Tuesday, January 10, 2023

Intel's 4th Gen Xeon brings accelerators for data center, vRANs

Intel launched its 4th Gen Xeon Scalable processors (code-named Sapphire Rapids), Xeon CPU Max Series (code-named Sapphire Rapids HBM) and Data Center GPU Max Series (code-named Ponte Vecchio).

Intel described the rollout as one of the most important product launches in company history.

The new processors promise a leap in data center performance, efficiency, security and new capabilities for AI, the cloud, the network and edge, and the world’s most powerful supercomputers. Intel said 4th Gen Intel Xeon customers can expect a 2.9x average performance per watt efficiency improvement for targeted workloads when utilizing built-in accelerators, up to 70-watt power savings per CPU in optimized power mode with minimal performance loss, and a 52% to 66% lower TCO.

For 5G core workloads, built-in accelerators help increase throughput and decrease latency, while advances in power management enhance both the responsiveness and the efficiency of the platform. And, when compared to previous generations, 4th Gen Xeon delivers up to twice the virtualized radio access network (vRAN) capacity without increasing power consumption. This enables communications service providers to double the performance-per-watt to meet their critical performance, scaling and energy efficiency needs.

“The launch of 4th Gen Xeon Scalable processors and the Max Series product family is a pivotal moment in fueling Intel’s turnaround, reigniting our path to leadership in the data center and growing our footprint in new arenas,” said Sandra Rivera, Intel executive vice president and general manager of the Data Center and AI Group. “Intel’s 4th Gen Xeon and the Max Series product family deliver what customers truly want – leadership performance and reliability within a secure environment for their real-world requirements – driving faster time to value and powering their pace of innovation.”

Notably, the 4th Gen Xeon and the Intel Max Series product family offer built-in accelerator engines. These include:

Intel Advanced Matrix Extensions (Intel AMX)

With new Intel AMX, AI performance on the CPU expands to include fine-tuning and small and medium deep learning training models. Intel AMX is a built-in accelerator that improves the performance of deep learning training and inference. It is ideal for workloads like natural language processing, recommendation systems and image recognition.

Intel QuickAssist Technology (Intel QAT)

By offloading encryption, decryption and compression, Intel QAT— now integrated as a built-in accelerator — helps free up processor cores so systems can serve a larger number of clients or use less power. With Intel QAT, 4th Gen Intel Xeon Scalable processors are the highest- performance CPUs that can compress and encrypt in a single data flow.

Intel Data Streaming Accelerator (Intel DSA)

Intel DSA drives high performance for storage, networking and data-intensive workloads by improving streaming data movement and transformation operations. Designed to offload the most common data movement tasks that cause overhead in data center-scale deployments, Intel DSA helps speed up data movement across the CPU, memory and caches, as well as all attached memory, storage and network devices.

Intel Dynamic Load Balancer (Intel DLB)

Intel DLB helps improve system performance related to handling network data on multicore Intel® Xeon Scalable processors. It enables the efficient distribution of network processing across multiple CPU cores/threads and dynamically distributes network data across multiple CPU cores for processing as the system load varies. Intel DLB also restores the order of networking data packets processed simultaneously on CPU cores.

Intel In-Memory Analytics Accelerator (Intel IAA)

Intel IAA helps run database and analytics workloads faster, with potentially greater power efficiency. This built-in accelerator increases query throughput and decreases the memory footprint for in-memory database and big data analytics workloads. Intel IAA is ideal for in- memory databases, open source databases, and data stores like RocksDB and ClickHouse.

Intel Advanced Vector Extensions 512 (Intel AVX-512)

Intel AVX-512 is the latest x86 vector instruction set, with up to two fused-multiply add (FMA) units and other optimizations to accelerate performance for demanding computational tasks, including scientific simulations, financial analytics, and 3D modeling and analysis.

Intel Advanced Vector Extensions 512 (Intel AVX-512) for vRAN

Intel AVX-512 for virtualized radio access network (vRAN) is designed to deliver greater capacity at the same power envelope for vRAN workloads. This helps communications service providers increase their performance per watt to meet critical performance, scaling and energy efficiency requirements.

