Fungible ships its disaggregated NVMe storage platform powered by DPUs

Fungible, a start-up based in Santa Clara, California, unveiled a disaggregated data storage platform powered by its own Fungible Data Processing Unit (DPU).

The new Fungible Storage Cluster delivers 15M IOPS in a 2RU form factor, scaling linearly to 300M IOPS in a single 40RU rack, and extending further to many racks. The company says its high-performance design improves $/IOPS by at least 3x compared to existing software-defined storage solutions by consolidating workloads and increasing utilization of storage media.

The Fungible Storage Cluster comprises a cluster of Fungible FS1600 storage target nodes connected over a standards-based IP network and the Fungible Composer software. The FS1600s implement the data path for storage while the Fungible Composer performs control and management functions. This clean separation of functions results in higher performance, better scalability and better reliability. Each FS1600 storage target node is powered by two Fungible F1 DPUs and packs 24 standard NVMe SSDs delivering an aggregate of 15M IOPS in a 2RU form factor.

Notably, the Fungible Storage Cluster has been validated with IBM Spectrum Scale, delivering more than 80M read IOPS/PB.

“Today, we demonstrate how the breakthrough value of the Fungible DPU is realized in a storage product,” said Pradeep Sindhu, CEO and Co-Founder of Fungible. “The Fungible Storage Cluster is not only the fastest storage platform in the market today, it is also the most cost-effective, reliable, secure and easy to use. This is truly a significant milestone on our journey to realize the vision of Fungible Data Centers — where compute and storage resources are hyperdisaggregated and then composed on-demand to dynamically serve application requirements.”

“Innovations in data center infrastructure have occurred largely within the silos of compute, storage and networking,” said Raj Yavatkar, CTO at Juniper Networks. “Fungible has broken down these silos delivering end-to-end value with Fungible DPU enabled servers interconnected by TrueFabric, a truly ground-breaking networking technology, and software composable for on-demand provisioning. This approach will serve as a blueprint for future data centers from core to edge.”

Fungible announces its DPU for scale-out data centers

Tuesday, August 18, 2020  Data Centers, Fungible, Silicon, SmartNICs  

Fungible, a start-up based in San Jose, California, unveiled its Fungible Data Processing Unit (Fungible DPU), a microprocessor optimized for data interchange and data-centric computation in scale-out architectures. Fungible describes its DPU as the "third socket" in data centers, complementing the CPU and GPU, and delivering significant gains in performance, footprint and cost efficiencies for next-generation, scale-out networking, storage, security,...

READ MORE

Fungible raises $200 million for Data Processing Units (DPUs)

Thursday, June 27, 2019    

Fungible, a start-up based in Santa Clara, California, closed $200 million in Series C financing for its efforts to create an entirely new category of programmable processor. The Fungible Data Processing Unit (DPU) aims to deliver an order of magnitude improvement in the execution of data-centric workloads. The company sees its DPU as a fundamental building block for next-generation data centers. Fungible has not yet announced its first products....

READ MORE

Video: Scaling-out Data Centers with the Fungible Data Processing Unit

Wednesday, August 19, 2020  Data Centers, DPU, Fungible, Silicon Valley, SmartNICs, Start-Ups, Video  

Fungible was founded in 2015 to revolutionize the performance, economics, reliability, and security of scale-out data centers. In this video, Pradeep Sindhu, Co-Founder and CEO of Fungible, shares observations about scale-out data centers and the key innovations of Fungible’s Data Processing Unit (Fungible DPU™) which has been positioned as the “third socket” in data centers, complementing the CPU and GPU. https://youtu.be/spJAOn_y21A...

READ MORE

Read More

AMD to acquire Xilinx for $35 billion

AMD agreed to acquire Xilinx in an all-stock transaction valued at $35 billion. The acquisition price represents approximately $143 per share of Xilinx common stock.

The deal significantly expands AMD’s product portfolio, which will now cover CPUs and GPUs, with Xilinx's FPGAs, Adaptive SoCs and software expertise. The combined company's addressable market will now include industry growth segments from the data center to gaming, PCs, communications, automotive, industrial, aerospace and defense.

