Intel debuts Gaudi 3 AI processor

Intel introduced its Gaudi 3 AI accelerator for training and inference on popular large language models (LLMs) and multimodal models.

The Gaudi 3 processor delivers 4x AI compute for BF16,  1.5x increase in memory bandwidth, and 2x networking bandwidth for massive system scale out compared to its predecessor.

Features and Improvements:

• The Gaudi 3 AI accelerator is built on a 5nm process, offering advanced efficiency for large-scale AI compute.
• It includes 64 AI-custom Tensor Processor Cores (TPCs) and eight Matrix Multiplication Engines (MMEs), capable of performing 64,000 parallel operations for improved computational efficiency and deep learning computations.
• The accelerator boasts 128GB of HBMe2 memory, 3.7TB of memory bandwidth, and 96MB of on-board SRAM, facilitating large GenAI dataset processing with enhanced performance and cost efficiency.
• It features twenty-four 200Gb Ethernet ports for flexible, open-standard networking and efficient system scaling from single nodes to large clusters.
• Integrates with PyTorch framework and provides optimized community-based models for ease of use and productivity in GenAI development.

Performance Projections, according to Intel: 

• Compared to Nvidia's H100, the Intel Gaudi 3 is expected to offer 50% faster training times and inference throughput for various LLMs, including Llama and GPT-3 models, with significant improvements in inference power efficiency.
• A projected 30% faster inferencing compared to Nvidia's H200 on similar models.

Market Adoption and Availability:

• Scheduled for OEM availability in Q2 2024 with general availability in Q3 and the PCIe add-in card in Q4 2024.
• Notable OEMs like Dell Technologies, HPE, Lenovo, and Supermicro will market the Gaudi 3.
• The Gaudi 3 accelerator aims to power cost-effective cloud LLM infrastructures, offering performance and cost advantages.

Strategic Importance:

• The accelerator supports critical sectors transitioning GenAI projects to full-scale implementations, requiring open, cost-effective, and energy-efficient solutions.
• Designed for scalability, performance, and energy efficiency, meeting enterprise needs for return on investment and operational efficiency.
• The momentum of Gaudi 3 accelerators is foundational for the development of Falcon Shores, Intel’s next-generation GPU, combining Intel Gaudi and Intel Xe IP under a unified programming interface based on the Intel oneAPI specification.

“In the ever-evolving landscape of the AI market, a significant gap persists in the current offerings. Feedback from our customers and the broader market underscores a desire for increased choice. Enterprises weigh considerations such as availability, scalability, performance, cost, and energy efficiency. Intel Gaudi 3 stands out as the GenAI alternative presenting a compelling combination of price performance, system scalability, and time-to-value advantage," stated Justin Hotard, Intel executive vice president and general manager of the Data Center and AI Group.

https://www.intel.com/content/www/us/en/newsroom/news/vision-2024-gaudi-3-ai-accelerator.html#gs.7ploog

Read More

Intel looks to Ultra Ethernet as its AI fabric

Achieving scale-up and scale-out AI systems requires an advanced networking fabric. In his keynote. Intel CEO Pat Gelsinger said he expects Ultra Ethernet to meet this requirement. 

Intel isintroducing an array of AI-optimized Ethernet solutions, including a network interface card, AI chiplets, as well as soft and hard IP through Intel Foundry. These Ultra Ethernet developments build on Intel’s work with integrating Xeon and Gaudi into AI systems.  “We don’t need proprietary networking solutions for our AI systems,” said Gelsinger.

