Is quantum-secured networking ready for commercialization?

Is quantum-secured networking ready for commercialization? What value does it provide?

https://youtu.be/gGVkMcYJ9kw

In this video, Andrew Lord, Distinguished Engineer and Senior Manager Optical Networks and Quantum Research, BT, explains that while quantum has often been perceived as a complex science experiment, it has moved on incredibly in the last few years, and it is now ready for showtime. 

The proof of this is in the demonstration that BT and partners have built in London, which is different from a science experiment. They are using equipment that is installed in BT exchanges, and the management system is part of a normal standard BT management system. The alarms and monitoring come back to a Network Operation Center, where someone else will see those alarms on a Quantum screen in the Management Center. To all intents and purposes, this is ready to go, and they are now working with major customers to see what are the use cases and ultimately what customers are prepared to pay for a service running over the top of ultimate quantum security.

See also: BT and Toshiba test quantum secured communication services 

Read More

NVIDIA accelerates its generative AI platforms

NVIDIA launched four inference platforms optimized for generative AI applications:

• 
  NVIDIA L4 for AI Video can deliver 120x more AI-powered video performance than CPUs, combined with 99% better energy efficiency. Serving as a universal GPU for virtually any workload, it offers enhanced video decoding and transcoding capabilities, video streaming, augmented reality, generative AI video and more.
• NVIDIA L40 for Image Generation is optimized for graphics and AI-enabled 2D, video and 3D image generation. The L40 platform serves as the engine of NVIDIA Omniverse, a platform for building and operating metaverse applications in the data center, delivering 7x the inference performance for Stable Diffusion and 12x Omniverse performance over the previous generation.
• NVIDIA H100 NVL for Large Language Model Deployment is ideal for deploying massive LLMs like ChatGPT at scale. The new H100 NVL with 94GB of memory with Transformer Engine acceleration delivers up to 12x faster inference performance at GPT-3 compared to the prior generation A100 at data center scale.
• NVIDIA Grace Hopper for Recommendation Models is ideal for graph recommendation models, vector databases and graph neural networks. With the 900 GB/s NVLink-C2C connection between CPU and GPU, Grace Hopper can deliver 7x faster data transfers and queries compared to PCIe Gen 5.

“The rise of generative AI is requiring more powerful inference computing platforms,” said Jensen Huang, founder and CEO of NVIDIA. “The number of applications for generative AI is infinite, limited only by human imagination. Arming developers with the most powerful and flexible inference computing platform will accelerate the creation of new services that will improve our lives in ways not yet imaginable.”

https://nvidianews.nvidia.com/news/nvidia-launches-inference-platforms-for-large-language-models-and-generative-ai-workloads

Read More

Google Cloud offers NVIDIA’s L4 Tensor Core GPUs for generative AI

Google Cloud  is the first cloud services provider to offer NVIDIA’s L4 Tensor Core GPU. Additionally, L4 GPUs will be available with optimized support on Vertex AI, which now supports building, tuning and deploying large generative AI models.

NVIDIA’s L4 GPU is a universal GPU capable of delivering 120x more AI-powered video performance than CPUs. The company also claims 99% better energy efficiency.

“Surging interest in generative AI is inspiring a wave of companies to turn to cloud-based computing to support their business models,” said Jensen Huang, founder and CEO of NVIDIA. “We are working with Google Cloud to help ensure that the capabilities they require are easily available and able to help fuel the incredible new tools and applications they will create.”

“Generative AI represents a new era of computing — one that demands the speed, scalability and reliability we provide on Google Cloud,” said Amin Vahdat, vice president of Systems & Services Infrastructure at Google Cloud. “As our customers begin to explore the possibilities of generative AI, we’re proud to offer them NVIDIA’s latest L4 GPU innovation as part of our workload-optimized Compute Engine portfolio.”

https://www.nvidia.com/en-us/data-center/l4/

Read More

Oracle Cloud deploys NVIDIA BlueField-3 DPUs

Oracle Cloud Infrastructure (OCI) has selected the NVIDIA BlueField-3 DPU as the latest addition to its networking stack, offering OCI customers a new option for offloading data center tasks from CPUs.

BlueField-3 is NVIDIA’s third-generation data processing unit BlueField-3 is the foundation of the data center control plane that delivers cloud and AI services. The company cites power reductions of up to 24% on servers using NVIDIA BlueField DPUs compared to servers without DPUs. The DPUs support Ethernet and InfiniBand connectivity at up to 400 Gbps and provide 4x more compute power, up to 4x faster crypto acceleration, 2x faster storage processing and 4x more memory bandwidth compared to the previous generation of BlueField.

“The age of AI demands cloud data center infrastructures to support extraordinary computing requirements,” said Jensen Huang, founder and CEO of NVIDIA. “NVIDIA’s BlueField-3 DPU enables this advance, transforming traditional cloud computing environments into accelerated, energy-efficient and secure infrastructure to process the demanding workloads of generative AI.”

