Thursday, September 14, 2023

BT tests liquid cooled network switches and servers

BT is trialling "precision liquid cooled" network switches using a solution provided by Iceotope and Juniper Networks QFX Series Switches, which are widely used in existing network cloud architectures. 

In addition to its trial with Iceotope and Juniper, BT will test the following liquid cooling systems, which were also demonstrated at BT Group’s Sustainability Festival:

  • Precision Liquid Cooled networking servers and data centre equipment, with Iceotope and Juniper
  • Full immersion of networking servers in an immersion tank, with Immersion4
  • Liquid-cooled cold plates of networking equipment in a cooling enclosure, with Nexalus
  • Cooling using sprayed-on partial immersion of data centre equipment, with Airsys.

BT Group expects that several different cooling solutions could eventually be deployed, depending on specific location and operational requirements. The trials will aim to establish which solutions are optimal for each scenario, and the extent of potential energy savings.

Maria Cuevas, Networks Research Director, BT Group said, “As the UK’s largest provider of fixed-line broadband and mobile services in the UK, it isn’t a surprise that over 90% of our overall energy consumption – and nearly 95% of our electricity - comes from our networks. In a world of advancing technology and growing data demands, it’s critical that we continue to innovate for energy efficiency solutions. Liquid cooling for network and IT infrastructure is one part of a much bigger jigsaw but is an area we’re very excited to explore with our technology partners.”

https://newsroom.bt.com/bt-takes-the-plunge-with-new-liquid-cooling-trials/

Napatech debuts IPU powered by Intel Xeon + Agilex 7 FPGA

Napatech introduced a 200 Gbps IPU (infrastructure processing unit) based on the Intel IPU Platform F2000X-PL, which leverages an an Intel Xeon D SoC and Intel Agilex 7 FPGA.

Napatech’s F2070XTM IPU is engineered for cloud, enterprise, and telecom data centers that are optimized for hybrid multi-cloud and edge-computing architectures, supporting applications that may be virtualized (virtual machines), cloud-native (containers), bare-metal and microservices-based.

The Napatech F2070X IPU is a 200 Gbps card that includes two ports configurable for 10, 25, and 100 gigabit Ethernet. Multiple versions are
available in various SoC, FPGA, and memory configurations, and are supported in standard, high-volume servers from multiple manufacturers.

The F2070X IPU is powered by Napatech’s feature-rich software and high-velocity roadmap that deliver NIC functionality, while offloading and accelerating networking (OVS), Storage (NVMe/TCP), Security (TLS), and other workloads.

Key benefits of IPUs: 

  • Performance: hardware-based, line-rate forwarding with sophisticated packet processing.
  • Efficiency: offloading of infrastructure processes, reclaiming valuable host CPU resources for applications and services.
  • Customization: software and hardware programmable, delivering hardware performance at the speed of software
    innovation.
  • Security: Hard isolation between tenant applications and services, and operator infrastructure processes.
  • Sustainability: tenant and service scalability per server, reducing cost, power, and cooling per rack.
  • Ease of Use: The Intel Xeon D processor simplifies moving the networking and storage stacks from the host to the
    IPU.

“Napatech is pleased to have reached this important milepost in our collaboration with Intel,” said Henrik Brill Jensen, CEO of Napatech. “Our joint efforts to bring IPU hardware and software solutions to IT organizations of every size unlock new high-growth markets for our products, and underpin our aim for transformational growth of our business.”

“Our collaboration with Napatech is an indication of our commitment to expanding our leadership in infrastructure processing in data center networks,” said Jim Dworkin, Vice President and General Manager of the Cloud & Enterprise Acceleration Division at Intel. “We are pleased to collaborate with Napatech to combine the high performance of Intel Agilex 7 FPGAs with Napatech’s production-grade hardware and software expertise. Napatech’s upcoming F2070X IPU isa high-performance data center infrastructure server on a PCIe card that can help deliver the scalable and high-performance products, solutions, and services customers require to make their cloud and enterprise data centers moreefficient and cost-effective with high feature velocity.”

https://www.napatech.com



Prisma Photonics raises $20M for optical sensing of power grids

Prisma Photonics, a start-up based in Tel Aviv, raised approximately $20 million in a Series C round for its optical sensing technology for monitoring large-scale infrastructure, such as power grids.

