trudyniisiТруды НИИСИSRISA Proceedings2225-73493033-6422НИЦ «КУРЧАТОВСКИЙ ИНСТИТУТ» - НИИСИtrudyniisi-65Research ArticleПРОЕКТИРОВАНИЕ И МОДЕЛИРОВАНИЕ СБИСDESIGN AND MODELING OF VLSIПрименимость методов машинного обучения для тестирования моделей микропроцессораA Survey of the Machine Learning Methods Applicability for Microprocessor Models VerificationГревцевН. А.GrevtsevN. A.

Москва

ngrevcev@cs.niisi.ras.ruМанеркинА. Д.ManerkinA. D.

Москва

manerkin@cs.niisi.ras.ruЧибисовП. А.ChibisovP. A.

Москва

chibisov@cs.niisi.ras.ruФГУ ФНЦ НИИСИ РАНРоссия20232110202513497104Copyright © Гревцев Н.А., Манеркин А.Д., Чибисов П.А., 20252025Гревцев Н.А., Манеркин А.Д., Чибисов П.А.Grevtsev N.A., Manerkin A.D., Chibisov P.A.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.t-niisi.ru/jour/article/view/65

В статье приведен обзор использования методов машинного обучения для различных направлений функциональной верификации. Рассматривается использование машинного обучения в «presilicon» верификации, а именно в имитационном тестировании и верификации при помощи UVM. Приводится обзор в области «post-silicon» верификации. Делается вывод об основных областях применения машинного обучения, а также о возможных будущих направлениях исследований.

The article provides an overview about the using machine learning methods in various areas of functional verification. We consider the use of machine learning in "pre-silicon" verification, precisely in simulation-based verification and Universal Verification Methodology. Then we discuss the field of "post-silicon" verification. The main decision was made in conclusion about the main areas of machine learning applications, as well as possible future directions of research.

