.jpg)
1 hour ago
4
Article content
Joint achievement highlights how Analog In-Memory Computing can address the growing energy and thermal challenges of AI while laying the foundation for deeper collaboration on next-generation memory and computing architectures.
THIS CONTENT IS RESERVED FOR SUBSCRIBERS ONLY
Subscribe now to read the latest news in your city and across Canada.
- Exclusive articles from Barbara Shecter, Joe O'Connor, Gabriel Friedman, and others.
- Daily content from Financial Times, the world's leading global business publication.
- Unlimited online access to read articles from Financial Post, National Post and 15 news sites across Canada with one account.
- National Post ePaper, an electronic replica of the print edition to view on any device, share and comment on.
- Daily puzzles, including the New York Times Crossword.
SUBSCRIBE TO UNLOCK MORE ARTICLES
Subscribe now to read the latest news in your city and across Canada.
- Exclusive articles from Barbara Shecter, Joe O'Connor, Gabriel Friedman and others.
- Daily content from Financial Times, the world's leading global business publication.
- Unlimited online access to read articles from Financial Post, National Post and 15 news sites across Canada with one account.
- National Post ePaper, an electronic replica of the print edition to view on any device, share and comment on.
- Daily puzzles, including the New York Times Crossword.
REGISTER / SIGN IN TO UNLOCK MORE ARTICLES
Create an account or sign in to continue with your reading experience.
- Access articles from across Canada with one account.
- Share your thoughts and join the conversation in the comments.
- Enjoy additional articles per month.
- Get email updates from your favourite authors.
THIS ARTICLE IS FREE TO READ REGISTER TO UNLOCK.
Create an account or sign in to continue with your reading experience.
- Access articles from across Canada with one account
- Share your thoughts and join the conversation in the comments
- Enjoy additional articles per month
- Get email updates from your favourite authors
Sign In or Create an Account
or
Article content
SAN JOSE, Calif. & ICHEON, South Korea — TetraMem Inc., a leader in Analog In-Memory Computing (A-IMC) technology, and SK hynix Inc., a global leader in AI memory and semiconductor technologies, today announced the successful completion of a joint technology collaboration, highlighted by the publication of their research paper, “A Memristor-based In-Memory Computing SoC with Efficient Depthwise Convolution,” in Advanced Intelligent Systems. The work has also been selected as the cover feature of the journal, recognizing its technical innovation and potential impact on next-generation AI computing.
Article content
Article content
Article content
Article content
The collaboration brings together SK hynix’s expertise in advanced memory technologies and TetraMem’s Analog In-Memory Computing platform to explore new computing architectures capable of addressing one of artificial intelligence’s most pressing challenges: reducing the energy consumption and thermal limitations associated with rapidly growing AI workloads.
Article content
By signing up you consent to receive the above newsletter from Postmedia Network Inc.
Article content
As foundation models continue to scale from billions to trillions of parameters, data movement between processors and memory has become a dominant contributor to system power consumption, latency, and thermal challenges. Analog In-Memory Computing (A-IMC) addresses this bottleneck with a fundamentally different architecture by performing matrix operations directly where the model weights reside, dramatically reducing data movement while improving system-level performance and energy efficiency—compute where the AI model weights live.
Article content
The published work demonstrates a memristor-based AI System-on-Chip (SoC) implementing efficient depthwise convolution, an important building block for modern AI inference workloads. Beyond demonstrating the feasibility of Analog In-Memory Computing, the project showcases the successful integration of emerging memory devices, circuit design, AI architecture, software, and system optimization into a practical semiconductor platform.
Article content
More importantly, the project reflects the strong engineering collaboration between the SK hynix RTC and TetraMem teams, combining complementary expertise to advance memory-centric AI computing technologies.
Article content
“We are honored to celebrate this important milestone together with SK hynix,” said Glenn Ge, CEO and Co-Founder of TetraMem. “This achievement demonstrates what can be accomplished through close collaboration across the semiconductor ecosystem. As AI continues to evolve, breakthroughs will require innovation not only in compute, but also in memory and system architecture. We believe memory-centric computing and Analog In-Memory Computing will become increasingly important technologies for addressing future AI energy efficiency and thermal challenges, and we look forward to continuing our collaboration with SK hynix.”
Article content
Soo Gil Kim, Vice President of SK hynix
Article content
, said, “We are pleased to see the successful outcome of this collaboration and the recognition from
Article content
Article content
Advanced Intelligent Systems
Article content
. This project demonstrates the value of exploring innovative memory technologies and new computing architectures for future AI systems. We appreciate the excellent collaboration with the TetraMem team and look forward to continued technical exchanges in areas of mutual interest.”
Article content
The selection of the work as the journal’s cover feature further recognizes the significance of the joint achievement and the growing importance of memory-centric computing within the AI industry.
Article content
Looking ahead, both companies recognize that future AI infrastructure will require continued advances across memory technology, computing architecture, and system integration to address increasing demands for performance, energy efficiency, and sustainable computing. Building upon the success of this collaboration, the two organizations look forward to exploring additional opportunities for technical collaboration that advance next-generation AI computing technologies.
Article content
The paper, “A Memristor-based In-Memory Computing SoC with Efficient Depthwise Convolution,” is now available online in Advanced Intelligent Systems.
Article content
About TetraMem
Article content
TetraMem Inc. is a Silicon Valley semiconductor company pioneering Analog In-Memory Computing (A-IMC) based on multi-level memristor (RRAM) technology. Its memory-centric AI computing platform enables high-performance, energy-efficient AI inference for edge, enterprise, and future data center applications.
Article content
About SK hynix
Article content
SK hynix Inc. is a global semiconductor company and a leading supplier of HBM, NAND Flash, and advanced AI memory solutions. The company continues to develop innovative memory technologies that power next-generation AI, high-performance computing, and data-centric applications worldwide.
Article content
Article content
Article content
Article content
View source version on businesswire.com:
Article content
Article content
Article content
Contacts
Article content
English (US)