Friday, October 2, 2026
AI 인프라 · 뉴스 & 분석
홈 › 반도체·하드웨어 › 리포트
반도체·하드웨어 · 리포트

Q/C Technologies is collaborating with Sandia National Laboratories on nanophotonics-based optical processing units for AI inference acceleration.

Optical compute moves from academic research toward production via vendor-lab partnership; diversifies inference substrate options beyond electronic silicon.
업계 전문지Slicast · 2026년 10월 1일 14:30 UTC · 글로벌 · 출처: HPCwire
중요도 64

Q/C Technologies, Inc., a developer of next-generation optical computing solutions, has announced a collaboration with the Center for Integrated Nanotechnologies (CINT) at Sandia National Laboratories to advance its proprietary optical processing unit (OPU) initiative for artificial intelligence inference. The partnership focuses on joint research into nanophotonic components and the physical building blocks required for scalable optical AI processing.

Sandia National Laboratories, one of the nation's leading multi-mission science and engineering laboratories operated for the U.S. Department of Energy's National Nuclear Security Administration, brings substantial resources to the effort. The lab employs approximately 17,000 people and maintains an annual budget of roughly $5 billion, with deep capabilities spanning microelectronics, photonics, advanced materials, high-performance computing and systems engineering.

Q/C Technologies' collaboration with CINT aims to establish and verify a defensible roadmap for optical AI hardware that goes beyond incremental GPU scaling. The project will identify and prioritize optical operations and device technologies for Q/C's OPU architecture while addressing key technical challenges including nonlinear operations, memory, precision, optical loss and integration with electronic systems.

"Access to CINT's scientific expertise and advanced research capabilities in photonics and nanoscale technologies represents an important step as we develop our proprietary optical computing platform," said Joshua Silverman, Executive Chairman of Q/C Technologies. "As AI infrastructure faces increasing constraints in power consumption, bandwidth and scalability, we believe optical computing has the potential to fundamentally change how computationally intensive AI workloads are processed. This collaboration will help us evaluate key architectural concepts as we continue building the foundation for our next-generation optical computing solution."

Yossef Ehrlichman, Ph.D., Chief Technology Officer at Q/C Technologies, added: "This collaboration provides an opportunity to accelerate our work toward a practical, scalable optical computing architecture. We believe this work with CINT will help us define the pathway from fundamental optical capabilities to an integrated OPU architecture."

The partnership marks another milestone for Q/C Technologies' OPU initiative. The company recently established a 4,800-square-foot integrated photonics laboratory in San Francisco and continues to build its foundation of knowledge and engineering expertise in AI, photonics and computing to support development of its proprietary architecture.

원문 보기
Q/C Technologies is collaborating with Sandia… · Slicast