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

#define SIZE 1024

void matmul(float** A, float** B, float** C, int n) {
    for (int i = 0; i < n; i++) {
        for (int j = 0; j < n; j++) {
            float sum = 0.0;
            for (int k = 0; k < n; k++) {
                sum += A[i][k] * B[k][j];
            }
            C[i][j] = sum;
        }
    }
}

int main() {
    float** A = (float**)malloc(SIZE * sizeof(float*));
    float** B = (float**)malloc(SIZE * sizeof(float*));
    float** C = (float**)malloc(SIZE * sizeof(float*));

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

    clock_t start = clock();
    matmul(A, B, C, SIZE);
    clock_t end = clock();

    printf("»ù´¡¾ØÕó³Ë·¨ºÄʱ: %lf ºÁÃë\n", 1000.0 * (end - start) / CLOCKS_PER_SEC);

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