Jianan Wen

Jianan Wen

Auto-generated profile, based on publicly available information

Jianan Wen

IHPLeibniz-Institut fr innovative Mikroelektronik, Frankfurt (Oder), Germany

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
18 December 2023
Verified
Conference Paper
Open access
MUMax Uhlmann
Max Uhlmann
TRTommaso Rizzi
Tommaso Rizzi
JWJianan Wen
Jianan Wen
Emilio Perez-Bosch QuesadaEmilio Perez-Bosch Quesada
Emilio Perez-Bosch Quesada
BBBakr Al Beattie
Bakr Al Beattie
GKGerhard Kahmen
Gerhard Kahmen
Neural hardware accelerators have been proven to be energy-efficient when used to solve tasks which can be mapped into an artificial neural network (ANN) structure. Resistive random-access memories (RRAMs) are currently under investigation together with several different memristive devices as promising technologies to build such accelerators combined together with complementary metal-oxide semiconductor (CMOS)-technologies in integrated circuits (ICs). While many research groups are actively developing sophisticated physical-based representations to better understand the underlying phenomena characterizing these devices, not much work has been dedicated to exploit the trade-off between simulation time and accuracy in the definition of low computational demanding models suitable to be used at many abstraction layers. Indeed, the design of complex mixed-signal systems as a neural hardware accelerators requires frequent interaction between the application- and the circuit-level that can be enabled only with the support of accurate and fast-simulating devices’ models. In this work, we propose a solution to fill the aforementioned gap with a lookup table (LUT)-based Verilog-A model of IHP’s 1-transistor-1-RRAM (1T1R) cell. In addition, the implementation challenges of conveying the communication between the abstract ANN simulation and the circuital analysis are tackled with a design flow for resistive neural hardware accelerators that features a custom Python wrapper. As a demonstration of the proposed design flow and 1T1R model, an ANN for the MNIST handwritten digit recognition task is assessed with the last layer verified in circuit simulation. The obtained recognition confidence intervals show a considerable discrepancy between the purely application-level PyTorch simulation and the proposed design flow which spans across the abstraction layers down to the circuital analysis.

18 April 2025 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Open access
MUMax Uhlmann
Max Uhlmann
MKMilosz Bartlomiej Krysik
Milosz Bartlomiej Krysik
JWJianan Wen
Jianan Wen
MFMax Frohberg
Max Frohberg
ABAndrea Baroni
Andrea Baroni
GKGerhard Kahmen
Gerhard Kahmen
Emerging non-volatile memories (eNVMs) such as resistive random-access memory (RRAM) offer an alternative solution compared to standard CMOS technologies for implementation of in-memory computing (IMC) units used in artificial neural network (ANN) applications. Existing measurement equipment for device characterisation and programming of such eNVMs are usually bulky and expensive. In this work, we present a compact size characterization platform for RRAM devices, including a custom programming unit IC that occupies less than 1 mm2 of silicon area. Our platform is capable of testing one-transistor-one-RRAM (1T1R) as well as one-transistor-multiple-RRAM (1TNR) cells. Thus, to the best knowledge of the authors, this is the first demonstration of an integrated programming interface for 1TNR cells. The 1T2R IMC cells were fabricated in the IHP’s 130 nm BiCMOS technology and, in combination with other parts of the platform, are able to provide more synaptic weight resolution for ANN model applications while simultaneously decreasing the energy consumption by 50 %. The platform can generate programming voltage pulses with a 3.3 mV accuracy. Using the incremental step pulse with verify algorithm (ISPVA) we achieve 5 non-overlapping resistive states per 1T1R device. Based on those 1T1R base states we measure 15 resulting state combinations in the 1T2R cells.

