United States

We utilize analog and non-volatile resistive memory devices to construct in-memory computing platforms offering lower power and increased speed. Integration of oxide-based devices with CMOS has been performed in back-end processing, showing analog tunability of the memory elements. We demonstrate acceleration of deep learning neural networks, optimization, finite automata models and tree-based machine learning. We show the potential for significant improvement over CPUs, GPUs, and custom ASICs using these in-memory and analog systems.

DRC 2021

In-memory computing with non-volatile analog memories for machine learning applications

analog

computing

memory

machine learning


![](https://assets.underline.io/uploads/markdown_image/1/image/2e10c515564e9ec3287ee4c664011c20.png)

The energy cost of storing and moving data is enormous, and is growing at such a rapid pace that within a few years the power demand may overwhelm some developed nations. Non-volatile memory (NVM) and neuromorphic computing are enabling critical advances in this area, but there are many scientific and technological challenges. This conference will cover the materials challenges of different memory technologies, from the fundamental processes and mechanisms, to industry perspectives on materials specifications and manufacturing.

Materials Challenges for Memory

technical paper


**[DOWNLOAD THE DRC 2021 DIGEST](https://drive.google.com/file/d/17_-pkYf4IBbVuNYgohTf0iZJORVGp_uN/view?usp=sharing)**

**[DOWNLOAD A COPY OF THE FINAL DRC PROGRAM](https://drive.google.com/file/d/1Ek8UIDCowpLq0z2hXav5tn67FboxS03N/view?usp=sharing)**

For almost eight decades, the Device Research Conference (DRC) has brought together leading scientists, researchers and students to share their latest discoveries in device science, technology and modeling. Notably, many of the first public disclosures of key device technologies were made at the DRC. This year marks the 79th anniversary of the DRC—the longest running device research meeting in the world. As we commemorate this meeting, the high-caliber technical sessions will be highlighted by plenary talks and invited talks by international research pioneers and leaders behind modern electronic technology.

Given the ongoing global health concerns associated with COVID-19 (Coronavirus), the DRC leadership has decided to hold the 2021 Device Research Conference in a virtual (online) format. This follows an enormously successful 2020 DRC held virtually, in which we had record attendance and worldwide participation of more than 875 attendees from 33 countries.

The 2021 Conference will feature:

* Informative, timely short courses in rapidly developing fields
* Oral and poster presentations on electronic/photonic device experiments and simulations
* Plenary and invited presentations given by worldwide leaders
* Evening “rump” session
* Strong student participation and Student Paper Awards

DRC is held in coordination with the Electronic Materials Conference (EMC), which will occur the same week, from June 23-25. As has happened in person in past years, in 2021, the virtual DRC and EMC sessions on the shared day, Wednesday, June 23, will be open to all attendees from both conferences. This recognizes the strong interaction between device and electronic materials research and provides fruitful exchanges of information between attendees of both Conferences. For information on the 63rd Electronic Materials Conference, please visit the [EMC 2021 website.](https://www.mrs.org/63rd-emc/)

2021 DRC individual presentation videos will become available in Underline at the end of each technical session. A recording of each full live session with Q&A will be posted later during the conference. To facilitate re-viewing of recorded talks and sessions, the DRC Underline site will remain open through 11:59pm (US EDT) on July 7th. DRC Conference registration will remain open at www.mrs.org/drc-2021/registration through June 30th.

Thank you for joining us at the 2021 Device Research Conference!

**General Chair**
<br>Zhihong Chen, Purdue University

**Technical Program Chair**
<br>Becky (R.L.) Peterson, University of Michigan

**Technical Program Vice-Chair**
<br>Gregg Jessen, BAE Systems

You can register for the 79th Device Research Conference with the following link. https://www.mrs.org/drc-2021

For almost eight decades, the Device Research Conference (DRC) has brought together leading scientists, researchers and students to share their latest discoveries in device science, technology and modeling. Notably, many of the first public disclosures of key device technologies were made at the DRC. This year marks the 79th anniversary of the DRC—the longest running device research meeting in the world. As we commemorate this meeting, the high-caliber technical sessions will be highlighted by plenary talks and invited talks by international research pioneers and leaders behind modern electronic technology.

Recently, low-power analog switches have been enjoying rapidly growing interest owing to their proliferation in mobile and reconfigurable communication and connectivity systems often with multiple-input-multiple-output architecture. To develop this ideal switch, non-volatile switches based on memory devices have been investigated with the potential of zero static power dissipation. Here, we report the first single-pole-double-throw (SPDT) non-volatile RF switches based on monolayer MoS2.

Single-Pole-Double-Throw RF switches based on monolayer MoS2

Platinum diselenide, Photodetector, 2D materials, PtSe2, Infrared photodetector

Waveguide-Integrated Photodetectors based on 2D Platinum Diselenide

"Amorphous GaOx back-gated TFTs with Al2O3 dielectric are demonstrated. Both the channel and dielectric are grown by ALD. The TFTs exhibit high Ion/Ioff (1e6) and low sub-threshold slope (138 mV/dec).

Vt variation with forward and reverse Vg sweeps, with repeated runs, and with channel length and thickness is observed. Encapsulating the channel with in-situ ALD Al2O3 improves the Vt shift.

This is the first demonstration of ALD a-GaOx TFT, aimed towards 3D BEOL integration for More-than-Moore applications.

AAmorphous ALD-grown GaOx TFT for BEOL integration

thin-film transistor, indium oxide, indium zinc oxide, high-k, semiconductor modeling

Mobility Boost in Transparent Oxide Semiconductors with High-κ Gated TFTs

Antiferromagnets, Spin torque, LLG, Terahertz gap, spintronics

Terahertz auto oscillations in non-collinear coplanar metallic antiferromagnets

Electrical isolation of read and write paths, exchange coupling, perpendicular magnetic anisotropy, spintronic device, compute-in-memory, neuromorphic application

Exchange-Coupling-Enabled Electrical-Isolation of Compute and Programming Paths in Valley-Spin Hall Effect based Spintronic Device for Neuromorphic Applications

Ultra-low loss; Silicon nitride waveguide

Downloads

Next from DRC 2021

Single-Pole-Double-Throw RF switches based on monolayer MoS2

Similar lecture

Analog memory: materials, devices, applications

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from DRC 2021

Single-Pole-Double-Throw RF switches based on monolayer MoS2

Similar lecture

Analog memory: materials, devices, applications

Downloads