Prisma Photonics says its optical fiber sensing technology offers power transmission operators better ways to manage their grids. It allows them to maximize the electrical capacity of the current grid to increase the integration of renewable energy sources. Doing that, operators respond to new emerging regulations such as FERC order 881 in the U.S. and similar. Real-time alerts on electrical faults and extreme weather conditions such as wildfires and icing offer better ways to retain grid resiliency in changing environments. Prisma Photonics uses existing optical fibers and can monitor distances of up to thousands of kilometers without the need to install any sensors on the infrastructure itself.

The funding round was led by New York-based global private equity and venture capital firm Insight Partners, with participation from Elements, a Climatech fund, SE Ventures (Schneider Electric's venture capital arm), Future Energy Ventures (the venture capital investment and collaboration platform of E.ON),  Events and alerts are reported in real time and within meters of accuracy.

"Grid congestion and the integration of renewable sources have become pressing challenges for power market operators such as our Tier-1 customers," states Dr. Eran Inbar, CEO of Prisma Photonics. "Our AI-driven technology not only adds a layer of resilience to the grid but also enables dynamic line rating capabilities, unlocking the full potential of existing infrastructure. This investment led by Insight Partners highlights the urgent need for innovative, scalable solutions in critical infrastructure management."

https://www.prismaphotonics.com

  • In January, Prisma Photonics, which has been using optical fibers to monitor Israel's national transmission electrical grid since 2020, was awarded a contract by Israel Electric Corporation (IEC) to extend coverage to 1,000 km (over 620 miles), which is 20% of the transmission grid. 

Lumen expands its SASE with cloud-hosted gateways

Lumen introduced new Secure Access Service Edge (SASE) features including:

Security Service Edge (SSE) and cloud-hosted gateways

  • SSE is a collection of integrated, cloud-centric security capabilities – including cloud-hosted gateways – that provide safe access to websites. It also includes the access and sharing of sensitive data and user permission management for software-as-a-service (SaaS) applications provided by leading SD-WAN and security partners.
  • Cloud-hosted gateways enable organizations to adopt "grow as they go" network and security management features without the need for premise-based equipment.

Customers benefit from Lumen-hosted gateways because they:

  • Enable customers to migrate off shared gateways and onto a dedicated node providing enhanced security and reliability nationwide.
  • Provide flexible, centralized security services and dedicated cloud hosting with simplified and predictable pricing.
  • Enable secure remote access from virtually anywhere to the customer's data and cloud applications.

Global expansion

  • U.S.-based customers can now deploy premise-based SASE services to locations in Canada and EMEA.

VIAVI offers Network Intelligence and Optimization on Google Cloud

Viavi released its NITRO AIOps on Google Cloud.

Highlights:

  • Network Performance Optimization: NITRO AIOps enables CSPs to proactively monitor and optimize network performance. By identifying potential bottlenecks and anomalies, CSPs can take timely actions to ensure seamless network operations and consistent, high-quality service delivery. 
  • Enhanced Customer Experience: With granular insights into customer behavior and usage patterns, the solution allows CSPs to tailor services to individual preferences. This results in personalized offerings, improved customer satisfaction, and increased loyalty. 
  • Capacity Planning and Resource Management: The solution's AI-driven analytics aids CSPs in effective capacity planning and resource management. By optimizing network resources, CSPs can achieve better resource utilization and cost efficiency. 
  • Real-Time Anomaly Detection: AIOps empowers CSPs with real-time issue detection, enabling swift response to network anomalies and potential service disruptions, minimizing downtime and enhancing network reliability. 
  • Predictive Maintenance and Quality Assurance: By predicting potential network issues and faults, the solution helps CSPs adopt a proactive approach to maintenance and quality assurance, ultimately leading to improved service quality and reduced operational costs. 


