1. CPU端（程序：cpu.c）
#include <stdio.h> #define N 10 void add(int *a, int *b, int *c){ int tid = 0; while(tid < N){ c[tid] = a[tid] + b[tid]; tid++; } } int main(){ int a[N], b[N], c[N]; for(int i=0; i<N; i++){ a[i] = i; b[i] = i+1; } add(a, b, c); for(int i=0; i<N; i++){ printf("%d + %d = %d\n", a[i], b[i], c[i]); } return 0; }2. GPU端（程序：gpu.cu）
#include "cuda_runtime.h" #include "device_launch_parameters.h" #include <stdio.h> #define N 10 __global__ void add(int *a, int *b, int *c){ int tid = blockIdx.x; if(tid < N){ c[tid] = a[tid] + b[tid]; } } int main(){ int a[N], b[N], c[N]; int *dev_a, *dev_b, *dev_c; cudaMalloc((void**)&dev_a, N*sizeof(int)); cudaMalloc((void**)&dev_b, N*sizeof(int)); cudaMalloc((void**)&dev_c, N*sizeof(int)); for(int i=0; i<N; i++){ a[i] = i; b[i] = i+1; } cudaMemcpy(dev_a, a, N*sizeof(int), cudaMemcpyHostToDevice); cudaMemcpy(dev_b, b, N*sizeof(int), cudaMemcpyHostToDevice); add<<<N, 1>>>(dev_a, dev_b, dev_c); cudaMemcpy(c, dev_c, N*sizeof(int), cudaMemcpyDeviceToHost); for(int i=0; i<N; i++){ printf("%d + %d = %d\n", a[i], b[i], c[i]); } return 0; }Reference Sanders J, Kandrot E. Cuda by Example: An Introduction to General-Purpose GPU Programming[J]. 2010, 11(4):387-415.
