Matrix Multiplication

#!/usr/bin/env python3
import numpy as np

def read_matrix(N):
    matrix = []
    for _ in range(N):
        row = list(map(int, input().split()))
        matrix.append(row)
    return matrix

def multiply_matrices(A, B, N):
    result = [[0] * N for _ in range(N)]
    
    # Adjust block size as necessary to be cache-friendly
    block_size = int(1 + N / 4)

    # Perform matrix multiplication block-by-block
    for i in range(0, N, block_size):
        for j in range(0, N, block_size):
            for k in range(0, N, block_size):
                # Mini matrix multiplication within block
                for i1 in range(i, min(i + block_size, N)):
                    for j1 in range(j, min(j + block_size, N)):
                        for k1 in range(k, min(k + block_size, N)):
                            result[i1][j1] += A[i1][k1] * B[k1][j1]
    np_result = np.array(result)

    formatted_result = format_array(np_result)

    return formatted_result

def format_array(arr): return np.array2string(arr).replace('[[','').replace(' [','').replace(']','')

if __name__ == "__main__":
    N = int(input().strip())

    matrix_A = read_matrix(N)
    
    matrix_B = read_matrix(N)

    result_matrix = multiply_matrices(matrix_A, matrix_B, N)

    print(result_matrix)