SAN JOSE, Calif. & ICHEON, South Korea - Wednesday, 08. July 2026
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.
(BUSINESS WIRE) -- 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.
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.
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.
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.
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.
“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.”
Soo Gil Kim,
Vice President of SK hynix, said, “We are pleased to see the successful
outcome of this collaboration and the recognition from Advanced
Intelligent Systems. 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.”
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.
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.
The paper, “A Memristor-based In-Memory Computing
SoC with Efficient Depthwise Convolution,” is now available online in
Advanced Intelligent Systems.
About TetraMem
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.
About SK hynix
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.
View source version on businesswire.com: https://www.businesswire.com/news/home/20260708244132/en/
Permalink
https://www.aetoswire.com/en/news/0807202656110
Contacts
Media Contact:
Glenn Ge
pr@tetramem.com
No comments:
Post a Comment