Monday, March 19, 2018

P4 programming language gets folded into the Linux Foundation

The P4 Language Consortium (P4.org), creator of the P4 programming language,  will become a project of the Open Networking Foundation (ONF) and become part of the Linux Foundation portfolio.

P4 was designed to be target-independent (i.e. a program written in P4 could be compiled, without modification, to run on a variety of targets, such as ASICs, FPGAs, CPUs, NPUs, and GPUs), and protocol-independent (i.e. a P4 program can describe existing standard protocols, or be used to specify innovative, new, customized forwarding behaviors). P4 can be used for both programmable and fixed-function devices alike. For example, it is used to accurately capture the switch pipeline behavior under the Switch Abstraction Interface (SAI) APIs, used by the SONiC open-source switch OS. P4 is also used by the ONF Stratum project to describe forwarding behavior across a variety of fixed and programmable devices.

“A group of us decided on May 19, 2013 that we needed an industry-standard, open language for specifying forwarding behaviors,” said Nick McKeown, Professor of Computer Science at Stanford University, and P4 Board Member. “We created a language that students are studying in our universities, and using to prototype and publish new research ideas at the best networking conferences. Industry has adopted P4 to program devices and capture existing behaviors. In the future, we hope that Internet RFCs and IEEE Standards will include a clear, unambiguous P4 specification too, paving the way for interoperability by design.”

“SDN has transformed the networking industry and P4 takes SDN to the next level by bringing programmability to the forwarding plane,” said Guru Parulkar, Executive Director at Open Networking Foundation. “We are excited to have P4.org join ONF and are looking forward to seeing our synergy bring incredible benefits to the P4 and the larger SDN community.”

“Linux Foundation is thrilled to welcome the P4 community,” said Jim Zemlin, Executive Director at Linux Foundation. “Networking is a major focus at the foundation and the addition of the thriving P4 community combined with Linux Foundation Networking Projects in similar domains will drive innovation in networking to the next level.”

Verizon tests Cisco’s Hybrid Information-Centric Networking

Verizon completed a series of tests on Cisco's Hybrid Information-Centric Networking (ICN), which is described as an innovative approach to content-aware service offerings based on “named data” rather than location identifiers such as IP addresses.

Specifically, Verizon successfully demonstrated Cisco’s open-source ICN software and validated its benefits over standard TCP/IP solutions for optimized mobile video delivery in a lab at the Verizon Innovation Center in Waltham MA. The demonstrated benefits include key features of the ICN communication model – including dynamic adaptive streaming solutions and dynamic load balancing of media – which will lead to a better user experience. In the network, forwarding/caching strategies maximize traffic localization and bandwidth savings in backhaul/core via enhanced multicast.

“The Hybrid-ICN solution delivers all the benefits of ICN communication with minimal existing IP infrastructure upgrades required,” said Srini Kalapala, vice president, Technology Architecture and Strategy at Verizon. “By demonstrating the benefits of a virtualized Hybrid-ICN network at scale, we showcased how the technology can simplify the way users access content in a mobile environment and lead to a better user experience. We’re pleased with the results of our collaboration with Cisco and with the promise of the technology.”

“Cisco’s Hybrid-ICN solution provides secure content-intelligent transport for network service providers,” said Dave Ward, senior vice president, CTO of Engineering and Chief Architect at Cisco. “Through our co-development with Verizon, we found that H-ICN empowers the network edge with low latency caching and computing capabilities for the support of new revenue-generating applications such as enterprise multi-radio access, augmented and virtual reality, and IoT for 5G.”

Rambus and IBM target future hybrid memory systems

Rambus and IBM announced a research pact to develop hybrid memory systems for data centers.

The companies aim to optimize the use of DRAM and emerging memories to create a high-capacity memory subsystem that "delivers comparable performance to DRAM alone."

As part of the collaboration, Rambus will develop a flexible prototype hybrid memory platform using the OpenCAPI interface to demonstrate the performance of multiple memory types in real-world server applications. Specifically, Rambus will leverage IBM’s POWER9 processor and its OpenCAPI high-performance interface to build a Hybrid Memory and development subsystem prototype. To move forward on this project, Rambus announced it has joined the OpenCAPI Consortium, an open development community based on Coherent Accelerator Processor Interface technology, and OpenPOWER Foundation, an open development community based on the IBM Power Architecture.

“The exploding volume of data and rapidly evolving workloads for Big Data applications are placing tremendous pressure on data center memory systems for increased performance and capacity,” said Laura Stark, senior vice president and general manager of the Emerging Solutions Division at Rambus. “This project with IBM demonstrates our ongoing collaboration with the industry to accelerate the development and adoption of advanced memory solutions.”

“IBM is excited to collaborate with Rambus regarding advanced memory technologies on the OpenCAPI interface of POWER9 systems,” said Steve Fields, IBM fellow and chief engineer of Power Systems. “IBM believes in transforming the architecture of server memory to allow open innovation and to fully exploit the diversity of memory technologies that will emerge in the coming years. This project leverages the new architecture to combine the best attributes of multiple types of media to achieve new levels of system cost/performance for memory-intensive cloud deployments and AI applications.”

OE Solutions debuts 25G Transceivers for 5G fronthaul

OE Solutions, a global supplier of optical transceivers based in Gwangju, South Korea with R&D centres in the USA, the Netherlands as well as offices worldwide, introduced three new 25Gbps SFP28 transceiver products at OFC designed for emerging 5G wireless fronthaul architectures.

