In the News

ECOC 2026

Avicena won the Post Deadline Award for Lower Optical Communications Value Chain Technology and Products for their LightBundle™ eKit 1Tbps Evaluation Kit for microLED-based interconnects. Avicena demoed the eKit live at ECOC in their booth, and the significance of this technological advancement certainly drew the attention of the organizers and attendees of ECOC 2026.

Watch the ECOC Award Interview on YouTube.

Avicena LightBundle connector

IEEE Spectrum

In the race to an all-optical AI data center, a major player has now placed a bet on a different horse. Semiconductor manufacturing giant TSMC announced that it will work with Sunnyvale startup Avicena to produce microLED-based interconnects. The technology is a pragmatic twist on replacing electrical connections with optical ones to meet the high needs of communication among an increasing number of GPUs in a low cost, energy efficient way.

Avicena and TSMC logos

GazettaByte

GazettaByte — TSMC, the leading semiconductor foundry, will make the photo-detectors used for Avicena Tech’s microLED optical interconnect technology.

Avicena is developing an optical interface that uses hundreds of parallel fibre links – each link comprising a tiny LED tranmitter and a silicon photo-detector receiver – to deliver terabit-per-second (Tbps) data transfers.

ECOC Exhibitor News

Avicena’s LightBundle µLED-based chip-to-chip interconnect will be showcased at the European Conference on Optical Communications (ECOC) 2024, with a particular focus on its advantages for On-Board and Co-Packaged Optics.
OC_ECOC News image

Optical Connections

Optical Connections — The demand for processing power in HPC (High Performance Computing), AI (Artificial Intelligence) and ML (Machine Learning) is increasing at an unprecedented rate and although Moore’s law isn’t happening anymore, by its strictest definition, it is still delivering steady improvements in processor performance, albeit at a slower pace.
PHOTONICS spectra

Photonics Spectra

The LightBundle from Avicena is a scalable chiplet interconnect for extending high bandwidth memory modules and die-to-die connections from GPUs. The chiplets can extend connections up to 10 m and dissipate <1 pJ/bit for optical interconnects and support multi-Tbps/mm beachfront density.

Optical Connections

Optical Connections — Avicena has debuted its scalable LightBundle chiplet interconnect, which extends ultra-high density die-to-die (D2D) connections up to 10m at multi-Tbps/mm shoreline bandwidth density and sub-pJ/bit energy efficiency. Based on Avicena’s LightBundle platform which supports shoreline density and energy efficiency, it unlocks increased performance from HPC and AI cluster architectures.

Gazettabyte

Avicena has demonstrated what it claims is the world’s smallest one terabit optical transceiver. And the company will reveal more about how it is advancing its optical technology for volume production at the upcoming OFC event in San Diego in March.

Optical Connections

Optical Connections covered Avicena’s debut of the world’s smallest 1Tbps optical transceiver as part its LightBundle™ multi-Tbps chip-to-chip interconnect technology at the 2023 SuperComputing event. The microLED-based architecture supports unprecedented throughput, shoreline density and low power, unlocking the performance of processors, memory, and sensors.
LightCounting LightTrends Newsletter logo

Lightcounting

Avicena is featured in LightCounting Light Trends Newsletter for December 2023 where they discuss highlights from Supercomputing Conference: SC 2023. “Other photonic show highlights include optical interconnect demonstrations from Avicena that showed what it claims is the world’s smallest 1 terabit-per-second (Tb/s) microLED-based transceiver.”

IEEE Spectrum

Avicena is featured in IEEE Spectrum for December 2022. While conventional Silicon Photonics provides a solution for medium to long reach communications, Avicena’s microLED technology enables ultra-low energy interconnects for short reach links ideally suited for chip-to-chip applications in HPC, AI/ML and memory disaggregation.