橢圓曲線密碼處理器的高效并行處理架構(gòu)研究與設計
doi: 10.11999/JEIT161380
-
1.
(解放軍信息工程大學 鄭州 450000) ②(復旦大學專用集成電路與系統(tǒng)國家重點實驗室 上海 201203)
基金項目:
國家自然科學基金(61404175)
Research and Design of Efficient Parallel Processing Architecture for Elliptic Curve Cryptographic Processor
-
1.
(PLA Information Engineering University, Zhengzhou 450000, China)
Funds:
The National Natural Science Foundation of China (61404175)
-
摘要: 為了解決當前橢圓曲線密碼處理器普遍存在靈活性低、資源占用大的問題,該文采用統(tǒng)計建模的方式,以面積-時間(AT)綜合性能指標為指導,提出了一種面向橢圓曲線密碼并行處理架構(gòu)的量化評估方式,并確定3路異構(gòu)并行處理架構(gòu)可使處理器綜合性能達到最優(yōu)。其次,該文提出一個分離分級式存儲結(jié)構(gòu)和一個運算資源高度復用的模運算單元,可增強存儲器的訪問效率和運算資源的利用率。在90 nm CMOS工藝下綜合,該文處理器的面積為1.62mm2,完成一次GF(2571)和GF(p521)上的點乘運算分別需要2.26 ms/612.4J和2.63 ms/665.4J。與同類設計相比,該文處理器不僅具有較高的靈活性、可伸縮性,而且其芯片面積和運算速度達到了很好的折中。
-
關(guān)鍵詞:
- 橢圓曲線密碼 /
- 并行處理架構(gòu) /
- 量化評估 /
- 分離分級式存儲結(jié)構(gòu) /
- 資源復用
Abstract: To overcome the common problem of low flexibility and much resource in Elliptic Curve Cryptographic (ECC) processor, a quantitative evaluation on Area-Time product (AT) for parallel processing architecture of ECC processor is proposed by statistics and modeling, and a conclusion that 3-way processing architecture is optimal can be drawn. Besides, a separated and hierarchical storage structure is exploited to strengthen the efficiency of data interaction. At the same time, a modular arithmetic unit is designed with a high level of resource reuse. Using 90 nm CMOS technology, the proposed processor occupied1.62mm2 can perform the scalar multiplication in2.26 ms/612.4J overGF(2571) and 2.63 ms/665.4 J overGF(p521), respectively. Compared to other works, this processor is advantageous not only in flexibility and scalability but also in making a good compromise between the hardware and the speed. -
EBRAHIM A and ARASH R. New regular radix-8 scheme for elliptic curve scalar multiplication without pre-computation [J]. IEEE Transactions on Computaters, 2008, 64(2): 438-451. doi: 10.1109/TC.2013.213. KHAN A and BENAISSA M. High-speed and low-latency ECC processor implementation over on FPGA[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017, 25(1): 165-176. doi: 10.1109/TVLSI.2016. 2574620. YANG Xiaohui, DAI Zibin, ZHANG Jun, et al. ASIP for elliptic curve cryptography based on VLIW architecture[J]. China Communications, 2010, 7(4): 161-165. LIAO Kai, CUI Xiaoxin, LIAO Nan, et al. High-performance noninvasive side-channel attack resistant ECC coprocessor for [J]. IEEE Transactions on Industrial Electronics, 2017, 64(1): 727-738. doi: 10.1109/TIE.2016.2610402. LAI J and HUANG C. Energy-adaptive dual-field processor for high-performance elliptic curve cryptographic application [J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2011, 19(8): 1512-1517. doi: 10.1109/TVLSI.2010. 