IEEE Journal of Solid-State Circuits · 2023 · 21 citations · 33 references
EngineeringComputer EngineeringElectrical EngineeringAnalog ElectronicsComputer ArchitectureMicroelectronicsAnalog IntegrationDevice ModelingEmbedded Memory BlocksAccuracyDynamic Random-access MemoryDynamic Random-access Memory DesignEnergy-efficient ComputationEnergy-efficient Digital CircuitsEnergy-efficient Memory DesignMemory Circuit DesignRandom-access Memory
Analog computing-in-memory (CIM) has been widely explored for computing neural networks (NNs) efficiently. However, most analog CIM implementations trade compute accuracy for energy efficiency. The low accuracy restricts the practical application of analog CIM. In this article, a current-programming CIM that unifies the weight programming and computing in the current domain is proposed to address this dilemma. The enabled technique is a novel 3-transistor 1-capacitor (3T1C) embedded dynamic random access memory (eDRAM) cell. The current-programming mechanism and the dynamic-cascode read structure of the 3T1C cell make it immune to transistor-level non-idealities, including nonlinear <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$I$</tex-math> </inline-formula> – <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$V$</tex-math> </inline-formula> , threshold voltage variations, and short-channel effect. Therefore, the cell enables multi-level-cell (MLC) operations without any calibration, supporting eight current-weight levels (0–700 nA). In addition, a voltage–current two-step programming scheme is proposed to boost the sub-microamphere current-weight writing speed. To support signed 4-b weights, a pseudo-differential CIM cell composed of two 3T1C MLCs is developed. Fabricated in a 65-nm CMOS, the prototype demonstrates 2.2 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times$</tex-math> </inline-formula> reduction in macro-level variation through current programming. Benefiting from sub-microamphere compute currents, the prototype achieves the 4-b energy efficiencies of 233–304 TOPS/W. With a refresh interval of 0.4 ms, the macro achieves <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$>$</tex-math> </inline-formula> 90% inference accuracy on CIFAR10.
33
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
1.1 Computing's energy problem (and what we can do about it)
Mark Horowitz · 2014 · 1.9K citations
In-Memory Computing: Advances and Prospects
Naveen Verma, Hongyang Jia, Hossein Valavi et al. · IEEE Solid-State Circuits Magazine · 2019 · 430 citations