"VIAVI constantly strives to provide innovative solutions and purposeful industry partnerships that address emerging opportunities in our markets. This partnership enables the transition to cloud-based networks with end-to-end visibility. Working with Google Cloud, we are pleased to offer critical problem-solving solutions for service providers as part of their native cloud services," said Deepak Shahane, Vice President and General Manager, Service Enablement, VIAVI. "As this partner demonstration shows, we aim to enable the industry to leverage VIAVI capabilities to improve operations and management that includes fully validated, provisioned, and observable networks in any use case."

Wednesday, September 13, 2023

Arm readies IPO at $51.00 per ADS

Arm Holdings plc priced its initial public offering of 95,500,000 American depositary shares at a price to the public of $51.00 per ADS. 

The ADSs are expected to begin trading on the Nasdaq Global Select Market on September 14, 2023 under the symbol “ARM.”

The selling shareholder, a wholly-owned subsidiary of SoftBank Group Corp., in the IPO has granted the underwriters an option to purchase up to an additional 7,000,000 ADSs to cover over-allotments, if any, for 30 days after the date of the final prospectus. The IPO is expected to close on September 18, 2023, subject to customary closing conditions.

https://www.arm.com

Some notes on Arm

  • Arm CPUs shipped in greater than 99% of the world’s smartphones in 2022
  • More than 30 billion Arm-based chips reported as shipped in the fiscal year ended March 31, 2023, representing an approximately 70% increase since the fiscal year ended March 31, 2016.
  • To date, Arm technology has shipped in more than 250 billion chips
  • Approximately 70% of the world’s population uses Arm-based products
  • For the fiscal year ended March 31, 2023, Arm's total revenue was relatively flat at $2,679 million, as compared to $2,703 million in the fiscal year ended March 31, 2022. 
  • In the fiscal year ended March 31, 2023, as a percentage of total revenue our gross profit margin was 96% and operating income margin was 25%.
  • As of March 2023, Arm had 5,963 full-time employees across North America, Europe and Asia.
  • Arm began as a joint venture between Acorn Computers, Apple Computer, and VLSI Technology in 1990.


Deutsche Telekom and Microsoft launch 5G Private Networks

Deutsche Telekom launched its new “Campus Network Smart” solution built on  Microsoft Azure private multi-access edge compute (MEC), which includes the new Azure Private 5G Core service deployed on Azure Stack Edge. This provides customers with a private 5G network that can operate across multiple sites.

Deutsche Telekom tested the new private 5G network solution with Microsoft in a lab environment in Bonn, Germany, last year. As a second step, the two companies carried out a field trial with a leading pharmaceutical company in Germany, beginning in February this year. This pilot customer tested the 5G campus network with various use cases, including the use of AR glasses for remote maintenance. Another use case saw forklifts enabled for object recognition in a high-bay warehouse, in order to monitor inventory and automatically scan barcodes.

Hagen Rickmann, Managing Director Business Customers at Deutsche Telekom in Germany says: “Our new 5G Campus Network Smart solution lowers the barriers to entry for campus networks, in terms of both cost and effort.  Customers with an existing Microsoft Azure landscape, as well as new customers in the small and medium-sized enterprise segment benefit from the solution. They can get started with 5G technology and drive forward their digitalization – while maintaining flexibility”.

"German industry is taking a leading role in adopting Industry 4.0 Transformation, and we are excited to enable Deutsche Telekom to provide complete solutions including network and a growing ecosystem of Modern Connected Apps into this market. Customers can now benefit with a choice of ready to deploy applications over superior cloud-managed private network to accelerate their business transformation." said Shriraj Gaglani, VP Product Management, Microsoft.

https://www.telekom.com/en/media/media-information/archive/telekom-and-microsoft-launch-campus-network-offering-1048758

SES partners with Starlink on MEO-LEO for cruise ships

SES is partnering with SpaceX on a low-latency, high-throughput satellite connectivity service enabled by integrating Starlink’s low-earth orbit (LEO) and SES’s medium earth orbit (MEO) constellations.

