#include <arm_neon.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.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; i += 4) {
    
        float32x4_t a = vld1q_f32(A + i);
        float32x4_t b = vld1q_f32(B + i);
        float32x4_t c = vaddq_f32(a, b);
        vst1q_f32(C + i, c);
    }
    
    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));
    float *C_optimized = (float*)malloc(SIZE * sizeof(float));

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

    
    clock_t start = clock();
    vector_add(A, B, C, SIZE);
    clock_t end = clock();
    double base_time = (double)(end - start) / CLOCKS_PER_SEC;


    start = clock();
    vector_add_optimized(A, B, C_optimized, SIZE);
    end = clock();
    double optimized_time = (double)(end - start) / CLOCKS_PER_SEC;


    printf("base: %f s\n", base_time);
    printf("NEON: %f s\n", optimized_time);

    
    free(A);
    free(B);
    free(C);
    free(C_optimized);

    return 0;
}