Montgomery multiplication VHDL Implementation

Question

I am trying to create a modular arithmetic operation in this case:

x*y mod n

As far as I have read the fastest way to do it is using the Montgomery multiplication, but I cant understand how that is actually done in other to implement it in hardware using VHDL.

Has someone been able to do it or have any library that enables me to use it?

Answer 1

A basic shift and add modular multiplication can be found here as a part of this open cores project.

Here's another project that is using the Montgomery multiplication.