ABSTRACT
Spike-based convolutional neural networks (CNNs) are empowered with on-chip learning in their convolution layers, enabling the layer to learn to detect features by combining those extracted in the previous layer. We propose ECHELON, a generalized design template for a tile-based neuromorphic hardware with on-chip learning capabilities. Each tile in ECHELON consists of a neural processing units (NPU) to implement convolution and dense layers of a CNN model, an on-chip learning unit (OLU) to facilitate spike-timing dependent plasticity (STDP) in the convolution layer, and a special function unit (SFU) to implement other CNN functions such as pooling, concatenation, and residual computation. These tile resources are interconnected using a shared bus, which is segmented and configured via the software to facilitate parallel communication inside the tile. Tiles are themselves interconnected using a classical Network-on-Chip (NoC) interconnect. We propose a system software to map CNN models to ECHELON, maximizing the performance. We integrate the hardware design and software optimization within a co-design loop to obtain the hardware and software architectures for a target CNN, satisfying both performance and resource constraints. In this preliminary work, we show the implementation of a tile on a FPGA and some early evaluations. Using 8 STDP-enabled CNN models, we show the potential of our co-design methodology to optimize hardware resources.
- Adarsha Balaji, Anup Das, Yuefeng Wu, Khanh Huynh, Francesco G Dell'Anna, Giacomo Indiveri, Jeffrey L Krichmar, Nikil D Dutt, Siebren Schaafsma, et al. 2019. Mapping spiking neural networks to neuromorphic hardware. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 28, 1 (2019), 76--86.Google ScholarCross Ref
- Adarsha Balaji, Phu Huynh, Francky Catthoor, Nikil D. Dutt, Jeffrey Krichmar, and Anup Das. 2023. NeuSB: A scalable interconnect architecture for spiking neuromorphic hardware. arXiv (2023).Google Scholar
- Adarsha Balaji, Shihao Song, Twisha Titirsha, Anup Das, Jeffrey Krichmar, Nikil Dutt, James Shackleford, Nagarajan Kandasamy, et al. 2021. NeuroXplorer 1.0: An extensible framework for architectural exploration with spiking neural networks. In International Conference on Neuromorphic Systems (ICONS).Google ScholarDigital Library
- Adarsha Balaji, Yuefeng Wu, Anup Das, Francky Catthoor, and Siebren Schaafsma. 2019. Exploration of segmented bus as scalable global interconnect for neuromorphic computing. In Great Lakes Symposium on VLSI.Google ScholarDigital Library
- Ben Varkey Benjamin, Peiran Gao, Emmett McQuinn, Swadesh Choudhary, Anand R Chandrasekaran, Jean-Marie Bussat, Rodrigo Alvarez-Icaza, John V Arthur, et al. 2014. Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations. Proc. of the IEEE 102, 5 (2014), 699--716.Google ScholarCross Ref
- Geoffrey W. Burr, Robert M. Shelby, Abu Sebastian, Sangbum Kim, Seyoung Kim, Severin Sidler, Kumar Virwani, Masatoshi Ishii, Pritish Narayanan, Alessandro Fumarola, Lucas L. Sanches, Irem Boybat, Manuel Le Gallo, Kibong Moon, Jiyoo Woo, Hyunsang Hwang, and Yusuf Leblebici. 2017. Neuromorphic computing using non-volatile memory. Advances in Physics: X 2, 1 (2017), 89--124.Google Scholar
- Natalia Caporale, Yang Dan, et al. 2008. Spike timing-dependent plasticity: a Hebbian learning rule. Annual Review of Neuroscience 31, 1 (2008), 25--46.Google ScholarCross Ref
- Francky Catthoor, Srinjoy Mitra, Anup Das, and Siebren Schaafsma. 2018. Very large-scale neuromorphic systems for biological signal processing. In CMOS Circuits for Biological Sensing and Processing. Springer, 315--340.Google Scholar
- Federico Corradi, Guido Adriaans, and Sander Stuijk. 2021. Gyro: A digital spiking neural network architecture for multi-sensory data analytics. In Drone Systems Engineering and Rapid Simulation and Performance Evaluation: Methods and Tools Proceedings. 9--15.Google ScholarDigital Library