The new 25Gbps transceivers joining OE Solutions’ extensive list of IT-rated transceivers for wireless applications are:

  • 25Gbps SFP28 1270nm/1310nm BIDI IT for distances up to 30km
  • 25Gbps SFP28 1310nm Duplex IT for distances up to 30km
  • 25Gbps SFP28 CWDM IT for distances up to 10km

Sampling is expected in Q2.

“OE Solutions has played a key role delivering optical transceivers for past generation wireless
networks and we are excited to support the global rollout of also the next generation, 5G, which will
revolutionize broadband delivery to end users and kick off the IOT era,” said Per Hansen, VP
Marketing & Sales of OE Solutions. “We are pleased to be teaming with leading equipment providers
to address the ever-increasing need for bandwidth in the wireless infrastructure while meeting their
stringent requirements to physical design and operating conditions.”

RagingWire opens facility in Ashburn's Data Center Alley

RagingWire Data Centers, which is a subsidiary of NTT Communications, inaugurated its new Ashburn VA3 Data Center, a state-of-the-art facility with 245,000 square feet of space and 16 megawatts of critical power, located on RagingWire’s new Ashburn Data Center Campus.

The VA3 Data Center is RagingWire’s third data center in Ashburn, and the first building on RagingWire’s new Ashburn Data Center Campus, a 78-acre parcel of land that is planned to contain seven data centers with a total of 108 megawatts of critical load and over 1 million square feet of space on a highly secured location.

RagignWire has already started construction and pre-leasing on VA4, which is expected to come online next year with another 16 megawatts of critical power and approximately 200,000 square feet of data center space.

“Congratulations to RagingWire for opening the new VA3 Data Center and Ashburn Data Center Campus,” said Masaaki Moribayashi, Senior Vice President of Cloud Services at NTT Communications and Member of the Board for both NTT Communications and RagingWire. “Through your innovation and execution, RagingWire has helped NTT Communications become one of the largest and most successful data center companies in the world.”

Dr. Risa Lavizzo-Mourey elected to Intel’s board of directors

Dr. Risa Lavizzo-Mourey was elected to Intel’s board of directors. Dr. Lavizzo-Mourey has served as the Robert Wood Johnson Foundation PIK Professor of Population Health and Health Equity at the University of Pennsylvania since January 2018. From 2003 to 2017, she was the president and chief executive officer of the Robert Wood Johnson Foundation, the largest U.S. philanthropy organization dedicated to health. She is a member of the National Academy of Medicine, the board of regents of the Smithsonian Institution, and the board of fellows of Harvard Medical School. Dr. Lavizzo-Mourey holds an MBA from the University of Pennsylvania and an M.D. from Harvard Medical School.

Intel has now added five independent directors to its board since the beginning of 2016.

Intel's board also voted unanimously to extend Andy Bryant’s term as Intel chairman in order to ensure board continuity and a smooth integration for new directors. Bryant became Intel chairman in May 2012 and will stand for re-election at the company’s 2018 annual stockholders’ meeting. If elected, he will continue to serve as chairman until the conclusion of the company’s 2019 annual stockholders’ meeting.

Etisalat selects NEC/Netcracker's NaaS for vCPE

Etisalat has selected NEC/Netcracker's Network-as-a-Service (NaaS) to deploy a virtual customer premises equipment (vCPE) solution for enterprises.

Specifically, Etisalat is using NEC/Netcracker's full-stack Network-as-a-Service solution comprised with Self-Service Portals, Service Orchestration and MANO offerings. The initial service includes security virtual network functions selected from NEC/Netcracker's Ecosystem 2.0 marketplace.

The deployment is part of the service provider's larger virtualization initiative and builds on its recent deployment of the NaaS platform for residential vCPE.

"Using virtualization to drive more sophisticated functionality to our business customers will play a major role in enabling their evolution into digital enterprises, allowing them to open new revenue streams by offering more diverse services," said Esmaeel Alhammadi, Senior Vice President of Network Development at Etisalat. "We selected NEC/Netcracker's NaaS solution for our large-scale virtualization program because of its ability to support both residential and enterprise transformation."

Toshiba delivers data center SSDs based on 64-layer 3-bit-per-cell flash

Toshiba announced its latest line-up of NVM Express (NVMe) and SATA data center solid-state drives (SSDs) based on its 64-layer 3-bit-per-cell TLC (triple-level cell) BiCS FLASH 3D flash memory. The drives feature controllers designed and developed in-house.

The two PCIe® NVMe SSDs are designed to accommodate multiple data center workload profiles, with capacities ranging from 960GB to 7.68TB in a 2.5-inch form factor. These drives deliver up to 500,000 IOPS random read, up to 35,000 IOPS random write, up to 3,140MB/s sequential read, and up to 1,980MB/s sequential write performance within a 9-14W power envelope.

The XD5 Series is a small-footprint M.2 22110 form factor SSD that supports capacities up to 3.84TB and delivers up to 2,600 MB/s sequential read and up to 890MB/s sequential write performance in a 7W power envelope. All three series are optimized for low latency and performance consistency in read-intensive workloads, for Open Compute Project (OCP) and hyper-scale/cloud applications.

The HK6-DC Series is a 6Gbits/s SATA SSD and is available in 960GB, 1.92TB and 3.84TB capacities. It delivers a performance of up to 85,000IOPS random read and 16,000IOPS random write, and up to 550 MB/s sequential read and 500MB/s sequential write.

Enea acquires Openwave Mobility

Enea AB completed its acquisition of Openwave Mobility, a company offering a scalable NFV platform for mobile operators. The acquisition price was approximately US$90 million.

Openwave Mobility is headquartered in California and generated preliminary adjusted revenues of approximately US$27 million in 2017 and an EBIT of US$ 3 million.

ENEA said the acquisition expands its portfolio and addressable market.

See also