“Oracle Cloud Infrastructure offers enterprise customers nearly unparalleled accessibility to AI and scientific computing infrastructure with the power to transform industries,” said Clay Magouyrk, executive vice president of Oracle Cloud Infrastructure. “NVIDIA BlueField-3 DPUs are a key component of our strategy to provide state-of-the-art, sustainable cloud infrastructure with extreme performance.” 

Read More

Arista debuts enterprise-class WAN Routing System

Arista Networks has begun customer trials of a new WAN Routing System that combines its enterprise-class routing platforms, carrier/cloud-neutral internet transit capabilities, and its CloudVision Pathfinder Service, which modernizes WAN management and provisioning, aligning the operating model with visualization and orchestration across all network transport domains

The Arista WAN Routing System aims for a consistent networking architecture across all enterprise network domains from the client to campus to the data center to multi-cloud with a single instance of EOS, a consistent management platform, and a modern operating model.

The new Arista 5000 Series of WAN Platforms, powered by Arista EOS, support enterprise-class WAN edge and aggregation requirement with 1/10/100GbE interfaces. The platforms deliver from 5Gb to over 50Gbps of bidirectional AES256 encrypted traffic with high VRF and tunnel scale. Use cases include:

• Aggregation and High-Performance Edge Routing – The Arista 5500 WAN System, supporting up to 50Gbps of encrypted traffic, is ideal for data center, campus, high-performance edge, and physical transit hub architectures.
• Flexible Edge Routing – The Arista 5300 WAN System is suited for high-volume edge connectivity and transitioning WAN locations to multi-carrier, 5G, and high-speed Internet connectivity with performance rates of up to 5Gbps of encrypted traffic.
• Scalable Virtual Routing – Arista CloudEOS is a binary-consistent virtual machine implementing identical features and capabilities of the other Arista WAN systems. It is often deployed in carrier-neutral transit hub facilities or to provide scale-out encryption termination capabilities.
• Public Cloud Edge Routing – Arista CloudEOS is also deployable through public cloud marketplaces and enables Cloud Transit routing and Cloud Edge routing capabilities as part of the end-to-end WAN Routing System. CloudEOS is available on AWS, Azure, Google Cloud, and through Platform Equinix.
• CPE Micro Edge – In addition to the fully integrated, dynamically configured, and adaptive Arista WAN Routing System platforms, the Arista Micro Edge is capable of small-site interoperability with the WAN Routing System to provide simple downstream connectivity options.

Arista also highlighted a partnership with Equinix to develop virtual and physical implementations of the Arista WAN Routing System that are globally deployable in Equinix data centers.

“Arista Pathfinder leverages Equinix’s Network Edge, Equinix Metal, and Equinix Fabric services to deliver scalable routing architectures that accelerate customers with cloud and carrier-neutral networking,” stated Zachary Smith, Global Head of Edge Infrastructure Services at Equinix. “Pathfinder’s ability to scale, in software, from a single virtual deployment to a multi-terabit globally distributed core that reallocates paths as network conditions change is a radical evolution in network capability and self-repair.”

https://www.arista.com/en/company/news/press-release/17212-pr-20230321

Read More

Stuart Pann appointed GM of Intel Foundry Services

Intel announced the appointment of Stuart Pann as senior vice president and general manager of Intel Foundry Services (IFS), reporting to Intel CEO Pat Gelsinger. He succeeds Dr. Randhir Thakur, the inaugural general manager of Intel Foundry Services, who stepped down from the role in November 2022 and will depart Intel at the end of March.

“The industry is responding well to our systems foundry approach and we’re seeing strong momentum, including the recent announcement of a significant cloud, edge and data center solutions provider as a customer for our upcoming Intel 3 process,” said Gelsinger. “With deep expertise in capital and capacity strategies, supply chain management, and sales and operations planning across internal and external manufacturing, Stuart is an ideal leader to accelerate this momentum and drive long-term growth for IFS.”

Pann previously served as senior vice president, chief business transformation officer and general manager of Intel’s Corporate Planning Group. As part of this role, he established the company’s IDM 2.0 Acceleration Office to guide the implementation of an internal foundry model, fundamentally shifting the way the company operates to be more consistent with other top foundries. Pann started his career at Intel and returned to the company in 2021, having previously served as chief supply chain officer and chief information officer at HP for six years. Prior to that, Pann served as corporate vice president and general manager of Intel’s Business Management Group, responsible for pricing, revenue and forecasting functions.

Read More

Connecting data center racks for AI/ML

How do you build a data center rack for AI/ML training? At OFC23, Credo showcased a high-performance rack with 3 next gen appliances connected with 3 types of physical networking, including a big backbone for RDMA sharing, which could be used for GPT-style applications. 

https://youtu.be/nHb7Bee1_M8

Also on display was a Credo 800G Active Electrical Cable with the Screaming Eagle retimer. Another demo featured Credo's Dove 800G Digital Signal Processor (DSP) demonstrating the ability to support extra host performance in a hyperscaler environment by supporting an (MR) interface. 

A suite of Dove 800 optical DSP demos showcased performance in various applications, interoperability, internal VCSEL driver, host performance and silicon photonics integration. 

Here is a booth tour with Don Bartleson and Easwar Shanker.

Read More