- Gaël Daoudal and Dominique Debanne. 2003. Long-term plasticity of intrinsic excitability: learning rules and mechanisms. Learning & Memory 10, 6 (2003).Google Scholar
- Anup Das. 2022. Real-Time Scheduling of Machine Learning Operations on Heterogeneous Neuromorphic SoC. In International Symposium on Formal Methods and Models for System Design (MEMOCODE).Google Scholar
- Anup Das, Akash Kumar, and Bharadwaj Veeravalli. 2014. Energy-aware task mapping and scheduling for reliable embedded computing systems. ACM Transactions on Embedded Computing Systems 13, 2s (2014), 1--27.Google ScholarDigital Library
- Anup Das, Paruthi Pradhapan, Willemijn Groenendaal, Prathyusha Adiraju, Raj Thilak Rajan, Francky Catthoor, Siebren Schaafsma, Jeffrey L Krichmar, Nikil Dutt, and Chris Van Hoof. 2018. Unsupervised heart-rate estimation in wearables with liquid states and a probabilistic readout. Neural Networks 99 (2018), 134--147.Google ScholarDigital Library
- Mike Davies, Narayan Srinivasa, Tsung Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain, Yuyun Liao, Chit Kwan Lin, Andrew Lines, Ruokun Liu, Deepak Mathaikutty, Steven McCoy, Arnab Paul, Jonathan Tse, Guruguhanathan Venkataramanan, Yi Hsin Weng, Andreas Wild, et al. 2018. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 1 (2018), 82--99.Google ScholarCross Ref
- Michael V. Debole, Brian Taba, Arnon Amir, et al. 2019. TrueNorth: Accelerating from zero to 64 million neurons in 10 years. Computer 52, 5 (2019), 20--29.Google ScholarCross Ref
- Steve Furber, Francesco Galluppi, Steve Temple, and Luis A Plana. 2014. The SpiNNaker project. Proc. of the IEEE 102, 5 (2014), 652--665.Google ScholarCross Ref
- Eric Hunsberger and Chris Eliasmith. 2015. Spiking deep networks with LIF neurons. arXiv (2015).Google Scholar
- Phu Khanh Huynh, M Lakshmi Varshika, Ankita Paul, Murat Isik, Adarsha Balaji, and Anup Das. 2022. Implementing spiking neural networks on neuromorphic architectures: A review. arXiv (2022).Google Scholar
- Yu Ji, YouHui Zhang, ShuangChen Li, Ping Chi, CiHang Jiang, Peng Qu, Yuan Xie, and WenGuang Chen. 2016. NEUTRAMS: Neural network transformation and co-design under neuromorphic hardware constraints. In International Symposium on Microarchitecture (MICRO). 1--13.Google ScholarCross Ref
- Xin Jin, Alexander Rast, Francesco Galluppi, Sergio Davies, and Steve Furber. 2010. Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware. In International Joint Conference on Neural Networks (IJCNN).Google ScholarCross Ref
- Saeed Reza Kheradpisheh, Mohammad Ganjtabesh, Simon J Thorpe, and Timothée Masquelier. 2018. STDP-based spiking deep convolutional neural networks for object recognition. Neural Networks 99 (2018), 56--67.Google ScholarDigital Library
- M Lakshmi Varshika, Adarsha Balaji, Federico Corradi, Anup Das, Jan Stuijt, and Francky Catthoor. 2022. Design of Many-Core Big Little μBrain for Energy-Efficient Embedded Neuromorphic Computing. In Design, Automation & Test in Europe Conference & Exhibition (DATE).Google Scholar
- Corey Lammie, Tara Julia Hamilton, André van Schaik, and Mostafa Rahimi Azghadi. 2018. Efficient FPGA implementations of pair and triplet-based STDP for neuromorphic architectures. IEEE Transactions on Circuits and Systems I: Regular Papers 66, 4 (2018), 1558--1570.Google ScholarCross Ref
- Edward A Lee and David G Messerschmitt. 1987. Synchronous data flow. Proc. of the IEEE 75, 9 (1987), 1235--1245.Google ScholarCross Ref
- Chit-Kwan Lin, Andreas Wild, Gautham N. Chinya, Tsung-Han Lin, Mike Davies, and Hong Wang. 2018. Mapping Spiking Neural Networks onto a Manycore Neuromorphic Architecture. In Conference on Programming Language Design and Implementation (PLDI). 78--89.Google ScholarDigital Library
- Xiaoxiao Liu, Wei Wen, Xuehai Qian, Hai Li, and Yiran Chen. 2018. Neu-NoC: A high-efficient interconnection network for accelerated neuromorphic systems. In Asia and South Pacific Design Automation Conference (ASP-DAC). 141--146.Google ScholarDigital Library
