Weebit Nano's ReRAM Selected for Korean National Compute-in-Memory Program
MWN-AI** Summary
Weebit Nano Limited (ASX: WBT) has been selected for a significant initiative funded by the Republic of Korea aimed at enhancing ultra-low-power analog compute-in-memory (ACiM) technology for artificial intelligence (AI) applications. This program addresses the energy and performance limitations of traditional AI accelerators by enabling computation to occur directly within memory arrays using Weebit’s advanced Resistive RAM (ReRAM) technology.
The ACiM paradigm allows for storing neural network weights in ReRAM crossbar arrays, facilitating in-place vector-matrix multiplication. This innovative method is expected to minimize data movement, significantly increasing throughput and energy efficiency for both AI inference and training workloads.
Weebit Nano has renewed its collaboration with DB HiTek, the South Korean foundry responsible for manufacturing devices for this consortium. Other participants include several prestigious institutions like the Daegu Gyeongbuk Institute of Science and Technology and Seoul National University, along with AnalogAI, which aims to commercialize the resulting ACiM technology.
A major focus of the program is transitioning from initial test structures to large-scale silicon implementations. The consortium plans to develop silicon-verified ACiM blocks and work on application-scale evaluations and co-optimization across both device and circuit levels, targeting an impressive energy efficiency of approximately 200 TOPS/W.
Coby Hanoch, CEO of Weebit Nano, emphasized the importance of bringing memory closer to computation to lower power consumption and latency, highlighting the project's role in advancing ACiM technology from research stages to commercial readiness. This initiative reflects Korea's broader AI Transformation Initiative, seeking to bolster domestic capabilities in the AI semiconductor sector. Beyond AI, the methodologies developed are likely to have wide applications across various semiconductor areas, indicating a promising future for Weebit Nano's technology advancements.
MWN-AI** Analysis
**Market Analysis and Investment Advice for Weebit Nano (ASX: WBT)**
Weebit Nano's recent selection for the Korean National Compute-in-Memory Program marks a critical milestone for the company, solidifying its position in the rapidly evolving semiconductor landscape. The advent of ultra-low-power analog compute-in-memory (ACiM) technology highlights Weebit's ReRAM as a pivotal technology for addressing the increasing demands of AI applications.
The strategic partnership with DB HiTek and involvement in a consortium with notable academic and industrial players positions Weebit for significant growth opportunities. This program not only seeks to enhance the energy and performance of AI accelerators but also aims to scale their technology from theoretical constructs to practical applications in commercial silicon. With a goal of achieving approximately 200 TOPS/W energy efficiency, the implications for AI workloads—particularly in inference and training—are profound.
Investors should take note of the country's strong commitment to fostering semiconductor innovation through its AI Transformation Initiative, creating a favorable backdrop for Weebit Nano to capture market share in this critical sector. The company's technology stands to disrupt traditional memory solutions, presenting a compelling value proposition given the global trend towards energy-efficient computing.
Additionally, Weebit's ability to integrate its ReRAM technology into existing manufacturing processes allows for relatively low barriers to entry when scaling operations. This attribute, combined with the consortium's focus on application-scale evaluations, enhances the likelihood of rapid adoption across various semiconductor domains beyond AI.
In light of these developments, Weebit Nano presents a viable investment opportunity. Investors should consider entering or increasing their position in WBT as the company progresses through this national initiative, with a long-term view toward the broader applicability of its ReRAM technology in diverse, high-growth segments including automotive and industrial systems. Monitoring milestones related to the Korean program will be essential for gauging the company's trajectory.
**MWN-AI Summary and Analysis is based on asking OpenAI to summarize and analyze this news release.
HOD HASHARON, Israel, March 05, 2026 (GLOBE NEWSWIRE) -- Weebit Nano Limited (ASX:WBT) (Weebit or Company), a leading developer and licensor of advanced memory technologies for the global semiconductor industry, has been selected to participate in a Republic of Korea government-funded program focused on advancing ultra-low-power analog compute-in-memory (ACiM) technology for AI applications. Weebit’s ReRAM technology is a foundational memory element for the program.
