Research on Multi-Core Processor Analysis for WCET Estimation

doi:10.12142/ZTECOM.202401010

ZTE Communications ›› 2024, Vol. 22 ›› Issue (1): 87-94.DOI: 10.12142/ZTECOM.202401010

收稿日期:2023-06-21 出版日期:2024-03-29 发布日期:2024-03-28

Research on Multi-Core Processor Analysis for WCET Estimation

LUO Haoran¹, HU Shuisong¹, WANG Wenyong¹(), TANG Yuke², ZHOU Junwei²

^1.University of Electronic Science and Technology of China, Chengdu 611731, China
^2.ZTE Corporation, Shenzhen 518057, China

Received:2023-06-21 Online:2024-03-29 Published:2024-03-28
About author:LUO Haoran received his bachelor's degree from Sichuan University, China. He is pursuing a master's degree at University of Electronic Science and Technology of China (UESTC). Driven by a deep passion for computer science, he actively engages in various academic activities and research projects.
HU Shuisong received his bachelor's degree from University of Electronic Science and Technology of China (UESTC). He is pursuing a master's degree at UESTC. He actively engages in research and exploration in various areas, including computer networks and operation system.
WANG Wenyong (wangwy@uestc.edu.cn) is a professor at the School of Computer Science, University of Electronic Science and Technology of China (UESTC). He is an IEEE member and a senior member of the China Computer Federation (CCF). He serves as a member of the CCF Information Network, Software Engineering, and High-Performance Computing committees, a council member of the China Internet Association, a member of the Expert Committee of China Education and Research Computer Network (CERNET), and a member of the Expert Committee of China Next Generation Internet (CNGI). He is also a member of the Ministry of Education's Next Generation Internet Technology Innovation Team and serves on the Technical Committee of the National Engineering Laboratory for Next Generation Internet Core Network at Tsinghua University, China. His research interests include computer networks and data sharing and exchange.
TANG Yuke is currently working at the tool support project team of the Department of Operating System Products, ZTE Corporation. He is mainly engaged in compilation, debugging, performance tuning and defect detection of operating systems.
ZHOU Junwei graduated from Southwest JiaoTong University, China, with a major in computer science and joined ZTE Corporation in 2022. He is currently working at the Department of Operation System Products and mainly responsible for the development of WCET tools.
Supported by:
ZTE Industry?University?Institute Cooperation Funds(2022ZTE09)

摘要/Abstract

Abstract:

Real-time system timing analysis is crucial for estimating the worst-case execution time (WCET) of a program. To achieve this, static or dynamic analysis methods are used, along with targeted modeling of the actual hardware system. This literature review focuses on calculating WCET for multi-core processors, providing a survey of traditional methods used for static and dynamic analysis and highlighting the major challenges that arise from different program execution scenarios on multi-core platforms. This paper outlines the strengths and weaknesses of current methodologies and offers insights into prospective areas of research on multi-core analysis. By presenting a comprehensive analysis of the current state of research on multi-core processor analysis for WCET estimation, this review aims to serve as a valuable resource for researchers and practitioners in the field.

Key words: real-time system, worst-case execution time (WCET), multi-core analysis

. [J]. ZTE Communications, 2024, 22(1): 87-94.

LUO Haoran, HU Shuisong, WANG Wenyong, TANG Yuke, ZHOU Junwei. Research on Multi-Core Processor Analysis for WCET Estimation[J]. ZTE Communications, 2024, 22(1): 87-94.

