Sunday, October 16, 2022

Google Cloud's C3 VMs powered by Intel Xeon + IPU

Google Cloud introduced its Compute Engine C3 VMs powered by the 4th Gen Intel Xeon Scalable processor and Google’s custom Intel Infrastructure Processing Unit (IPU).

C3 machine instances use offload hardware for more predictable and efficient compute, high-performance storage, and a programmable packet processing capability for low latency and accelerated, secure networking.  

The VMs are optimized to work with Hyperdisk, Google Cloud's next-generation block storage. The company says this new architecture decouples compute instance sizing from storage performance to deliver 80% higher IOPS per vCPU than other leading hyperscale cloud provider. Compared with the previous generation C2, C3 VMs with Hyperdisk deliver 4x higher throughput and 10x higher IOPS. 

“We are pleased to have codesigned the first ASIC infrastructure processing unit with Google Cloud, which has now launched in the new C3 machine series. A first of its kind in any public cloud, C3 VMs will run workloads on 4th Gen Intel Xeon Scalable processors while they free up programmable packetprocessing to the IPUs securely at line rates of 200 gigabits per second,” says Nick McKeown, Intel senior vice president, Intel Fellow and general manager of Network and Edge Group. “This Intel and Google collaboration enables customers through infrastructure that is more secure, flexible and performant.”

Intel unveils IPU roadmap with ASIC and FPGA designs

Intel unveiled its IPU roadmap extending through 2026, featuring new FPGA + Intel architecture platforms (code-named Hot Springs Canyon) and the Mount Morgan (MMG) ASIC, as well as next-generation 800GB products. The discussion also a look at Intel's open-source software foundation, including the infrastructure programmer development kit (IPDK), which builds upon SPDK, DPDK and P4.In terms of the timeline, Intel's roadmap includes:2022: Mount Evans,...

Google collaborates on Intel's ASIC-based infrastructure processor

Intel and Google Cloud announced a deep collaboration to develop an ASIC P4-programmable infrastructure processing unit (IPU).Code-named “Mount Evans,” this open solution supports open source standards, including an infrastructure programmer development kit (IPDK) to simplify developer access to the technology in Google Cloud data centers. Machine learning, large-scale data processing and analytics, media processing, and high-performance computing...

Intel rolls FPGA-based Infrastructure Processing Unit (IPU)

Intel outlined its vision for the infrastructure processing unit (IPU), a programmable network device that intelligently manages system-level infrastructure resources by securely accelerating those functions in a data center.In a video, Guido Appenzeller, chief technology officer with Intel's Data Platforms Group says the idea is to cleanly separate the processing of client workloads from workloads of the cloud service provider.Intel cites several...

Intel moves to an internal foundry model

Intel is adopting an internal foundry model for external customers and for its own Intel product lines. The effort will be led by Stuart Pann, Senior Vice President of our Corporate Planning Group (CPG). In addition to his responsibility leading CPG, Stu will take on the role of Chief Business Transformation Officer, reporting to Chief Financial Officer Dave Zinsner and joining the executive leadership team. 

Intel CEO Pat Gelsinger writes: "Implementing an internal foundry model means establishing consistent processes, systems and guardrails between our business unit, design and manufacturing teams. This will allow us to identify and address structural inefficiencies that exist in our current model by driving accountability and costs back to decision-makers in real time. It will also put Intel’s product groups on a similar footing as external Intel Foundry Services customers and vice versa."

For example, our business unit and design teams will be able to consider the potential impact on their margins if they want to run an additional product stepping, while the manufacturing team will be able to assess requests based on actual costs and impact on factory output. This will give teams the tools and transparency they need to find the most effective and cost-efficient solutions before implementation in silicon, ultimately helping us maximize factory output, reduce costs and shorten design cycles."

"We will also create a foundry accounting model that encompasses manufacturing, technology development and Intel Foundry Services. This will give us more transparency into our financial execution and will allow us to fully benchmark and drive ourselves to best-in-class foundry performance."

Intel welcomes investment from Brookfield in Arizona fabs

Intel announced a cost-sharing partnership in which the infrastructure affiliate of Brookfield Asset Management, one of the largest global alternative asset managers, will provide Intel with a new, expanded pool of capital for manufacturing build-outs.Intel describes its new Semiconductor Co-Investment Program (SCIP) as a new funding model that will accelerate its IDM 2.0 foundry strategy. The partnership with Brookfield is expected to enhance Intel's...