The joint offering – SES Cruise mPOWERED + Starlink – seamlessly integrated, sold and delivered by SES – will combine the best of both MEO and LEO orbits to provide high-speed and secure connectivity 24/7 to cruise ships and their guests, regardless of their route and location.

The solutions are available in either Premium tier (3Gbps/ship) – for the leading ships who wish to deliver the highest throughput in the industry or Pro tier (1.5Gbps/ship) – for the operators who wish to manage user experience by matching the right application to the right orbit.

“At SES, we strive to provide a world-class connectivity experience for our cruise customers and deliver the same level of service they would enjoy on land,” said John-Paul Hemingway, Chief Strategy Officer at SES. “By being the only one in the cruise industry to expand our unique multi-orbit GEO and MEO network to utilise LEO, we believe it opens new opportunities for us to meet the needs of cruise guests and crew members, and the operational requirements of cruise operators to accelerate their digital transformations – wherever they may be.”

https://www.ses.com/press-release/ses-introduces-cruise-industrys-first-integrated-meo-leo-service-starlink

Adtran intros smallest Combo PON OLT

Adtran released its SDX 6324 optical line terminal (OLT), specifically designed to deliver high-performance broadband services to low-density applications. 

The new fiber access platform features four Combo PON ports supporting up to 500 subscribers. It offers the same capabilities of Adtran's higher-port count SDX solutions at a significantly lower upfront cost.

“Service providers often struggle with small-scale deployments. Finding the right technology at the right price isn’t always easy. The practice of deploying over-dimensioned solutions has challenged operators for many years. Our new SDX 6324 hits the sweet spot. It’s been engineered to help service providers easily roll out fiber services to low-density environments without any risk or unused capacity. You pay for exactly what you need,” commented Andy Ruble, GM of Access and Aggregation, Adtran. 

https://www.adtran.com/en/newsroom/press-releases/20230912-adtran-extends-sdx-family-of-olts-to-tackle-low-density-ftth-deployments

Deutsche Telekom demonstrates 12 Gbps with 6 GHz spectrum

Deutsche Telekom has demonstrated a mobile connection operating at 12 Gbps over 100m, made possible by the additional use of the frequency spectrum at 6 gigahertz (6 GHz). 

For the test, Telekom equipped a rooftop location in the town of Alzey in Rheinhessen with a 6 GHz antenna. In addition, an antenna was mounted that is already used today for the 5G mobile communications standard and transmits via the 3.6 GHz frequency band. During the measurements at a distance of around 100 metres, around 12 Gbps were measured with slight fluctuations.

https://www.telekom.com/en/media/media-information/archive/world-record-12-gigabits-per-second-in-mobile-communications-1048610


Tarana raises $50 million for next-gen fixed wireless

Tarana Wireless, a start-up based in Milpitas, California, raised $50 million in an up round for its next-generation fixed wireless access (ngFWA) platform.

Since launching its G1 in late 2021, Tarana reports deployments by more than 270 service providers in 19 countries, and in 41 of the 50 states in the US. Revenues in G1’s first full year of sales (2022) were nearly $100M, and orders plus sales continue to climb in 2023. These strong business fundamentals drove a 40% year-over-year increase in the company’s valuation. 

The funding round was led by Digital Alpha. Rick Shrotri, Founder and Managing Partner at Digital Alpha, explained, “As we developed our wireless ISP investment thesis, we became aware of Tarana’s breakthrough technology, and each operator’s story underscored how ngFWA is fundamentally changing network performance and operator economics. Tarana’s G1 platform supplies the key missing ingredient in enabling wireless ISPs to offer highly competitive broadband, take share, and grow value in their businesses — at a months-not-years deployment pace competitive technologies just cannot match.”