“Our acquisition of Xilinx marks the next leg in our journey to establish AMD as the industry’s high performance computing leader and partner of choice for the largest and most important technology companies in the world,” AMD President and CEO Dr. Lisa Su said. 

“We are excited to join the AMD family. Our shared cultures of innovation, excellence and collaboration make this an ideal combination. Together, we will lead the new era of high performance and adaptive computing,” said Victor Peng, Xilinx president and CEO. “Our leading FPGAs, Adaptive SoCs, accelerator and SmartNIC solutions enable innovation from the cloud, to the edge and end devices. We empower our customers to deploy differentiated platforms to market faster, and with optimal efficiency and performance. Joining together with AMD will help accelerate growth in our data center business and enable us to pursue a broader customer base across more markets.”

Some highlights of the combined company

• Dr. Lisa Su will lead the combined company as CEO. Xilinx President and CEO 
• Victor Peng, will join AMD as president responsible for the Xilinx business and strategic growth initiatives
• 13,000 engineers
• $2.7 billion of annual1 R&D investment
• Post-closing, current AMD stockholders will own approximately 74 percent of the combined company Immediately accretive to AMD margins, cash flow and EPS 
• Combined revenue of $11.6B 

https://www.amd.com/en/corporate/xilinx-acquisition?utm_campaign=xilinx-acquisition&utm_medium=redirect&utm_source=301

Read More

Acacia and Inphi demo interoperability of 400ZR over 120 km

Acacia Communications and Inphi have demonstrated error free links in 400ZR mode between Inphi’s COLORZ II QSFP-DD and Acacia’s 400ZR QSFP-DD module in Arista switches over a 120 km amplified link using 75GHz channel spacing. 

“Hyperscale network operators are planning to utilize interoperable 400ZR solutions to support growing bandwidth requirements between data centers,” said Josef Berger, AVP of Marketing, Optical Interconnect at Inphi. “This testing provides an exciting validation of the 400ZR ecosystem designed to meet the need for high-performance, low power coherent pluggable solutions that support cost-effective DWDM architectures for DCI.”

“The industry has been anticipating the availability of interoperable 400ZR solutions to meet the growing demand for DCI bandwidth, particularly for network operators evolving their data center architectures to 400G Ethernet with optical connections between switches,” said Tom Williams, Vice President of Marketing at Acacia. “These solutions provide data center operators with greater flexibility in the components and suppliers they use to build out their networks.”

NeoPhotonics and Inphi show 400ZR interoperability

Tuesday, July 28, 2020  400ZR, Inphi, Neophotonics  

Inphi and NeoPhotonics have completed the first interoperability demonstration of OIF 400ZR Implementation Agreement compliant coherent transceivers, operating successfully across the C-Band over 120km of optical fiber. Transceiver pairs consisting of Inphi's COLORZ II QSFP-DD with its Canopus 7nm Coherent DSP and NeoPhotonics 400ZR ClearLight OSFP were successfully linked. Both 400ZR coherent optics transceivers carried error-free traffic over...

READ MORE

OIF publishes 400ZR implementation agreeement

Wednesday, April 29, 2020  400ZR, OIF  

OIF published the Implementation Agreement (IA) for a low-cost, 400ZR coherent optical interface.

OIF launched the 400ZR project in response to requests from large-scale data center operators and their suppliers for an interoperable coherent interface that transports 400 Gigabit Ethernet over longer distances. Traditional network operators also became interested in 400ZR for their metro needs. Based on their different requirements, OIF developed specs and tweaked the channel requirements so the IA would benefit both data center and network operators. While developing the IA, OIF collaborated closely with other standards bodies.