EXFO acquires EHVA, a Photonics Integrated Circuit test company

EXFO has acquired EHVA, an innovative Photonics Integrated Circuits (PICs) and system automation company based in Quebec City, Canada. Financial terms were not disclosed.

EHVA, which is a spin-off from the Center for Optics, Photonics, and Lasers (COPL) at Universit√© Laval in Quebec, combines manufacturing intelligence with wafer-to-single device capabilities to deliver scalable solutions for PIC testing and manufacturing. 

EXFO said the acquisition will accelerate its advanced capabilities in PIC testing, enabling delivery of automated, turnkey end-to-end testing of optical components from lab applications to high-volume and high-speed manufacturing.

EHVA’s process software suite  integrates EXFO’s advanced swept continuous laser scanning technology into customer manufacturing settings for exceptional testing reliability and efficiency, delivering a fully-automated solution that helps avoid production bottlenecks. This seamless integration is critical, given the diversity in PIC designs used for varied applications and the lack of standards for PIC technology which poses added challenges for automated testing.

NEC charters submarine cable ship under 4 year contract

NEC Corporation signed a charter contract with U.K.-based Global Marine Systems for an optical submarine cable-laying ship for approximately four years. 

The deal is for the submarine cable-laying ship "Normand Clipper", a 127m long vessel capable of carrying approximately 7,000km of spooled cable.

NEC has been a leading global vendor in the submarine cable system business for over 50 years, manufacturing submarine cables, submarine repeaters, and terminal station equipment, in addition to coordinating marine surveys and route design, equipment installation work, cable laying, training and delivery testing. 

Until now, NEC has procured submarine cable-laying ships for each project separately. In order to respond to the growing demand for new submarine cables due to the recent spread of 5G and the increase in data traffic between data centers in various countries, NEC has chartered a long-term dedicated cable-laying ship for the first time. As a result, NEC will provide submarine cable systems more quickly and flexibly than ever before to meet customer demand.

NEC to build 24-fiber-pair transatlantic cable for Facebook

NEC has been contracted by Facebook to build an ultra-high performance transatlantic subsea fiber-optic cable connecting the USA and Europe. The project will use NEC’s newly developed 24 fiber pair cable and repeater, enabling the system to deliver a maximum transmission capacity of a half Petabit per second, the highest to date for a long-distance repeatered optical subsea cable system.Facebook confirmed its first-ever transatlantic, 24-fiber-pair...

NEC qualifies subsea repeaters and cables for 24 fiber pairs

 NEC and its subsidiary OCC Corporation have completed full qualification of subsea repeaters and optical cable containing up to 24 fiber pairs (FPs) (48 fibers). The new qualification is a 50% improvement in fiber count over the 16 fiber pair systems generally available today. Only minor modifications were needed to NEC's existing repeater and cable designs. Keeping NEC's quadruple pump redundancy in the repeater (established more than...

Gulf Bridge upgrades its transport backbone with Nokia's PSE-V

Gulf Bridge International (GBI) will upgrade its existing subsea cables and terrestrial links with new network interface cards for its Nokia 1830 Photonic Service Switch (PSS) optical transport platforms. The new cards are powered by Nokia's Photonic Service Engine V (PSE-V) digital signal processors. This will enable upgrade to wavelength connections from 50 Gbps to 200 Gbps over GBI’s existing end-to-end subsea cable and terrestrial links spanning thousands of km and will allow the introduction of 400 Gbps services in the future.

This upgrade will increase GBI’s international network capacity ahead of the World Cup to enable high-speed connectivity between Doha, Qatar and Milan, Italy. The solution maximizes the capacity of two existing subsea cable links by greatly improving the optical spectrum efficiency through advanced techniques such as continuous baud rate adjustment. It also eliminates regeneration of the optical signal over two long-haul terrestrial links. Removing the need to convert between optical and electrical signals to boost the optical signal at intermediate regeneration points increases network efficiency and reduces latency and cost.

Gavin Rea, Chief Technical Officer at GBI, said: “We selected Nokia because its proven PSE technology will enable us to grow the capacity of our subsea cables and terrestrial networks efficiently and cost-effectively. We will be able to meet our customers’ increasing demand for the best connectivity services between the Middle East and Europe while ensuring that we can increase speed and capacity in the future. These routes are critical to our international carrier-grade fiber-optic Smart Network that connects service provider, cloud provider and enterprise customers to important financial and communications hubs across the Middle East, Europe, Africa and Asia.”