In addition to traditional equity investments into wireless Internet services providers, Digital Alpha is also offering a novel revenue-share financing solution to Tarana customers looking to expand their deployments of G1. Digital Alpha's deep domain and industry expertise makes them uniquely suited to fund infrastructure deployments that are bridging the digital divide and enabling connectivity transformations across local communities. To date, Digital Alpha has funded existing Tarana customers such as Element 8 and Wisper ISP and is looking forward to partnering with Tarana to offer its funding model in pursuit of new market opportunities and additional wireless internet service providers.

Tarana CEO Basil Alwan noted, “Digital Alpha knows our customers’ business intimately, which has provided early insights into ngFWA and the momentum building in our business. This investment along with those in our customers makes them a natural and great partner. Our rapid growth has created more opportunities along with higher working capital requirements; this financing will play an essential role in maintaining our trajectory, supporting our customers’ continued growth, and expanding our reach globally.”

Vantage Data Centers replaces diesel with hydrotreated vegetable oil

Vantage Data Centers is replacing diesel in its back-up generators with hydrotreated vegetable oil (HVO). The company said it intends to roll out HVO in several of its largest markets in North America and EMEA.

HVO is 100% biodegradable and non-toxic, offering a more sustainable fuel option while delivering the same level of functionality as traditional diesel. Repurposing waste oils like vegetable oil to create sustainable fuels significantly reduces the embodied carbon due to the cleaner sourcing and creation process. 

Given the success of a pilot deployment in 2022 at its campus in Wales, Vantage officially implemented HVO at its newest facility, CWL13, on the Cardiff campus and is currently working to deploy the renewable fuel throughout the rest of the campus. In addition, Vantage will deploy HVO in Santa Clara, California, by the end of the year. 

“Making the switch to renewable diesel is one of the many ways we are reducing the carbon emissions of our operations. Reaching net zero by 2030 is an incredibly ambitious goal that will require us to implement a wide variety of solutions. Our focus is on maintaining reliability and affordability while achieving emissions reductions,” said Amanda Abell, senior director of sustainability at Vantage. “We look forward to continuing the rollout of HVO at our campuses across North America and EMEA, where available, in addition to the other programs we have in place to reach our sustainability targets.”

EdgeUno upgrades data center interconnect with Ciena

EdgeUno, a leading infrastructure as a service (IaaS) company in Latin America, hasupgraded its data center interconnect network in Mexico and Brazil with Ciena’s Waveserver 5 compact interconnect platform, powered by WaveLogic 5 Nano 400ZR coherent pluggables.

EdgeUno has doubled its network capacity from 200G channels to 400G per channel, improved its cloud service offerings, and reduced its carbon footprint by optimizing data center space and reducing energy consumption. EdgeUno is also leveraging Ciena’s edge-optimized, compact Coherent ELS open line system to achieve lower latency, operational simplicity, and deliver higher quality experiences to its customers.

“To provide the best possible digital experience and support bandwidth-intensive applications like high-speed gaming, cloud-based services, and live video streaming, we need the most innovative and reliable technology available,” said Tiago Setti, Director of Network Engineering, EdgeUno. “Ciena’s industry-leading WaveLogic technology plays a critical role in helping us meet our customers’ digital demands and also supports our sustainability commitments.”

“In an age where our lives revolve around the digital world, continually improving the customer experience is critical,” said Fernando Capella, Country Manager, Ciena Brazil. “Our optical technology is not only helping EdgeUno achieve that goal, but also provides the scalability and sustainability benefits needed to continue expanding in the future.”

Texas A&M picks Ribbon's IP Wave for its Private 5G

 Texas A&M University (TAMU) has selected Ribbon's NPT IP Routing for wireless backhaul on its private 5G research network, which connects the labs at the Internet2 Technology Evaluation Center (ITEC) with Engineering and Computer Science labs on TAMU's main campus, the public safety training area at Disaster City, and the labs and testbeds at the RELLIS Campus.

