SiPho Loss Reality Check: The Trick Behind Low-Loss SiN
jwt0625 · x · 2026-08-22
A technical rebuttal to claims about "high density SiN with 0.1 dB/cm propagation loss."
- Definition Debate: This should be classified as medium density at best. Truly low-loss nitride often "cheats" using thin waveguides where the mode is mostly in oxide.
- Current State: Good SiPho foundries already have multiple nitride layers.
- Specific Metrics: Edge coupler loss should be 0.4-0.6 dB (not <1 dB). Grating couplers often have alignment tolerances placed in the wrong row.
- Missing Factors: Bandwidth was not discussed, which is critical for CWDM or bidi DWDM.
Related event: Engineers Push Back on Silicon Photonics Interconnect Claims(4 posts)→
More from Infra
- TSMC earnings note cross-referenced with WFE model and power checks in CS Atlas — BenBajarin · 2026-10-16
- Fluidstack hires Electrical Engineer for Modular R&D to build frontier AI infrastructure — MxMnr · 2026-10-16
- Jensen Huang joins BG2 podcast: does AI revenue justify capex, '27 bottlenecks — elonmusk · 2026-10-16
- Mistral's on-device infra rack revealed: DGX Spark, Mac Studio and more — gregmushen · 2026-10-16
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16