Implement dot kernel in OpenMP 3

OMP3Stream.cpp

@@ -91,6 +91,21 @@ void OMP3Stream<T>::triad()
   }
 }
 
+template <class T>
+T OMP3Stream<T>::dot()
+{
+  T sum = 0.0;
+
+  #pragma omp parallel for reduction(+:sum)
+  for (int i = 0; i < array_size; i++)
+  {
+    sum += a[i] * b[i];
+  }
+
+  return sum;
+}
+
+
 void listDevices(void)
 {
   std::cout << "0: CPU" << std::endl;

OMP3Stream.h

@@ -33,6 +33,7 @@ class OMP3Stream : public Stream<T>
     virtual void add() override;
     virtual void mul() override;
     virtual void triad() override;
+    virtual T dot() override;
 
     virtual void write_arrays(const std::vector<T>& a, const std::vector<T>& b, const std::vector<T>& c) override;
     virtual void read_arrays(std::vector<T>& a, std::vector<T>& b, std::vector<T>& c) override;