Inner unloop leads to wrong results about how-to-optimize-gemm HOT 2 CLOSED

// MMult.h
void MMult_base(int m, int k, int n, double *A, double *B, double *C, int lda, int ldb, int ldc);
void MMult_unroll(int m, int k, int n, double *A, double *B, double *C, int lda, int ldb, int ldc);
void MMult_unroll_inner(int m, int k, int n, double *A, double *B, double *C, int lda, int ldb, int ldc);

// utils.h
#include <stdlib.h>
#include <stdio.h>
#include <sys/time.h>
#include <time.h>
#include "assert.h" 

void random_matrix( int m, int n, double *mat, int ldm);
void zero_matrix( int m, int n, double *mat, int ldm);
void print_matrix(int m, int n, double *mat, int ldm);
double compare_matrix(int m, int n, double *mat1, double *mat2, int ldm);

// utils.c
#include "params.h"
#include "utils.h"

void random_matrix(int m, int n, double *mat, int ldm){
    double drand48();

    for (int i = 0; i < m; ++i){
        for (int j = 0; j < n; ++j)
            // mat(i, j) = 2.0 * drand48( ) - 1.0;
            mat(i, j) = (double) (i + 1);
    }
    // print_matrix(m, n, mat, n);
}

void zero_matrix(int m, int n, double *mat, int ldm){
    for (int i = 0; i < m; ++i){
        for (int j = 0; j < n; ++j)
            mat(i, j) = (double) 0;
    }
    // print_matrix(m, n, mat, n);
}

void print_matrix(int m, int n, double *mat, int ldm){
    for (int i = 0; i < m; ++i){
        for (int j = 0; j < n; ++j){
            //std::cout<<mat(i, j)<<" ";
            printf("%f\t", mat(i, j));
        }
        // std::cout<<std::endl;
        printf("\n");
    }
    printf("\n");   
}

double compare_matrix(int m, int n, double *mat, double *mat2, int ldm){
    double max_diff = 0, diff;
    for (int i = 0; i < m; ++i){
        for (int j = 0; j < n; ++j){
            diff = abs(mat(i, j) - mat2(i, j));
            max_diff = diff > max_diff ? diff : max_diff;
        }
    }

    return max_diff;
}

#define B(i, j) B[i*ldb + j]

// params.h
#define A(i, j) A[i*lda + j]
#define B(i, j) B[i*ldb + j]
#define C(i, j) C[i*ldc + j]
#define mat(i, j) mat[(i)*(ldm) + (j)]
#define mat2(i, j) mat2[(i)*(ldm) + (j)]

// params.h
#define A(i, j) A[(i)*lda + j]     // add brackets here
#define B(i, j) B[(i)*ldb + j]     // add brackets here
#define C(i, j) C[(i)*ldc + j]     // add brackets here
#define mat(i, j) mat[(i)*(ldm) + (j)]
#define mat2(i, j) mat2[(i)*(ldm) + (j)]