In addition, Intel announced new edge silicon across the Intel Core Ultra, Intel Core and Intel Atom processor and Intel Arc graphics processing unit (GPU) families of products, targeting key markets including retail, industrial manufacturing and healthcare. All new additions to Intel’s edge AI portfolio will be available this quarter and will be supported by the Intel Tiber Edge Platform this year. 

https://www.intel.com/content/www/us/en/newsroom/news/vision-2024-keynote-livestream-replay.html#gs.7pxeb3

Ultra Ethernet Consortium targets networking for AI and HPC

Wednesday, July 19, 2023    

A new Ultra Ethernet Consortium (UEC) has been established with the goal of bringing together leading companies for industry-wide cooperation to build a complete Ethernet-based communication stack architecture for high-performance networking. UEC is 

The aim is to capitalize on Ethernet's ubiquity and flexibility for handling a wide variety of workloads in Artificial Intelligence (AI) and High-Performance Computing (HPC).

Founding members of Ultra Ethernet Consortium, which is a Joint Development Foundation project hosted by The Linux Foundation , include AMD, Arista, Broadcom, Cisco, Eviden (an Atos Business), HPE, Intel, Meta and Microsoft.

The consortium will follow a systematic approach with modular, compatible, interoperable layers with tight integration to provide a holistic improvement for demanding workloads. The founding companies are seeding the consortium with highly valuable contributions in four working groups: Physical Layer, Link Layer, Transport Layer and Software Layer.

The technical goals for the consortium are to develop specifications, APIs, and source code to define:

1. Protocols, electrical and optical signaling characteristics, application program interfaces and/or data structures for Ethernet communications.
2. Link-level and end-to-end network transport protocols to extend or replace existing link and transport protocols.
3. Link-level and end-to-end congestion, telemetry and signaling mechanisms; each of the foregoing suitable for artificial intelligence, machine learning and high-performance computing environments.
4. Software, storage, management and security constructs to facilitate a variety of workloads and operating environments.

"This isn't about overhauling Ethernet," said Dr. J Metz, Chair of the Ultra Ethernet Consortium. "It's about tuning Ethernet to improve efficiency for workloads with specific performance requirements. We're looking at every layer - from the physical all the way through the software layers - to find the best way to improve efficiency and performance at scale."

Read More

Google unwraps Arm-based CPUs for the data center

Google introduced Axion, its first custom Arm-based CPUs designed for the data center.

Built using the Arm Neoverse V2 CPU, Axion processors promise up to 30% better performance than the fastest general-purpose Arm-based instances currently available in the cloud , up to 50% better performance and up to 60% better energy-efficiency than comparable current-generation x86-based instances.

Axion is supported by Titanium, Google's specialized framework consisting of custom-designed silicon microcontrollers and scalable tiered offloading systems. These Titanium offloads handle essential platform functions such as networking and security, freeing up Axion processors to allocate more resources and boost performance for client tasks. Additionally, Titanium enhances system efficiency by redirecting storage input/output operations to Hyperdisk, Google's block storage service. Hyperdisk separates performance capabilities from the size of the instance and offers the flexibility of being provisioned dynamically in real-time.

https://cloud.google.com/blog/products/compute/introducing-googles-new-arm-based-cpu

Read More

STACK reaches $3.3B in green financing for global data centers

Global data center developer and operator STACK Infrastructure announced securing $3.3 billion in green financing to fund eco-friendly data center construction worldwide. This significant capital injection highlights STACK's commitment to sustainable practices and aligns with growing investor demand for environmentally responsible projects.

Key Highlights:

• $3.3 billion secured in green financing for global data center development.
• Funds will be used to build water and energy-efficient data centers with features like low-carbon materials and electric vehicle charging stations.
• 
  STACK prioritizes responsible development, aiming to benefit surrounding communities through job creation and environmental initiatives.

Global Expansion:

The $3.3 billion will be allocated to projects across various regions, including Silicon Valley ($1.4 billion), Loudoun County, Virginia ($750 million), and Milan, Italy ($1.2 billion). These data centers will support the growing demand for cloud computing, artificial intelligence, and other cutting-edge technologies.

