From 8d6548bc67ed11170330beb2d01bf827bae2fde4 Mon Sep 17 00:00:00 2001
From: Neil Kichler <neil.kichler@gmail.com>
Date: Thu, 20 Feb 2025 00:55:18 +0100
Subject: [PATCH] main.cu only includes main project header

---
 src/main.cu | 51 +--------------------------------------------------
 1 file changed, 1 insertion(+), 50 deletions(-)

diff --git a/src/main.cu b/src/main.cu
index 3bf56b9..27c0dd0 100644
--- a/src/main.cu
+++ b/src/main.cu
@@ -1,50 +1 @@
-#include <iostream>
-#include <math.h>
-
-// Kernel function to add the elements of two arrays
-__global__ void add(int n, float *x, float *y)
-{
-
-    int index  = threadIdx.x + blockDim.x * blockIdx.x;
-    int stride = blockDim.x * gridDim.x;
-
-    for (int i = index; i < n; i += stride)
-        y[i] = x[i] + y[i];
-}
-
-int main(void)
-{
-    int N = 1 << 20;
-    float *x, *y;
-
-    // Allocate Unified Memory – accessible from CPU or GPU
-    cudaMallocManaged(&x, N * sizeof(float));
-    cudaMallocManaged(&y, N * sizeof(float));
-
-    // initialize x and y arrays on the host
-    for (int i = 0; i < N; i++) {
-        x[i] = 1.0f;
-        y[i] = 2.0f;
-    }
-
-    int block_size = 256;
-    int num_blocks = (N + block_size - 1) / block_size;
-
-    // Run kernel on 1M elements on the GPU
-    add<<<num_blocks, block_size>>>(N, x, y);
-
-    // Wait for GPU to finish before accessing on host
-    cudaDeviceSynchronize();
-
-    // Check for errors (all values should be 3.0f)
-    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;
-
-    // Free memory
-    cudaFree(x);
-    cudaFree(y);
-
-    return 0;
-}
+#include <cuinterval/cuinterval.h>