The 400ZR IA addresses two applications:

• Amplified, point-to-point DWDM links with reaches of 120 km or less
• Unamplified, single wavelength links with a loss budget of 11dB

The IA aims to enable interoperable, cost-effective, 400Gbps implementations based on single-carrier coherent DP-16QAM modulation, low-power DSPs supporting absolute (Non-Differential) phase encoding/decoding, and a Concatenated FEC (C-FEC) with a post-FEC error floor <1 .0e-15.="" 400gbase-r="" 400zr="" a="" as="" operates="" p="" phy.="">

No restriction on the physical form factor is implied by the IA (QSFP-DD, OSFP, COBO, CFP2, CFP8), but the specifications target a pluggable DCO architecture with port densities equivalent to grey client optics.

Read More

ESnet upgrades optical backbone with Infinera

The U.S. Department of Energy (DOE)’s Energy Sciences Network (ESnet) has selected Infinera to build the optical substrate for its next-generation science network, ESnet6, interconnecting the DOE’s national laboratory system and experimental facilities with research and commercial networks around the globe. ESnet connects all of the DOE’s geographically distributed laboratories, experimental facilities, and computing centers across a dedicated fiber optic backbone.

Infinera confirmed that the ESnet6 optical network is powered by the its GX Series Compact Modular Platform and FlexILS Open Optical Line System. ESnet’s open optical networking approach combined with Infinera’s GX and FlexILS with coherent 600G technology enables the network to seamlessly upgrade to 800G capability once available. Partnering with ESnet, Infinera quickly and safely deployed new equipment, performed testing, and turned up services over 15,000 miles of fiber during the pandemic.

“ESnet6 represents a transformational change in the capacity, resiliency, and flexibility and brings tangible benefits to the DOE’s science mission,” said Kate Mace, ESnet6 Project Director. “Open optical networking technology plays a key role in ESnet’s ability to meet the ongoing challenges of data traffic growth while supporting the high-speed and real-time collaboration capabilities that are critical to our nation’s science programs.”

“ESnet was pleased to see Infinera’s team make such fast work of this large installation task during a pandemic. This high-speed connectivity provides the foundation to meet our mission of accelerating scientific discovery,” said Inder Monga, Executive Director of ESnet and Division Director of Scientific Networking at Lawrence Berkeley National Laboratory. “ESnet enables tens of thousands of scientists to access data portals, transfer vast research data streams, and tap into remote scientific instruments and sources — all in real time.”

“Infinera is delighted to partner with ESnet to deploy a high-capacity open optical network connecting all the national laboratory locations in the U.S. with high-performance computing locations,” said Nick Walden, Senior Vice President, Sales at Infinera. “This collaboration underscores the value of our relationship and ability to deliver advanced networking solutions quickly and efficiently to meet the needs of our customers even during a pandemic.”

ESnet6 makes progress toward 400G upgrade

Monday, August 17, 2020  400G, Esnet  

The Energy Sciences Network (ESnet) is making great progress with the rollout of ESnet6, its next-generation network dedicated to serving the Department of Energy (DOE) national lab complex and overseas collaborators. ESnet6, which is expected to be complete in 2023, will see the deployment of next gen optical, core and service edge equipment on ESnet’s dedicated fiber optic cable backbone. “We’ve had some delays, but our first priority is making...

READ MORE

Read More

Ericsson's Cloud RAN is coming in Q4 2021

Ericsson involved a cloud-native software solution for handling compute functionality in the RAN. 

Cloud RAN by Ericsson, which will be released in stages, will complement high-performing purpose-built baseband offerings in the Ericsson Radio System portfolio. The first stage will be available in the fourth quarter of 2021 and will include Ericsson’s new Cloud RAN application software – Cloud RAN DU and Cloud RAN CU. It also includes new Radio Gateways, enabling a full utilization of the installed base of remote radios, making them fully compatible with Cloud RAN. These products set the foundation for future mid-band rollouts. Ericsson Cloud RAN is fully compatible with the Ericsson Radio System portfolio, and supports Ericsson Spectrum Sharing and 5G standalone and non-standalone.

Ericsson said its cloud-native software solution will deliver network capabilities for both large-scale and centralized 5G deployments, including for new 5G use cases for indoor, industry, enterprise, stadiums, etc.

