Memory doubled when calling zgetrf in Csharp,

Hi,

I'm solving a large complex dense matrix (10k*10k) in Csharp by calling zgetrf first to LU-decompse the matrix. If I understand correctly, zgetrf will do a in-place LU-decomposition. So there should be no extra copies produced. But the memory usage becomes doubled (from 1.6G to more than 3G) when zgetrf is running. Can someone kindly tell me the reason? It would be great if I can figure out a solution to avoid the extra memory usage.

Here is the code

class Program
    {


        static void Main(string[] args)
        {
            int n1 = 10000;
            int n2 = n1 * n1;
            complex[] A = new complex[n2];
            complex[] b = new complex[n1];

            for (int i = 0; i < n1; i++)
            {
                for (int j = 0; j < n1; j++)
                {
                    int ij = j * n1 + i;
                    A[ij].r = i + 1;
                    A[ij].i = j + 1;
                }
                b[i].r = i + 1;
                b[i].i = i + 2;
            }

            int info = 0;
            int[] ipiv = new int[n1];
            MKL.LU_decomposition(A, ref n1, ref n2, ipiv, ref info);
            MKL.LU_solve(A, b, ref n1, ref n2, ipiv, ref info);
        }


        [SuppressUnmanagedCodeSecurity]
        public sealed class MKL
        {
            private MKL() { }

            [DllImport("customMKL_Sequential.dll", CallingConvention = CallingConvention.Cdecl, ExactSpelling = true, SetLastError = false)]
            public static extern void LU_decomposition([In, Out] complex[] A, ref int n1, ref int n2, [In, Out] int[] ipiv, ref int info);

            [DllImport("customMKL_Sequential.dll", CallingConvention = CallingConvention.Cdecl, ExactSpelling = true, SetLastError = false)]
            public static extern void LU_solve([In] complex[] A, [In, Out] complex[] b, ref int n1, ref int n2, [In] int[] ipiv, ref int info);
        }


        [StructLayout(LayoutKind.Sequential)]/* Force sequential mapping */
        public struct complex
        {
            [MarshalAs(UnmanagedType.R8, SizeConst = 64)]
            public double r;
            [MarshalAs(UnmanagedType.R8, SizeConst = 64)]
            public double i;
        };
    }

subroutine LU_decomposition (A, n1, n2, ipiv, info)
    implicit none
    !dec$ attributes dllexport :: LU_decomposition
    !dec$ attributes alias:'LU_decomposition' :: LU_decomposition

    integer, intent(in) :: n1, n2
    integer, intent(inout) :: info
    integer, dimension(n1), intent(inout) :: ipiv
    complex(8), dimension(n2), intent(inout) :: A

    call zgetrf(n1, n1, A, n1, ipiv, info)
end subroutine


subroutine LU_solve (A, b, n1, n2, ipiv, info)
    implicit none
    !dec$ attributes dllexport :: LU_solve
    !dec$ attributes alias:'LU_solve' :: LU_solve

    integer, intent(in) :: n1, n2
    integer, intent(inout) :: info
    integer, dimension(n1), intent(in) :: ipiv
    complex(8), dimension(n2), intent(inout) :: A
    complex(8), dimension(n1), intent(inout) :: b

    call zgetrs('N', n1, 1, A, n1, ipiv, b, n1, info)
end subroutine

Thanks alot in advance