SAMSUNG-ELECTRONICS
13.1.2022 10:02:06 CET | Business Wire | Press release
Samsung Electronics Co., Ltd., a world leader in advanced semiconductor technology, today announced its demonstration of the world's first in-memory computing based on MRAM (Magnetoresistive Random Access Memory). The paper on this innovation was published online by Nature on January 12 (GMT), and is set to be published in the upcoming print edition of Nature . Titled ‘A crossbar array of magnetoresistive memory devices for in-memory computing’1 , this paper showcases Samsung’s leadership in memory technology and its effort to merge memory and system semiconductors for next-generation artificial intelligence (AI) chips.
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20220113005393/en/
The research was led by Samsung Advanced Institute of Technology (SAIT) in close collaboration with Samsung Electronics Foundry Business and Semiconductor R&D Center. The first author of the paper, Dr. Seungchul Jung, Staff Researcher at SAIT, and the co-corresponding authors Dr. Donhee Ham, Fellow of SAIT and Professor of Harvard University, and Dr. Sang Joon Kim, Vice President of Technology at SAIT, spearheaded the research.
In the standard computer architecture, data is stored in memory chips and data computing is executed in separate processor chips.
In contrast, in-memory computing is a new computing paradigm that seeks to perform both data storage and data computing in a memory network. Since this scheme can process a large amount of data stored within the memory network itself without having to move the data, and also because the data processing in the memory network is executed in a highly parallel manner, power consumption is substantially reduced. In-memory computing has thus emerged as one of the promising technologies to realize next-generation low-power AI semiconductor chips.
For this reason, research on in-memory computing has been intensely pursued worldwide. Non-volatile memories, in particular RRAM (Resistive Random Access Memory) and PRAM (Phase-change Random Access Memory), have been actively used for demonstrating in-memory computing. By contrast, it has so far been difficult to use MRAM ─ another type of non-volatile memory ─ for in-memory computing despite MRAM’s merits such as operation speed, endurance, and large-scale production. This difficulty stems from the low resistance of MRAM, due to which MRAM cannot enjoy the power reduction advantage when used in the standard in-memory computing architecture.
The Samsung Electronics researchers have provided a solution to this issue by an architectural innovation. Concretely, they succeeded in developing an MRAM array chip that demonstrates in-memory computing, by replacing the standard, ‘current-sum’ in-memory computing architecture with a new, ‘resistance sum’ in-memory computing architecture, which addresses the problem of small resistances of individual MRAM devices.
Samsung’s research team subsequently tested the performance of this MRAM in-memory computing chip by running it to perform AI computing. The chip achieved an accuracy of 98% in classification of hand-written digits and a 93% accuracy in detecting faces from scenes.
By ushering MRAM ─ the memory which has already reached commercial-scale production embedded in the system semiconductor fabrication ─ into the realm of in-memory computing, this work expands the frontier of the next-generation low-power AI chip technologies.
The researchers have also suggested that not only can this new MRAM chip be used for in-memory computing, but it also can serve as a platform to download biological neuronal networks. This is along the line of the neuromorphic electronics vision that Samsung’s researchers recently put forward in a perspective paper published in the September 2021 issue of the journal Nature Electronics .
"In-memory computing draws similarity to the brain in the sense that in the brain, computing also occurs within the network of biological memories, or synapses, the points where neurons touch one another,” said Dr. Seungchul Jung, the first author of the paper. “In fact, while the computing performed by our MRAM network for now has a different purpose from the computing performed by the brain, such solid-state memory network may in the future be used as a platform to mimic the brain by modelling the brain’s synapse connectivity."
As highlighted in this work, by building on its leading memory technology and merging it with system semiconductor technology, Samsung plans to continue to expand its leadership in next-generation computing and AI semiconductors.
# # #
About Samsung Electronics Co., Ltd.
Samsung inspires the world and shapes the future with transformative ideas and technologies. The company is redefining the worlds of TVs, smartphones, wearable devices, tablets, digital appliances, network systems, and memory, system LSI, foundry and LED solutions. For the latest news, please visit the Samsung Newsroom at news.samsung.com.
1 https://www.nature.com/articles/s41586-021-04196-6
View source version on businesswire.com: https://www.businesswire.com/news/home/20220113005393/en/
Link:
About Business Wire
Subscribe to releases from Business Wire
Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.