Manuel Ortiz Fernandez, Senior Vice President of EMEA Webscale Business, said: “There is a growing need for wholesale services that provide higher speed, reliable connectivity between cloud data centers, co-location facilities and interconnection hubs in the Middle East and Europe. We are delighted that GBI has selected Nokia to upgrade important routes of its Smart Network. GBI’s customers will benefit from the scale, reliability and efficiency of our optical solution while GBI will be able to increase network capacity while reducing network operations costs.”

Nokia supplies 7750 Service Routers for ESnet6

Nokia confirmed that it is supplying its 7750 SR-s routers with Nokia-developed FP silicon and Service Router OS software for ESnet6, the U.S. Department of Energy’s (DOE) high performance network dedicated to collaborative scientific research. ESnet has deployed Nokia’s 7750 Service Router (SR) platforms to provide high-speed 100Gbps and 400 Gbps services over an IP/MPLS network designed to support over 46 Tbps of capacity.

Nokia7750 SR-s ssupports segment routing, EVPN-based services and model-driven management. ESnet research activities require petabyte traffic flows made possible through the Nokia FP silicon’s advanced traffic engineering and QoS capabilities combined with deep buffers. ESnet also selected Nokia’s Network Services Platform Path Computation Element, which builds upon the 7750 SR-s deployment, providing visibility of network and link usage and the ability to conduct traffic engineering of Segment Routing tunnels.

Inder Monga, Executive Director at ESnet, said: “ESnet6 represents a transformational change in the way networks are built for research, with improved capacity, resiliency, and flexibility. Together, we are enabling scientists around the world to conduct and collaborate on ground-breaking research in a faster and more efficient way.”

Mike Loomis, General Manager of Nokia Federal, said: “We are delighted to work with ESnet to help the scientific community advance the next generation of science. Our technology has set the foundation by more than tripling ESnet’s WAN from 100G to 400G, and it has been built to provide future-proofed scale and capacity. When ESnet is ready to scale to 800GE, we will be here to help them.”

Kyndryl, Microsoft and Dell partner on a hybrid cloud solution

Kyndryl, Microsoft and Dell Technologies introduced a hybrid cloud solution that combines elements of Microsoft Azure, Kyndryl managed services and Dell Technologies infrastructure.

The new Kyndryl Distributed Cloud for Microsoft Azure Stack hyperconverged infrastructure (HCI) with Azure Arc consists of Dell Integrated System for Azure Stack HCI, based on Dell PowerEdge servers and Microsoft Azure Stack HCI software. Businesses will be able to transform their on-premises and remote workloads through fully managed distributed cloud services, high-performance operations and full-stack lifecycle management.

Customers can deploy Kyndryl Distributed Cloud for Microsoft Azure Stack HCI with Azure Arc in a data center, remote office and branch office (ROBO) locations or even next to an assembly line in a factory to run augmented reality maintenance and repair (ARMAR) in real-time and collect IoT data to derive insights for predictive maintenance and manage operations.

“We are glad to collaborate with Microsoft and Dell Technologies to help customers benefit from cloud automation and centralized management of their IT and operational environments, all while supporting performance and compliance requirements,” said Stephen Leonard, Kyndryl’s Strategic Global Alliances Leader. “Our new HCI offering provides flexibility of data deployments and access with advanced security capabilities, whether workloads are in the cloud, on-premises, or remote locations.”

SpaceX launches EUTELSAT HOTBIRD 13F Satellite

Eutelsat's HOTBIRD 13F satellite was successfully launched into Geostationary Transfer Orbit by SpaceX using a Falcon 9 rocket from Cape Canaveral, Florida.

EUTELSAT HOTBIRD 13F, which is one of two satellites built by manufacturer Airbus Defence and Space, is based on the Eurostar Neo telecommunications satellite platform. Once into orbit and positioned, the satellite EUTELSAT HOTBIRD 13F will, with its twin EUTELSAT HOTBIRD 13G, reinforce and enhance the broadcast of more than a thousand television channels into homes across Europe, Northern Africa and the Middle East. Moreover, the satellites will offer advanced features in terms of uplink signal protection and resilience.

The two satellites will be replacing three older satellites at Eutelsat’s 13° East flagship neighbourhood position.

Pascal Homsy, Eutelsat Chief Technical Officer said: "Our congratulations to the Eutelsat, Airbus and SpaceX teams for successfully launching our EUTELSAT HOTBIRD 13F satellite into geostationary orbit. This satellite brings the latest technology resources of the new Eurostar Neo platform at our leading 13-degree East position and confirms a long-term partnership between Airbus and Eutelsat”.