Intel Crypto Acceleration

Intel Crypto Acceleration reduces the impact of implementing pervasive data encryption and increases the performance of encryption-sensitive workloads, like secure sockets layer (SSL) web servers, 5G infrastructure and VPNs/firewalls.

Intel Speed Select Technology (Intel SST)

Intel SST is designed to grant more active and expansive control over CPU performance. Intel SST enables improved server utilization and reduced qualification costs by allowing customers to configure a single server to match fluctuating workloads. The result is one flexible server with multiple configurations, leading to improved TCO.

Intel Data Direct I/O Technology (Intel DDIO)

Intel DDIO helps remove inefficiencies by enabling direct communication between Intel Ethernet controllers and adapters and host processor cache. Eliminating frequent visits to main memory can help reduce power consumption, provide greater I/O bandwidth scalability and reduce latency.

Intel Software Guard Extensions (Intel SGX)

With Intel SGX, organizations can unlock new opportunities for business collaboration and insights — even with sensitive or regulated data. Intel SGX is the most researched, updated and deployed confidential computing technology in data centers on the market today, with the smallest trust boundary. Confidential computing improves the isolation of sensitive data with enhanced hardware-based memory protections. Support for Intel SGX on Intel Xeon CPU Max Series is on DDR flat mode only.

Intel Trust Domain Extension (Intel TDX)

Intel TDX is a new capability available through select cloud providers in 2023 that offers increased confidentiality at the virtual machine (VM) level, enhancing privacy and control over data. Within an Intel TDX confidential VM, the guest OS and VM applications are isolated from access by the cloud host, hypervisor and other VMs on the platform.

Intel Control-Flow Enforcement Technology (Intel CET)

Intel CET provides enhanced hardware-based protections against return-oriented and jump/call- oriented programming attacks, two of the most common software-based attack techniques. Using this technology helps shut down an entire class of system memory attacks that long evaded software-only solutions.


Vantage Data Centers invests £500 million in 48MW London campus

Vantage Data Centers unveiled plans for a 48MW £500 million data center campus in London. The new facility, which is situated on nearly five acres (two hectares) in the PowerGate neighborhood of North Acton, an established data center community in the northwest part of the city, will total 430,000 square feet (40,000 square meters) across two 24MW multi-story data centers once fully developed. 

The first facility will open its doors to hyperscale customers and cloud providers in late 2024, which will mark Vantage’s 11th campus in EMEA.

“Vantage has experienced rapid growth over the past three years as we continue developing state-of-the-art data center campuses across EMEA,” said Antoine Boniface, president, EMEA at Vantage Data Centers. “With London being one of the largest data center markets in the world, this expansion further solidifies Vantage’s role at the forefront of the digital infrastructure revolution. With relatively little inventory available in London and requirements on the rise, we are ideally positioned to deliver for our customers.”

“The continuing demand for data centers in London offers a prime opportunity for Vantage Data Centers to make its entrance into the highly-coveted market,” said Tim Kay, deputy director for technology, Department for International Trade in London. “Vantage’s presence in London will play a key role in enabling leading technology enterprises with additional IT capacity to support digital transformation initiatives and cloud adoption.”

In addition to the development of its London campus, Vantage has completed the first phase (12MW) of a second 40MW facility at its growing Cardiff campus, located in Wales, the second largest data center market in the U.K. The new facility boasts one of the lowest power usage effectiveness (PUE) ratios across all of Vantage’s facilities thanks in part to its extremely energy efficient indirect evaporative free cooling system, which negates the need for compressors in the cooling cycle. Once fully developed, the 46-acre campus (19 hectares) will include three data centers totaling 148MW across 2 million square feet (186,000 square meters). Conveniently located in the U.K.’s tech corridor near the M4 and just 100 miles (160 kilometers) from London’s urban density, the campus offers numerous connectivity options with low latency between Wales and London of less than 1.5 milliseconds. The sustainable campus operates entirely on renewable energy sources.