图/表 5

参考文献 30

1	LYU M S, GUAN N, ZHANG Y, et al. A survey of WCET analysis of real-time operating systems [C]//Proc. International Conference on Embedded Software and Systems. IEEE, 2009: 65–72. DOI: 10.1109/ICESS.2009.24
2	LYU M S. Research on worst-case execution time analysis techniques of real-time systems [D]. Shenyang: Northeastern University, 2010
3	HECKMANN R, LANGENBACH M, THESING S, et al. The influence of processor architecture on the design and the results of WCET tools [J]. Proceedings of the IEEE, 2003, 91(7): 1038–1054. DOI: 10.1109/JPROC.2003.814618
4	LI X F, ROYCHOUDHURY A, MITRA T. Modeling out-of-order processors for WCET analysis [J]. Real-time systems, 2006, 34(3): 195–227. DOI: 10.1007/s11241-006-9205-5
5	YAN J, ZHANG W. WCET analysis for multi-core processors with shared L2 instruction caches [C]//Proc. IEEE Real-Time and Embedded Technology and Applications Symposium. IEEE, 2008: 80–89. DOI: 10.1109/RTAS.2008.6
6	LYU M, YI W, GUAN N, et al. Combining abstract interpretation with model checking for timing analysis of multicore software [C]//31st IEEE Real-Time Systems Symposium. IEEE, 2010: 339–349. doi: 10.1109/RTSS.2010.30 .
7	ZHU Y A, SHI X C, YAO Y, et al. A WCET analysis method for multi-core processors with multi-tier coherence protocol [J]. Journal of computer research and development, 2023, 60(1): 30–42. DOI: 10.7544/issn1000-1239.202111244
8	CHATTOPADHYAY S, ROYCHOUDHURY A, MITRA T. Modeling shared cache and bus in multi-cores for timing analysis [C]//Proc. 13th International Workshop on Software & Compilers for Embedded Systems. ACM, 2010: 1–10. DOI: 10.1145/1811212.1811220
9	KELTER T, FALK H, MARWEDEL P, et al. Bus-aware multicore WCET analysis through TDMA offset bounds [C]//Proc. 23rd Euromicro Conference on Real-Time Systems. IEEE, 2011: 3–12. DOI: 10.1109/ECRTS.2011.9
10	DEVERGE J F, PUAUT I. Safe measurement-based WCET estimation [C]//5th International Workshop on Worst-Case Execution Time Analysis (WCET'05). OASICS, 2007: 13–16. DOI: 10.4230/OASICS.WCET.2005.808
11	RIEDER B, WENZEL I, STEINHAMMER K, et al. Using a runtime measurement device with measurement-based WCET analysis [C]//Embedded System Design: Topics, Techniques and Trends, Proc. of IFIP TC10 Working Conference: International Embedded Systems Symposium (IESS). Springer, 2007: 15–26. DOI:10.1007/978-0-387-72258-0_2
12	WENZEL I, RIEDER B, KIRNER R, et al. Automatic timing model generation by CFG partitioning and model checking [C]//Design, Automation and Test in Europe. IEEE, 2005: 606-611. DOI: 10.1109/DATE.2005.76
13	DASARI D, NELIS V. An analysis of the impact of bus contention on the WCET in multicores [C]//Proc. IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems. IEEE, 2012: 1450–1457. DOI: 10.1109/HPCC.2012.212
14	CHATTOPADHYAY S, ROYCHOUDHURY A. Unified cache modeling for WCET analysis and layout optimizations [C]//Proc. 30th IEEE Real-Time Systems Symposium. IEEE, 2009: 47–56. DOI: 10.1109/RTSS.2009.20
15	PUSCHNER P, BURNS A. Guest editorial: a review of worst-case execution-time analysis [J]. Real-time systems, 2000, 18(2): 115–128. DOI: 10.1023/A: 1008119029962
16	THEILING H, FERDINAND C, WILHELM R. Fast and precise WCET prediction by separated cache and path analyses [J]. Real-time systems, 2000, 18(2): 157–179. DOI: 10.1023/A: 1008141130870
17	LI X F, LIANG Y, MITRA T, et al. Chronos: a timing analyzer for embedded software [J]. Science of computer programming, 2007, 69(1/2/3): 56–67
18	HUYNH B K, JU L, ROYCHOUDHURY A. Scope-aware data cache analysis for WCET estimation [C]//Proc. 17th IEEE Real-Time and Embedded Technology and Applications Symposium. IEEE, 2011: 203–212. DOI: 10.1109/RTAS.2011.27
19	LIANG Y, DING H P, MITRA T, et al. Timing analysis of concurrent programs running on shared cache multi-cores [J]. Real-time systems, 2012, 48(6): 638–680. DOI: 10.1007/s11241-012-9160-2
20	CHEN F Y, ZHANG D S, WANG Z Y. Static analysis of Run-time inter-thread interferences in shared cache multi-core architectures based on instruction fetching timing [C]//Proc. IEEE International Conference on Computer Science and Automation Engineering. IEEE, 2011: 208–212. DOI: 10.1109/CSAE.2011.5952455
21	CHEN F Y, ZHANG D S, WANG Z Y. Static analysis of run-time inter-core interferences for concurrent programs in shared cache multicore architectures [J]. Applied mechanics and materials, 2012, 198/199: 523–527. DOI: 10.4028/www.scientific.net/AMM.198-199.523
22	CHATTOPADHYAY S, CHONG L K, ROYCHOUDHURY A, et al. A unified WCET analysis framework for multicore platforms [J]. ACM transactions on embedded computing systems, 13(4s): 124. DOI: 10.1145/2584654
23	DAVIS R I, CUCU-GROSJEAN L. A survey of probabilistic timing analysis techniques for real-time systems [J]. Leibniz Transactions on Embedded Systems (LITES), 2019, 6(1): 03:1–03:60. DOI: 10.4230/LITES-v006-i001-a003
24	AbsInt. aiT [EB/OL]. [2023-01-17].
25	Systems Rapita. Rapitime [EB/OL]. [2023-01-17].
26	XMOS Ltd. XMOS [EB/OL]. [2023-01-17].
27	National University of Singapore. Chronos [EB/OL]. [2023-01-17].
28	Ltd Tidorum. Bound-T execution time analyzer [EB/OL]. [2023-01-17].
29	team IRISA. Heptane [EB/OL]. [2023-01-17].
30	MRTC. Swedish execution time analysis tool [EB/OL]. [2023-01-17].

