HW/SW Codesign for Robust and Efficient Binarized SNNs by Capacitor Minimization

Using accelerators based on analog computing is an efficient way to process the immensely large workloads in Neural Networks (NNs). One example of an analog computing scheme for NNs is Integrate-and-Fire (IF) Spiking Neural Networks (SNNs). However, to achieve high inference accuracy in IF-SNNs, the analog hardware needs to represent current-based multiply-accumulate (MAC) levels as spike times, for which a large membrane capacitor needs to be charged for a certain amount of time. A large capacitor results in high energy use, considerable area cost, and long latency, constituting one of the major bottlenecks in analog IF-SNN implementations. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14$\times$ reduction in capacitor size over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.

[1]  Yu Cao,et al.  SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks , 2022, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[2]  Hussam Amrouch,et al.  Binarized SNNs: Efficient and Error-Resilient Spiking Neural Networks through Binarization , 2021, 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD).

[3]  Chia-Lin Yang,et al.  Robust Brain-Inspired Computing: On the Reliability of Spiking Neural Network Using Emerging Non-Volatile Synapses , 2021, 2021 IEEE International Reliability Physics Symposium (IRPS).

[4]  Katharina Morik,et al.  Margin-Maximization in Binarized Neural Networks for Optimizing Bit Error Tolerance , 2021, 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[5]  Siddharth Joshi,et al.  Supervised Learning in All FeFET-Based Spiking Neural Network: Opportunities and Challenges , 2020, Frontiers in Neuroscience.

[6]  Yachen Xiang,et al.  Efficient and Robust Spike-Driven Deep Convolutional Neural Networks Based on NOR Flash Computing Array , 2020, IEEE Transactions on Electron Devices.

[7]  V. Nia,et al.  How Does Batch Normalization Help Binary Training , 2019, 1909.09139.

[8]  Diana Marculescu,et al.  Regularizing Activation Distribution for Training Binarized Deep Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Zhiru Zhang,et al.  Improving Neural Network Quantization without Retraining using Outlier Channel Splitting , 2019, ICML.

[10]  Yu Wang,et al.  PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[11]  Miao Hu,et al.  ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Rong Luo,et al.  Spiking neural network with RRAM: Can we use it for real-world application? , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  M. Khare,et al.  High performance UTBB FDSOI devices featuring 20nm gate length for 14nm node and beyond , 2013, 2013 IEEE International Electron Devices Meeting.

[16]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, ArXiv.