#include <stdio.h>
#include <stdlib.h>
#include <ctime>

#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 result_vec = vaddq_f32(a_vec, b_vec);


        vst1q_f32(&C[i], result_vec);
    }


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

int main() {

    float A[SIZE];
    float B[SIZE];
    float C[SIZE];


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

    clock_t start_time, end_time;

    start_time = clock();


    vector_add_optimized(A, B, C, SIZE);


    end_time = clock();


    double elapsed_time = ((double)(end_time - start_time)) / CLOCKS_PER_SEC;
    printf("NEON优化向量加法的运行时间：%f 秒\n", elapsed_time);

    return 0;
}