Tianyao Patrick Xiao

Tianyao Patrick Xiao

Auto-generated profile, based on publicly available information

Tianyao Patrick Xiao

Sandia National Laboratories, Albuquerque, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
14 March 2018 in The Journal of Physical Chemistry Letters
Verified
Journal Article
Open access
LPLuis M. Pazos-Outón
Luis M. Pazos-Outón
TXT. Patrick Xiao
T. Patrick Xiao
EYEli Yablonovitch
Eli Yablonovitch
Lead halide materials have seen a recent surge of interest from the photovoltaics community following the observation of surprisingly high photovoltaic performance, with opto-electronic properties similar to GaAs. This begs the question; what is the limit for the efficiency of these materials? It has been known that at 1-sun the efficiency limit of crystalline silicon is ~29%, despite the Shockley-Queisser (SQ) limit for its bandgap being ~33%, the discrepancy being due to strong Auger recombination. In this article, we show that Methyl Ammonium Lead Iodide (MAPbI3) likewise has a larger than expected Auger coefficient. Auger non-radiative recombination decreases the theoretical external luminescence efficiency to ~95% at open-circuit conditions. The Auger penalty is much reduced at the operating point where the carrier density is less, producing an oddly high fill factor of ~90.4%. This compensates the Auger penalty and leads to an operating point voltage and power conversion efficiency close to ideal for the MAPbI3 bandgap.

9 July 2020 in Applied Physics Reviews
Verified
Journal Article
Open access
PDF file
TXT. Patrick Xiao
T. Patrick Xiao
CBChristopher H. Bennett
Christopher H. Bennett
BFBen Feinberg
Ben Feinberg
SASapan Agarwal
Sapan Agarwal
MMMatthew J. Marinella
Matthew J. Marinella
Analog hardware accelerators, which perform computation within a dense memory array, have the potential to overcome the major bottlenecks faced by digital hardware for data-heavy workloads such as deep learning. Exploiting the intrinsic computational advantages of memory arrays, however, has proven to be challenging principally due to the overhead imposed by the peripheral circuitry and due to the non-ideal properties of memory devices that play the role of the synapse. We review the existing implementations of these accelerators for deep supervised learning, organizing our discussion around the different levels of the accelerator design hierarchy, with an emphasis on circuits and architecture. We explore and consolidate the various approaches that have been proposed to address the critical challenges faced by analog accelerators, for both neural network inference and training, and highlight the key design trade-offs underlying these techniques.

17 May 2021 in Applied Physics Letters
Verified
Journal Article
Closed access
PDF file
SLSamuel Liu
Samuel Liu
TXT. Patrick Xiao
T. Patrick Xiao
CCCan Cui
Can Cui
JIJean Anne Incorvia
Jean Anne Incorvia
CBChristopher H. Bennett
Christopher H. Bennett
MMMatthew J. Marinella
Matthew J. Marinella
Inspired by the parallelism and efficiency of the brain, several candidates for artificial synapse devices have been developed for neuromorphic computing, yet a nonlinear and asymmetric synaptic response curve precludes their use for backpropagation, the foundation of modern supervised learning. Spintronic devices—which benefit from high endurance, low power consumption, low latency, and CMOS compatibility—are a promising technology for memory, and domain-wall magnetic tunnel junction (DW-MTJ) devices have been shown to implement synaptic functions such as long-term potentiation and spike-timing dependent plasticity. In this work, we propose a notched DW-MTJ synapse as a candidate for supervised learning. Using micromagnetic simulations at room temperature, we show that notched synapses ensure the non-volatility of the synaptic weight and allow for highly linear, symmetric, and reproducible weight updates using either spin transfer torque (STT) or spin–orbit torque (SOT) mechanisms of DW propagation. We use lookup tables constructed from micromagnetics simulations to model the training of neural networks built with DW-MTJ synapses on both the MNIST and Fashion-MNIST image classification tasks. Accounting for thermal noise and realistic process variations, the DW-MTJ devices achieve classification accuracy close to ideal floating-point updates using both STT and SOT devices at room temperature and at 400 K. Our work establishes the basis for a magnetic artificial synapse that can eventually lead to hardware neural networks with fully spintronic matrix operations implementing machine learning.

