arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.09417cs.ET
收藏

通过寄生泄漏缓解实现的基于超低能量电荷陷阱闪存的突触

Ultra-low Energy charge trap flash based synapse enabled by parasitic leakage mitigation

Shalini Shrivastava, Tanmay Chavan, Udayan Ganguly

摘要:

大脑启发的计算有望以生物能源效率完成复杂的认知任务。大脑中每个神经元包含$10^4$突触。因此,脉冲神经网络需要超低能量、高密度的突触。在本文中,我们使用隧道使能的CTF(电荷陷阱闪存)堆栈的超低能量操作(1F);进一步,CTF上的SOI平台和背靠背连接的pn二极管和齐纳二极管(2D)防止寄生泄漏,以保持在阵列操作的能量优势。本体$100 μm $ x $100 μm$ CTF操作提供了可调的、渐进的电导变化$(ΔG) i.e. 10^4 $水平,这给出了比文献更好的$100$ x。1F 2D突触的SPICE模拟显示,长时程增强(LTP)和抑制(LTD)在180 nm节点处具有超低能量$(\leqslant 3 fJ/pulse)$,长时程增强(LTP)和抑制(LTD)在180 nm节点处具有超低能量$(\leqslant 3 fJ/pulse)$,这与生物突触中的能量估计(10 fJ)相当。创纪录的低学习率(即,G范围的最大$ΔG< 1%$)-这是可调的。观察到优异的可靠性(在全电导摆动下$>10^6耐久循环)。这种在CMOS平台上具有可调学习率的高能效突触是人脑规模系统的关键使能器。关键词:脉冲神经网络;电荷陷阱闪光; SONAS; Fowler-Nordheim隧道;突触

英文摘要:

Brain-inspired computation promises complex cognitive tasks at biological energy efficiencies. The brain contains $10^4$ synapses per neuron. Hence, ultra-low energy, high-density synapses are needed for spiking neural networks (SNN). In this paper, we use tunneling enabled CTF (Charge Trap Flash) stack for ultra-low-energy operation (1F); Further, CTF on an SOI platform and back-to-back connected pn diode and Zener diode (2D) prevent parasitic leakage to preserve energy advantage in array operation. A bulk $100 μm $ x $100 μm$ CTF operation offers tunable, gradual conductance change $(ΔG) i.e. 10^4 $levels, which gives $100$x improvement over literature. SPICE simulations of 1F2D synapse shows ultra-low energy $(\leqslant 3 fJ/pulse)$ at 180 nm node for long-term potentiation (LTP) and depression (LTD), at 180nm node for long-term potentiation (LTP) and depression (LTD), which is comparable to energy estimate in biological synapses (10 fJ). A record low learning rate (i.e., maximum $ΔG< 1%$ of G-range) is observed - which is tunable. Excellent reliability ($>10^6 endurance cycles at full conductance swing) is observed. Such a highly energy efficient synapse with tunable learning rate on the CMOS platform is a key enabler for the human-brain-scale systems. Keywords: Spiking Neural Network; Charge trap flash, SONAS, Fowler-Nordheim Tunneling, Synapse

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