Jie Lin

Mr. Jie Lin


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 June 2019
Verified
Conference Paper
Open access
ZHZhezhi He
Zhezhi He
JLJie Lin
Jie Lin
RERickard Ewetz
Rickard Ewetz
JYJiann-Shiun Yuan
Jiann-Shiun Yuan
DFDeliang Fan
Deliang Fan
In this work, we investigate various non-ideal effects (Stuck-At-Fault (SAF), IR-drop, thermal noise, shot noise, and random telegraph noise)of ReRAM crossbar when employing it as a dot-product engine for deep neural network (DNN) acceleration. In order to examine the impacts of those non-ideal effects, we first develop a comprehensive framework called PytorX based on main-stream DNN pytorch framework. PytorX could perform end-to-end training, mapping, and evaluation for crossbar-based neural network accelerator, considering all above discussed non-ideal effects of ReRAM crossbar together. Experiments based on PytorX show that directly mapping the trained large scale DNN into crossbar without considering these non-ideal effects could lead to a complete system malfunction (i.e., equal to random guess) when the neural network goes deeper and wider. In particular, to address SAF side effects, we propose a digital SAF error correction algorithm to compensate for crossbar output errors, which only needs one-time profiling to achieve almost no system accuracy degradation. Then, to overcome IR drop effects, we propose a Noise Injection Adaption (NIA) methodology by incorporating statistics of current shift caused by IR drop in each crossbar as stochastic noise to DNN training algorithm, which could efficiently regularize DNN model to make it intrinsically adaptive to non-ideal ReRAM crossbar. It is a one-time training method without the request of retraining for every specific crossbar. Optimizing system operating frequency could easily take care of rest non-ideal effects. Various experiments on different DNNs using image recognition application are conducted to show the efficacy of our proposed methodology.

8 September 2017 in Electronics
Verified
Journal Article
Open access
PDF file
JYJiann-shiun Yuan
Jiann-shiun Yuan
JLJie Lin
Jie Lin
QAQutaiba Alasad
Qutaiba Alasad
Shayan TaheriShayan Taheri
Shayan Taheri
In this review article for Internet of Things (IoT) applications, important low-power design techniques for digital and mixed-signal analog–digital converter (ADC) circuits are presented. Emerging low voltage logic devices and non-volatile memories (NVMs) beyond CMOS are illustrated. In addition, energy-constrained hardware security issues are reviewed. Specifically, light-weight encryption-based correlational power analysis, successive approximation register (SAR) ADC security using tunnel field effect transistors (FETs), logic obfuscation using silicon nanowire FETs, and all-spin logic devices are highlighted. Furthermore, a novel ultra-low power design using bio-inspired neuromorphic computing and spiking neural network security are discussed.

1 January 2020 in Neurocomputing
Verified
Journal Article
Closed access
JLJie Lin
Jie Lin
JYJiann-Shiun Yuan
Jiann-Shiun Yuan

16 July 2018 in IEEE Transactions on Biomedical Circuits and Systems
Verified
Journal Article
Closed access
JLJie Lin
Jie Lin
JYJiann-shiun Yuan
Jiann-shiun Yuan
The stochastic neuron is a key for event-based probabilistic neural networks. We propose a stochastic neuron using a metal-oxide resistive random-access memory (ReRAM). The ReRAM's conducting filament with built-in stochasticity is used to mimic the neuron's membrane capacitor, which temporally integrates input spikes. A capacitor-less neuron circuit is designed, laid out, and simulated. The output spiking train of the neuron obeys the Poisson distribution. Using the 65-nm CMOS technology node, the area of the neuron is 14 × 5 μm 2 , which is one ninth the size of a 1-pF capacitor. The average power consumption of the neuron is 1.289 μW. We introduce the neural array-A modified one-transistor-one-ReRAM (1T1R) crossbar that integrates the ReRAM neurons with ReRAM synapses to form a compact and energy efficient in-memory spiking neural network. A spiking deep belief network (DBN) with a noisy rectified linear unit (NReLU) is trained and mapped to the spiking DBN using the proposed ReRAM neurons. Simulation results show that the ReRAM neuron-based DBN is able to recognize the handwritten digits with 94.7% accuracy and is robust against the ReRAM process variation effect.

13 June 2023 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
CNChen Nie
Chen Nie
CTChenyu Tang
Chenyu Tang
JLJie Lin
Jie Lin
HHHuan Hu
Huan Hu
CLChenyang Lv
Chenyang Lv
Zhezhi HeZhezhi He
Zhezhi He
Processing-in-Memory (PIM) has been widely explored for accelerating data-intensive machine learning computation that mainly consists of general-matrix-multiplication (GEMM), by mitigating the burden of data movements and exploiting the ultra-high memory parallelism. The two mainstreams of PIM, the analog- and digital-type, have both been exploited in accelerating machine learning workloads by numerous outstanding prior works. Currently, the digital-PIM is increasingly favored due to the broader computing support and the avoidance of errors caused by intrinsic non-idealities, e.g., process variation. Nevertheless, it still lacks further optimization considering the characteristics of the GEMM computation, including better efficient data layout and scheduling, and the ability to handle the sparsity of activations at the bit-level. To boost the performance and efficiency of digital SRAM PIM, we propose the architecture called VSPIM that performs the computation in a bit-serial fashion, with unique support of vector-scalar computing pattern. The novelties of the VSPIM can be concluded as follows: 1) support bit-serial based scalar-vector computing via ingenious parallel bit-broadcasting; 2) refine the GEMM mapping strategy and computing pattern to enhance performance and efficiency; 3) powered by the introduced scalar-vector operation, the bit-sparsity of activation is leveraged to halt unnecessary computation to maximize efficiency and throughput. Our comprehensive evaluation shows that, compared to the state-of-the-art SRAM-based digital-PIM design (Neural Cache), VSPIM can significantly boost the performance and energy efficiency by up to $8.87\times$ and $4.81\times$ respectively, with negligible area overhead, upon multiple representative neural networks.

1 October 2017
Verified
Conference Paper
Closed access
JLJie Lin
Jie Lin
JYJiann-Shiun Yuan
Jiann-Shiun Yuan
Stochastic neuron is the key for event-based probabilistic neural networks. Here, for the first time, we propose a stochastic neuron based on Metal-Oxide Resistive Random-Access Memory (RRAM). The RRAM's conducting filament with built-in stochasticity is used to mimic the neuron's membrane capacitor that temporally integrates input spikes. A fully asynchronous and capacitor-less neuron circuit is designed, laid out, and simulated. The output spike train of the neuron is shown to obey the Poisson distribution. Using the 65nm CMOS technology node, the area of the neuron is 14 × 5 μm 2 , which is one ninth size of an 1pF capacitor. The average power consumption of the neuron is 1.289 μW. Finally, an event-based spiking deep belief network (DBN) is evaluated using our neuron design. The DBN is trained using MNIST database. Simulation results show that the DBN is able to recognize the handwritten digits with 90% accuracy.