arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.13552cs.ET
收藏

使用1T1R ReRAM交叉阵列的有限状态自动机设计

Finite State Automata Design using 1T1R ReRAM Crossbar

Simranjeet Singh, Omar Ghazal, Chandan Kumar Jha, Vikas Rana, Rolf Drechsler, Rishad Shafik, Alex Yakovlev, Sachin Patkar, Farhad Merchant

AI总结:

针对机器学习系统中数据移动成本高的问题,提出使用1T1R ReRAM交叉阵列实现有限状态自动机,利用多级ReRAM和异步控制电路实现状态按需切换,实验证明其能无缝完成状态转换且性能无损。

摘要:

数据移动成本构成了现代机器学习(ML)系统中的一个重要瓶颈。当与算法(如神经网络)的计算复杂性相结合时,设计低能耗的硬件加速器仍然具有挑战性。有限状态自动机(FSA)是一种计算模型,在ML系统中用作低复杂度的学习单元。FSA的实现包含多个存储状态。然而,在给定时间FSA只能处于其中一个状态。它根据当前状态和输入到FSA的内容切换到另一个状态。由于其与存储器的天然协同作用,它是用于减少数据移动成本的存内计算的有希望的候选者。本工作专注于一种新颖的FSA实现,使用电阻式RAM(ReRAM)进行状态存储,并与CMOS晶体管串联用于偏置控制。我们提出使用能够根据偏置脉冲幅度和持续时间在状态之间转换的多级ReRAM技术。我们使用异步控制电路写入每个ReRAM-晶体管单元,以实现FSA的按需切换。我们研究了器件间和周期间变化对单元的影响,并表明FSA转换可以无缝实现而不会降低性能。通过广泛的实验评估,我们展示了在1T1R ReRAM交叉阵列上实现FSA。

英文摘要:

Data movement costs constitute a significant bottleneck in modern machine learning (ML) systems. When combined with the computational complexity of algorithms, such as neural networks, designing hardware accelerators with low energy footprint remains challenging. Finite state automata (FSA) constitute a type of computation model used as a low-complexity learning unit in ML systems. The implementation of FSA consists of a number of memory states. However, FSA can be in one of the states at a given time. It switches to another state based on the present state and input to the FSA. Due to its natural synergy with memory, it is a promising candidate for in-memory computing for reduced data movement costs. This work focuses on a novel FSA implementation using resistive RAM (ReRAM) for state storage in series with a CMOS transistor for biasing controls. We propose using multi-level ReRAM technology capable of transitioning between states depending on bias pulse amplitude and duration. We use an asynchronous control circuit for writing each ReRAM-transistor cell for the on-demand switching of the FSA. We investigate the impact of the device-to-device and cycle-to-cycle variations on the cell and show that FSA transitions can be seamlessly achieved without degradation of performance. Through extensive experimental evaluation, we demonstrate the implementation of FSA on 1T1R ReRAM crossbar.

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。

↑