@inproceedings{bos2013montgomery,
author = {Bos, Joppe and Montgomery, Peter and Shumow, Dan and Zaverucha, Greg},
title = {Montgomery Multiplication Using Vector Instructions},
booktitle = {Selected Areas in Cryptography 2013 (SAC 2013)},
year = {2013},
month = {September},
abstract = {In this paper we present a parallel approach to compute interleaved Montgomery multiplication. This approach is particularly suitable to be computed on 2-way single instruction, multiple data platforms as can be found on most modern computer architectures in the form of vector instruction set extensions. We have implemented this approach for tablet devices which run the x86 architecture (Intel Atom Z2760) using SSE2 instructions as well as devices which run on the ARM platform (Qualcomm MSM8960, NVIDIA Tegra 3 and 4) using NEON instructions. When instantiating modular exponentiation with this parallel version of Montgomery multiplication we observed a performance increase of more than a factor of 1.5 compared to the sequential implementation in OpenSSL for the classical arithmetic logic unit on the Atom platform for 2048-bit moduli.},
publisher = {Springer},
url = {http://approjects.co.za/?big=en-us/research/publication/montgomery-multiplication-using-vector-instructions/},
edition = {Selected Areas in Cryptography 2013 (SAC 2013)},
}