верификация микропроцессоровмашинное обучениеDeep LearningUVMmicroprocessor verificationmachine learningDeep LearningUVMПубликация выполнена в рамках государственного задания ФГУ ФНЦ НИИСИ РАН по теме № FNEF-2022-0004.ReferencesКамкин, А. С. Метод автоматизации имитационного тестирования микропроцессоров с конвейерной архитектурой на основе формальных спецификаций, диссертация на соискание ученой степени кандидата физико-математических наук; Федеральное государственное бюджетное учреждение науки Институт системного программирования им. В. П. Иванникова Российской академии наук. — Москва, 2009. — 181 c.Камкин, А. С. Метод автоматизации имитационного тестирования микропроцессоров с конвейерной архитектурой на основе формальных спецификаций, диссертация на соискание ученой степени кандидата физико-математических наук; Федеральное государственное бюджетное учреждение науки Институт системного программирования им. В. П. Иванникова Российской академии наук. — Москва, 2009. — 181 c.Hughes, William & Srinivasan, Sandeep & Suvarna, Rohit & Kulkarni, Maithilee. (2019). Optimizing Design Verification using Machine Learning: Doing better than Random.Hughes, William & Srinivasan, Sandeep & Suvarna, Rohit & Kulkarni, Maithilee. (2019). Optimizing Design Verification using Machine Learning: Doing better than Random.K. H. Mami Miyamoto, Finding effective simulation patterns for coverage-driven verification using deep learning, in: SASIMI 2016 Proceedings, 2016, pp. 335–340.K. H. Mami Miyamoto, Finding effective simulation patterns for coverage-driven verification using deep learning, in: SASIMI 2016 Proceedings, 2016, pp. 335–340.A.S. Jagadeesh Accelerating coverage closure for hardware verification using machine learning, Master thesis, 2019, Texas A&M UniversityA.S. Jagadeesh Accelerating coverage closure for hardware verification using machine learning, Master thesis, 2019, Texas A&M UniversityDanciu, Gabriel Mihail, and Alexandru Dinu. 2022. "Coverage Fulfillment Automation in Hardware Functional Verification Using Genetic Algorithms" Applied Sciences 12, no. 3: 1559. https://doi.org/10.3390/app12031559Danciu, Gabriel Mihail, and Alexandru Dinu. 2022. "Coverage Fulfillment Automation in Hardware Functional Verification Using Genetic Algorithms" Applied Sciences 12, no. 3: 1559. https://doi.org/10.3390/app12031559S. L. Tweehuysen, G. L. A. Adriaans and M. Gomony, "Stimuli Generation for IC Design Verification using Reinforcement Learning with an Actor-Critic Model," 2023 IEEE European Test Symposium (ETS), Venezia, Italy, 2023, pp. 1-4, doi: 10.1109/ETS56758.2023.10174129.S. L. Tweehuysen, G. L. A. Adriaans and M. Gomony, "Stimuli Generation for IC Design Verification using Reinforcement Learning with an Actor-Critic Model," 2023 IEEE European Test Symposium (ETS), Venezia, Italy, 2023, pp. 1-4, doi: 10.1109/ETS56758.2023.10174129.Mammo, Biruk. (2017). Reining in the Functional Verification of Complex Processor Designs with Automation, Prioritization, and Approximation.Mammo, Biruk. (2017). Reining in the Functional Verification of Complex Processor Designs with Automation, Prioritization, and Approximation.Chen, W. (2014). Data Learning Methodologies for Improving the Efficiency of Constrained Random Verification. UC Santa Barbara. ProQuest ID: Chen_ucsb_0035D_12213. Merritt ID: ark:/13030/m5sv2nkc. Retrieved from https://escholarship.org/uc/item/0db4j3jpChen, W. (2014). Data Learning Methodologies for Improving the Efficiency of Constrained Random Verification. UC Santa Barbara. ProQuest ID: Chen_ucsb_0035D_12213. Merritt ID: ark:/13030/m5sv2nkc. Retrieved from https://escholarship.org/uc/item/0db4j3jpAggoune M. (2022) Acceleration of Hardware Code Coverage Closure Using Machine Learning. University of Oulu, Degree Programme in Computer Science and Engineering, 56 p.Aggoune M. (2022) Acceleration of Hardware Code Coverage Closure Using Machine Learning. University of Oulu, Degree Programme in Computer Science and Engineering, 56 p.G. Parthasarathy et al., "RTL Regression Test Selection using Machine Learning," 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC), Taipei, Taiwan, 2022, pp. 281-287, doi: 10.1109/ASP-DAC52403.2022.9712550.G. Parthasarathy et al., "RTL Regression Test Selection using Machine Learning," 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC), Taipei, Taiwan, 2022, pp. 281-287, doi: 10.1109/ASP-DAC52403.2022.9712550.N. Bruns, V. Herdt, E. Jentzsch and R. Drechsler, "Cross-Level Processor Verification via Endless Randomized Instruction Stream Generation with Coverage-guided Aging," 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), Antwerp, Belgium, 2022, pp. 1123-1126, doi: 10.23919/DATE54114.2022.9774771.N. Bruns, V. Herdt, E. Jentzsch and R. Drechsler, "Cross-Level Processor Verification via Endless Randomized Instruction Stream Generation with Coverage-guided Aging," 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), Antwerp, Belgium, 2022, pp. 1123-1126, doi: 10.23919/DATE54114.2022.9774771.Wang, F.; Zhu, H.; Popli, P.; Xiao, Y.; Bodgan, P.; Nazarian, S. Accelerating Coverage Directed Test Generation for Functional Verification: A Neural Network-Based Framework. In Proceedings of the Great Lakes Symposium on VLSI, ACM, New York, NY, USA, 23–25 May 2018; pp. 207–212.Wang, F.; Zhu, H.; Popli, P.; Xiao, Y.; Bodgan, P.; Nazarian, S. Accelerating Coverage Directed Test Generation for Functional Verification: A Neural Network-Based Framework. In Proceedings of the Great Lakes Symposium on VLSI, ACM, New York, NY, USA, 23–25 May 2018; pp. 207–212.Dinu, A.; Ogrutan, P.L. Opportunities of using artificial intelligence in hardware verification. In Proceedings of the 2019 IEEE 25th International Symposium for Design and Technology in Electronic Packaging (SIITME), Cluj-Napoca, Romania, 23 October 2019; pp. 224–227.Dinu, A.; Ogrutan, P.L. Opportunities of using artificial intelligence in hardware verification. In Proceedings of the 2019 IEEE 25th International Symposium for Design and Technology in Electronic Packaging (SIITME), Cluj-Napoca, Romania, 23 October 2019; pp. 224–227.Gogri, S.; Hu, J.; Tyagi, A.; Quinn, M.; Ramachandran, S.; Batool, F.; Jagadeesh, A. Machine Learning-Guided Stimulus Generation for Functional Verification. In Proceedings of the Design and Verification Conference (DVCON-USA), Virtual Conference, 2–5 March 2020.Gogri, S.; Hu, J.; Tyagi, A.; Quinn, M.; Ramachandran, S.; Batool, F.; Jagadeesh, A. Machine Learning-Guided Stimulus Generation for Functional Verification. In Proceedings of the Design and Verification Conference (DVCON-USA), Virtual Conference, 2–5 March 2020.Fajcik, M.; Smrz, P.; Zachariasova, M. Automation of Processor Verification Using Recurrent Neural Networks. In Proceedings of the 2017 18th International Workshop on Microprocessor and SOC Test and Verification (MTV), Austin, TX, USA, 11–12 December 2017; pp. 15–20.Fajcik, M.; Smrz, P.; Zachariasova, M. Automation of Processor Verification Using Recurrent Neural Networks. In Proceedings of the 2017 18th International Workshop on Microprocessor and SOC Test and Verification (MTV), Austin, TX, USA, 11–12 December 2017; pp. 15–20.Truong, A.; Hellstrom, D.; Duque, H.; Viklund, L. Clustering and Classification of UVM Test Failures Using Machine Learning Techniques. In Proceedings of the Design and Verification Conference (DVCON), San Jose, CA, USA, 26 February–1 March 2018.Truong, A.; Hellstrom, D.; Duque, H.; Viklund, L. Clustering and Classification of UVM Test Failures Using Machine Learning Techniques. In Proceedings of the Design and Verification Conference (DVCON), San Jose, CA, USA, 26 February–1 March 2018.A. DeOrio, Q. Li, M. Burgess and V. Bertacco, "Machine learning-based anomaly detection for post-silicon bug diagnosis," 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 2013, pp. 491-496, doi: 10.7873/DATE.2013.112.A. DeOrio, Q. Li, M. Burgess and V. Bertacco, "Machine learning-based anomaly detection for post-silicon bug diagnosis," 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 2013, pp. 491-496, doi: 10.7873/DATE.2013.112.Mandouh, Ema & Wassal, Amr. Application of Machine Learning Techniques in Post-Silicon Debugging and Bug Localization. Journal of Electronic Testing, 2018, 34. 1-19. 10.1007/s10836-018-5716-y.Mandouh, Ema & Wassal, Amr. Application of Machine Learning Techniques in Post-Silicon Debugging and Bug Localization. Journal of Electronic Testing, 2018, 34. 1-19. 10.1007/s10836-018-5716-y.

The authors declare that there are no conflicts of interest present.