The network leverages Ribbon's advanced  NPT 1800 multi service aggregation router and NPT 2100 access edge and pre aggregation router, part of Ribbon's comprehensive IP Wave portfolio, for increased performance and availability. 

https://www.rbbn.com

Tuesday, September 12, 2023

Nokia debuts its next-gen IP access, aggregation and edge routers

Nokia unveiled its 7730 Service Interconnect Router (SXR) family of next-generation IP access, aggregation and edge platforms based on its new FPcx  network processing unit (NPU), 112G SerDes, and SFP-DD optics.

The new, fully programmable FPcx processor, which is implemented in 7nm silicon, enables network security features such as in-line filtering for DDoS mitigation and line-rate MACsec/ANYsec encryption. The chip also features 7-level hierarchical QoS, queueing and a hierarchical memory design with superior scalability for services, tunnels, queues, counters. 

The FPcx supports 1GE to 400GE interfaces with flexible 4x10G, 4x25G, 2x100G, 4x100G and 1x400G break-out options.

Nokia says the NPU can accommodate new services and standards as they emerge.


The new 7730 Service Interconnect Router (SXR) family includes four fixed form-factor and two modular platform variants, with a mix of port options ranging from 1GE to 400GE.  Backplanes range from 3.6 Tbps to 5.6 Tbps of system capacity.

The platforms support stringent synchronization demands with highly accurate timing enabled by integrated dual-band Global Navigation Satellite System (GNSS) receivers. 7730 can support time-sensitive packet transport and fronthaul networks with a Class C-based Telecom Boundary Clock.

The rollout brings focus to the Nokia SR Linux network operating system (NOS), which embraces cloud-native design principles, and the Nokia Network Services Platform (NSP) automation suite.

Ken Kutzler, Vice President of IP Routing Hardware at Nokia, said: “As service providers and network builders scale their IP networks for increased capacity, they require the ability to confidently deliver deterministic, secure and reliable services with easy, efficient service evolution and network operations – all with solid TCO savings. Nokia’s new family of routers enables them to get the benefits of service routing available today at the IP edge/core into the IP access and aggregation networks. We do this without performance compromise while ensuring the latest requirements are met.”

https://www.nokia.com/networks/ip-networks/7730-sxr

Accton intros 51.2 Tbps switch with 64x800G ports

Taiwan-based Accton Technology introduced a series of 800G-optimized products that can provide Ethernet-based fabric and Virtual Output Queue (VoQ) based fabric for AI/ML workloads. 

The announcement includes a 2RU 51.2 Tbps Ethernet-based fabric system with 64x800G ports, a 4RU 51.2 Tbps Ethernet-based fabric system with 128x400G ports, and a VoQ-based fabric Distributed Disaggregated Chassis (DDC) architecture with a 128x800G Network Cloud Fabric (NCF) engine.

Accton said its 51.2 Tbps Broadcom StrataXGS Tomahawk 5 series-based system with 64x800G or 128x400G ports provides a high-radix, deployment-friendly Ethernet-fabric. The 2RU system design is packed in a compact form factor with power and fan tray redundancy to achieve five-nines high availability and a wide environmental operating range for data center cloud applications. 

The platform comes in two variants, OSFP800 or QSFP-DD800 interface options, for flexible deployment supporting passive copper DAC on all ports and long-distance ZR+ optics. The 4RU 51.2 Tbps Tomahawk 5 series-based 128x400G system provides high-radix 200G/400G QSFP112 (compatible with QSFP56 and QSFP28) connectivity to accelerators and compute nodes in a flat architecture that reduces latency and required power, which enables networks to be scaled-out sustainably.

Accton’s Broadcom StrataDNX Jericho3-AI and StrataDNX Ramon3 systems are designed to form a VoQ-based fabric DDC Network Cloud Cluster that is optimized to support AI/ML applications. The Broadcom Jericho3-AI based Network Cloud Packet Forwarder (NCP) supports a 14.4 Tbps full-duplex switching and features 18x800G OSFP network interface ports and 20x800G OSFP fabric interface ports. The Broadcom Ramon3-based Network Cloud Fabric (NCF) engine supports a 51.2 Tbps switching capacity. The cell-based switching eliminates the Ethernet overhead and can effectively load balance all fabric links to build an efficient and high-availability DDC cluster.

