mkl_ddiamm bug ?

I am trying to multiply two matrices using mkl_ddiamm method:

C = A * B

where A is diagonal matrix 3x3 and B is general matrix 3x3. No matter what I try, i get as a result no A*B, but B*A. This is my sample code. It essentially does SVD decomposition of matrix A and checks, if the computed matrices U, S and VT satisfy all requirements according to theory i.e.

1. U * UT = I, where I us identity matrix

2. V * VT = I

3. U * S * VT = A

Result of temporary operation S * VT is not correct. In fact, the function mkl_ddiamm computes VT * S.

   // requirement: m >= n
   int m = 3;
   int n = 3;
   double *a = (double *)mkl_malloc(m * n * sizeof(double), 16);
   double *s = (double *)mkl_malloc(n * sizeof(double), 16);
   double *u = (double *)mkl_malloc(m * n * sizeof(double), 16);
   double *vt = (double *)mkl_malloc(n * n * sizeof(double), 16);
   double *superb = (double *)mkl_malloc((n-1) * sizeof(double), 16);
   // identity matrix m x m
   double *unit_m = (double *)mkl_malloc(m * m * sizeof(double), 16);

   for (int i = 0; i < m; i++)
      for (int j = 0; j < m; j++)
         unit_m[i*m+j] = i == j ? 1.0 : 0;

   // identity matrix n x n
   double *unit_n = (double *)mkl_malloc(n * n * sizeof(double), 16);

   for (int i = 0; i < n; i++)
      for (int j = 0; j < n; j++)
         unit_n[i*n+j] = i == j ? 1.0 : 0;

   a[0] = 1;   a[1] = 1; a[2] = 1;
   a[3] = 2.5; a[4] = 3; a[5] = 4;
   a[6] = 3;   a[7] = 2; a[8] = 1;

   lapack_int res = LAPACKE_dgesvd(LAPACK_ROW_MAJOR, 'S', 'S', m, n, a, n, s, u, n, vt, n, superb);

   // Checking correctness of SVD calculation ...

   // u * ut = I
   double *temp = (double *)mkl_malloc(m * m * sizeof(double), 16);
   memset(temp, 0, m * m * sizeof(double));
   cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasTrans, m, m, n, 1.0, u, n, u, n, 0, temp, m);

   // v * vt = I
   memset(temp, 0, n * n * sizeof(double));
   cblas_dgemm(CblasRowMajor, CblasTrans, CblasNoTrans, n, n, n, 1.0, vt, n, vt, n, 0, temp, n);

   // u * s * vt = a
   memset(temp, 0, n * n * sizeof(double));
   int lval = 3;
   int idiag = 0;
   int ndiag = 1;
   double alpha = 1.0;
   double beta = 0;
   mkl_ddiamm("N", &n, &n, &n, &alpha, "DLNF", s, &lval, &idiag, &ndiag, vt, &n, &beta, temp, &n);
   double *temp2 = (double *)mkl_malloc(m * n * sizeof(double), 16);
   memset(temp2, 0, m * n * sizeof(double));
   cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans, m, n, n, 1.0, u, n, temp, n, 0, temp2, n);