From 8857db8abc751ce0e699c58770887223c5df1bd1 Mon Sep 17 00:00:00 2001
From: Nigel Barink <nigelbarink@hotmail.com>
Date: Sun, 29 Sep 2024 18:41:02 +0200
Subject: [PATCH] Adding a bunch of variables using cuda or cpu

Signed-off-by: Nigel Barink <nigelbarink@hotmail.com>
---
 .gitignore  |  3 +++
 README.md   |  4 ++++
 add.cpp     | 31 +++++++++++++++++++++++++++++++
 add_cuda.cu | 35 +++++++++++++++++++++++++++++++++++
 4 files changed, 73 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 README.md
 create mode 100644 add.cpp
 create mode 100644 add_cuda.cu

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..f5519bd
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+*.exp
+*.lib
+*.exe
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..b4098bd
--- /dev/null
+++ b/README.md
@@ -0,0 +1,4 @@
+# Practicing CUDA 
+## Doing some parallel compute on the GPU 
+
+
diff --git a/add.cpp b/add.cpp
new file mode 100644
index 0000000..5247552
--- /dev/null
+++ b/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;
+}
diff --git a/add_cuda.cu b/add_cuda.cu
new file mode 100644
index 0000000..02536ce
--- /dev/null
+++ b/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;
+}