OpenSpike: An OpenRAM SNN Accelerator

OpenSpike: An OpenRAM SNN Accelerator
复制标题

OpenSpike:OpenRAM SNN 加速器

DOI:
10.1109/iscas46773.2023.10182182
复制
发表时间:
2023
期刊:
Proceedings IEEE International Symposium on Circuits and Systems
影响因子:
--
通讯作者:
Eshraghian, Jason K.
Eshraghian, Jason K.
中科院分区:
--
文献类型:
--
作者:
Modaresi, Farhad;Guthaus, Matthew;Eshraghian, Jason K.

文献摘要

参考文献

被引文献

相似文献

本文提出了一种使用完全开源的EDA工具、工艺设计工具包(PDK)和使用Open-RAM合成的内存宏来实现的尖峰神经网络(SNN)加速器。该芯片采用130 nm Skywater工艺流片,集成了100多万个突触权重,并提供了可重新编程的架构。它的时钟速度为40 MHz,电源为1.8 V,使用PicoRV32内核进行控制,占地面积为33.3 mm2。该加速器的吞吐量为每秒48,262幅图像,壁时钟时间为20.72,在56.8 GOPS/W下。尖峰神经元利用滞后来提供一个自适应阈值(即施密特触发器),可以减少状态不稳定性。这导致了一系列基准的高性能SNN,这些基准保持了与最先进的全精度SNN的竞争力。该设计是开源的,可以在网上获得:https://githuh.com/sJmth/OpenSpike
This paper presents a spiking neural network (SNN) accelerator made using fully open-source EDA tools, process design kit (PDK), and memory macros synthesized using Open-RAM. The chip is taped out in the 130 nm SkyWater process and integrates over 1 million synaptic weights, and offers a reprogrammable architecture. It operates at a clock speed of 40 MHz, a supply of 1.8 V, uses a PicoRV32 core for control, and occupies an area of 33.3 mm2. The throughput of the accelerator is 48,262 images per second with a wallclock time of 20.72, at 56.8 GOPS/W. The spiking neurons use hysteresis to provide an adaptive threshold (i.e., a Schmitt trigger) which can reduce state instability. This results in high performing SNNs across a range of benchmarks that remain competitive with state-of-the-art, full precision SNNs. The design is open sourced and available online: https://githuh.com/sJmth/OpenSpike
DOI: 10.1088/2634-4386/ac5ac5
发表时间: 2022-03
期刊: Neuromorphic Computing and Engineering
影响因子: --
作者:
J. Turner;James C. Knight;Ajay Subramanian;Thomas Nowotny
通讯作者: J. Turner;James C. Knight;Ajay Subramanian;Thomas Nowotny
DOI: 10.1109/mnano.2022.3141443
发表时间: 2022-01-25
影响因子: 1.6
作者:
Eshraghian, Jason K.;Wang, Xinxin;Lu, Wei D.
通讯作者: Lu, Wei D.
OpenRAM:开源内存编译器
DOI: --
发表时间: 2016
期刊: 2016 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
影响因子: --
作者:
Matthew R. Guthaus;J. Stine;Samira Ataei;Brian Q. Chen;Bin Wu;M. Sarwar
通讯作者: M. Sarwar
DOI: 10.48550/arxiv.2211.10725
发表时间: 2022-11
期刊: ArXiv
影响因子: --
作者:
P. Sun;A. Titterton;Anjlee Gopiani;Tim Santos;A. Basu;Wei Lu;J. Eshraghian
通讯作者: P. Sun;A. Titterton;Anjlee Gopiani;Tim Santos;A. Basu;Wei Lu;J. Eshraghian
Brian2GeNN:一种使用图形硬件加速各种尖峰神经网络的系统
DOI: 10.1101/448050
发表时间: 2018
期刊: bioRxiv
影响因子: --
作者:
M. Stimberg;Dan F. M. Goodman;Thomas Nowotny
通讯作者: Thomas Nowotny