News


Samsung breakthrough demos in-memory computing using MRAM

24 November 2021 News

A research breakthrough by Samsung Electronics has resulted in the world’s first in-memory computing based on MRAM (magnetoresistive random access memory). The research demonstrates Samsung’s advanced memory technology and its effort to merge memory and system semiconductors for next-generation artificial intelligence (AI) chips.

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 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 realise 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 merits such as operation speed, endurance and large-scale production. This difficulty stems from the low resistance of MRAM, due to which it 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 through an architectural innovation resulting in an MRAM array chip that demonstrates in-memory computing by replacing the standard ‘current-sum’ in-memory computing architecture with a new ‘resistance sum’ alternative, 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 93% accuracy in detecting faces from scenes.

The researchers have also suggested that not only can this new MRAM chip be used for in-memory computing, but it can also 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 a solid-state memory network may in the future be used as a platform to mimic the brain by modelling the brain’s synapse connectivity.”




Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

Vicor Powering Innovation podcast
News
The episode explores electrification with Lightning Motorcycles, a company that produces the fastest electric motorcycle on the planet.

Read more...
ModusToolbox Workshop 3
News
This workshop will focus on enabling a PSoC development kit, connected over Wi-Fi and leveraging MQTT, to create the framework of an IoT application.

Read more...
Indium celebrates 90 years of innovation
Techmet News
The company’s innovative products, especially its advanced soldering solutions, are found in many common consumer electronics and high-reliability technologies.

Read more...
Revamped technical training centre in Welkom
News
Resolution Circle has announced the launch of its newly revamped training centre in Welkom, which will enhance technical education and foster industry partnerships.

Read more...
From the editor's desk: Funga: The unseen rulers of a new kingdom
Technews Publishing News
Up until a few weeks ago, our classification kingdoms were split into two parts; fauna and flora. I was amazed when I recently read that National Geographic has now changed this and has split the classification ...

Read more...
Hiconnex announces new partnership
Hiconnex News
With over 60 years of experience in the civil, military aeronautics, and space industries, Petercem offers robust solutions for position detection and human machine interfaces.

Read more...
Global semiconductor sales increase YoY
News
The Semiconductor Industry Alliance (SIA) has announced global semiconductor sales totalled $47,6 billion during the month of January, an increase of 15,2% compared to January 2023.

Read more...
Utility-scale solar development for local company
News
Teraco has announced that it has secured its first grid capacity allocation from Eskom, and will commence construction of a 120 MW utility-scale solar PV energy facility in the Free State province.

Read more...
Collab between Arrow and Infineon
Altron Arrow News
Arrow Electronics, represented by Altron Arrow in South Africa, and its engineering services company, eInfochips, are working with Infineon Technologies to help eInfochip’s customers accelerate the development of EV chargers.

Read more...
Printing as a subscription
News
HP has done the unthinkable and released its All-In Plan, a subscription-based printing solution that has many IT professionals and business users shaking their heads.

Read more...