_) * k + i;
           rec[k] = static_cast<double>(score[idx]);