With Accton’s 6RU, dual-Ramon3, 128x800G (dual-51.2 Tbps) fabric port switch and 2RU, Jericho3-AI, 18x800G (14.4 Tbps leaf) Ethernet network interface port switch, customers can build a 32K-GPU 800G/400G AI/ML cluster with a two-stage DDC network architecture to enable 400G GPU clusters now and migrate to 800G GPU clusters later with a software upgrade without replacing the switches. This provides excellent cost saving and investment protection that reduces capital spending while providing the flexibility for customers to “pay as you grow” without large upfront cost to enable AI and ML applications.

Michael K.T. Lee, Sr. Vice President of Research and Development Center, at Accton said, “Broadcom’s Tomahawk 5 and Roman3/Jericho3-AI form the building blocks of Accton’s 800G-optimized products for next-generation AI/ML clusters. We are proud of Accton's engineers who have excelled in the innovative design and development of these groundbreaking 800G systems. The significant increase in radix and throughput offered by the 800G AI fabric together with the reduced power consumption delivers a performance that will push the boundaries of efficiency in AI clusters.”

https://www.accton.com/800g-ai-ml-fabrics/

Enfabrica raises $125M for its 8 Tbps Accelerated Compute Fabric

Enfabrica,  a start-up based in Mountain View, California, closed a $125 million Series B financing round for its converged networking and memory fabric silicon and software.

The company says the new capital will be deployed to advance the production of itsAccelerated Compute Fabric Switch (ACF-S) devices and solutions, which complement GPUs, CPUs and accelerators to solve critical networking, I/O and memory scaling problems in data center AI and high-performance computing clusters. 

Earlier this year, Enfabrica emerged from stealth mode to announce its new class of AI infrastructure interconnect chips called Accelerated Compute Fabric devices. Enfabrica’s ACF devices deliver unmatched scalability, performance and total cost of ownership for distributed AI, extended reality, high-performance computing and in-memory database infrastructure.

Enfabrica’s 8 Terabit/second ACF switching system, which directly bridges and internetworks GPUs, CPUs, and memories at scale with native, multi-port 800-Gigabit-Ethernet networking, is now accessible to customers for pre-order.

Enfabrica’s first, production-grade ACF switching system powered by Enfabrica silicon, produced in collaboration with partners, is an 8 Tbps platform enabling direct-attach of any combination of GPUs, CPUs, CXL-attached DDR5 memory and SSD storage to high-performance, multi-port 800-Gigabit-Ethernet networks. ACF switching systems incorporate Enfabrica’s high-performance ACF-S silicon having 100 percent standards-compliant interfaces and host networking software stack components running on standard Linux kernel and userspace interfaces. The ACF-S chip offers multi-port 800 Gigabit Ethernet networking and high-radix PCIe Gen5 and CXL 2.0+ interfaces. 

The company envisions composable AI fabrics of compute, memory and network resources that scales from a single system to tens of thousands of nodes. The design provides uncontended access to >50X DRAM expansion over existing GPU networks via ComputeExpressLink (CXL) bridging.

“The fundamental challenge with today’s AI boom is the scaling of infrastructure,” said Rochan Sankar, Enfabrica CEO and co-founder. “There’s no denying the transformative value that AI delivers to a multitude of economic sectors. But there is a critical need to bridge the exploding demand to the overall cost, efficiency, and ease of scaling AI compute, across all customers seeking to take control of their distributed AI infrastructure and services. Much of the scaling problem lies in the I/O subsystems, memory movement and networking attached to GPU compute, where Enfabrica’s ACF solution shines.”

Infinera's ICE-X coherent pluggables comply with Buy America

Infinera confirmed that its ICE-X intelligent coherent pluggables and compound semiconductor components  will be manufactured in the U.S. and compliant with the Build America, Buy America requirements recently released by the Commerce Department for the Broadband Equity, Access, and Deployment (BEAD) program. 

