add vecAdd for test

src/vecAdd.cu

+#include <stdlib.h>
+
+// Start vectorAdd_float
+/**
+ * CUDA Kernel Device code
+ *
+ * Computes the vector addition of A and B into C. The 3 vectors have the same
+ * number of elements numElements.
+ */
+__global__ void vectorAdd_float(const float *A, const float *B, float *C, int numElements)
+{
+    int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+    if (i < numElements)
+    {
+        C[i] = A[i] + B[i];
+    }
+}
+
+// Start Parameters
+float * vectorAdd_float_ha;
+float * vectorAdd_float_hb;
+float * vectorAdd_float_hc;
+constexpr int SIZE_float = 10000;
+// End Parameters
+
+// Start Init function
+void initialize_vectorAdd_float() {
+	vectorAdd_float_ha = (float*)malloc(SIZE_float*sizeof(float));
+	vectorAdd_float_hb = (float*)malloc(SIZE_float*sizeof(float));
+	vectorAdd_float_hc = (float*)malloc(SIZE_float*sizeof(float));
+
+	float * vectorAdd_float_da;
+	float * vectorAdd_float_db;
+	float * vectorAdd_float_dc;
+
+	cudaMalloc(&vectorAdd_float_da, SIZE_float * sizeof(float));
+	cudaMalloc(&vectorAdd_float_db, SIZE_float * sizeof(float));
+	cudaMalloc(&vectorAdd_float_dc, SIZE_float * sizeof(float));
+
+	for (int i = 0; i < SIZE_float; i++) {
+		vectorAdd_float_ha[i] = 1.0;
+		vectorAdd_float_hb[i] = 2.0;
+	}
+
+	cudaMemcpy(vectorAdd_float_da, vectorAdd_float_ha, SIZE_float*sizeof(float), cudaMemcpyHostToDevice);
+	cudaMemcpy(vectorAdd_float_db, vectorAdd_float_hb, SIZE_float*sizeof(float), cudaMemcpyHostToDevice);
+}
+// End Init Function
+
+// End vectorAdd_float
+
+// Start vectorAdd_int
+__global__ void vectorAdd_int(const int *A, const int *B, int *C, int numElements)
+{
+    int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+    if (i < numElements)
+    {
+        C[i] = A[i] + B[i];
+    }
+}
+
+// Start Parameters
+int * vectorAdd_int_ha;
+int * vectorAdd_int_hb;
+int * vectorAdd_int_hc;
+constexpr int SIZE_int = 10000;
+// End Parameters
+
+// Start Init function
+void initialize_vectorAdd_int() {
+	vectorAdd_int_ha = (int*)malloc(SIZE_int*sizeof(int));
+	vectorAdd_int_hb = (int*)malloc(SIZE_int*sizeof(int));
+	vectorAdd_int_hc = (int*)malloc(SIZE_int*sizeof(int));
+
+	int * vectorAdd_int_da;
+	int * vectorAdd_int_db;
+	int * vectorAdd_int_dc;
+	cudaMalloc(&vectorAdd_int_da, SIZE_int * sizeof(int));
+	cudaMalloc(&vectorAdd_int_db, SIZE_int * sizeof(int));
+	cudaMalloc(&vectorAdd_int_dc, SIZE_int * sizeof(int));
+
+	for (int i = 0; i < SIZE_int; i++) {
+		vectorAdd_int_ha[i] = 1.0;
+		vectorAdd_int_hb[i] = 2.0;
+	}
+
+	cudaMemcpy(vectorAdd_int_da, vectorAdd_int_ha, SIZE_int*sizeof(int), cudaMemcpyHostToDevice);
+	cudaMemcpy(vectorAdd_int_db, vectorAdd_int_hb, SIZE_int*sizeof(int), cudaMemcpyHostToDevice);
+}
+// End Init Function
+// End vectorAdd_int