top of page
OPTICS · SEMICONDUCTORS · AI INFRASTRUCTURE | stt@simpletechtrend.com
Articles: Blog2
ARTICLES
Articles
Explainers, conference notes, earnings-call reads and market insights on optical communications, silicon photonics, CPO and the AI infrastructure supply chain.
Search


EPIC Photonics for AI Data Centers 2026 | Lumentum | External Laser Sources for Deployable CPO-Based AI Networks
CPO was sold on pJ/bit, but MTTR will decide it. Lumentum framed laser placement as a service-model question and answered with faceplate ELSFPs, while five other speakers pointed to the next bottleneck: up to a million fiber cores per rack.
3 days ago8 min read


Earnings Call: ams OSRAM (AMS) | Q3 2026 — €319M Net Profit Came From Selling Businesses and the Core Still Loses Money; AI Photonics Bets on 850nm microVCSEL With No Revenue Yet
ams OSRAM's €319M reported profit was almost entirely a divestment gain; on an adjusted basis it still lost money, with LEDs and automotive lamps carrying the core. Its AI bet is an 850nm microVCSEL for slow-and-wide links, backed by Credo and BizLink, but reliability and volume manufacturing still stand between it and revenue.
Nov 148 min read


OCP Global Summit 2026 | LightXcelerate | Weipeng Zhang, Manchen Hu | High-Density Optical I/O Using Micro-VCSEL Arrays and Multicore Fiber
Slow-and-wide optics keeps losing on fiber count. LightXcelerate matches its micro-VCSEL layout to a 19-core fiber, so 57 lanes need only 3 fibers, but its 32G eye margin is just 5.5% and 1.5 pJ/bit is still simulated.
Oct 237 min read


OCP Global Summit 2026 | Ligent Tech | Weiping Huang, Jianwei Mu | Beyond Pluggable Optics: The Emerging Role of NPO
Same 3.2T, two engines with a 5x power gap: Ligent's 23 W SiPh engine targets switch network I/O, its 4.5 W VCSEL engine targets XPU scale-up. NPO is not one product but a movable E/O boundary, and the contest is shifting to packaging and interface specs.
Oct 227 min read


OCP Global Summit 2026 | Lumentum | Oleg Shchekin | Slow and Wide 12.8T VCSEL Solutions
Lumentum's 12.8T is not a new chip but the same 1060 nm VCSEL array repeated 16 times. Slow-and-wide fits best where the host is natively NRZ, like PCIe, and today's ~1 Tb/s/mm is about 6x short of the 12.8T configuration.
Oct 208 min read


It Wasn't Physics That Killed Slow-and-Wide, It Was 60,000 Fibers: The Network's Shape Before 2029 and Who Wins
Bandwidth is per-lane speed times lane count. Push speed and you hit the SerDes energy floor; push lane count and you hit fiber and connector cost. The new fact this year: the second wall arrived first.
Oct 72 min read


After Copper Gives Out for AI: Seven Paths for Scale-Up Optical Interconnect, and Two Ways to Live With the Bottlenecks
Scale-up optical interconnect looks like a seven-way melee, but there are really only two strategies, Fast-and-Narrow and Slow-and-Wide, each hitting a symmetric wall. Learn the yardstick first, then see how the seven approaches layer and coexist.
Oct 53 min read


OFC 2026 - Breaking the GPU Cluster Scaling Bottleneck: A 1060nm Sensing-Grade VCSEL Interconnect - Lumentum Operations LLC
Tackling both the power and capacity bottlenecks of GPU scale-up, Lumentum taps the mature 3D sensing and LiDAR supply chain to redefine high-density interconnect with 1060nm VCSEL arrays.
Oct 52 min read


OFC 2026 - 800G CPO Breakthrough: 1060-nm Single-Mode VCSEL Reaches 2 km at 4.1 pJ/bit - Furukawa Electric
Can a VCSEL go 2 km? At OFC 2026, Furukawa Electric showed an ultra-compact 800G CPO transceiver that uses 1060-nm single-mode VCSELs to hit 4.1 pJ/bit over standard single-mode fiber, challenging silicon photonics in AI interconnects.
Oct 53 min read


Paper Analysis | Intel Takes VCSEL CPO Below 1 pJ/b: A Full Circuit Breakdown from 4×50G NRZ to 108G PAM4
Silicon photonics gets the spotlight, but Intel's 0.9 pJ/b 108G PAM4 link shows VCSELs remain an underrated low-power path for short-reach CPO. We walk through this CICC 2026 paper section by section, figure by figure, and identify the last three miles VCSEL CPO must cover to reach volume: equalization, packaging and thermals.
Oct 57 min read


