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

#define SIZE 1024  

void vector_add(float* A, float* B, float* C, int size) {
    for (int i = 0; i < size; ++i) {
        C[i] = A[i] + B[i];  
    }
}
 
void vector_add_optimized(float* A, float* B, float* C, int size) {
    int i;

    for (i = 0; i <= size - 4; 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 = clock(); 

    vector_add_optimized(A, B, C, SIZE);

    clock_t end = clock(); 

    double time_taken = (double)(end - start) / CLOCKS_PER_SEC;   
    printf("NEON优化的向量加法的运行时间: %e 秒\n", time_taken);  

    return 0;
}