2048134. AZARDERAKHSH R and REYHANI A. High-performance implementation of point multiplication on koblitz curves[J]. IEEE Transactions on Circuits and Systems-II: Express Briefs, 2013, 60(1): 41-45. doi: 10.1109/TCSII.2012.2234916. LIU Zhe, SEO H, GROBSCHADL J, et al. Efficient implementation of NIST-Compliant elliptic curve cryptography for 8-bit AVR-Based sensor nodes[J]. IEEE Transaction on Information Forensics and Security, 2016, 11(7): 1385-1397. doi: 10.1007/978-3-319-02726-5_22. AZARDERAKHSH R, JARVINEN K U, MOZAFFARI- KERMANI M, et al. Efficient algorithm and architecture for elliptic curve cryptography for extremely constrained secure applications[J]. IEEE Transactions on Circuits and Systems-I: Regular Papers, 2014, 61(4): 1144-1155. doi: 10.1109/TCSI. 2013.2283691. 楊曉輝, 戴紫彬, 李淼, 等. 面向橢圓曲線密碼的處理器并行體系結(jié)構(gòu)研究與設計[J]. 通信學報, 2011, 32(5): 70-77. doi: 10.3969/j.issn.1000-436X.2011.05.010. YANG Xiaohui, DAI Zibin, LI Miao, et al. Research and design of parallel architecture processor for elliptic curve cryptography[J]. Journal on Communications, 2011, 32(5): 70-77. doi: 10.3969/j.issn.1000-436X.2011.05.010. AZARDERAKHSH R and REYHANI-MASOLEH A. Parallel and high-speed computations of elliptic curve cryptography using hybrid-double multipliers[J]. IEEE Transactions on Parallel and Distributed Systems, 2015, 26(6): 1668-1677. doi: 10.1109/TPDS.2014.2323062. MARZOUQI H, MAHMOUD A, SALAH K, et al. A high- speed FPGA implementation of an RSD-Based ECC processor[J]. IEEE Transactions on Very Large Scale Integration (VLSI) System, 2016, 24(1): 151-164. doi: 10. 1109/TVLSI.2015.2391274. 馮曉, 戴紫彬, 李偉, 等. 基于 Amdahl 定律的多核密碼處理器性能模型研究[J]. 電子與信息學報, 2016, 38(4): 827-833. doi: 10.11999/JEIT150474. FENG Xiao, DAI Zibin, LI Wei, et al. Performance model of multicore crypto processor based on amdahls law[J]. Journal of Electronics Information Technology, 2016, 38(4): 827-833. doi: 10.11999/JEIT150474. WONG C and CHANG H. High-efficiency processing schedule for parallel turbo decoders using QPP interleaver[J]. IEEE Transactions on Circuits and System, 2011, 58(6): 1412-1420. doi: 10.1109/TCSI.2010.2097690. KALISKI B. The Montgomery inverse and its applications[J]. IEEE Transactions on Computers, 1995, 44(8): 1064-1065. doi: 10.1109/12.403725. LIU Bin and BAAS B M. Parallel AES encryption engines for many-core processor arrays[J]. IEEE Transactions on Computers, 2013, 62(3): 536-547. doi: 10.1109/TC.2011.251. FURBASS F and WOLKERSTORFER J. ECC processor with low die size for RFID applications[C]. IEEE International Symposium on Circuits and Systems, New Orleans, 2007: 1835-1838. doi: 10.1109/ISCAS.2007.378271. HONG Jinhua and WU Weichung. The design of high performance elliptic curve cryptographic[C]. IEEE International Symposium on Circuits and Systems, Cancun, 2009: 527-530. doi: 10.1109/MWSCAS.2009.5236038. LEE J, CHUNG S, CHANG H, et al. A 3.40 ms/ and 2.77 ms/ DF-ECC processor with side-channel attack resistance[C]. 2013 IEEE International Solid-State Circuits Conference, California, 2013: 50-52. doi: 10.1109/ ISSCC.2013.6487632. -
計量
- 文章訪問數(shù): 1345
- HTML全文瀏覽量: 133
- PDF下載量: 229
- 被引次數(shù): 0