[paper] ULTRARAM Neuromorphic Memory Device

Abhishek Kumar, Peter D. Hodgson, Manus Hayne, and Avirup Dasgupta

Artificial synapse based on ULTRARAM memory device for neuromorphic applications

Journal of Applied Physics 139, no. 12 (2026)

DOI: 10.1063/5.0314826

1. Department of Electrical Engineering and Computer Sciences, UCB (USA)

2. Department of Physics, Lancaster University, Lancaster LA1 4YB (UK)

3. Quinas Technology Limited, Lancaster LA1 4YB, (UK)

4. Department of Electronics and Communication Engineering, IIT Roorkee (IN)

Abstract: The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory, such as dynamic random-access memory, which reduces energy efficiency and increases training time. Monolithic crossbar or pseudo-crossbar arrays using analog non-volatile memories, which can store and update weights on-chip, present an opportunity to efficiently accelerate DNN training. In this article, we present on-chip training and inference of a neural network using an ULTRARAM memory device-based synaptic array and complementary metal–oxide–semiconductor (CMOS) peripheral circuits. ULTRARAM is a promising emerging memory exhibiting high endurance (⁠> 10E7P/E cycles), ultrahigh retention (⁠>1000 years), and ultralow switching energy per unit area. A physics-based compact model of ULTRARAM memory device has been proposed to capture the real-time trapping/de-trapping of charges in the floating gate and utilized for the synapse simulations. A circuit-level macro-model is employed to evaluate and benchmark the on-chip learning performance in terms of area, latency, energy, and accuracy of an ULTRARAM synaptic core. In comparison with CMOS-based design, it demonstrates an overall improvement in area and energy by 1.8x and 1.52x⁠, respectively, with 91% of training accuracy.

FIG: Schematic of an ULTRARAM memory cell and the corresponding transmission electron microscope image of the device’s epilayers

Acknowledgments: This work was supported in part by the Quinas Technology Limited, Lancaster, United Kingdom; Indian Institute of Technology Roorkee, India; and Prime Minister’s Research Fellowship, Ministry of Education, Government of India under Grant No. PM-31-22-773-414.

Data Availability: The data that support the findings of this study are available within the article.

[PhD] ULTRARAM™ at Lancaster University

Lancaster University, Physics Department has three open PhD Projects, Programmes & Scholarships

• Scaling ULTRARAM™ on FindAPhD.com
  The PhD project will further advance the development of ULTRARAM™ memory. ULTRARAM™ is an ultra-efficient, multi-award-winning memory technology that combines the non-volatility of flash with the speed and endurance of dynamic random access (DRAM).
• Vertical-cavity surface-emitting lasers for below-screen consumer (and other) applications at Lancaster University on FindAPhD.com
  The PhD project will further develop a patented approach to implementing vertical-cavity surface-emitting lasers (VCSELs) operating at telecoms wavelengths
• Novel compound-semiconductor logic for computing applications on FindAPhD.com
  The PhD project will further develop a patent-pending alternative approach to digital logic that abandons the CMOS paradigm underpinning computing

Supervisor: Prof. M. Hayne

Application deadline: 29 February 2024 // Competition Funded PhD Project (UK Students Only)

[paper] ULTRARAM Memory on Silicon

Peter D. Hodgson, Dominic Lane, Peter J. Carrington, Evangelia Delli, 

Richard Beanland and Manus Hayne

ULTRARAM: A Low-Energy, High-Endurance, Compound-Semiconductor Memory 

on Silicon

First published: 05 January 2022

Adv. Electron. Mater. 2022, 8, 2101103

DOI: 10.1002/aelm.202101103

Abstract: ULTRARAM is a nonvolatile memory with the potential to achieve fast, ultralow-energy electron storage in a floating gate accessed through a triple-barrier resonant tunneling heterostructure. Here its implementation is reported on a Si substrate; a vital step toward cost-effective mass production. Sample growth using molecular beam epitaxy commences with deposition of an AlSb nucleation layer to seed the growth of a GaSb buffer layer, followed by the III–V memory epilayers. Fabricated single-cell memories show clear 0/1 logic-state contrast after ≤10ms duration program/erase pulses of ≈2.5V, a remarkably fast switching speed for 10 and 20µm devices. Furthermore, the combination of low voltage and small device capacitance per unit area results in a switching energy that is orders of magnitude lower than dynamic random access memory and flash, for a given cell size. Extended testing of devices reveals retention in excess of 1000 years and degradation-free endurance of over 107 program/erase cycles, surpassing very recent results for similar devices on GaAs substrates.

FIG: a) Schematic cross-section of ULTRARAM device concept with corresponding material layers. The floating gate (1: FG), triple-barrier resonant-tunneling structure (2: TBRT), and readout channel (3) are highlighted. Arrows indicate the direction of electron flow during program/erase operations; b) Scanning electron micrograph of a fabricated device of 10 µm gate length. 

Acknowledgements: P.D.H. and D.L. contributed equally to this work. This work was supported by the Engineering and Physical Sciences Research Council, UK, via the 2017–2020 Impact Acceleration Account funding allocation to Lancaster University under grant EP/R511560/1, a scholarship under grant EP/N509504/1, equipment funding under grant EP/T023260/1, and the Future Compound Semiconductor Manufacturing Hub grant EP/P006973/1, by the ATTRACT project funded by the EC under Grant Agreement 777222 and by the Joy Welch Educational Charitable Trust.