Significant opportunities include:

• A 48MW Santa Clara data center, featuring immediately available shell space powered by an onsite substation with rare, contracted capacity.
• A 56MW Toronto campus, spanning 19 acres, including an existing 8MW data center and 48MW expansion capacity, all supported by committed power.
• A 48MW build-to-suit opportunity in the Dallas/Fort Worth area, boasting abundant power and connectivity options.
• A 200MW campus in Portland spanning 55 acres with 24MW of available capacity with committed power.
• A New Albany, Ohio 58MW data center campus with immediately available capacity and build-to-suit expansion opportunities.
• A planned five-building data center campus offering 250MW of scale in Central Phoenix with a dedicated on-site substation.
• A strategically located data center campus in Osaka, Japan with 72MW of capacity across three planned buildings.
• A 30MW data center campus in Stockholm with 18MW under development.

Read More

MEF intros Enterprise and Operational Lifecycle Service Orchestration APIs

MEF released an API portfolio that empowers enterprises to seamlessly perform automated business and operations with their service providers.

The new MEF enterprise business and operational Lifecycle Service Orchestration (LSO) API portfolio features a range of new and existing MEF assets to fuel the advancement of Network-as-a-Service (NaaS) for enterprises. The APIs enable large enterprises undergoing digital transformation and cloud migration to seamlessly connect their internal automation systems and applications with service provider networks. 

Currently available MEF business LSO APIs include address validation, site query, product catalog, product offering qualification, product offering availability discovery, quote, price discovery, product order, product inventory, trouble ticketing and incidents, appointment, work order, and billing and settlement. Current and planned MEF operational LSO APIs include service function testing, service performance monitoring, and fault management. 

MEF enterprise business and operational LSO APIs are available for Carrier Ethernet (E-Line, E-LAN and E-Tree) and traditional IP Broadband and Direct Internet Access network services.  New services to be added in coming months include dark fiber, wavelengths, edge compute, cross-connects, cloud connects, and satellite followed by SD-WAN, SASE, Zero Trust, and SSE.   

“MEF’s enterprise business and operational LSO API portfolio is a game-changer for enterprises undergoing digital transformation,” said Debika Bhattacharya, Chair, MEF Board of Directors, and Chief Technology Solutions Officer, Verizon Business. “These APIs allow for seamless automation of managed services between businesses and their technology partners, giving enterprises greater control, flexibility and visibility over their NaaS environments and eliminating the need for proprietary APIs. This translates to improved operational efficiency and a stronger foundation for innovation.” 

Initial use-cases of the enterprise portfolio include: 

• Buying and managing enterprise services such as network services, cloud connectivity, low latency edge compute for AI, cybersecurity, IoT, and more 
• Incident reporting for rapid enterprise response to service changes and cybersecurity threats 

In addition, MEF noted that more than 155 service providers worldwide are now in various stages of the adoption lifecycle for MEF business and operational LSO APIs. At least 35 service providers are already in production with these APIs to automate business and/or operational functions with their service provider partners, and this number is forecasted to surpass 100 by the end of 2025. 

https://www.mef.net/news/mef-pioneers-industry-leading-enterprise-business-and-operational-lso-api-portfolio-for-network-services/

Read More

Blue Planet Cloud Native Platform aims for service lifecycle automation

Ciena's Blue Planet division introduced a first-of-its-kind Blue Planet Cloud Native Platform that leverages Kubernetes (K8s) technology to support multiple modular Operating Support System (OSS) applications.

Converging inventory, orchestration, and assurance applications on a common platform, it provides a game-changing strategy to improve operational efficiency and streamline service lifecycle automation.

Built on a K8s-based architecture, the new platform offers significant advantages to CSPs beyond what Blue Planet is already known for today. These new features include:

• In-service software upgrades (ISSU) and continuous integration / continuous delivery (CI/CD) support, allowing CSPs to embrace a DevOps model and quickly introduce innovative new services.
• Support for any cloud environment, including public, private and hybrid cloud environments, to reduce vendor lock-in and significantly improve operational scale, flexibility, and resilience.
• Common lifecycle management across all Blue Planet OSS applications, delivering a lower total cost of ownership (TCO).
• 
  AI-driven operations by using an AI Studio that can apply machine learning and AI-based capabilities developed by CSP data science teams, Blue Planet, or third parties, to any mix of product applications or operational processes.

