Abstract
The long-precision modular multiplier is usually performed by Montgomery algorithm with bit shifts, yielding a result in the form of A · B · 2 − n mod M . In fact, with the precomputation of δ · 2 n mod M proposed by others, it is able to compute classic modular multiplication A · B mod M rather than Montgomery modular multiplication A · B · N − 1 mod M . In this work, a multi-bit CSA-based long-precision modular multiplier is proposed for hardware implementation. It includes two carry save adders and one RAM access to perform modular multiplications. After every modular multiplication, a division is applied to reduce the result down to [ 0 , M ) . Hardware implementation results show that a 1024-bit modular multiplication can be completed in 2.39 μs on the XC5V FPGA platform, costing 5793 slices, 8 DSPs and 36 BRAMs, which is a promising candidate to compute incontinuous classic modular multiplications.

This publication has 20 references indexed in Scilit: