Ziyang Kang
ABSTRACT
Neuromorphic processors can support the design of various Spiking Neural Networks (SNN) to deal with different tasks, such as recognition and tracking. Neuromorphic processors use Network-on-Chip (NoC) to support communication between neurons in SNN. The different SNN has different communication traffic patterns. It will pose the different challenges of the NoC designing. A reasonable NoC architecture can improve the overall performance such as lower latency of the processor. Hence, it is critical to implement the exploration of NoC architecture design for neuromorphic processors.
This paper proposes a rapid NoC design space exploration (DSE) framework. As to our knowledge, it is the first work for the NoC DSE for the neuromorphic processor. The framework takes the spikes of the SNN application as input. It can support multiple optimization objectives for NoC design. Meanwhile, an optimized simulated annealing algorithm has been used to perform the DSE for the NoC design space. Then it outputs the final NoC design configuration. We apply this framework to 7 SNN applications to perform the NoC DSE. Compared with baseline NoC configuration, the NoC DSE framework can improve performance (Average Transport latency) by 54% to 93%. Compared with the Simulated Annealing (SA) algorithm, the Better-History SA (BHSA) algorithm speeds up the searching process by 1.5 to 8 times.
- Filipp Akopyan, Jun Sawada, Andrew Cassidy, Rodrigo Alvarez-Icaza, John Arthur, Paul Merolla, Nabil Imam, Yutaka Nakamura, Pallab Datta, Gi-Joon Nam, et al. 2015. Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip. IEEE transactions on computer-aided design of integrated circuits and systems 34, 10 (2015), 1537--1557.Google Scholar
Digital Library
- Edith Beigné, Fabien Clermidy, Pascal Vivet, Alain Clouard, and Marc Renaudin. 2005. An asynchronous NOC architecture providing low latency service and its multi-level design framework. In 11th IEEE International Symposium on Asynchronous Circuits and Systems. IEEE, 54--63.Google ScholarDigital Library
- Michael Beyeler, Kristofor D Carlson, Ting-Shuo Chou, Nikil Dutt, and Jeffrey L Krichmar. 2015. CARLsim 3: A user-friendly and highly optimized library for the creation of neurobiologically detailed spiking neural networks. In 2015 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8.Google ScholarCross Ref
- Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain, et al. 2018. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 1 (2018), 82--99.Google ScholarCross Ref
- Haowen Fang, Amar Shrestha, De Ma, and Qinru Qiu. 2018. Scalable noc-based neuromorphic hardware learning and inference. In 2018 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8.Google ScholarCross Ref
- Steve B Furber, David R Lester, Luis A Plana, Jim D Garside, Eustace Painkras, Steve Temple, and Andrew D Brown. 2012. Overview of the spinnaker system architecture. IEEE Trans. Comput. 62, 12 (2012), 2454--2467.Google ScholarDigital Library
- Shasha Guo, Lei Wang, Shuquan Wang, Yu Deng, Zhijie Yang, Shiming Li, Zhige Xie, and Qiang Dou. 2019. A Systolic SNN Inference Accelerator and its Co-optimized Software Framework. In Proceedings of the 2019 on Great Lakes Symposium on VLSI. 63--68.Google ScholarDigital Library
- Eugene M Izhikevich. 2003. Simple model of spiking neurons. IEEE Transactions on neural networks 14, 6 (2003), 1569--1572. https://doi.org/document/1257420Google ScholarDigital Library
- Z Jackson. 2016. Free Spoken Digit Dataset (fsdd). Technical Report. Technical report.Google Scholar
- Nan Jiang, George Michelogiannakis, Daniel Becker, Brian Towles, and William J Dally. 2010. Booksim 2.0 user's guide. Standford University (2010).Google Scholar
- Michel A Kinsy, Michael Pellauer, and Srinivas Devadas. 2013. Heracles: a tool for fast RTL-based design space exploration of multicore processors. In Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays. 125--134.Google ScholarDigital Library
- Shashi Kumar, Axel Jantsch, J-P Soininen, Martti Forsell, Mikael Millberg, Johny Oberg, Kari Tiensyrja, and Ahmed Hemani. 2002. A network on chip architecture and design methodology. In Proceedings IEEE Computer Society Annual Symposium on VLSI. New Paradigms for VLSI Systems Design. ISVLSI 2002. IEEE, 117--124.Google ScholarCross Ref
- Markos Kynigos, Javier Navaridas, Luis A Plana, and Steve Furber. 2018. Network-on-chip evaluation for a novel neural architecture. In Proceedings of the 15th ACM International Conference on Computing Frontiers. 216--219.Google ScholarDigital Library
- Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.Google ScholarCross Ref