POET begins production of optical engines for 100G, 200G and 400G

POET Technologies released to production foursmall form factor optical engines with integrated directly modulated lasers (DMLs), optical multiplexer, high-speed photodiodes and optical demultiplexer. The devices enable low power, cost-efficient and highly scalable 100G CWDM4, 200G FR4 and 400G FR4 pluggable transceivers for telecom and data center markets.

The 100G CWDM4 transmit optical engine consists of four high-speed DMLs, monitor photodiodes and an optical multiplexer. The receive optical engines for 100G CWDM4, 200G FR4 and 400G FR4 have four high-speed photodiodes and an optical demultiplexer integrated in a compact form factor. Customers of POET’s optical engines have the option to procure the engines with an integrated fiber array unit (FAU), which provides an even more complete solution for next generation data center interconnects.  

POET noted that it reached its production release milestones while working with Super Photonics, the joint venture company formed with Sanan IC of Xiamen, China. POET and Super Photonics have jointly completed design verification testing and reliability testing of the optical engines per relevant industry standards. The next step in the commercialization process is for POET’s customers to qualify the products internally with their clients. Purchase orders are expected to follow.

“We have worked closely with our customers to engineer the optical engines to their requirements. So far, everyone involved in the process is very satisfied with the results. The release of POET’s optical engines to production sets the stage for high-volume deployment and widespread acceptance of our technology,” said Vivek Rajgarhia, President & GM of POET.  “Our customers can realize the immense value of POET’s Optical Interposer platform when they move to high-volume production and achieve a cost-effective solution with simplified transceiver design, fewer active alignments, and reduced OpEx and CapEx spending.”

POET to use Lumentum’s DMLs for 400G, 800G and 1.6T transceivers

POET Technologies confirmed that it will use high-speed directly modulated laser (DML) technology from Lumentum in its own transmit optical engines to enable high volume, low power, and cost-efficient 400G, 800G, and 1.6T pluggable transceivers for hyperscale data centers.POET expects to start sampling the 400G FR4 transmit optical engines with integrated drivers in the first half of 2023 and production by the second half of 2023. The 400G FR4 optical...

POET samples 200G FR4 optical engines

POET Technologies has begun sampling its 200G FR4 Transmit (TX) and Receive (RX) Optical Engines through Super Photonics, its joint venture with Sanan IC. Commercial production is expected by the end of the year.The Optical Engines are based on the POET Optical Interposer packaging platform. The 200G FR4 Transmit Optical Engine integrates four high-speed directly modulated lasers (DMLs) each operating at 50 Gbps with a low-loss AWG (Arrayed Waveguide...

IonQ acquires Entangled Networks

IonQ has acquired the operating assets of Entangled Networks, a Toronto-based start-up focused on enabling computation across multiple distributed quantum processors. The Entangled Networks team will join IonQ to launch IonQ Canada. Financial terms were not disclosed.

IonQ said the acquisition advances its  goal of developing quantum systems capable of supporting the quantum networks of the future. IonQ’s own quantum networking hardware is currently under development, and IonQ expects to demonstrate an early version of a quantum network between two quantum computers in 2023.

“We believe IonQ is a clear market leader, both commercially and in system performance, which is why our team is so excited to join forces,” said Aharon Brodutch, co-founder and CEO of Entangled Networks. “We are ready to work on amplifying IonQ’s quantum computing solutions to bring even more powerful applications to our customers.”

“Partnering with Entangled Networks furthers our goal of making IonQ the world’s best performing quantum computing company,” said Peter Chapman, IonQ’s President and CEO. “In acquiring the Entangled Networks assets, IonQ will benefit from not only some of the top experts in quantum architecture, but also from software tools that we intend to use to drive substantial speed-ups in our system performance. We are also excited about the opening of IonQ Canada. This expansion will help us better support the thriving quantum computing community in Canada and further our collaborations with IonQ partners and customers.”