Fredrik Jejdling, Executive Vice President and Head of Business Area Networks, Ericsson, says: “5G is a platform for open innovation. By empowering a larger ecosystem of developers and industries, we can co-create and bring new cloud innovations to the 5G space. With Cloud RAN by Ericsson, we will help our customers evolve their networks with future-proof technology while maximizing their network investments today.”

Read More

Juniper reports better than expected demand during Q3

Juniper Networks reported net revenues of $1,138.2 million, up slightly year-over-year, and an increase of 5% sequentially. GAAP operating margin was 11.0%, a decrease from 12.2% in the third quarter of 2019, and an increase from 8.3% in the second quarter of 2020.  increase of 24% sequentially, resulting in non-GAAP diluted earnings per share of $0.43.

“We experienced better than expected demand during the September quarter, as our teams continued to execute extremely well, despite the various challenges created by the pandemic,” said Juniper’s CEO, Rami Rahim. “I am encouraged by the business momentum we are seeing, particularly in our enterprise and service provider verticals. Given the strength of our current portfolio and the investments we have made in our go-to-market organization, I am confident not only in our Q4 outlook, but our ability to deliver organic growth in 2021.”

“We delivered better than expected Q3 sales and achieved our non-GAAP EPS forecast,” said Juniper’s CFO, Ken Miller. “We are entering Q4 with healthy backlog and making progress against COVID-19 related supply chain challenges. While we will continue to effectively manage costs and remain committed to improving profitability, we are making the needed investments to capitalize on the opportunities ahead and expect to deliver sustained growth and margin expansion over time.”

Read More

Akamai acquires Asavie for software-defined global access platform

Akamai Technologies has acquired Asavie, a privately-held company based in Dublin, Ireland, that offers a global platform for managing the security, performance and access policies for mobile and Internet-connected devices. Financial terms were not disclosed.

Asavie automates and manages private networks for businesses at scale, and its solutions are sold by top global mobile network operators. Its platform automates the creation of self-serve, private, network-based services that secure access from mobile and Internet-connected devices to applications and data without requiring installation and management of client software.

Asavie will now become part of Akamai’s Security and Personalization Services product line sold to carrier partners that embed the solution within the technology bundle sold to their subscribers.

“We believe the addition of Asavie will help Akamai’s carrier partners address enterprise and mid-market customer demand for IoT and mobile device security and management services,” said Dr. Tom Leighton, chief executive officer and co-founder, Akamai Technologies. “What’s notable about the Asavie solution is that, as more IoT devices connect over cellular and 5G, it has been shown to be very easy to scale and protect them.”

“We expect COVID-19 to have a lasting impact on how employees work and how businesses operate. Network security needs will be required to evolve in a 5G era where the office needs to go wherever employees happen to work,” said Ralph Shaw, Asavie chief executive officer. “The Asavie suite of software-defined solutions is designed to enable enterprises to provide access to business resources while continuously protecting the business in a world of evolving cyber threats targeting mobile devices, users and applications.”

Read More

A10 reports revenue of $56.6 million, up 7.1% yoy

A10 Networks reported Q3 revenue of $56.6 million, up 7.1% year-over-year. GAAP gross margin was 76.8%. The company achieved record GAAP net income of $6.5 million, or $0.08 per share, compared with GAAP net income of $173,000, or $0.00 per share in the third quarter of 2019.

 

“We have successfully positioned A10 for consistent organic growth and increased profitability amidst a challenging economic environment,” said Dhrupad Trivedi, President and Chief Executive Officer of A10 Networks. “Over the past two years, we have streamlined our fixed cost structure by approximately 25% and realigned our leaner sales organization on the highest quality opportunities. In the third quarter, this focus resulted in better than 7% organic growth, more than $6 million year-over-year improvement in net income and an $8.5 million improvement in Adjusted EBITDA. With a strong balance sheet, including more than $159 million of cash and cash equivalents, and no debt, we are on a solid footing and our improved financial profile enables us to prudently fund a significant stock buyback.”

Read More