10 April 2025 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Open access
MFMarkus Fritscher
Markus Fritscher
MUMax Uhlmann
Max Uhlmann
POPhilip Ostrovskyy
Philip Ostrovskyy
DRDaniel Reiser
Daniel Reiser
JCJunchao Chen
Junchao Chen
CWChristian Wenger
Christian Wenger
The breakdown of Dennard scaling has been the driver for many innovations such as multicore CPUs and has fueled the research into novel devices such as resistive random access memory (RRAM). These devices might be a means to extend the scalability of integrated circuits since they allow for fast and nonvolatile operation. Unfortunately, large analog circuits need to be designed and integrated in order to benefit from these cells, hindering the implementation of large systems. This work elaborates on a novel solution, namely, creating digital standard cells utilizing RRAM devices. Albeit this approach can be used both for small gates and large macroblocks, we illustrate it for a 2T2R-cell. Since RRAM devices can be vertically stacked with transistors, this enables us to construct a nand standard cell, which merely consumes the area of two transistors. This leads to a 25% area reduction compared to an equivalent CMOS nand gate. We illustrate achievable area savings with a half-adder circuit and integrate this novel cell into a digital standard cell library. A synthesized RISC-V core using RRAM-based cells results in a 10.7% smaller area than the equivalent design using standard CMOS gates.

12 March 2025 in Microelectronics Reliability
Verified
Journal Article
Open access
JWJianan Wen
Jianan Wen
FVFabian Luis Luis Vargas
Fabian Luis Luis Vargas
FZFukun Zhu
Fukun Zhu
DRDaniel Reiser
Daniel Reiser
ABAndrea Baroni
Andrea Baroni
MKMilos Krstic
Milos Krstic

30 October 2025 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Open access
JWJianan Wen
Jianan Wen
ABAndrea Baroni
Andrea Baroni
MUMax Uhlmann
Max Uhlmann
EPEduardo Perez
Eduardo Perez
CWChristian Wenger
Christian Wenger
MKMilos Krstic
Milos Krstic
The fast Fourier transform (FFT) is a highly efficient algorithm for computing the discrete Fourier transform (DFT). It is widely employed in various applications, including digital communication, image processing, and signal analysis. Recently, in-memory computing architectures based on emerging technologies, such as resistive RAM (RRAM), have demonstrated promising performance with low hardware cost for data-intensive applications. However, directly mapping FFT onto RRAM crossbars is challenging because the algorithm relies on many small, sequential butterfly operations, while crossbars are optimized for large-scale, highly parallel vector–matrix multiplications (VMMs). In this article, we introduce ReFFT, a system architecture that reformulates FFT computations for efficient execution on RRAM crossbars. ReFFT combines the reduced computational complexity of FFT with the parallel VMM capability of RRAM. We incorporate measured device data into our framework to analyze the effect of variability and develop an adaptive mapping scheme that improves twiddle-factor programming accuracy, leading to a 9.9 dB peak signal-to-noise ratio (PSNR) improvement for a 256-point FFT. Compared with prior RRAM-based DFT designs, ReFFT achieves up to $\mathbf {4.6\times }$ and $\mathbf {19.5 \times }$ higher energy efficiency for 256- and 2048-point FFTs, respectively. The system is further validated in digital communication and satellite image compression tasks.

5 June 2026 in IEEE Transactions on Device and Materials Reliability
Verified
Journal Article
Open access
ABAndrea Baroni
Andrea Baroni
JWJianan Wen
Jianan Wen
EPEduardo Perez
Eduardo Perez
KRKeerthi Dorai Swamy Reddy
Keerthi Dorai Swamy Reddy
MUMax Uhlmann
Max Uhlmann
CZCristian Zambelli
Cristian Zambelli
Drift of multi-level conductance states is a key reliability concern for resistive random access memory (RRAM) used in multi-level storage and in-memory computing applications. This work experimentally quantifies how repeated read operations and elevated-temperature storage reshape multiple conductive states in Al5%:HfO2-based RRAM cells. Systematic read-disturb and multi-temperature retention experiments are performed on one-transistor-one-resistor (1T1R) arrays, and their evolution is analyzed through intra-level transition matrices and a distance-weighted reshuffling factor Fr that jointly capture internal reshuffling dynamics beyond median and spread. Read-disturb exhibits a pronounced voltage dependence, with increasing reshuffling as VRD rises, whereas retention shows a two-phase thermal evolution dominated by an early warm-up reshuffling followed by a slower isothermal regime. Comparing incremental step pulse and verify algorithm (ISPVA) and one-shot programming (OSP) under identical targets and read-stress conditions further shows that both algorithms experience redistribution, but with different directionality and level dependence. These results clarify the distinct statistical signatures of field-and temperature-induced drift and identify the programming algorithm, read-voltage budget, and warm-up handling as key design knobs to improve the number of reliable levels in multi-level RRAM arrays.