#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <arm_neon.h>

#define SIZE 1024


void vector_add_optimized(float* A, float* B, float* C, int size) {
    int i;
    for (i = 0; i < size - 3; i += 4) {
        
        float32x4_t A_vec = vld1q_f32(A + i);
        float32x4_t B_vec = vld1q_f32(B + i);
        
        float32x4_t C_vec = vaddq_f32(A_vec, B_vec);
        
        vst1q_f32(C + i, C_vec);
    }
    
    for (; i < size; i++) {
        C[i] = A[i] + B[i];
    }
}

int main() {
    float A[SIZE], B[SIZE], C[SIZE];
    srand(time(NULL)); 

   
    for (int i = 0; i < SIZE; i++) {
        A[i] = rand() % 100;
        B[i] = rand() % 100;
    }

    
    clock_t start, end;
    start = clock(); 

   
    vector_add_optimized(A, B, C, SIZE);

    end = clock(); 
    double time_spent = (double)(end - start) / CLOCKS_PER_SEC; 

    printf("NEON优化向量加法的运行时间为: %lf 秒\n", time_spent);

    return 0;
}