- Carver Mead. 1990. Neuromorphic electronic systems. Proc. of the IEEE 78, 10 (1990), 1629--1636.Google ScholarCross Ref
- Lars Niedermeier, Kexin Chen, Jinwei Xing, Anup Das, Jeffrey Kopsick, Eric Scott, Nate Sutton, Killian Weber, Nikil Dutt, and Jeffrey L Krichmar. 2022. CARLsim 6: An Open Source Library for Large-Scale, Biologically Detailed Spiking Neural Network Simulation. In International Joint Conference on Neural Networks.Google Scholar
- Ning Qiao, Hesham Mostafa, Federico Corradi, Marc Osswald, Fabio Stefanini, Dora Sumislawska, and Giacomo Indiveri. 2015. A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses. Frontiers in Neuroscience 9 (2015), 141.Google ScholarCross Ref
- Abhronil Sengupta, Yuting Ye, Robert Wang, Chiao Liu, and Kaushik Roy. 2019. Going deeper in spiking neural networks: VGG and residual architectures. Frontiers in Neuroscience 13 (2019), 95.Google ScholarCross Ref
- Teresa Serrano-Gotarredona, Timothée Masquelier, Themistoklis Prodromakis, Giacomo Indiveri, and Bernabe Linares-Barranco. 2013. STDP and STDP variations with memristors for spiking neuromorphic learning systems. Frontiers in Neuroscience 7 (2013), 2.Google ScholarCross Ref
- Luping Shi, Jing Pei, Ning Deng, Dong Wang, Lei Deng, Yu Wang, Youhui Zhang, Feng Chen, Mingguo Zhao, Sen Song, et al. 2015. Development of a neuromorphic computing system. In International Electron Devices Meeting (IEDM). 4--3.Google ScholarCross Ref
- Shihao Song, Adarsha Balaji, Anup Das, and Nagarajan Kandasamy. 2022. Design-Technology Co-Optimization for NVM-based Neuromorphic Processing Elements. ACM Transactions on Embedded Computing Systems (TECS) (2022).Google Scholar
- Shihao Song, Adarsha Balaji, Anup Das, Nagarajan Kandasamy, et al. 2020. Compiling spiking neural networks to neuromorphic hardware. In International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES).Google ScholarDigital Library
- Shihao Song, Lakshmi Mirtinti, Anup Das, and N. Kandasamy. 2021. A Design Flow for Mapping Spiking Neural Networks to Many-Core Neuromorphic Hardware. In International Conference On Computer Aided Design (ICCAD). 1--9.Google Scholar
- Amirreza Yousefzadeh, Timothée Masquelier, Teresa Serrano-Gotarredona, and Bernabé Linares-Barranco. 2017. Hardware implementation of convolutional STDP for on-line visual feature learning. In International Symposium on Circuits and Systems (ISCAS).Google ScholarCross Ref
- Robert S Zucker, Wade G Regehr, et al. 2002. Short-term synaptic plasticity. Annual Review of Physiology 64, 1 (2002), 355--405.Google ScholarCross Ref
Index Terms
- Hardware-Software Co-Design for On-Chip Learning in AI Systems
Recommendations
SpikeHard: Efficiency-Driven Neuromorphic Hardware for Heterogeneous Systems-on-Chip
Special Issue ESWEEK 2023Neuromorphic computing is an emerging field with the potential to offer performance and energy-efficiency gains over traditional machine learning approaches. Most neuromorphic hardware, however, has been designed with limited concerns to the problem of ...
Spike-driven multi-scale learning with hybrid mechanisms of spiking dendrites
AbstractNeural dendrites play a critical role in various cognitive functions, including spatial navigation, sensory processing, adaptive learning, and perception. The spatial layout, signal processing, and nonlinear dynamics of dendrites endow them with ...
Hardware-software co-design of AES on FPGA
ICACCI '12: Proceedings of the International Conference on Advances in Computing, Communications and InformaticsThis paper presents a compact hardware-software co-design of Advanced Encryption Standard (AES) on the field programmable gate arrays (FPGA) designed for low-cost embedded systems. The design uses MicroBlaze, a soft-core processor from Xilinx. The ...
Comments