The new Blue Planet Cloud Native Platform allows CSPs to deploy individual applications independently or together to address their most important OSS modernization projects at their own pace. These include the Blue Planet Inventory (BPI), Blue Planet Orchestration (BPO) and Blue Planet Assurance (BPA) applications.

“The Blue Planet Cloud Native Platform transcends the traditional approach of custom ‘spaghetti integrations’ that have shackled CSPs’ ability to be adaptable, open and agile. We are pioneering a new level of convergence that embraces the cloud and transforms the OSS to be a competitive differentiator, reducing operational costs and allowing for rapid creation of new business models,” stated Joe Cumello, Senior Vice President and General Manager, Blue Planet.

Read More

CoreSite signs on as NVIDIA DGX-Ready Data Center Partner

CoreSite has been certified as part of the NVIDIA DGX-Ready Data Center program to host scalable, high-performance infrastructure for organizations looking to capitalize on rising demand for artificial intelligence (AI), machine learning (ML) and other high-density applications.

By choosing to host their NVIDIA DGX™ infrastructure with CoreSite, customers can benefit from a national portfolio of high-density-powered data center campus environments for NVIDIA AI and high-performance computing at CoreSite locations including Los Angeles (LA3), Silicon Valley (SV9), Chicago (CH2) and Northern Virginia (VA3).

“The exponential growth of AI and other emerging applications has increased the need for highly interconnected, purpose-built data centers to meet the growing demands for IT, power and cooling infrastructure,” said Juan Font, President and CEO of CoreSite, SVP of American Tower. “Our certification as an NVIDIA DGX-Ready Data Center program partner will enhance CoreSite’s ability to deliver the data center space, advanced cooling and ultra high-density power requirements customers need while making it easier for them to deploy advanced technologies and bring their innovations to market.”

Read More

TSMC to receive up to $6.6B under the CHIPS and Science Act.

TSMC Arizona is to receive up to $6.6 billion in direct funding under the CHIPS and Science Act to support its investment of more than $65 billion in three greenfield leading-edge fabs in Phoenix, Arizona.

After initially announcing two fabs in the U.S., TSMC Arizona is committing to build an additional third fab before the end of the decade. With this proposed funding, TSMC Arizona would be ensuring the formation of a scaled leading-edge cluster in Arizona, creating approximately 6,000 direct manufacturing jobs, more than 20,000 accumulated unique construction jobs, and tens of thousands of indirect jobs in this decade and bringing the most advanced process technology to the United States.

In Arizona, TSMC’s three fabs are expected to bring a suite of the most advanced process node technologies to the United States: the first fab  will produce 4nm FinFET process technologies; today, TSMC Arizona announced that the second fab will produce the world’s most advanced 2nm nanosheet process technology, in addition to previously announced plans to produce 3nm process technologies; and TSMC Arizona’s third fab will produce 2nm or more advanced process technologies depending on customer demand. At full capacity, TSMC Arizona’s three fabs would manufacture tens of millions of leading-edge chips that will power products like 5G/6G smartphones, autonomous vehicles, and AI datacenter servers. TSMC Arizona expects to begin high-volume production in their first fab in the U.S. by the first half of 2025.

The new facilities are expected to support key U.S. companies AMD, Apple, Nvidia, and Qualcomm, among others, by addressing their leading-edge capacity demand, mitigating supply chain concerns, and enabling them to compete effectively in the ongoing digital transformation era. With the proposed incentives, TSMC Arizona has also committed to support the development of advanced packaging capabilities – the next frontier of technology innovation for chip manufacturing – through its partners in the U.S., creating the opportunity for TSMC Arizona’s customers to be able to purchase advanced chips that are made entirely on U.S. soil.

