Journal Highly available systems №3 for 2018 г.
Article in number:
Programmable in high-level languages energy-efficient specialized VLSI for solving information security problems
Type of article: scientific article
DOI: 10.18127/j20729472-201803-07
UDC: 004.272.23
Authors:

S.G. Elizarov – Ph.D.(Phys.-Math.), Head of Laboratory, Physics Faculty of Lomonosov Moscow State University E-mail: elizarov@physics.msu.ru

G.A. Lukyanchenko – Ph.D.(Phys.-Math.), Research Scientist, Physics Faculty of Lomonosov Moscow State University E-mail: lukyanchenko@physics.msu.ru

D.S. Markov – Senior Research Scientist, Physics Faculty of Lomonosov Moscow State University

E-mail: markovds@maltsystem.com

A.M. Monakhov – Research Scientist, Physics Faculty of Lomonosov Moscow State University

E-mail: monahov.aleksandr@physics.msu.ru

A.D. Sizov – Research Scientist, Physics Faculty of Lomonosov Moscow State University

E-mail: anatoliy.sizov@gmail.com

V.A. Roganov – Senior Research Scientist, Institute of Mechanics of Lomonosov Moscow State University E-mail: radug-a@ya.ru

Abstract:

In this article we define and evaluate a set of requirements for custom energy-efficient programmable ASIC intended to be used in digital security applications. We discuss our practical experience of development and implementation of such ASICs using modern semiconductor technology. We present data on cryptography performance and energy efficiency of our ASICs which are already created and projected characteristics for future chips. Performance and energy efficiency values of our ASICs for hashing and stream encryption/decryption algorithms are compared against values for commercially available general purpose CPUs, GPUs and FPGAs. We conclude that our approach with development of custom programmable ASICs for cryptographic applications is viable and have several advantages over general purpose computing systems. On a number of targets, the solutions being developed are an order of magnitude superior to universal computing systems in terms of performance per watt.

Pages: 40-48
References
  1. Pirogova L.A., Grekul V.I., Poklonov B.E. Ocenka sovokupnoj stoimosti vladeniya centrom obrabotki dannyh // Biznes-informatika. 2016. S. 32−40. URL = https://bijournal.hse.ru/2016–2 (36)/186020074.html.
  2. Kurokawa M. The k computer: 10 peta-flops supercomputer // In the 10th International Conference on Optical Internet (COIN2012). 1−1. May 2012.
  3. O’Dwyer K.J., Malone D. Bitcoin mining and its energy footprint // In 25th IET Irish Signals Systems Conference 2014 and 2014 ChinaIreland International Conference on Information and Communications Technologies (ISSC 2014/CIICT 2014). 06 2014. P. 280−285.
  4. Modern Microprocessors: A 90-Minute Guide! URL = http://www.lighterra.com/papers/modernmicroprocessors/.
  5. Tarasov I.E. Razrabotka cifrovyh ustrojstv na osnove PLIS Xilinx s primeneniem yazyka VHDL. Sovremennaya ehlektronika. M.: Goryachaya liniya–Telekom. 2005. URL = https://books.google.ru/books?id=QU69AQAACAAJ.
  6. Francisco Rodriguez-Henriquez, Saqib N.A., Arturo Daz Prez, Cetin Kaya Koc Cryptographic Algorithms on Reconfigurable Hardware. Springer Publishing Company, Inc. 1st edition. 2010.
  7. Xilinx Virtex UltraScale+ FPGA VCU118 Evaluation Kit. URL = https://www.xilinx.com/products/boards-and-kits/vcu118.html.
  8. A Next-Generation Smart Contract and Decentralized Application Platform. URL = https://github.com/ethereum/wiki/wiki/White-Paper.
  9. Eitan N. Shauly Cmos leakage and power reduction in transistors and circuits: process and layout considerations // Journal of Low Power Electronics and Applications. 2012. № 2(1). P. 1−29. URL = http://www.mdpi.com/2079-9268/2/1/1.
  10. B.D. de Dinechin, Ayrignac R., Beaucamps P.E., Couvert P., Ganne B., P.G. de Massas, Jacquet F., Jones S., Chaisemartin N.M., Riss F., Strudel T. A clustered manycore processor architecture for embedded and accelerated applications // In 2013 IEEE High Performance Extreme Computing Conference (HPEC). 09 2013. P. 1−6.
  11. Manycore Architecture with Lightweight Threads. URL = https://maltsystem.ru/.
  12. Pat. RF 2018.05.21. Reg. № 2018118432/08(028834). Vychislitel'nyj modul' dlya mnogopotokovoj obrabotki cifrovyh dannyh i sposob obrabotki s ispol'zovaniem dannogo modulya / Elizarov S.G., Lukyanchenko G.A., Monahov A.M., Sizov A.D., Sovetov P.N.
  13. Kranenburg T., R. Van Leuken Mb-lite: a robust, light-weight soft-core implementation of the microblaze architecture // In 2010 Design, Automation Test in Europe Conference Exhibition (DATE 2010). 03 2010. P. 997−1000.
  14. MicroBlaze Processor Reference Guide. URL = https://www.xilinx.com/support/documentation/sw_manuals/mb_ref_guide.pdf.
  15. S fabriki TSMC polucheny pervye obrazcy mikroprocessora MALT-C 9Mb96G. URL = https://maltsystem.ru/ru/news/135-fabget.
  16. Processory MALT-C. URL = https://maltsystem.ru/ru/product/malt-processors#malt-c.
  17. Hashcat. URL = https://hashcat.net/hashcat/.
  18. Udal'cov V.A., Pavlov V.Eh. Uvelichenie skorosti raboty algoritma shifrovaniya «KUZNECHIK» s ispol'zovaniem tekhnologii CUDA // Teoriya. Praktika. Innovacii. 2017. № 4(16). S. 5−11.
  19. Kroleveckij A. Proizvoditel'nost' GOST-shifrovaniya na h86- i GPU-processorah // Storage News. 2014. 4/60. URL = http:// www.storagenews.ru/60/Code_Sec_cripto_GOST_60.pdf.
  20. John M. AES-GCM Encryption Performance on Intel® Xeon® E5 v3 Processors. URL = https://software.intel.com/en-us/articles/aesgcm-encryption-performance-on-intel-xeon-e5-v3-processors.
  21. Abdelrahman A.A., Fouad M.M., Dahshan H., Mousa A.M. High performance CUDA AES implementation: A quantitative performance analysis approach // Computing Conference. London. 2017. P. 1077−1085. URL = http://ieeexplore.ieee.org/stamp/stamp.jsp?tp= &arnumber=8252225&isnumber=8252073.
Date of receipt: 3 августа 2018 г.