15 March 2021 in Applied Physics Letters
Verified
Journal Article
Closed access
PDF file
MAMahshid Alamdar
Mahshid Alamdar
TLThomas Leonard
Thomas Leonard
CCCan Cui
Can Cui
BRBishweshwor P. Rimal
Bishweshwor P. Rimal
LXLin Xue
Lin Xue
JIJean Anne Incorvia
Jean Anne Incorvia
There are pressing problems with traditional computing, especially for accomplishing data-intensive and real-time tasks, that motivate the development of in-memory computing devices to both store information and perform computation. Magnetic tunnel junction memory elements can be used for computation by manipulating a domain wall, a transition region between magnetic domains, but the experimental study of such devices has been limited by high current densities and low tunnel magnetoresistance. Here, we study prototypes of three-terminal domain wall-magnetic tunnel junction in-memory computing devices that can address data processing bottlenecks and resolve these challenges by using perpendicular magnetic anisotropy, spin–orbit torque switching, and an optimized lithography process to produce average device tunnel magnetoresistance TMR = 171% and average resistance-area product RA = 29 Ω   μ m 2 , close to the RA of the unpatterned film. Device initialization variation in switching voltage is shown to be curtailed to 7%–10% by controlling the domain wall initial position, which we show corresponds to 90%–96% accuracy in a domain wall-magnetic tunnel junction full adder simulation. Repeatability of writing and resetting the device is shown. A circuit shows an inverter operation between two devices, showing that a voltage window is large enough, compared to the variation noise, to repeatably operate a domain wall-magnetic tunnel junction circuit. These results make strides in using magnetic tunnel junctions and domain walls for in-memory and neuromorphic computing applications.

4 May 2018 in Journal of Applied Physics
Verified
Journal Article
Open access
PDF file
TXT. Patrick Xiao
T. Patrick Xiao
KCKaifeng Chen
Kaifeng Chen
PSParthiban Santhanam
Parthiban Santhanam
SFShanhui Fan
Shanhui Fan
EYEli Yablonovitch
Eli Yablonovitch
Electroluminescence—the conversion of electrons to photons in a light-emitting diode (LED)—can be used as a mechanism for refrigeration, provided that the LED has an exceptionally high quantum efficiency. We investigate the practical limits of present optoelectronic technology for cooling applications by optimizing a GaAs/GaInP double heterostructure LED. We develop a model of the design based on the physics of detailed balance and the methods of statistical ray optics, and predict an external luminescence efficiency of ηext = 97.7% at 263 K. To enhance the cooling coefficient of performance, we pair the refrigerated LED with a photovoltaic cell, which partially recovers the emitted optical energy as electricity. For applications near room temperature and moderate power densities (1.0–10 mW/cm2), we project that an electroluminescent refrigerator can operate with up to 1.7× the coefficient of performance of thermoelectric coolers with ZT = 1, using the material quality in existing GaAs devices. We also predict superior cooling efficiency for cryogenic applications relative to both thermoelectric and laser cooling. Large improvements to these results are possible with optoelectronic devices that asymptotically approach unity luminescence efficiency.

17 October 2022 in Frontiers in Nanotechnology
Verified
Journal Article
Open access
SLSamuel Liu
Samuel Liu
TXT. Patrick Xiao
T. Patrick Xiao
JKJaesuk Kwon
Jaesuk Kwon
BDBert J. Debusschere
Bert J. Debusschere
SASapan Agarwal
Sapan Agarwal
CBChristopher H. Bennett
Christopher H. Bennett
Bayesian neural networks (BNNs) combine the generalizability of deep neural networks (DNNs) with a rigorous quantification of predictive uncertainty, which mitigates overfitting and makes them valuable for high-reliability or safety-critical applications. However, the probabilistic nature of BNNs makes them more computationally intensive on digital hardware and so far, less directly amenable to acceleration by analog in-memory computing as compared to DNNs. This work exploits a novel spintronic bit cell that efficiently and compactly implements Gaussian-distributed BNN values. Specifically, the bit cell combines a tunable stochastic magnetic tunnel junction (MTJ) encoding the trained standard deviation and a multi-bit domain-wall MTJ device independently encoding the trained mean. The two devices can be integrated within the same array, enabling highly efficient, fully analog, probabilistic matrix-vector multiplications. We use micromagnetics simulations as the basis of a system-level model of the spintronic BNN accelerator, demonstrating that our design yields accurate, well-calibrated uncertainty estimates for both classification and regression problems and matches software BNN performance. This result paves the way to spintronic in-memory computing systems implementing trusted neural networks at a modest energy budget.