@techreport{longa2016fourqneon,
author = {Longa, Patrick},
title = {FourQNEON: Faster Elliptic Curve Scalar Multiplications on ARM Processors},
year = {2016},
month = {May},
abstract = {We present a high-speed, high-security implementation of the recently proposed elliptic curve FourQ (ASIACRYPT 2015) for 32-bit ARM processors with NEON support. Exploiting the versatile and compact arithmetic of this curve, we design a vectorized implementation that achieves high-performance across a large variety of ARM platforms. Our software is fully protected against timing and cache attacks, and showcases the impressive speed of FourQ when compared with other curve-based alternatives. For example, one single variable-base scalar multiplication is computed in about 235,000 Cortex-A8 cycles or 132,000 Cortex-A15 cycles which, compared to the results of the fastest genus 2 Kummer and Curve25519 implementations on the same platforms, offer speedups between 1.3x-1.7x and between 2.1x-2.4x, respectively. In comparison with the NIST standard curve K-283, we achieve speedups above 4x and 5.5x.},
url = {http://approjects.co.za/?big=en-us/research/publication/fourqneon-faster-elliptic-curve-scalar-multiplications-on-arm-processors/},
number = {MSR-TR-2016-25},
}