SpikeSim: An End-to-End Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks
- 10 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 42 (11) , 3815-3828
Abstract
Spiking Neural Networks (SNNs) are an active research domain towards energy efficient machine intelligence. Compared to conventional artificial neural networks (ANNs), SNNs use temporal spike data and bio-plausible neuronal activation functions such as Leaky-Integrate Fire/Integrate Fire (LIF/IF) for data processing. However, SNNs incur significant dot-product operations causing high memory and computation overhead in standard von-Neumann computing platforms. To this end, In-Memory Computing (IMC) architectures have been proposed to alleviate the “memory-wall bottleneck" prevalent in von-Neumann architectures. Although recent works have proposed IMC-based SNN hardware accelerators, the following key implementation aspects have been overlooked 1) the adverse effects of crossbar non-ideality on SNN performance due to repeated analog dot-product operations over multiple time-steps 2) hardware overheads of essential SNN-specific components such as the LIF/IF and data communication modules. To this end, we propose SpikeSim, a tool that can perform realistic performance, energy, latency and area evaluation of IMC-mapped SNNs. SpikeSim consists of a practical monolithic IMC architecture called SpikeFlow for mapping SNNs. Additionally, the non-ideality computation engine (NICE) and energy-latency-area (ELA) engine performs hardware-realistic evaluation of SpikeFlow-mapped SNNs. Based on 65nm CMOS implementation and experiments on CIFAR10, CIFAR100 and TinyImagenet datasets, we find that the LIF/IF neuronal module has significant area contribution (>11% of the total hardware area). To this end, we propose SNN topological modifications that leads to 1.24× and 10× reduction in the neuronal module’s area and the overall energy-delay-product value, respectively. Furthermore, in this work, we perform a holistic comparison between IMC implemented ANN and SNNs and conclude that lower number of time-steps are the key to achieve higher throughput and energy-efficiency for SNNs compared to 4-bit ANNs. The code repository for the SpikeSim tool is available at https://github.com/Intelligent-Computing-Lab-Yale/Quanitzation-aware-SNN-training-and-hardware-evaluation-for-IMC-ArchitecturesKeywords
All Related Versions
Funding Information
- JUMP2.0 Center and CBRIC a JUMP1.0 Center
- DARPA and SRC
- Google Research Scholar Award
- National Science Foundation CAREER Award, TII
- DARPA AI Exploration (AIE) program
- DoE MMICC Center SEACROGS (DE-SC0023198)
This publication has 41 references indexed in Scilit:
- An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor DataFrontiers in Neuroscience, 2017
- RESPARC2017
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- ISAACACM SIGARCH Computer Architecture News, 2016
- TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic ChipIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- Unsupervised learning of digit recognition using spike-timing-dependent plasticityFrontiers in Computational Neuroscience, 2015
- Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing2015
- Vortex2015
- A detailed and flexible cycle-accurate Network-on-Chip simulator2013
- A Functional Hybrid Memristor Crossbar-Array/CMOS System for Data Storage and Neuromorphic ApplicationsNano Letters, 2011