“One of the key goals of President Biden’s CHIPS and Science Act was to bring the most advanced chip manufacturing in the world to the U.S., and with this announcement and TSMC’s increased investment in their Arizona campus, we are working to achieve that goal,” said U.S. Secretary of Commerce Gina Raimondo. “The leading-edge semiconductors that will be made here in Arizona are foundational to the technology that will define global economic and national security in the 21st century, including AI and high-performance computing. Thanks to President Biden’s leadership and TSMC’s continued investments in U.S. semiconductor manufacturing, this proposed funding would help make our supply chains more secure and create thousands of good-quality construction and manufacturing jobs for Arizonans.”

“The proposed funding from the CHIPS and Science Act would provide TSMC the opportunity to make this unprecedented investment and to offer our foundry service of the most advanced manufacturing technologies in the United States,” said TSMC Chairman Dr. Mark Liu. “Our U.S. operations allow us to better support our U.S. customers, which include several of the world’s leading technology companies. Our U.S. operations will also expand our capability to trailblaze future advancements in semiconductor technology.”

https://www.commerce.gov/news/press-releases/2024/04/biden-harris-administration-announces-preliminary-terms-tsmc-expanded

Read More

Researchers transfer electron spin to photons

Researchers at the University of Buffalo applied an electrical pulse to transfer spin information from electrons to photons, a technique that potentially could be useful in optical communications over great distances. The method met three crucial criteria — operation at room temperature, no need of magnetic field and the ability for electrical control.

“For decades we were dreaming of and predicting room-temperature spintronic devices beyond magnetoresistance and just storing information. With this team’s discovery, our dreams become reality,” says the study’s co-author, Igor Zutic, SUNY Distinguished Professor of physics at the University at Buffalo.

The research, described in a study published March 27 in Nature, was supported by the National Science Foundation’s Electronics, Photonics and Magnetic Devices (EPMD) program and the U.S. Department of Energy’s Basic Energy Sciences (BES) program. 

The study was led by the Jean Lamour Institute, a joint unit of France’s National Centre for Scientific Research (CNRS) and the University of Lorraine. Other contributors represent universities and institutes in France, Germany, Japan, China and the United States.

https://www.buffalo.edu/news/releases/2024/03/transporting-spin-information-at-the-speed-of-light.html?sf187449744=1

Read More

Starlink advances its global Direct-to-Cell ambitions

 On Saturday, April 6, 2024, SpaceX's Falcon 9 rocket successfully carried out its 35th launch for the Starlink 8-1 mission from Vandenberg Space Force Base in California. This launch saw the deployment of 21 Starlink satellites, including 6 Direct-to-Cell satellites, marking a pivotal step in the company's ambition to launch global Direct-to-Cell and Internet-of-Things service.

Key Highlights:

• Direct-to-Cell Advancements: With the addition of 6 Direct-to-Cell satellites in this launch, the total number in orbit has reached 12. These satellites are part of Starlink's ambitious plan to scale its Direct to Cell network rapidly. The initiative aims to launch hundreds of satellites to provide text service by 2024 and expand to voice, data, and Internet of Things (IoT) services by 2025.
• Technical Innovations: Starlink's Direct to Cell satellites are equipped with custom silicon, large advanced phased array antennas, and sophisticated software algorithms. These innovations allow the satellites to communicate with standard cell phones on Earth, overcoming significant technical and regulatory challenges.
• Global Partnerships and Regulatory Milestones: Starlink has formed partnerships with several global operators, including T-Mobile, Rogers, and Optus, providing critical LTE spectrum for satellite communication. These collaborations, coupled with rapid regulatory approvals, aim to deliver seamless and lifesaving communication services worldwide.
• Future Plans: Leveraging SpaceX's vertical integration and the upcoming Starship launches, Starlink plans to further improve its Direct to Cell service. The company's advanced LTE modems enable the satellites to function as cell towers in space, ensuring reliable and seamless communication.
• Launch Success: The Falcon 9 rocket's 35th mission from Space Launch Complex 4E included the sixth flight of its booster, which has previously supported various missions, including Crew-7 and CRS-29. The successful landing on the drone ship "Of Course I Still Love You" in the Pacific Ocean underscores SpaceX's commitment to reusability.