Windstream lands $35 million in grants for fiber rollouts in Georgia

Kinetic by Windstream has been awarded $34.9 million in grants to build out fiber to more than 4,500 homes and businesses in Georgia.

Communities covered by this round of grants:

Clay County - 1,216 locations

Clinch County - 1,665 locations

Randolph County – 1,116 locations

Schley County – 512 locations

“We celebrate every time families get the benefits for fiber internet in their homes,” said Tony Thomas, president and CEO of Windstream. “We are grateful for the leadership of Gov. Kemp and Sens. Raphael Warnock and Jon Ossoff to forge public private partnerships that bring high speed internet to rural locations in Georgia that there is not a business case to serve otherwise.”


  • $34,900,000 / 4,509 = $7,740 average per location served

Teledyne LeCroy debuts 800G PAM4 protocol tester

 Teledyne LeCroy announced availability of the SierraNet M1288 Protocol Test Solution, which supports analysis of up to 8 lanes of IEEE 802.3ck based Ethernet traffic and 112GbE four-level Pulse Amplitude Modulation (PAM4).  The new M1288 tester enables troubleshooting from the physical layer through the application layer for up to 800 Gigabit Ethernet traffic.

The SierraNet M1288 Protocol Test Solution supports capture and analysis of links utilizing PAM4 or legacy Non-Return to Zero (NRZ) signal modulation techniques, at up to 8 lanes of Ethernet traffic, as well as clause 73 and 162 for auto negotiation and link training.  The SierraNet M1288 offers error injection and analysis for all layers of the Ethernet Open Systems Interconnection (OSI) model, which helps design and test engineers shorten product time-to-market by:

  • testing link negotiation to ensure it results in good signal quality
  • confirming upper layer protocol compliance
  • validating overall interoperability and performance
  • stressing product designs to find issues early in the test cycle

"In network environments, as signaling rates increase so does the susceptibility to errors.  To reduce the error rate, systems negotiate transmission parameters that should maximize signal quality at the receiver.  PAM4 systems designers are demanding link-layer analysis capabilities to ensure the negotiation among components is effective" said Nick Kriczky, Vice President of Network Solutions at Teledyne LeCroy.  "As the networking industry moves to 800Gb Ethernet, there is an growing need to fully validate Ethernet products. The SierraNet M1288 does this by identifying link-training issues and in validating protocol interoperability between major fabric components such as switches, network interface cards, servers, and Network Attached Storage (NAS)."  


Infineon sells its DC-DC converter business to Micross

Micross Components has agreed to purchase Infineon’s HiRel DC-DC converter business including its hybrid and custom board-based power products. Financial terms were not disclose

The HiRel DC-DC converter business is a leading provider of high reliability DC-DC power conversion solutions for the toughest environments, including outer space, and will operate under the Micross Hi-Rel Products business segment. These DC-DC converter products are complete power solutions, including main power converter, control circuits, filters and housing.

Infineon said the sale enables it to focus on core semiconductor developments for the high-reliability market.

“Infineon is pleased to have reached an agreement with Micross to provide a more strategic home for our HiRel DC-DC converter business,” said Bob LeFort, President of Infineon Technologies Americas. “We believe this sale is in the best interest of both companies; our customers, employees, and shareholders. This transaction enables Infineon to remain focused on the HiRel business areas that benefit from Infineon’s leading semiconductor technologies. We look forward to working with Micross to ensure a seamless transition for our customers and employees.”

Vince Buffa, Chairman and CEO of Micross, said, “We are pleased to have reached an agreement with Infineon on their HiRel DC-DC converter business and to have the opportunity to partner with their highly experienced team which further expands Micross’ design capabilities. We are excited about the significant proprietary power management IP that combined with their state of the art manufacturing capabilities and product portfolio leads the way for advancement of innovative solutions. We will be better positioned to produce an even wider range of high-quality products for our customers. Together, we plan to pursue a number of compelling opportunities to further realize our exciting growth prospects, all while upholding excellent quality and service to our customers.”