Adding a bunch of variables using cuda or cpu

Signed-off-by: Nigel Barink <nigelbarink@hotmail.com>

.gitignore

@@ -0,0 +1,3 @@
+*.exp
+*.lib
+*.exe

README.md

@@ -0,0 +1,4 @@
+# Practicing CUDA 
+## Doing some parallel compute on the GPU 
+
+

add.cpp

@@ -0,0 +1,31 @@
+#include <iostream>
+#include <math.h>
+
+void add (int n, float* x, float* y){
+    for(int i = 0; i< n; i++)
+        y[i] = x[i] +y[i];
+}
+
+int main (void) {
+    int N = 1<<20;
+    float *x = new float [N];
+    float *y = new float [N];
+
+    for (int i = 0; i<N; i++){
+        x[i] = 1.0f;
+        y[i] = 2.0f;
+    }
+
+    add(N, x, y );
+
+    float maxError= 0.0f;
+    for (int i =0; i < N; i++){
+        maxError = fmax(maxError, fabs(y[i] -3.0f));
+    }
+    std::cout << "Max error: " << maxError << std::endl;
+
+    delete [] x;
+    delete [] y;
+
+    return 0;
+}

add_cuda.cu

@@ -0,0 +1,35 @@
+#include <iostream>
+#include <math.h>
+
+__global__
+void add (int n, float* x, float* y){
+    for(int i = 0; i< n; i++)
+        y[i] = x[i] +y[i];
+}
+
+
+int main (void) {
+    int N = 1<<20;
+    float *x, *y;
+    cudaMallocManaged(&x, N*sizeof(float));
+    cudaMallocManaged(&y, N*sizeof(float));
+
+
+    for (int i = 0; i<N; i++){
+        x[i] = 1.0f;
+        y[i] = 2.0f;
+    }
+
+    add<<<1,1>>>(N, x, y );
+    cudaDeviceSynchronize();
+
+    float maxError= 0.0f;
+    for (int i =0; i < N; i++){
+        maxError = fmax(maxError, fabs(y[i] -3.0f));
+    }
+    std::cout << "Max error: " << maxError << std::endl;
+
+    cudaFree(x);
+    cudaFree(y);
+    return 0;
+}