850 nm Didn't Lose on Speed, It Lost on Junction Temperature: The 1060 Generation Replaces the Entire Chain
850 nm is being pushed off the AI scale-up shortlist not because of speed but because of junction temperature. Moving to 1060 nm isn't swapping a die — fiber, PD, packaging and standards all have to change together.
Oct 52 min read


ECOC 2026 | 850nm Dies at 1,600 Hours, 1060nm Hits 5,000 Hours with Zero Failures: How One Lumentum Chart Moved the VCSEL Battle from Speed to Heat
An 850nm VCSEL that passed a 20-year, 100G production spec failed after 1,600 hours in scale-up rack thermal conditions, while a 1060nm device under identical conditions ran 5,000 hours unscathed. At ECOC 2026, Lumentum used one chart to show the VCSEL bottleneck was never speed—it is heat.
Oct 512 min read


ECOC 2026 | A 1,024-Lane Switch Stuck at 0.07 T/mm: Huawei Says NPO Isn't "LPO Moved onto the Board" — It's a Full Switch Redesign
Chasing every option would force optical module makers to develop more than 50 SKUs. And at 1,024 lanes, OSFP beachfront density is just 0.07 T/mm versus a 0.3 T/mm target — a gap of over 4x. Huawei argues NPO means redesigning the whole switch, from sockets and thermals to PI/SI.
Oct 510 min read


ECOC 2026 | Same Day, Same Wavelength, Opposite Answers on Fiber: Lumentum Says OM3 Won't Work at 1060nm, Berxel Just Ran 100m of OM3
On the same day and at the same wavelength, Lumentum said OM3 and OM4 can't be used at 1060nm, while Berxel ran 100 meters of OM3. The number that really matters from this talk is ±22 µm: it downgrades optical packaging from precision alignment to simply placing the part.
Oct 511 min read


ECOC 2026 | VCSELs Hit ≤1 pJ/bit Long Ago; Fiber Is the Real Bottleneck. Did NVIDIA Pause Its Slow-and-Wide Project Over It, and Propose a New 26/80 Fiber?
In a session dominated by silicon photonics, NVIDIA argued that VCSELs already deliver ≤1 pJ/bit. What holds them back is fiber: 2,304 strands per GPU, 60,000 per data hall, and fiber cost is why NVIDIA paused its own slow-and-wide project.
Oct 513 min read


ECTC 2026 | Furukawa | Technical Analysis | VCSELs Can Go 2 km: Furukawa Fits a 1060nm Single-Mode VCSEL CPO into a Standard MT Ferrule
VCSELs have long been dismissed as 100-meter light sources. Furukawa's 1060nm single-mode VCSEL CPO reaches 2 km at 4.1 pJ/bit using a standard MT ferrule and off-the-shelf fiber. The real breakthrough is not lower power, but finally plugging into existing fiber infrastructure.
Oct 57 min read


What Does OSFP 800G SR8 Actually Mean? The Five Axes Behind Optical Module Naming
"OSFP 800G SR8" is not a part number — it is five axes stacked together. Learn form factor, data rate, reach, electrical I/O and light source, and you can read any optical module spec and see why two 800G modules can differ 3x in price. Interactive lookup tool included.
Oct 59 min read


OFC 2026 - A Key Step Toward 1.6 Tbps Silicon-Based NPO: Berxel Photonics Unveils a 940nm Back-Emitting VCSEL with an Integrated Metalens
VCSELs evolve again. At OFC 2026, Berxel Photonics revealed a back-emitting VCSEL with an integrated metalens, overcoming thermal and alignment challenges in a 1.6 Tbps array demo and sketching a new blueprint for short-reach AI interconnect.
Oct 53 min read


Technical Article Analysis | Broadcom 200G VCSEL Deep Dive: NPO, the Power-Saving Weapon for AI Scale-Up Networks
Broadcom's latest 200G VCSEL paper reports over 35 GHz bandwidth and about 1 pJ/bit efficiency, paired with a new NPO architecture aimed at replacing copper in AI scale-up networks. We walk through all 12 figures.
Oct 53 min read


OFC 2026: A Deep Dive into VCSEL Mass Production and Process Control at WIN Semiconductors
At OFC 2026, WIN Semiconductors showed what it takes to be the world's leading III-V foundry: tight control of trench etch and oxide aperture underpins a VCSEL supply chain of millions of wafers, while it builds out advanced processes for CPO and autonomous driving.
Oct 53 min read
SUBSCRIBE
Want the full supply-chain breakdown?
Subscribe to STT for premium articles: in-depth earnings-call reads, supply-chain maps and weekly industry insights.
bottom of page