On January 8, the Starlink successfully sent and received the first text messages using T -Mobile network spectrum through one of its new Direct to Cell satellites launched six days prior.

In August 2022, Starlink announced its first partnership with T-Mobile, and have since announced deals with Rogers in Canada, Optus in Australia, One New Zealand, KDDI in Japan, Salt in

Switzerland, and Entel in Chile & Peru. The operators provide critical LTE spectrum in the 1.6-2.7 GHz range that we use to transmit our satellite signals. This allows Starlink to integrate

like a standard roaming partner with operators. Starlink says operators in its network have access to reciprocal global access that allows their users to access the service when they travel to one of partner countries. 

false

Read More

Grupo Aire deploys Infinera's ICE-X coherent pluggables

Grupo Aire, a wholesale telecommunications operator in Spain and Portugal, deployed Infinera’s software-programmable ICE-X coherent pluggable solution to expand the capacity of its single-fiber network infrastructure. The ability of Infinera’s ICE-X solution to provide ultra-high-speed transmissions over a single fiber in a pluggable form factor enables Aire Networks to continue to meet the bandwidth demands of its customers while maintaining its cost-effective single-fiber infrastructure.

Aire Networks operates a network that spans over 33,000 kilometers across the Iberian peninsula, providing connectivity, voice, mobile virtual network enabler (MVNE), media, cloud, and data center solutions to local and regional operators as well as enterprise customers.

Leveraging digital subcarrier technology, Infinera’s ICE-X solution can transmit up to 200 Gb/s bidirectionally per wavelength on a single fiber in a compact and power-efficient pluggable form factor. With 64 wavelengths supported per fiber, this translates to 12.8 Tb/s of capacity on a single fiber – substantially increasing the number of services that can be delivered by Aire Networks. Infinera partnered with APFutura to design and deploy the solution.

“Aire Networks is committed to providing our customers with the best connectivity available by utilizing cutting-edge industry solutions and innovations,” said Zigor Gaubeca, CTO at Aire Networks. “Leveraging innovative technology like Infinera’s ICE-X enables us to meet the needs of our customers, providing efficient, high-quality services that can scale to meet our customers’ demand.”

“Infinera is pleased to collaborate with APFutura in providing an innovative solution to Aire Networks that enabled them to meet their network objectives,” said Lorraine Twigg, Global VP of Channel Partners, Infinera. “This achievement underscores how network operators can leverage Infinera’s unique solutions to improve connectivity and infrastructure across the globe and the critical role our partners play in delivering open optical network.”

false

Read More

#OFC24: OIF's Energy Efficient Interfaces Framework

Check out OFC Conference and Exposition 2024 videos here: https://ngi.fyi/ofc24yt

The OIF's Energy Efficient Interfaces (EEI) Framework, which got underway in May 2023, is studying new energy-efficient electrical and optical interfaces (which, among others, includes the next generation of low power optics, also referred to as “Linear” or “Direct Drive”). Nathan Tracy, President from OIF, shows the demo at #OFC24:

- The importance of the Energy Efficient Interfaces (EII) project, which aims to outline the requirements of an AI fabric interface and the trade-offs to consider for interoperable solutions.

- The demonstration of an Ethernet frontend switch that integrates real-world accelerators and future view versions of accelerator cards, showcasing the potential of electrical and optical interconnects working together.

- The ongoing efforts in the OIF to understand the requirements for different links, quantify them, and develop industry-standard solutions for full interoperability in an AI/ML fabric. 

https://youtu.be/QzS9D7H7-jc

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More

#OFC24: CPO External Laser Small Form-Factor Pluggables

Check out OFC Conference and Exposition 2024 videos here: https://ngi.fyi/ofc24yt

OIF has been studying the co-packaging of ASICs with optical and electrical transceivers within its Co-Packaging Framework Project.

