Low latency modular multiplication for public-key cryptosystems using a scalable array of parallel processing elements
Yinan Kong, Yufeng Lai · 2013
This work contributes to the modular multiplication operation C = A × B, the basis of many public-key cryptosystems including RSA and Elliptic Curve Cryptography (ECC). We use the Residue Number System (RNS) to speed up long wordlength modular multiplication. The RNS leads to a highly parallel algorithm which we exploit with a massively parallel hardware implementation capable of exceptionally low latency. This paper presents architecture for this scheme consisting of a scalable array of identical processing elements.