Towards Order-Preserving and Zero-Copy Communication on Shared Memory for Large Scale Simulation

LI Xiuhe; SHEN Yang; LIN Zhongwei; ZHAO Shunkai; SHI Qianqian; DAI Shaoqi

doi:10.23919/cje.2021.00.393

Volume 32 Issue 5

Sep. 2023

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2023 > 32(5): 1066-1076

LI Xiuhe, SHEN Yang, LIN Zhongwei, et al., “Towards Order-Preserving and Zero-Copy Communication on Shared Memory for Large Scale Simulation,” Chinese Journal of Electronics, vol. 32, no. 5, pp. 1066-1076, 2023, doi: 10.23919/cje.2021.00.393

Citation:

LI Xiuhe, SHEN Yang, LIN Zhongwei, et al., “Towards Order-Preserving and Zero-Copy Communication on Shared Memory for Large Scale Simulation,” Chinese Journal of Electronics, vol. 32, no. 5, pp. 1066-1076, 2023, doi: 10.23919/cje.2021.00.393

Citation:

PDF( 3619 KB)

Towards Order-Preserving and Zero-Copy Communication on Shared Memory for Large Scale Simulation

doi: 10.23919/cje.2021.00.393

1.
College of Electronic Engineering, National University of Defense Technology, Hefei 230031, China

Funds: This work was supported by the National Natural Science Foundation of China (61802422)

More Information

Author Bio:
Xiuhe LI was born in 1975. He received the Ph.D. degree in electronic engineering from The PLA Electronic Engineering Institute. He is a Professor of National University of Defense Technology (NUDT). His current research interests include theoretical innovation and application of electromagnetic environment, computational system confrontation simulation and effectiveness evaluation, and multisource sensor information fusion technology. (Email: xhli75@163.com)

Yang SHEN was born in 1978. He received the Ph.D. degree in Operational Research from The PLA Electronic Engineering Institute. He is an associate professor of National University of Defense Technology. His research interests include modelling and simulation of electromagnetic environment and test evaluation. (Email: eeishy@163.com)

Zhongwei LIN (corresponding author) received the B.S., M.S. and Ph.D. degrees in computer science and technology from NUDT in 2009, 2011 and 2016 respectively, and visited the Department of Computer Science of McGill University, Montreal, Canada as joint Ph.D. candidate from 2013 to 2015. He is a Lecturer with College of Electronic Engineering, NUDT. His research interests include computer simulation, high performance computing, and artificial intelligence. (Email: zwlin@nudt.edu.cn)

Shunkai ZHAO was born in 1987. He received the B.E degree in network engineering and M.S. degree in military science from Electronic Engineering Institue of PLA. His research interests include simulation and electronmagnetism. (Email: 364393242@qq.com)

Qianqian SHI was born in 1996. She received the M.S. degree in electromagnetic field from Army Engineering University of PLA, China. Her research interests include dynamic spectrum management and reinforcement learning. (Email: 1974604993@qq.com)

Shaoqi DAI was born in Hefei, China. He received the B.E. and M.S. degrees in electronic engineering from National University of Defense Technology, Changsha, China. His research interests include information and communication engineering and complex electromagnetic environment. (Email: daishaoqi12@nudt.edu.cn)
Received Date: 2021-11-09
Accepted Date: 2022-02-11

Available Online: 2022-07-25

Publish Date: 2023-09-05

Abstract

Abstract

Parallel simulation generally needs efficient, reliable and order-preserving communication. In this article, a zero-copy, reliable and order-preserving intra-node message passing approach named ZeROshm is proposed. This mechanism partitions shared memory into segments assigned to processes for receiving messages. Each segment consists of two levels of index L1 and L2 that recordes the order of messages in the host segment, and the processes also read from and write to the segments directly according to the indexes, thereby eliminating allocating and copying buffers. As experimental results show, ZeROshm exhibits nearly equivalent performance to message passing interface (MPI) for small message and superior performance for large message. Specifically, ZeROshm costs less time by 43%, 40% and 55% respectively in pure communication, communication with contention and real PHOLD simulation within a single node. Additionally, in hybrid environment, the combination of ZeROshm and MPI also shorten the execution time of PHOLD simulation by about 42% compared to pure MPI.
- Zero-copy,
- Order-preserving,
- Shared memory,
- Parallel simulation,
- Message passing interface,
- Interprocess communicaton

FullText(HTML)

References(18)

