2026 OCP APAC Summit
The event theme for the 2026 OCP APAC Summit, “Leading the Future of AI”, exemplifies the OCP Community’s collaborations over the years that drive openness, efficiency, sustainability, scalability and growth, shaping the future of AI data centers, driving innovation across the global data center and edge technology ecosystem. With AI, the pace of technological evolution has increased dramatically and the collaborations within the OCP Community have become central to enabling a rapid AI data center buildout.
We are at a technology inflection point in the data center industry, driven by a large investment in AI data centers. We see the need to rethink data center IT equipment, facilities and silicon supply chains. Thus, the OCP Community has expanded its Open Data Center Ecosystem Vision to include all elements of the data center, from grid to chip. Through its Open Systems for AI strategic initiative, the OCP Community is working on important technology advancements in (1) chiplet technology and associated advanced packaging, (2) in rack systems such as cooling and power distribution, networking and storage, server architectures and optical interconnect for scale-up networking, and (3) data center facility reference architectures that cover higher voltage, direct current distribution to the data hall, integrated telemetry and systems management between the facilities and data hall, and coordinated interactions with the power grid.
OCP APAC Summit Day 1 - Tuesday, August 11
9:15 AM - 11:30 AM: Keynotes
11:30 AM - 6:30 PM: Expo Hall Open
12:00 - 1:00 PM: Lunch
1:00 - 5:00 PM: Breakout Sessions
1:00 - 5:00 PM: SONiC Workshop
5:00 - 7:30 PM: Welcome Reception
OCP APAC Summit Day 2 - Wednesday, August 12
9:00 AM - 4:00 PM: Expo Hall Open
9:00 AM - 12:00 PM: Breakout Sessions
12:00 - 1:00 PM: Lunch
1:00 - 4:00 PM: Breakout Sessions
Wed, August 12, 2:45pm - 3:00pm | 7 Floor - 701G
Speaker: Erik Chen, Co-Founder & CEO, Artilux (Categories: Photonics)
A Hybrid Optoelectronic Computing Architecture for Energy-Efficient AI on Mature CMOS Nodes
The next phase of AI growth demands more than incremental advances in semiconductor scaling. In this talk, we introduce Inception™, a novel hybrid optoelectronic computing approach grounded in first-principles thinking, combining the strengths of photonics and electronics into a unified paradigm while remaining compatible with existing computing infrastructure.
The hybrid nature of this architecture enables massive parallel dot-product computation in a single step using dense 2D arrays of optoelectronic neurons (OENs). This approach delivers orders-of-magnitude improvements in energy efficiency within a compact chip footprint, while achieving no data skew and negligible propagation delay, overcoming limitations of conventional systolic arrays.
Implemented on mature CMOS nodes and requiring no active cooling, Inception™ offers a practical and scalable path toward next-generation AI systems. Key architectural principles, performance targets, and system-level implications will be discussed.
More details , please visit the official event site.