The national program aims to address the energy and performance limitations of conventional AI accelerators by enabling computation directly within memory arrays. In this ACiM* paradigm, neural-network weights are stored in ReRAM crossbar arrays, allowing vector-matrix multiplication to be performed in place. This approach can significantly reduce data movement, improving both throughput and energy efficiency for AI inference and, longer term, training workloads.
As part of this effort, Weebit Nano has extended its agreement with DB HiTek, the Korea-based foundry that will manufacture devices for the consortium. Additional participants include the Daegu Gyeongbuk Institute of Science and Technology, Seoul National University, Chungbuk National University, the Electronics and Telecommunications Research Institute (ETRI), and AnalogAI, a company focused on commercializing products based on the resulting ACiM blocks.
A key objective of the program is to move beyond small-scale test structures toward large, device-array-based silicon implementations. The consortium will focus on silicon-verified ACiM blocks, application-scale evaluation, and co-optimization across device, circuit, and architectural levels, targeting energy efficiency on the order of ~200 TOPS/W. The work is intended to demonstrate integration of emerging synapse-device arrays with commercial silicon-CMOS processes and circuits, establishing a complete and repeatable development flow for ACiM.
Coby Hanoch, CEO of Weebit Nano, said: “AI system designers are increasingly looking to bring memory closer to compute to reduce power and latency. In memory compute is a practical path toward that goal, but it requires validation at realistic scales. This initiative combines device innovation, circuit and architecture co-design, and manufacturable silicon, which is exactly what’s needed to move ACiM from research to deployable technology. We’re delighted to extend our agreement with DB HiTek as part of this effort, continuing our excellent relationship.”
Fred Kim, General Manager, Sales Division, DB HiTek, said: “This project is part of the Republic of Korea’s broader AI Transformation Initiative, which supports technologies critical to future AI semiconductor leadership. By combining emerging memory devices with proven CMOS manufacturing, the consortium aims to significantly improve AI energy efficiency while building domestic capability and a sustainable ecosystem spanning academia and industry. Weebit ReRAM is the ideal memory device to use as a foundation for this work.”
Beyond AI, the consortium’s methodologies for co-design, optimization, and verification of emerging devices are expected to have broader applicability across multiple semiconductor application domains.
* Also called ‘In Memory Compute’, or ‘IMC’
About Weebit Nano Limited
Weebit Nano Ltd. is a leading developer and licensor of advanced semiconductor memory technology. The company’s ground-breaking Resistive RAM (ReRAM) addresses the growing need for significantly higher performance and lower power memory solutions in advanced system-on-chip (SoC) designs for applications such as AI inference, automotive electronics, industrial systems, analog and power ICs, and secure devices. Weebit ReRAM allows semiconductor memory elements to be significantly faster, less expensive, more reliable and more energy efficient than those using existing flash memory solutions. As it is based on fab-friendly materials, the technology can be quickly and easily integrated with existing flows and processes, without the need for special equipment or large investments. See www.weebit-nano.com.
Weebit Nano and the Weebit Nano logo are trademarks or registered trademarks of Weebit Nano Ltd. in the United States and other countries. Other company, product, and service names may be trademarks or service marks of others.
For further information, please contact:
Media – US
Jen Bernier-Santarini, Weebit Nano
P: +1 650-336-4222
E: jen@weebit-nano.com
Media – Australia
Jasmine Walters, Automic Group
P: +61 498 209 019
E: jasmine.walters@automicgroup.com.au
Investors
Adrian Mulcahy
P: +61 438 630 422
E: Adrian.mulcahy@automicgroup.com.au
FAQ**
How does Weebit Nano WBTNF plan to leverage its ReRAM technology to enhance energy efficiency in AI applications within the Republic of Korea's ACiM program?
In what ways can Weebit Nano WBTNF's partnership with DB HiTek improve the scalability of their analog compute-in-memory technology?
How does the participation of academic institutions like Seoul National University benefit Weebit Nano WBTNF in advancing ultra-low-power memory solutions?
What potential broader applications does Weebit Nano WBTNF foresee for its co-design methodologies developed in the ACiM project?
**MWN-AI FAQ is based on asking OpenAI questions about Weebit Nano (OTC: WBTNF).
NASDAQ: WBTNF
WBTNF Trading
2.43% G/L:
$3.375 Last:
17,756 Volume:
$3.54 Open:
