A High Throughput SM2 Digital Signature Computing Scheme Based on Graphics Processing Unit Platform

ZHU Hui; HUANG Yukun; WANG Fengwei; YANG Xiaopeng; LI Hui

doi:10.11999/JEIT211049

Volume 44 Issue 12

Dec. 2022

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2022 > 44(12): 4274-4283

ZHU Hui, HUANG Yukun, WANG Fengwei, YANG Xiaopeng, LI Hui. A High Throughput SM2 Digital Signature Computing Scheme Based on Graphics Processing Unit Platform[J]. Journal of Electronics & Information Technology, 2022, 44(12): 4274-4283. doi: 10.11999/JEIT211049

Citation:

ZHU Hui, HUANG Yukun, WANG Fengwei, YANG Xiaopeng, LI Hui. A High Throughput SM2 Digital Signature Computing Scheme Based on Graphics Processing Unit Platform[J]. Journal of Electronics & Information Technology, 2022, 44(12): 4274-4283. doi: 10.11999/JEIT211049

Citation:

PDF( 2360 KB)

A High Throughput SM2 Digital Signature Computing Scheme Based on Graphics Processing Unit Platform

doi: 10.11999/JEIT211049

School of Cyber Engineering, Xidian University, Xi’an 710126, China

Funds: The National Natural Science Foundation of China (61972304, 61932015), The Natural Science Foundation of Shaanxi Province (2019ZDLGY12-02), The Technical Research Program of the Ministry of Public Security (2019JSYJA01)

Received Date: 2021-09-28
Accepted Date: 2022-03-03
Rev Recd Date: 2022-02-24

Available Online: 2022-03-09

Publish Date: 2022-12-10

Abstract

Abstract

With the pervasiveness of secure data transmission techniques and increasing requirements of information authentication, the public key-based digital signature scheme has been extensively used in various fields. However, the process speed of digital signature has gradually become the bottleneck of various security and high-concurrency applications. In this paper, a high-throughput SM2 digital signature computing scheme based on Graphics Processing Unit(GPU) platform is proposed. Firstly, the basic operations are optimized by low-level instructions of GPU. Then, according to the characteristics of GPU platform, the addition chain of SM2 recommended prime number is reduced and the speed of modular inverse operation based on Fermat's theorem is improved. Furthermore, a pre-computing table is constructed and the repeated doubling algorithm is introduced to accelerate the unknown point multiplication. Due to the construction of pre-computing table, divergence of threads can be successfully avoided. The experiments show that the proposed scheme can effectively speed up SM2 algorithm, and the throughput of signing and verification can respectively reach 76.09 million ops and 3.46 million ops on RTX3090.
- Digital signature,
- SM2,
- High throughput,
- Graphics Processing Unit(GPU)

FullText(HTML)

References(23)

