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

#define SIZE 1024

// NEON优化的向量加法函数
void vector_add_optimized(float* A, float* B, float* C, int size) {
    for (int i = 0; i < size; i += 4) {
        // 加载A和B的4个连续元素到NEON寄存器中
        float32x4_t a = vld1q_f32(A + i);
        float32x4_t b = vld1q_f32(B + i);
        // 执行向量加法
        float32x4_t c = vaddq_f32(a, b);
        // 将结果存回C
        vst1q_f32(C + i, c);
    }
}

int main() {
    // 分配内存并初始化向量
    float *A = (float*)malloc(SIZE * sizeof(float));
    float *B = (float*)malloc(SIZE * sizeof(float));
    float *C = (float*)malloc(SIZE * sizeof(float));

    // 随机初始化向量A和B
    srand((unsigned int)time(NULL));
    for (int i = 0; i < SIZE; ++i) {
        A[i] = rand() % 100;
        B[i] = rand() % 100;
    }

    // 计时开始
    clock_t start = clock();
    // 执行NEON优化的向量加法
    vector_add_optimized(A, B, C, SIZE);
    // 计时结束
    clock_t end = clock();

    // 输出运行时间
    printf("NEON优化向量加法耗时: %lf 毫秒\n", 1000.0 * (end - start) / CLOCKS_PER_SEC);

    // 释放内存
    free(A);
    free(B);
    free(C);

    return 0;
}