Gazettabyte is asking industry figures for their thoughts after attending the recent OFC show in San Diego. Here are the thoughts of BT's Professor Andrew Lord, author and consultant, Daryl Inniss, and Cignal AI's Kyle Hollasch.
Andrew Lord, senior manager of research and optical networks, BT Group.
I am excited to see the developments around 100G ZR pluggables. Assuming they can hit the power requirements, I can imagine them being used across the edge for years to come.
I learned that there is some confidence in the optical community that optics has a significant part to play in the AI revolution. But this is still primarily associated with high bit rate transport, whether it be fibres or inter-chip. Photonic integrated switches to assist with future GPUs is, on the other hand, likely to be limited by the wavelength of light and resulting small numbers of components on a realistic-sized photonic integrated circuit.
I was taken totally by surprise by the final paper in the conference: a 0.11dB/km Hollow Core Fibre from Lumensity/ Microsoft and Southampton University. What an incredible result! It makes me wonder where the main network impacts would be for fibres having losses significantly below standard fibre.
Daryl Inniss, consultant
My surprise at OFC 2024 is the number of colleagues and friends who announced retirement, are planning to retire, or who have retired. Where did the time go? I feel like the party just got going.
This OFC was unique because I attended as an individual contributor (i.e., analyst). I attended the conference to learn about technical and commercial advances, challenges, and opportunities.
I spent most of my time on the infrastructure required for AI, paying attention to developments in optical connections to chips. Given the enormous potential of optical interconnect for higher bandwidth, lower power, lower latency, and longer distances, the industry nonetheless has significant challenges to resolve.
I saw many approaches, yet no silver bullet for getting light from the semiconductor to the optical fibre. How will that be done? And at scale with high reliability and low cost?
I was impressed with South Korean firm, Lessengers, who I ran into during one of my exhibition hall walks. They use a Direct Optical Wiring (DOW) polymer process to connect fibres to chips. The polymer waveguide is air clad. The process is passive and in-situ, and they have demonstrated connecting an array of up to 64 fibres. I first thought Lessengers was part of Dow Corning given the material basis and the big "DOW" on their stand. Such is the power of branding.
I was also impressed with the SQS booth, a Czech company that presented a wide range of products for connecting chips and fibre.
There were also many interesting presentations and demonstrations with optics connected to chiplets.
- Lightmatter's wafer-scale approach with chipset optical connections using silicon photonics is impressive. Chiplets (CPUs, memory, etc.) are attached to the photonic integrated circuit wafer. Lightmatter reports 40 waveguides in the space of one optical fibre and 800+ Tbps input/output from each chipset, among other high-performance features.
- Intel demonstrated its Optical Compute Interconnect (OCI), a silicon photonics integrated circuit that can be packaged with XPUs. The integrated circuit delivers up to 4 Tbps today and is extendable to 32 Tbps. Intel touts its strength in laser reliability, given that it has shipped 32 million on-chip lasers.
- Ayar Labs unveiled its second generation of SuperNova multi-wavelength light source that delivers 16 terabits-per-second (Tbps) of bi-directional bandwidth (16 wavelengths and 16 ports).
The laser is a crucial element for these applications. As bandwidth demand grows, the market’s needs will grow from coarse WDM to dense WDM. Of note is that Innolume announced that it would increase its quantum dot laser capacity before the show to support the silicon photonics ecosystem that may use them.
Two post-deadline papers stood out because I worked closely in both areas: Southampton University's paper on hollow-core fibre loss less than 0.11 dB/km, lower than that of silica core glass, and KDDI's paper on 16.4 THz bandwidth in the O-band over 80.4 km in an unrepeated link. Both show new technologies that can serve the communications industry well.
We all return to OFC because it is like family. We get a chance to catch up with friends and acquaintances. Often, it takes OFC to catch up with people in our industry who live in the same town.
My biggest takeaway from OFC? It’s the people.
Kyle Hollasch, lead analyst, transport hardware at Cignal AI
The OFC show has always been about looking to the future of optical transport. For years, we envisioned a glorious day in the distant future when single wavelengths of light would carry a terabit per second of data, and the industry would shrink coherent optics to such tiny dimensions that they could fit into a router port. What was amazing about OFC 2024 is not that we saw products pushing terabit wavelengths or that we’re witnessing the realisation of the two-decade pursuit of IP-over-DWDM, but how ho-hum we are about it. The optical transport world feels like the dog which finally caught the car.
At OFC, it became clear that the pendulum of interest and investment had swung inside the data centre. Short-reach optical interconnect will dominate the show for the foreseeable future.
The proceedings and demos on the transport side struck me as a requiem for high-performance coherent optics.
Has the arms race that for 15 years steadily marked progress in optical networking, punctuated by OFC announcements, run its course? Half a dozen vendors touted their progress in terabit transmission. Kudos to Acacia for leading in time-to-market (again) and to Ciena for boldly blazing a technological trail to higher baud rates (again).
Yet the only WAN-centric development that generated much excitement was 800ZR pluggable, which packages two decades of intensely competitive technological wizardry into a standardized, interoperable transceiver small enough to be lost in your couch cushions. It’s everything the industry ever wanted: interoperable between multiple vendors and the ability to span metro and long-haul networks. It can also be put in a router and a transponder.
So, like that dog, we’re faced with the question: What do we do now? What will keep the transport world engaged at the coming OFCs?
The answer is to keep looking to the future. Just as data centre innovation revolves around its primary scarcity of power, transport network innovation will continue to be defined by its fundamental challenge: delivering capacity over distance.
We’re seeing that begin as new fibre types, such as hollow core, are getting a serious look, along with new transmission bands. High-end coherence will continue, and transmission rates higher than 1.6 terabits will be achieved. But those advancements won’t result in much more capacity or distance but rather at the other significant constraint in optical transport networks: cost.