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

#define SIZE 1024

void matmul(float** A, float** B, float** C, int n) {
    int i, j, k;
    for (i = 0; i < n; ++i) {
        for (j = 0; j < n; ++j) {
            C[i][j] = 0;
            for (k = 0; k < n; ++k) {
                C[i][j] += A[i][k] * B[k][j];
            }
        }
    }
}

void matmulNEON(float** A, float** B, float** C, int n) {
    for (int i = 0; i < n; i++) {
        for (int j = 0; j < n; j++) {
            float32x4_t vecC = vmovq_n_f32(0); 
            for (int k = 0; k < n; k += 4) {  
                float32x4_t vecA = vld1q_f32(&A[i][k]);
                float32x4_t vecB = vld1q_f32(&B[k][j]);
                vecC = vmlaq_f32(vecC, vecA, vecB);  
            }
            C[i][j] = vgetq_lane_f32(vecC, 0) + vgetq_lane_f32(vecC, 1) +
                       vgetq_lane_f32(vecC, 2) + vgetq_lane_f32(vecC, 3);
        }
    }
}

int main() {
    float** A = (float**)malloc(SIZE * sizeof(float*));
    float** B = (float**)malloc(SIZE * sizeof(float*));
    float** C = (float**)malloc(SIZE * sizeof(float*));
    int i, j;
    for (i = 0; i < SIZE; ++i) {
        A[i] = (float*)malloc(SIZE * sizeof(float));
        B[i] = (float*)malloc(SIZE * sizeof(float));
        C[i] = (float*)malloc(SIZE * sizeof(float));
    }

    srand(time(0));
    for (i = 0; i < SIZE; ++i) {
        for (j = 0; j < SIZE; ++j) {
            A[i][j] = rand() % 100; 
            B[i][j] = rand() % 100; 
        }
    }
    clock_t start1 = clock();
    matmul(A, B, C, SIZE);
    clock_t end1 = clock();
    double time1 = (double)(end1 - start1) / CLOCKS_PER_SEC;
    printf("tradition %f\n", time1);

    clock_t start2 = clock();
    matmulNEON(A, B, C, SIZE);
    clock_t end2 = clock();
    double time2 = (double)(end2 - start2) / CLOCKS_PER_SEC;
    printf("NEON %f\n", time2);

    for (i = 0; i < SIZE; i++) {
        free(A[i]);
        free(B[i]);
        free(C[i]);
    }
    free(A);
    free(B);
    free(C);

    return 0;
}