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


#define SIZE 10000000

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

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

        float32x4_t vecC = vaddq_f32(vecA, vecB);
        vst1q_f32(&C[i], vecC);
    }
    for (; i < size; ++i) {
        C[i] = A[i] + B[i];
    }
}

int main() {
    float* A = (float*)malloc(SIZE * sizeof(float));
    float* B = (float*)malloc(SIZE * sizeof(float));
    float* C = (float*)malloc(SIZE * sizeof(float));
    if (A == NULL || B == NULL || C == NULL) {
        return 1; 
    }

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

    clock_t start_time = clock();
    vectorAdd(A, B, C, SIZE);
    clock_t end_time = clock();
    double time1 = (double)(end_time - start_time) / CLOCKS_PER_SEC;
    printf("tradition: %f", time1);

    start_time = clock();
    vectorAddNEON(A, B, C, SIZE);
    end_time = clock();
    time1 = (double)(end_time - start_time) / CLOCKS_PER_SEC; 
    printf("NEON %f",time1);

    free(A);
    free(B);
    free(C);   
}