Marvell Demonstrates Silicon Photonics Light Engine for Low-power, Rack-scale Interconnect in AI Networks
Marvell Technology (NASDAQ: MRVL) has unveiled its new 1.6T silicon photonics light engine integrated into a linear-drive pluggable optics (LPO) module at OFC 2025. This innovative solution, the second in Marvell's light engine family, supports eight channels of 200 Gbps PAM4 optical interconnect with standards-based signaling.
The light engine consumes less than 5 picojoules per bit, including laser power, under typical conditions. It consolidates hundreds of components including modulators, photodetectors, drivers, and microcontrollers in a single package, optimized for pluggable modules.
This quarter-scale implementation of the 6.4T light engine addresses next-generation AI scale-up network requirements, offering a solution for mid-density rack-scale connectivity. The product is currently sampling to select customers.
Marvell Technology (NASDAQ: MRVL) ha presentato il suo nuovo motore luminoso in fotonica siliconica da 1,6T integrato in un modulo ottico pluggable a guida lineare (LPO) durante l'OFC 2025. Questa soluzione innovativa, la seconda nella famiglia di motori luminosi di Marvell, supporta otto canali di interconnessione ottica PAM4 da 200 Gbps con segnalazione basata su standard.
Il motore luminoso consuma meno di 5 picojoule per bit, inclusa la potenza laser, in condizioni tipiche. Consolida centinaia di componenti tra cui modulatori, fotodetettori, driver e microcontrollori in un unico pacchetto, ottimizzato per moduli pluggable.
Questa implementazione in scala ridotta del motore luminoso da 6,4T soddisfa i requisiti delle reti di scalabilità AI di prossima generazione, offrendo una soluzione per la connettività rack-scale a densità media. Il prodotto è attualmente in fase di campionamento per clienti selezionati.
Marvell Technology (NASDAQ: MRVL) ha presentado su nuevo motor de luz de fotónica de silicio de 1.6T integrado en un módulo óptico enchufable de conducción lineal (LPO) en OFC 2025. Esta solución innovadora, la segunda en la familia de motores de luz de Marvell, admite ocho canales de interconexión óptica PAM4 de 200 Gbps con señalización basada en estándares.
El motor de luz consume menos de 5 picojulios por bit, incluida la potencia del láser, en condiciones típicas. Consolida cientos de componentes, incluidos moduladores, fotodetectores, controladores y microcontroladores en un solo paquete, optimizado para módulos enchufables.
Esta implementación a escala de un cuarto del motor de luz de 6.4T aborda los requisitos de redes de escalabilidad de IA de próxima generación, ofreciendo una solución para la conectividad a escala de rack de densidad media. El producto se encuentra actualmente en fase de muestreo para clientes seleccionados.
마벨 테크놀로지 (NASDAQ: MRVL)는 OFC 2025에서 선형 구동 플러그형 광학 모듈(LPO)에 통합된 1.6T 실리콘 포토닉스 광 엔진을 공개했습니다. 이 혁신적인 솔루션은 마벨의 광 엔진 가족의 두 번째 제품으로, 표준 기반 신호를 사용하는 200 Gbps PAM4 광 상호 연결의 8개 채널을 지원합니다.
광 엔진은 일반적인 조건에서 레이저 전력을 포함하여 비트당 5 피코줄 미만을 소비합니다. 모듈레이터, 포토디텍터, 드라이버 및 마이크로컨트롤러를 포함한 수백 개의 구성 요소를 단일 패키지로 통합하여 플러그형 모듈에 최적화되었습니다.
6.4T 광 엔진의 1/4 스케일 구현은 차세대 AI 확장 네트워크 요구 사항을 충족하며, 중간 밀도의 랙 스케일 연결성을 위한 솔루션을 제공합니다. 이 제품은 현재 선택된 고객에게 샘플링되고 있습니다.
Marvell Technology (NASDAQ: MRVL) a dévoilé son nouveau moteur lumineux en photonique siliceuse de 1,6T intégré dans un module optique enfichable à entraînement linéaire (LPO) lors de l'OFC 2025. Cette solution innovante, la deuxième de la famille des moteurs lumineux de Marvell, prend en charge huit canaux d'interconnexion optique PAM4 de 200 Gbps avec signalisation basée sur des normes.
Le moteur lumineux consomme moins de 5 picojoules par bit, y compris la puissance du laser, dans des conditions typiques. Il regroupe des centaines de composants, y compris des modulateurs, des photodétecteurs, des pilotes et des microcontrôleurs dans un seul package, optimisé pour les modules enfichables.
Cette mise en œuvre à échelle réduite du moteur lumineux de 6,4T répond aux exigences des réseaux de montée en échelle de l'IA de prochaine génération, offrant une solution pour la connectivité rack-scale à densité moyenne. Le produit est actuellement en échantillonnage pour des clients sélectionnés.
Marvell Technology (NASDAQ: MRVL) hat seinen neuen 1,6T Silizium-Photonik-Lichtmotor vorgestellt, der in ein linear angetriebenes steckbares Optikmodul (LPO) integriert ist, und zwar auf der OFC 2025. Diese innovative Lösung, die zweite in der Lichtmotorenfamilie von Marvell, unterstützt acht Kanäle mit 200 Gbps PAM4 optischer Interkonnektivität mit standardbasierter Signalübertragung.
Der Lichtmotor verbraucht unter typischen Bedingungen weniger als 5 Pikojoule pro Bit, einschließlich Laserleistung. Er fasst Hunderte von Komponenten wie Modulatoren, Photodetektoren, Treiber und Mikrocontroller in einem einzigen Paket zusammen, das für steckbare Module optimiert ist.