- Shiming Li, Shasha Guo, Limeng Zhang, Ziyang Kang, Shiying Wang, Wei Shi, Lei Wang, and Weixia Xu. 2020. SNEAP: A Fast and Efficient Toolchain for Mapping Large-Scale Spiking Neural Network onto NoC-based Neuromorphic Platform. In Proceedings of the 2020 on Great Lakes Symposium on VLSI. to be published.Google ScholarDigital Library
- Carver Mead. 1990. Neuromorphic electronic systems. Proc. IEEE 78, 10 (1990), 1629--1636.Google ScholarCross Ref
- Deep Medhi and Karthik Ramasamy. 2017. Network routing: algorithms, protocols, and architectures. Morgan Kaufmann.Google Scholar
- Saber Moradi, Ning Qiao, Fabio Stefanini, and Giacomo Indiveri. 2017. A scalable multicore architecture with heterogeneous memory structures for dynamic neuromorphic asynchronous processors (DYNAPs). IEEE transactions on biomedical circuits and systems 12, 1 (2017), 106--122.Google Scholar
- Garrick Orchard, Ajinkya Jayawant, Gregory K Cohen, and Nitish Thakor. 2015. Converting static image datasets to spiking neuromorphic datasets using saccades. Frontiers in neuroscience 9 (2015), 437.Google Scholar
- Partha Pratim Pande, Cristian Grecu, Michael Jones, Andre Ivanov, and Resve Saleh. 2005. Performance evaluation and design trade-offs for network-on-chip interconnect architectures. IEEE transactions on Computers 54, 8 (2005), 1025--1040.Google ScholarDigital Library
- Jing Pei, Lei Deng, Sen Song, Mingguo Zhao, Youhui Zhang, Shuang Wu, Guanrui Wang, Zhe Zou, Zhenzhi Wu, Wei He, et al. 2019. Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572, 7767 (2019), 106--111.Google Scholar
- Johannes Schemmel, Andreas Grübl, Stephan Hartmann, Alexander Kononov, Christian Mayr, Karlheinz Meier, Sebastian Millner, Johannes Partzsch, Stefan Schiefer, Stefan Scholze, et al. 2012. Live demonstration: A scaled-down version of the brainscales wafer-scale neuromorphic system. In 2012 IEEE International Symposium on Circuits and Systems. IEEE, 702--702.Google ScholarCross Ref
- Benjamin Schrauwen, David Verstraeten, and Jan Van Campenhout. 2007. An overview of reservoir computing: theory, applications and implementations. In Proceedings of the 15th european symposium on artificial neural networks. p. 471--482 2007. 471--482.Google Scholar
- Cristina Silvano, William Fornaciari, Gianluca Palermo, Vittorio Zaccaria, Fabrizio Castro, Marcos Martinez, Sara Bocchio, Roberto Zafalon, Prabhat Avasare, Geert Vanmeerbeeck, et al. 2011. Multicube: Multi-objective design space exploration of multi-core architectures. In VLSI 2010 Annual Symposium. Springer, 47--63.Google ScholarCross Ref
- Marcel Stimberg, Romain Brette, and Dan FM Goodman. 2019. Brian 2, an intuitive and efficient neural simulator. Elife 8 (2019).Google Scholar
- Lei Wang, YuXing Tang, Yu Deng, Fangyan Qin, Qiang Dou, Guangda Zhang, and Feipeng Zhang. 2015. A Scalable and fast microprocessor design space exploration methodology. In 2015 IEEE 9th International Symposium on Embedded Multicore/Many-core Systems-on-Chip. IEEE, 33--40.Google ScholarDigital Library
- Qian Wang, Yingyezhe Jin, and Peng Li. 2015. General-purpose LSM learning processor architecture and theoretically guided design space exploration. In 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS). IEEE, 1--4.Google ScholarCross Ref
- Qian Wang, Yongtae Kim, and Peng Li. 2014. Architectural design exploration for neuromorphic processors with memristive synapses. In 14th IEEE International Conference on Nanotechnology. IEEE, 962--966.Google ScholarCross Ref
Index Terms
- Application-specific network-on-chip design space exploration framework for neuromorphic processor
Recommendations
On the area and energy scalability of wireless network-on-chip: a model-based benchmarked design space exploration
Networks-on-chip (NoCs) are emerging as the way to interconnect the processing cores and the memory within a chip multiprocessor. As recent years have seen a significant increase in the number of cores per chip, it is crucial to guarantee the ...
A modular simulation framework for architectural exploration of on-chip interconnection networks
CODES+ISSS '03: Proceedings of the 1st IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesisEver increasing complexity and heterogeneity of SoC platforms require diversified on-chip communication schemes beyond the currently omnipresent shared bus architectures. To prevent time consuming design changes late in the design flow, we propose the ...
P-NoC: Performance Evaluation and Design Space Exploration of NoCs for Chip Multiprocessor Architecture Using FPGA
AbstractThe network-on-chip (NoC) has emerged as an efficient and scalable communication fabric for chip multiprocessors (CMPs) and multiprocessor system on chips (MPSoCs). The NoC architecture, the routers micro-architecture and links influence the ...
Comments