References

[1]	国家密码管理局. GM/T 0003.2-2012 SM2椭圆曲线公钥密码算法第2部分: 数字签名算法[S]. 北京: 中国标准出版社, 2012. State Cryptography Administration of China. GM/T 0003.2-2012 Public key cryptographic algorithm SM2 based on elliptic curves-Part 2: Digital signature algorithm[S]. Beijing: Standards Press of China, 2012.
[2]	International Organization for Standardization. ISO/IEC 14888-3: 2018 IT security techniques - Digital signatures with appendix - Part 3: Discrete logarithm based mechanisms[S]. Geneva: ISO, 2018.
[3]	新浪科技. 阿里首席技术官程立: “双十一”的技术挑战进入新的历史阶段[EB/OL].https://tech.sina.com.cn/roll/2020-11-11/doc-iiznctke0933662.shtml, 2020. Sina Technology. Cheng Li, CTO of Alibaba: The technical challenges of "the Double Eleventh" have entered a new historical stage[EB/OL]. https://tech.sina.com.cn/roll/2020-11-11/doc-iiznctke0933662.shtml, 2020.
[4]	KOPPERMANN P, DE SANTIS F, HEYSZL J, et al. Low-latency X25519 hardware implementation: Breaking the 100 microseconds barrier[J]. Microprocessors and Microsystems, 2017, 52: 491–497. doi: 10.1016/j.micpro.2017.07.001
[5]	HUANG Junhao, LIU Zhe, HU Zhi, et al. Parallel implementation of SM2 elliptic curve cryptography on Intel processors with AVX2[C]. 25th Australasian Conference on Information Security and Privacy, Perth, Australia, 2020: 204–224.
[6]	OWENS J D, HOUSTON M, LUEBKE D, et al. GPU computing[J]. Proceedings of the IEEE, 2008, 96(5): 879–899. doi: 10.1109/JPROC.2008.917757
[7]	PAN Wuqiong, ZHENG Fangyu, ZHAO Yuan, et al. An efficient elliptic curve cryptography signature server with GPU acceleration[J]. IEEE Transactions on Information Forensics and Security, 2017, 12(1): 111–122. doi: 10.1109/TIFS.2016.2603974
[8]	SOLINAS J A. An improved algorithm for arithmetic on a family of elliptic curves[C]. 17th Annual International Cryptology Conference on Advances in Cryptology, Santa Barbara, USA, 1997: 357–371.
[9]	YAROM Y and BENGER N. Recovering OpenSSL ECDSA nonces using the FLUSH+RELOAD cache side-channel attack[J]. IACR Cryptology ePrint Archive, 2014, 2014: 140.
[10]	VAN DE POL J, SMART N P, and YAROM Y. Just a little bit more[C]. The Cryptographer’s Track at the RSA Conference, San Francisco, USA, 2015: 3–21.
[11]	ZHOU Lu, SU Chunhua, HU Zhi, et al. Lightweight implementations of NIST P-256 and SM2 ECC on 8-bit resource-constraint embedded device[J]. ACM Transactions on Embedded Computing Systems, 2019, 18(3): 23. doi: 10.1145/3236010
[12]	国家密码管理局. GM/T 0004-2012 SM3密码杂凑算法[S]. 北京: 中国标准出版社, 2012. State Cryptography Administration of China. GM/T 0004-2012 SM3 cryptographic hash algorithm[S]. Beijing: Standards Press of China, 2012.
[13]	国家密码管理局. GM/T 0004-2012 SM2椭圆曲线公钥密码算法第5部分: 参数定义[S]. 北京: 中国标准出版社, 2012. State Cryptography Administration of China. GM/T 0003.5-2012 Public key cryptographic algorithm SM2 based on elliptic curves-Part 5: Parameter definition[S]. Beijing: Standards Press of China, 2012.
[14]	ZHAO Zhenwei and BAI Guoqiang. Ultra high-speed SM2 ASIC implementation[C]. The 2014 IEEE 13th International Conference on Trust, Security and Privacy in Computing and Communications, Beijing, China, 2014: 182–188.
[15]	HU Xianghong, ZHENG Xin, ZHANG Shengshi, et al. A High-performance elliptic curve cryptographic processor of SM2 over GF(p)[J]. Electronics, 2019, 8(4): 431. doi: 10.3390/electronics8040431
[16]	RIVAIN M. Fast and regular algorithms for scalar multiplication over elliptic curves[J/OL]. IACR Cryptology ePrint Archive, 2011, 338.
[17]	Nvidia. Parallel thread execution ISA version 7.3[EB/OL]. https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#ptx-machine-mode, 2022.
[18]	SZERWINSKI R and GÜNEYSU T. Exploiting the power of GPUs for asymmetric cryptography[C]. 10th International Workshop on Cryptographic Hardware and Embedded Systems, Washington, USA, 2008: 79–99.
[19]	KOC C K, ACAR T, and KALISKI B S. Analyzing and comparing Montgomery multiplication algorithms[J]. IEEE Micro, 1996, 16(3): 26–33. doi: 10.1109/40.502403
[20]	HANKERSON D, VANSTONE S, and MENEZES A. Guide to Elliptic Curve Cryptography[M]. New York: Springer, 2004: 110–111.
[21]	DONG Jiankuo, ZHENG Fangyu, CHENG Juanjuan, et al. Towards high-performance X25519/448 key agreement in general purpose GPUs[C]. 2018 IEEE Conference on Communications and Network Security, Beijing, China, 2018: 1–9.
[22]	GAO Lili, ZHENG Fangyu, EMMART N, et al. DPF-ECC: Accelerating elliptic curve cryptography with floating-point computing power of GPUs[C]. 2020 IEEE International Parallel and Distributed Processing Symposium, New Orleans, USA, 2020: 494–504.
[23]	LEE S, SEO H, KWON H, et al. Hybrid approach of parallel implementation on CPU–GPU for high-speed ECDSA verification[J]. The Journal of Supercomputing, 2019, 75(8): 4329–4349. doi: 10.1007/s11227-019-02744-6