Company expands collaboration with DB HiTek towards AI in-memory-compute applications
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