Comparative Content	Static WCET Analysis	Dynamic WCET Analysis
Safety of analysis results	Safe	Unsafe
Analysis complexity	High	Low
Adaptability to new architectures	Bad	Good
Analytical accuracy	Mainly depending on the analysis technique	Mainly depending on the test vector
User assistance that improves the quality of analysis	Providing additional control flow information	Providing better test vectors

Comparative Content	Static WCET Analysis	Dynamic WCET Analysis
Safety of analysis results	Safe	Unsafe
Analysis complexity	High	Low
Adaptability to new architectures	Bad	Good
Analytical accuracy	Mainly depending on the analysis technique	Mainly depending on the test vector
User assistance that improves the quality of analysis	Providing additional control flow information	Providing better test vectors

Comparative Content	Analysis Based on Address Mapping	Analysis Based on Logical Order	Analysis Based on Model Checking	Analysis Based on Time Series Category
Analysis accuracy	Low	Higher	High	High
Analysis complexity	Low	High	High	Higher
Analytical method	Address mapping analysis	Cache conflict graph and logic analysis	Time automaton	Block-based temporal modeling

Comparative Content	Analysis Based on Address Mapping	Analysis Based on Logical Order	Analysis Based on Model Checking	Analysis Based on Time Series Category
Analysis accuracy	Low	Higher	High	High
Analysis complexity	Low	High	High	Higher
Analytical method	Address mapping analysis	Cache conflict graph and logic analysis	Time automaton	Block-based temporal modeling

Tool	Company	Method	Target Processors	Core Area
Tool	Company	Method	Target Processors	Cache	Pipeline	Periphery
aiT	AbsInt	Static analysis	Am486, IntelDX4, ARM, PowerPC, etc.	I-Cache, D-Cache, direct/SA, LRU, PLRU, pseudo round robin	In-order/ out-of-order	PCI bus
RapiTime	Rapita Systems	Hybrid-based	-	-	-	-
XMOS Timing Analyzer	XMOS Ltd.	Measurement-based	XMOS processors	-	-	-

Research on Multi-Core Processor Analysis for WCET Estimation

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 30

相关文章 0

编辑推荐

Metrics

Tool	Institution	Method	Target Processors	Core Area
Tool	Institution	Method	Target Processors	Cache	Pipeline	Periphery
Chronos	National University of Singapore	Static analysis	SimpleScalar	I-cache, D-cache, Unified cache, Direct/SA, LRU	Multi-issue superscalar, in-order, out-order, dynamic branch prediction
Bound-T	Tidorum	Static analysis	SPARC/ERC32, etc.	-	-	IPET
Heptane	IRISA	Static analysis	-	D-cache, I-cache,	Branch prediction
SWEET	Mälardalen Real-Time Research Centre	Static analysis	NECV850E ARM9	-	-	Flow analysis