Diese viertelmaßstabsgetreue Implementierung des 6,4T Lichtmotors erfüllt die Anforderungen an Netzwerke mit KI-Skalierung der nächsten Generation und bietet eine Lösung für die mitteldichte Rack-Skalierungskonnektivität. Das Produkt wird derzeit ausgewählten Kunden zur Verfügung gestellt.
- New product launch expands company's optical solutions portfolio
- High integration reduces component complexity and accelerates time to market
- Energy efficient design with less than 5 pJ/bit power consumption
- Strong market demand reported by industry analysts
- availability - only sampling to select customers
- Faces competition in the 1.6T optics market segment
Insights
Marvell's 1.6T silicon photonics light engine represents a significant advancement in AI network infrastructure. The technology addresses a critical bottleneck in AI scale-up architectures by enabling power-efficient optical interconnects at 200 Gbps per lane across eight channels. This solution bridges the gap between copper interconnects ( by reach) and future co-packaged optics.
What's technically impressive is the high level of integration - consolidating hundreds of components including modulators, drivers, TIAs, and microcontrollers into a single package while achieving less than 5 picojoules per bit power consumption. This power efficiency is crucial for dense AI compute environments where thermal constraints are significant limiting factors.
The strategic importance lies in Marvell's approach to ecosystem development. By providing a validated reference design, they're accelerating adoption while positioning themselves centrally in the AI networking value chain. The 1.6T light engine creates a foundation for both near-term LPO deployment and longer-term CPO architectures, giving Marvell flexibility as the market evolves.
The industry analyst quote confirms strong demand for 1.6T optics, validating Marvell's market timing. With the product currently sampling to select customers, this positions Marvell competitively in the high-growth AI infrastructure segment where optical interconnect is becoming increasingly critical for performance scaling.
- Highly integrated optical engine enables lower power and reduced latency for high-bandwidth LPO and on-board optics
- 1.6T light engine contains linear driver, TIA, and silicon photonics chip supporting 200 Gbps per lane, with embedded microcontroller and firmware in a single package
- Demonstrated at OFC 2025 in a 1.6T OSFP LPO module, 1.6T light engine simplifies system integration and accelerates time to market for rack-scale AI server deployments
For 1.6T pluggable applications, the light engine provides flexibility and accelerated time-to-market for both ecosystem module vendors and hyperscalers. As AI scale-up domains increase in size from rack-scale to row-scale, the scale-up fabric will transition from passive copper interconnects to customized and optimized optics. Even at rack-scale, for moderate compute-density racks, LPO at 200G per lane can serve as an alternative to passive copper, offering low power, low latency and longer reach than copper. Prior to the introduction of XPUs with integrated CPO, LPO modules and on-board optics can address row-scale reach requirements at 200 Gbps-per-lane rates.
The new light engine is a quarter-scale implementation of the 6.4T light engine. Like its predecessor, the 1.6T light engine is a highly integrated device featuring 200G electrical and optical interfaces. It consumes less than 5 picojoules per bit (pJ/bit), including laser power, measured under typical operating conditions. The 1.6T light engine consolidates hundreds of components such as modulators, photodetectors, modulator drivers, transimpedance amplifiers (TIAs), microcontrollers, and a host of other passive components in a single package optimized for use in pluggables such as LPO modules, transmitter-retimed optics and fully retimed optics modules.
"Marvell is advancing power-efficient AI scale up with its 1.6T light engine, delivering deployment-ready solutions for module vendors and hyperscalers," said Josef Berger, associate vice president marketing, Cloud Platforms at Marvell. "As the long-term transition from copper to optics in the scale-up domain unfolds, Marvell is well-positioned to co-develop the custom CPO systems that will be needed for high-density, row-scale scale-up domains."
"Demand for 1.6T optics is strong, but power consumption remains a challenge," said Vlad Kozlov, CEO and Chief Analyst at LightCounting. "Linear drive pluggables offer a lower power option for customers to consider and completes Marvell's product portfolio for 1.6T interconnects."
Availability
The 1.6T light engine is sampling to select customers.
About Marvell
To deliver the data infrastructure technology that connects the world, we're building solutions on the most powerful foundation: our partnerships with our customers. Trusted by the world's leading technology companies for over 25 years, we move, store, process and secure the world's data with semiconductor solutions designed for our customers' current needs and future ambitions. Through a process of deep collaboration and transparency, we're ultimately changing the way tomorrow's enterprise, cloud, automotive, and carrier architectures transform—for the better.
Marvell and the M logo are trademarks of Marvell or its affiliates. Please visit www.marvell.com for a complete list of Marvell trademarks. Other names and brands may be claimed as the property of others.
This press release contains forward-looking statements within the meaning of the federal securities laws that involve risks and uncertainties. Forward-looking statements include, without limitation, any statement that may predict, forecast, indicate or imply future events, results or achievements. Actual events, results or achievements may differ materially from those contemplated in this press release. Forward-looking statements are only predictions and are subject to risks, uncertainties and assumptions that are difficult to predict, including those described in the "Risk Factors" section of our Annual Reports on Form 10-K, Quarterly Reports on Form 10-Q and other documents filed by us from time to time with the SEC. Forward-looking statements speak only as of the date they are made. Readers are cautioned not to put undue reliance on forward-looking statements, and no person assumes any obligation to update or revise any such forward-looking statements, whether as a result of new information, future events or otherwise.
For further information, contact:
pr@marvell.com
View original content to download multimedia:https://www.prnewswire.com/news-releases/marvell-demonstrates-silicon-photonics-light-engine-for-low-power-rack-scale-interconnect-in-ai-networks-302415565.html
SOURCE Marvell