ARMv8 SIKE: Optimized Supersingular Isogeny Key Encapsulation on ARMv8 Processors
ARMv8 SIKE: Optimized Supersingular Isogeny Key Encapsulation on ARMv8 Processors
复制标题
DOI：
10.1109/tcsi.2019.2920869
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
A. Jalali;R. Azarderakhsh;Mehran Mozaffari Kermani;Matthew J. Campagna;David Jao
中科院分区：
文献类型：
--
作者：
A. Jalali;R. Azarderakhsh;Mehran Mozaffari Kermani;Matthew J. Campagna;David Jao
在本文中，我们提出了高度优化的恒定时间的软件库，超奇异iskey封装（SIKE）协议的ARMv8处理器。我们优化的手工汇编库可在64位ARM驱动的器件上提供最高效的时序结果。此外，所提出的库可以集成到任何其他密码原语针对相同的有限字段大小。利用A64和Advanced SIMD处理器并行工作的特点，设计了一种新的基于64位ARM处理器的域运算混合实现方案。使用这些技术，我们能够提高整个协议的性能的因素相比，优化的C实现64位ARM高性能内核，提供83位，124位和159位的量子安全级别。此外，我们将我们提出的库的性能与文献中先前高度优化的ARMv8组装库进行了比较。实施结果表明，与以前的工作相比，整体性能提高了10%，突出了相对较大的有限域大小使用混合实现的好处。
In this paper, we present highly-optimized constant-time software libraries for supersingular isogeny key encapsulation (SIKE) protocol on ARMv8 processors. Our optimized hand-crafted assembly libraries provide the most efficient timing results on 64-bit ARM-powered devices. Moreover, the presented libraries can be integrated into any other cryptography primitives targeting the same finite field size. We design a new mixed implementation of field arithmetic on 64-bit ARM processors by exploiting the A64 and Advanced SIMD processing units working in parallel. Using these techniques, we are able to improve the performance of the entire protocol by the factor of $5\times $ compared to optimized C implementations on 64-bit ARM high-performance cores, providing 83-, 124-, and 159-bit quantum-security levels. Furthermore, we compare the performance of our proposed library with the previous highly-optimized ARMv8 assembly library available in the literature. The implementation results illustrate the overall 10% performance improvement in comparison with previous work, highlighting the benefit of using mixed implementation over relatively-large finite field size.