The External Laser Small Form-Factor Pluggable (ELSFP) IA will define a future proofed external laser source form factor to support co-packaged optical modules. Nathan Tracy walks us through the #OFC24 demo.

https://youtu.be/9x2M3V8mSBA

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More

#OFC24: 800 Gigabit Ethernet Interoperability Demo

The Ethernet Alliance's OFC 2024 booth showcases Ethernet’s versatility and reliability at speeds of up to 800 Gigabit Ethernet (GbE). The booth demonstrated a wide range of switches, routers, interconnects and interfaces including OSFP, QSFP-DD, QSFP, and SFP pluggable form factors.  Dave Estes shares an overview.

https://youtu.be/xHjROKISoVM

 

false

Read More

#OFC24: All-Optical Circuit Switching for Scalable Data Centers

 Check out OFC Conference and Exposition 2024 videos here: https://ngi.fyi/ofc24yt

Google has deployed MEMS-based, all-optical switching technology in its data centers. Could all-optical switches gain traction with other operators? Coherent Corp. has just introduced  a new optical circuit switch (OCS) based on the company’s field-proven and ultrareliable Datacenter Lightwave Cross-Connect (DLX) technology. Sanjai Parthasarathi, CMO from Coherent explains:

- The unique features of Coherent's Optical switch platform, including its Liquid Crystal-based platform that requires lower drive voltage and has no moving parts, making it a highly reliable solution.

- The platform's data rate agnostic nature, which is a significant advantage in the rapidly evolving tech landscape.

- The substantial reduction in power consumption by 30-40%, a crucial factor in today's power-hungry data centers, and the promising customer attraction from data center operators, hyperscalers, and OEMs.

https://youtu.be/ck3B-IQ2-Fk

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More

#OFC24: 800ZR, 400ZR and OpenZR+ Optics Interoperability

Check out OFC Conference and Exposition 2024 videos here: https://ngi.fyi/ofc24yt

At #OFC24, OIF hosted its latest pluggable coherent optics demonstration, showcasing the latest advancements in 800ZR, 400ZR and ZR+ optics interoperability. The demo highlights include the first public 800ZR multivendor interop; high transmit power, OpenZR+ over a 1000km, multi-span network; OpenROADM/ITU-T over that same network; and 400ZR collocated on the single-span network with 800ZR. Karl Gass, Physical and Link Layer Working Group Optical Vice Chair from OIF, provides some highlights:

- The demonstration of a single span demo with eight channels at 400 ZR and four channels of 800 ZR, showcasing the actual optical spectrum of both the 400 and 800 ZR traffic.

- a multispan demo featuring Raman amplification over 1000 kilometers, with six more channels and one channel of open rodm application.

- The use of new Corning smf28 ultra low LOF fiber in one direction and standard smf28 in the other, with both terminal RMS and a set of equalizer RMS to balance the channels in the middle.

https://youtu.be/9IPF4LSb-tE

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More

#OFC24:Rethinking Optical Modules for Liquid Immersion in AI Clusters

Check out OFC Conference and Exposition 2024 videos here: https://ngi.fyi/ofc24yt

Many optical components used in data centers, such as transceivers, incorporate free-space gaps in their designs. These gaps enable effective coupling from the laser to the Photonic Integrated Circuit (PIC) and from the PIC to the optical fiber, however, because liquids (including immersion liquids) have a different index of refraction than air, when a traditional optical component is immersed in fluid, the light path is significantly altered, rendering these devices effectively unusable for liquid cooling.

DustPhotonics’ transmit Carmel-8-IMC chip supports an optical assembly with no free-space optics. Inside the chip, lasers are butt-coupled to the PIC and the fiber is also attached directly to the PIC, thus enabling transceiver designs that can be used for both immersion and air cooling.

Ronnen Lovinger, CEO from Dust Photonics, explains:

- The application of immersion cooling for power management in next-generation data centers.

