News

ICTGC Batch 4 Winner Introduction - Linque

 2026-06-26 By: InnoVEX Team

Disrupting Compute Infrastructure with Linque


Linque is a Germany-based startup aiming to transform AI infrastructure with photonic network switches for data centers. As one of the winners of the IC Taiwan Grand Challenge Batch 4 in the AI Core Technologies and Chips category, Linque’s CMOS-scalable technology reduces network power, space, and latency, unlocking the next generation of AI data centers.

Overcoming the AI Scaling and Cost Challenge


The rapid development and adoption of AI has driven compute requirements to a level where entire data centers need to act as a single contiguous unit as individual processors are unable to process data individually. This operational reality combined with the technological constraints of present day hardware places a massive strain on the technical requirements of the networks, particularly in terms of bandwidth throughput and data latency, as well as the massive amount of power consumption that stems from the energy-intensive translation between the electrical and the optical domain.

Current data centers already use up to 15% of their electrical power on networking and are expected to go as high as 50% by the end of this decade. In addition, networking hardware takes up to one-third of space in a single rack, resulting in lower efficiency and complex infrastructure planning as well as cooling costs. Linque RISE is an all-optical circuit switching technology built on large-scale photonic integrated circuits that routes data entirely in the optical domain, eliminating power-hungry optical-electrical-optical conversions, enabling ultra-high bandwidth, nanosecond-scale reconfiguration, and significantly lower energy consumption for AI-driven data center networks.

Introducing IC Taiwan Grand Challenge


To strengthen Taiwan's position as a global semiconductor powerhouse, the National Science and Technology Council (NSTC) organizes the IC Taiwan Grand Challenge. Started in 2024, the competition originally focused purely on innovative IC designs and advanced application solutions. Today, ICTGC also honors teams in the fields of AI Core Technologies and Chips, Smart Mobility, Smart Manufacturing, Smart Medtech, and Sustainability, which can support and contribute to the semiconductor industry and Taiwan’s industry in general. Linque is selected as one of the winners of ICTGC Batch 4 with their Linque RISE technology in the AI Core Technologies and Chips category.

Bringing Optical Switching to the Next Level with Linque RISE


Linque was founded in 2025 as a spinoff of LMU Munich and focuses on the development of photonic switch processors (PSPs) based on very-large-scale integrated photonic integrated circuits (VLSI-PICs). The core innovation is a proprietary low-loss, high-speed electro-optic modulator technology based on two-dimensional materials, enabling nanosecond-scale optical switching with low insertion loss.

Linque's technology enables all-optical circuit switching inside data centers, eliminating repeated optical-electrical-optical (OEO) conversions. This enables dynamic, ultra-fast reconfiguration of network topologies, providing scalable AI clusters, HPC systems, and future AI factories with 10s of Tb/s throughput and sub-microsecond latency. Linque's innovation is able to overcome the limitations of current technologies that utilize optical circuit switching (OCS) such as slow reconfiguration speed (over 10 ms), high unit costs, and low reliability that limits this approach to specific use-cases such as long-term topology changes, maintenance or dynamic redundancy. Applied in the Linque RISE, Linque's proprietary technology is capable of bringing 20x efficiency gain for AI Deployment. It is able to perform sub-microsecond configuration, provide transparent bandwidth, and remove overhead costs from transceivers.

[{"bannerId":"48dec9a1-3e73-4255-88e6-95d14d2c27b9","imgPathWide":"/2020/_uploads/202101040952071641.jpg","imgPathThin":null,"go2Url":"https://innovex.computex.biz/2020/SHOW/pressReleaseDetails.aspx?newsId=313","ifOpenNew":true,"landAt":"2020Show","seq":1,"title":null}]