Explore Snippets

#include<iostream>
#include<chrono>
#include<cuda_runtime.h>

using namespace std;
using namespace chrono;

__global__ void GPU_Vector_Addition(int* a, int* b, int* c, int n){
  int i = blockDim.x * blockIdx.x + threadIdx.x;

  if (i < n){
    c[i] = a[i] + b[i];
  }
}

void CPU_Vector_Addition(int*
...

#include <stdio.h>

__global__ void vecAdd(float *a, float *b, float *c, int n) {
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i < n) {
        c[i] = a[i] + b[i];
    }
}

int main() {
    int n = 1024;
    size_t bytes = n * sizeof(float);

    float *h_a = (float*)malloc(bytes);
   
...