- Dust Photonics' PICs are ready for integration into cutting-edge transceivers for this immersion cooling application

- A live demonstration of their product in collaboration with Amphenol

https://youtu.be/oWQDgSfbGUA

Want to be involved our video series? Contact info@nextgeninfra.io

Dust Photonics raises US$24 million in Series B

Wednesday, February 21, 2024    

DustPhotonics, a start-up based in Modi'in, Israel, raised US$24 million in Series B funding for its silicon photonics technology for data center and AI applications, The oversubscribed funding round was funded by a combination of prominent investors, including new and existing investors such as Sienna Venture Capital, Greenfield Partners, Atreides Management, and Exor Ventures.DustPhotonics said it plans to use the funding to scale production...

READ MORE

Read More

#OFC24: Materials Science, Lasers, All-Optical Switching

#OFC24 was a huge event for Coherent Corp., which made big announcements in material sciences, including new Indium Phosphide capabilities, pushing VCSELs to 200 Gbps per lane and thereby enabling optical transceivers with 1.6 Tbps capacity, and previewing an all-optical switching platform.  Sanjai Parthasarathi, CMO from Coherent, explains:

- The world’s first capability for 6-inch indium phosphide (InP) wafer fabrication, in the company’s Sherman, Texas, and Järfälla, Sweden, wafer fabs.

- The use of advanced materials, including diamond, for cooling applications in AI server pods, which is generating excitement among their customer base.

- The unveiling of their Optical circuit switch, which offers significant cost savings, latency reduction, and power savings, particularly for emerging applications in AI connectivity within the data center.

https://youtu.be/x4MacdEFTKM

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More

#OFC24: Advanced DFB Laser Arrays for I/O in AI Clusters

 Sivers Photonics is supplying its DFB laser arrays for Ayar Labs’ SuperNova optical interconnect for AI/ML clusters, disaggregated data centers, 6G networks, phased array sensor systems and etc. Anders Storm, CEO from Sivers Semiconductors explains:

- The current lack of communication and insufficient bandwidth between GPUs can be addressed by scaling the number of GPUs and using photons instead of electrons. This approach not only increases the bandwidth by 10x but also reduces electricity usage by the same factor.

- Sivers Semiconductors is partnering with Ayar Labs to demonstrate an eight-array optical interconnects capable of 4 Tbps, scaling to much higher rates

- The company is a promoter member of CW WDM, a forum that has created a standard for how laser sources will work within these systems. The technology is maturing, with new members joining the forum and the use of Indian phosphide lasers proving to be a very effective material for these applications.

https://youtu.be/6dGPDmynlpE

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More

#OFC24: Big Strides in Optical Transmission with Pluggables

Major strides are achieved this year in optical transmission thanks to new modules operating at high data rates and over greater distances. Coherent is introducing two such products.  Sanjai Parthasarathi, CMO from Coherent, explains:

- The introduction of the 100G ZR QSFP28 digital coherent optics (DCO) transceiver, an industrial temperature unit capable of functioning in outdoor environments, and the 800 GCR qsfp DD dco, boasting one of the highest optical power outputs in the industry.The DSP is paired with an efficient silicon photonics optical front-end and a power-optimized tunable laser, now enhanced to support a wider operating temperature range, resulting in module power consumption of less than 6 W at a case temperature of 85°C

- The introduction of an 800 Gbps coherent transceiver module in QSFP-DD form factor and capable of transmitting over 9000 ps/nm of dispersion, equivalent to approximately 450 km of fiber. This new 800G transceiver uses Coherent’s 140 Gbaud IC-TROSA optical subassembly, which features a high-efficiency indium phosphide modulator and receiver combined with a proprietary embedded wavelength-tunable laser. The Coherent 800G QSFP-DD transceiver has several operating modes that enable it to deliver up to 1000 km of reach at 800 Gbps and up to 2000 km at 400 Gbps in well-designed networks.

https://youtu.be/qGJJuxbHMOo

Want to be involved our video series? Contact info@nextgeninfra.io

false

Read More