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

#define SIZE 1024  

void vector_add_optimized(float* A, float* B, float* C, int size) {
    int i = 0;
    for (; i <= size - 4; i += 4) {
        float32x4_t vecA = vld1q_f32(&A[i]);
        float32x4_t vecB = vld1q_f32(&B[i]);
        float32x4_t result = vaddq_f32(vecA, vecB);
        vst1q_f32(&C[i], result);
    }

    for (; i < size; i++) {
        C[i] = A[i] + B[i];
    }
}

int main() {
    float A[SIZE], B[SIZE], C[SIZE];
    
    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: %f seconds\n", time_taken);

    return 0;
}