References

[1]	Z. W. Lin, C. Tropper, M. N. I. Patoary, et al., “NTW-MT: A multi-threaded simulator for reaction diffusion simulations in neuron,” in Proceedings of the 3rd ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, New York, NY, USA, pp.157–167, 2015.
[2]	Z. W. Lin, C. Tropper, R. A. McDougal, et al., “Multithreaded stochastic PDES for reactions and diffusions in neurons,” ACM Transactions on Modeling and Computer Simulation, vol.27, no.2, article no.7, 2016. doi: 10.1145/2987373
[3]	W. J. Tang, Y. P. Yao, and F. Zhu, “A hierarchical parallel discrete event simulation kernel for multicore platform,” Cluster Computing, vol.16, no.3, pp.379–387, 2013. doi: 10.1007/s10586-012-0201-3
[4]	D. Jagtap, N. Abu-Ghazaleh, and D. Ponomarev, “Optimization of parallel discrete event simulator for multi-core systems,” in Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium, Shanghai, China, pp.520–531, 2012.
[5]	T. Hoefler, J. Dinan, D. Buntinas, et al., “Leveraging MPI’s one-sided communication interface for shared-memory programming,” in Recent Advances in the Message Passing Interface, J. L. Träff, S. Benkner, and J. J. Dongarra, Eds. Springer, Berlin, Heidelberg, pp.132–141, 2012.
[6]	A. Venkataraman and K. K. Jagadeesha, “Evaluation of inter-process communication mechanisms,” Technical. report, Department of Computer Science, University of Wisconsin-Madison, 2015. http://pages.cs.wisc.edu/~adityav/Evaluation_of_Inter_Process_Communication_Mechanisms.pdf
[7]	D. Kranz, K. Johnson, A. Agarwal, J. et al., “Integrating message-passing and shared-memory: Early experience,” ACM SIGPLAN Notices, vol.28, no.7, pp.54–63, 1993. doi: 10.1145/173284.155338
[8]	P. L. Aublin, S. Ben Mokhtar, C. L. Gilles, et al., “ZIMP: Efficient inter-core communications on manycore machines,” Technical report, Grenoble University, 2011. http://lig-membres.imag.fr/aublin/zimp/zimp_TR.pdf
[9]	M. Li, “Research and implement on adaptive communication mechanism of high-performance RTI,” Master thesis, Nat. Univ. Defense Technol., Changsha, China, 2011. (in Chinese)
[10]	R. M. Fujimoto, Parallel and Distribution Simulation Systems. John Wiley & Sons, Inc., New York, NY, USA, 1999.
[11]	T. Hoefler and S. Gottlieb, “Parallel zero-copy algorithms for fast fourier transform and conjugate gradient using MPI datatypes,” in Recent Advances in the Message Passing Interface, R. Keller, E. Gabriel, M. Resch, et al., Eds. Springer, Berlin, Heidelberg, pp.132–141, 2010.
[12]	M. P. Forum, MPI: A Message-Passing Interface Standard, University of Tennessee, Hall Knoxville, TN, USA, 2021.
[13]	X. M. Zhu, J. C. Zhang, K. Yoshii, et al., “Analyzing MPI-3.0 process-level shared memory: A case study with stencil computations,” in 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, Shenzhen, China, pp.1099–1106, 2015.
[14]	B. P. Swenson and G. F. Riley, “A new approach to zero-copy message passing with reversible memory allocation in multi-core architectures,” in 2012 ACM/IEEE/SCS 26th Workshop on Principles of Advanced and Distributed Simulation, Zhangjiajie, China, pp.44–52, 2012.
[15]	Z. W. Lin, X. H. Li, Y. Mao, et al., “DISHM: A zero-copy intra-node communication approach in large scale simulation,” in 2019 IEEE 19th International Conference on Communication Technology (ICCT), Xi’an, China, pp.578–582, 2019.
[16]	S. V. Adve and K. Gharachorloo, “Shared memory consistency models: A tutorial,” Computer, vol.29, no.12, pp.66–76, 1996. doi: 10.1109/2.546611
[17]	T. L. Li, Y. P. Yao, W. J. Tang, et al., “An efficient multi-threaded memory allocator for PDES applications,” Simulation Modelling Practice and Theory, vol.100, article no.102067, 2020. doi: 10.1016/j.simpat.2020.102067
[18]	R. M. Fujimoto, “Research challenges in parallel and distributed simulation,” ACM Transactions on Modeling and Computer Simulation, vol.26, no.4, article no.22, 2016. doi: 10.1145/2866577