Infinera operates an optical compound semiconductor fabrication facility in California and an advanced testing and packaging facility in Pennsylvania.

Infinera’s suite of vertically integrated ICE-X intelligent coherent pluggables, based on the optical compound semiconductor indium phosphide, provide network operators the performance, scale, and efficiency critical to drive down network operating costs and to enhance service agility. These solutions are a critical part of network infrastructure and are optimized for metro, middle-mile, and access and aggregation networks that enable operators to expand their broadband infrastructures while helping them address Build America, Buy America requirements for the BEAD program.

“Infinera is a global leader in the development and production of advanced optical semiconductors, operating one of the most advanced U.S.-based compound optical semiconductor fabrication facilities for monolithically integrated photonic integrated circuits. We remain committed to investing in and keeping optical semiconductor fabrication in the U.S.,” said David Heard, Infinera CEO. “By leveraging our vertically integrated U.S.-based development, fabrication, and manufacturing capabilities, we can do our part to enhance national security and improve supply chain resiliency for important semiconductor technologies.”

https://www.infinera.com/press-release/infinera-announces-suite-of-ice-x-coherent-pluggables-and-compound-semiconductor-components-to-comply-with-buy-america-requirements/

OpenZR+ MSA Group adds 400G 8QAM and higher transmit power

The OpenZR+ Multi-Source Agreement (MSA) Group published the OpenZR+ Rev 3.0 specification which defines a higher performing 400G 8QAM mode as well as a higher transmit power mode.

The new specification is designed to further expand the application space for a coherent solution in small form factor pluggable modules, such as form factors defined by the QSFP-DD MSA and OSFP MSA.

“The OpenZR+ MSA is once again paving the way towards multi-vendor interoperability of small form factor pluggables, which are key for enabling network operators to support their growing bandwidth demands in a more cost-efficient manner,” said Atul Srivastava, Co-chair of the OpenZR+ MSA Group.

“With this Rev 3.0 specification, the MSA is continuing to expand the application space for OpenZR+ with new modes designed to address longer reaches and a wider range of network architectures,” said Tom Williams, Co-chair of the OpenZR+ MSA Group.

In the future, the OpenZR+ MSA plans to continue to expand membership in the organization with the goal of further collaborating on improvements to the specification that are in the best interest of the industry. The OpenZR+ MSA expects to play a key role in defining higher data rate operating modes for pluggable coherent interfaces as the industry looks toward 800G and beyond. 

https://openzrplus.org

Intel to sell 10% stake in the IMS Nanofabrication business to TSMC

Intel agreed to sell an approximately 10% stake in the IMS Nanofabrication business to TSMC. 

TSMC’s investment values IMS at approximately $4.3 billion, consistent with the valuation of the recent stake sale to Bain Capital Special Situations. 

Intel will retain majority ownership of IMS, which will continue to operate as a standalone subsidiary under the leadership of CEO Dr. Elmar Platzgummer. The transaction is expected to close in the fourth quarter of 2023.

Intel said Bain Capital's and TSMC’s investments provide IMS with increased independence and reinforce confidence in the significant opportunity ahead of IMS. This added autonomy will help IMS accelerate its growth and drive the next phase of lithography technology innovation to enable the industry’s transition into new patterning systems, such as high-numerical-aperture (high-NA) EUV.

IMS specializes in multi-beam mask writing tools required to develop advanced extreme ultraviolet lithography (EUV), which is broadly adopted in leading-edge technology nodes that enable the most demanding computing applications, such as artificial intelligence (AI) and mobile. 

Matt Poirier, senior vice president of Corporate Development at Intel, said, “This investment demonstrates the deep industry collaboration IMS is pioneering to advance critical lithography technology for leading-edge nodes, which will benefit the entire semiconductor manufacturing ecosystem. With enhanced independence, IMS will be well positioned to address the significant growth opportunity for multi-beam mask writing tools over the next decade and beyond.”