Latest releases from Business Wire
Spatial Announces Release 2027 1.0 with New Enhancements Across CAD Modeling, Interoperability, Data Preparation, and Meshing17.11.2026 20:10:00 CET | Press release
Spatial Corp., the leading software development kit provider for design, manufacturing and engineering solutions and a subsidiary of Dassault Systèmes, today announced the availability of its 2027 1.0 Release. This latest release introduces new capabilities and enhancements across Spatial's 3D ACIS Modeler, CGM Modeler, 3D InterOp, Data Prep and CSM/CVM product lines. Designed to improve efficiency, flexibility and robustness across CAD modeling, interoperability, data preparation and simulation workflows, the release delivers enhanced geometry processing, expanded modeling capabilities, improved CAD translation and advances in mesh generation for a better workflow coverage. 3D ACIS Modeler Enhanced Blending (Filleting) The 3D ACIS Modeler introduces support for asymmetric fixed-width blends with a conic cross-section, providing users with finer control over smooth transitions between edges. This enhancement builds on the symmetric fixed-width blend with a conic cross-section capabilit
Global EV Alliance Survey: EV Drivers Identify Myths and Misconceptions as the Biggest Barrier to Adoption17.11.2026 19:00:00 CET | Press release
Myths and misconceptions about electric cars, from battery lifespan and fire risk to grid collapse, are the biggest barrier to EV adoption, according to respondents to the annual Global EV Driver Survey. The 2026 survey draws on responses from more than 29,500 EV drivers across 34 countries. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261117539716/en/ MYTHS. Battery lifespan (72%), fire risk (58%) and grid collapse (45%) top the list of EV myths reported by respondents to the 2026 Global EV Driver Survey, which gathered responses from more than 29,500 EV drivers across 34 countries. “The EV transition is not just an infrastructure or affordability challenge. It is also an information challenge. Outdated information and misconceptions continue to influence decisions long after the technology has moved on,” says Ellen Hiep, from the Steering Committee of the Global EV Alliance (GEVA). Myths the greatest barrier Asked to ide
TreeFrog Therapeutics Appoints James Sterling as Chief Financial Officer17.11.2026 18:04:00 CET | Press release
Seasoned biotech CFO with gene therapy, diagnostics, IPO and Wall Street experience joins the executive leadership team TreeFrog Therapeutics, a biotechnology company developing scalable cell therapies built on its proprietary C-Stem™ technology, today announced the appointment of James Sterling as Chief Financial Officer, effective November 1, 2026. James joins TreeFrog’s executive leadership team and reports to Mark Rothera, President and Chief Executive Officer. He oversees finance, investor relations and corporate development as the company enters its next phase of growth. “I am delighted to welcome James to TreeFrog. James brings a valuable combination of biotech CFO and Wall Street experience that supports our ambitions to develop TreeFrog into a key enabling partner and drug developer in the regenerative medicines field,” said Mark Rothera, President and Chief Executive Officer of TreeFrog Therapeutics. James contributes deep experience in corporate finance, capital markets and
Visa Report: AI-Enabled Fraud and Third-Party Attacks Are Scaling Worldwide17.11.2026 16:40:00 CET | Press release
Third-party incidents surged 62%, while Visa Scam Disruption identified more than $1.4 billion in potential fraud Fraud is becoming more automated, targeted and global as criminals use AI to exploit weak points across the payments ecosystem and target third-party providers that can provide access to multiple downstream payment organizations, according to the Visa (NYSE: V) Fall 2026 Biannual Threats Report released today during International Fraud Awareness Week. Developed by Visa Payment Ecosystem Risk and Control (PERC), the report examines threat activity observed between January and June 2026 and finds that AI is not creating entirely new categories of fraud. Instead, it is helping criminals that execute existing attacks faster, at greater scale, and with greater precision, while increasingly targeting third-party providers that can provide access to multiple downstream organizations at once. Although attack volumes increased in several areas, the report also found evidence that co
Sparxity Appoints former Cray CEO Peter Ungaro and Semiconductor Veteran Daniel Armbrust to its Advisory Board17.11.2026 16:00:00 CET | Press release
Appointments bring decades of leadership experience in supercomputing, semiconductor commercialization, and scaling advanced computing business Sparxity, a leader in sparse-native computing, today announced that Peter Ungaro, former President and CEO of Cray, Inc., and Daniel Armbrust, former President and CEO of SEMATECH and co-founder of Silicon Catalyst, have joined its Advisory Board as independent members. Armbrust has been elected Chairman of the Advisory Board and Ungaro Deputy Chairman by their fellow board members. The appointments strengthen the company’s leadership as it scales its sparse-native computing technology for next-generation AI and high-performance computing (HPC). This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261117761685/en/ From left to right, Daniel Armbrust, former President and CEO of SEMATECH and co-founder of Silicon Catalyst and Peter Ungaro, former President and CEO of Cray, Inc. Peter Ungaro
In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.
Visit our pressroom
