Marvell Blog

Featuring technology ideas and solutions worth sharing

Marvell

Latest Articles

March 8th, 2017

NVMe-based Work Fabrics Blow Through Legacy Rotational Media Limitations in the Data Center: Speed and Cost Benefits of NVMe SSD Shared Storage Now in Its Second Generation

By Nick Ilyadis, VP of Portfolio Technology, Marvell

Marvell Debuts 88SS1092 Second-Gen NVM Express SSD Controller at OCP Summit  

88SS1092_C-sized
SSDs in the Data Center: NVMe and Where We’ve Been
When solid-state drives (SSDs) were first introduced into the data center, the infrastructure mandated they work within the confines of the then current bus technology, such as Serial ATA (SATA) and Serial Attached SCSI (SAS), developed for rotational media. Even the fastest hard disk drives (HDDs) of course, couldn’t keep up with an SSD, but neither could their current pipelines, which created a bottleneck that hampered the full exploitation of SSD technology. PCI Express (PCIe) offered a suitable high-bandwidth bus technology already in place as a transport layer for networking, graphics and other add-in cards. It became the next viable option, but the PCIe interface still relied on old HDD-based SCSI or SATA protocols. Thus the NVM Express (NVMe) industry working group was formed to create a standardized set of protocols and commands developed for the PCIe bus, in order to allow multiple paths that could take advantage of the full benefits of SSDs in the data center. The NVMe specification was designed from the ground up to deliver high-bandwidth and low-latency storage access for current and future NVM technologies.

The NVMe interface provides an optimized command issue and completion path. It includes support for parallel operation by supporting up to 64K commands within a single I/O queue to the device. Additionally, support was added for many Enterprise capabilities like end-to-end data protection (compatible with T10 DIF and DIX standards), enhanced error reporting and virtualization. All-in-all, NVMe is a scalable host controller interface designed to address the needs of Enterprise, Data Center and Client systems that utilize PCIe-based solid-state drives to help maximize SSD performance.

SSD Network Fabrics
New NVMe controllers from companies like Marvell allowed the data center to share storage data to further maximize cost and performance efficiencies. By creating SSD network fabrics, a cluster of SSDs can be formed to pool storage from individual servers and maximize overall data center storage. In addition, by creating a common enclosure for additional servers, data can be transported for shared data access. These new compute models therefore allow data centers to not only fully optimize the fast performance of SSDs, but more economically deploy those SSDs throughout the data center, lowering overall cost and streamlining maintenance. Instead of adding additional SSDs to individual servers, under-deployed SSDs can be tapped into and redeployed for use by over-allocated servers.

Here’s a simple example of how these network fabrics work: If a system has ten servers, each with an SSD sitting on the PCIe bus, an SSD cluster can be formed from each of the SSDs to provide not only a means for additional storage, but also a method to pool and share data access. If, let’s say one server is only 10 percent utilized, while another is over allocated, that SSD cluster will allow more storage for the over-allocated server without having to add SSDs to the individual servers. When the example is multiplied by hundreds of servers, you can see that cost, maintenance and performance efficiencies skyrocket.

Marvell helped pave the way for these new types of compute models for the data center when it introduced its first NVMe SSD controller. That product supported up to four lanes of PCIe 3.0, and was suitable for full 4GB/s or 2GB/s end points depending on host system customization. It enabled unparalleled IOPS performance using the NVMe advanced Command Handling. In order to fully utilize the high-speed PCIe connection, Marvell’s innovative NVMe design facilitated PCIe link data flows by deploying massive hardware automation. This helped to alleviate the legacy host control bottlenecks and unleash the true Flash performance.

Second-Generation NVMe Controllers are Here!
This first product has now been followed up with the introduction of the Marvell 88SS1092 second-generation NVMe SSD controller, which has passed through in-house SSD validation and third-party OS/platform compatibility testing. Therefore, the Marvell® 88SS1092 is ready to go to boost next-generation Storage and Datacenter systems, and is being debuted at the Open Computing Project (OCP) Summit March 8 and 9 in San Jose, Calif.

The Marvell 88SS1092 is Marvell’s second-generation NVMe SSD controller capable of PCIe 3.0 X 4 end points to provide full 4GB/s interface to the host and help remove performance bottlenecks. While the new controller advances a solid-state storage system to a more fully flash-optimized architecture for greater performance, it also includes Marvell’s third-generation error-correcting, low-density parity check (LDPC) technology for the additional reliability enhancement, endurance boost and TLC NAND device support on top of MLC NAND.

Today, the speed and cost benefits of NVMe SSD shared storage is not only a reality, but is now in its second generation. The network paradigm has been shifted. By using the NVMe protocol, designed from the ground up to exploit the full performance of SSDs, new compute models are being created without the limitations of legacy rotational media. SSD performance can be maximized, while SSD clusters and new network fabrics enable pooled storage and shared data access. The hard work of the NVMe working group is becoming a reality for today’s data center, as new controllers and technology help optimize performance and cost efficiencies of SSD technology.

Marvell 88SS1092 Second-Generation NVMe SSD Controller
New process and advanced NAND controller design includes:
88SS1092-chart-sized
 

March 1st, 2017

Marvell at the Forefront of Connecting the Cars of Tomorrow, Today

By Alex Tan, Director, Automotive Solutions Group

When you sit in a car today, the focal point of the interior is likely an infotainment system. From displaying vehicle diagnostics to parking assistance to enabling multimedia streaming and additional controls such as phone calls, navigation, etc., the infotainment system has become the touchpoint of the in-vehicle connectivity experience.

In order for drivers to take full advantage of these advanced features, internal vehicle data networks need to provide high bandwidth and seamless connectivity so these technologies can effectively communicate with each other. However, with multiple in-vehicle systems using different interfaces and connectivity technologies, how can we bridge the communication to get them to speak the same language?

The IEEE’s Ethernet standards act as the connectivity backbone to seamlessly link the different domains of the car such as infotainment and Advanced Driver Assistance Systems (ADAS). Marvell is proud to have played an instrumental role in the development of the IEEE 802.3bp 1000BASE-T1 PHY standard which enables data between in-vehicle systems to be distributed over a flexible, low cost and high bandwidth network. In October 2015, Marvell introduced the 88Q2112 automotive Ethernet physical layer (PHY) transceiver, the industry’s first 1000BASE-T1 automotive Ethernet PHY transceiver based on the IEEE’s draft 1000BASE-T1 spec. Leveraging our advanced wireless and Ethernet technology solutions, the 1000BASE-T1 solution supports uncompressed HD video, ideal for distributing camera and sensor data in ADAS applications. In the infotainment space, gigabit Ethernet over a single unshielded twisted pair copper cable is a logical solution for transporting audio, video and voice data at a higher data rate and resolution. Marvell’s 88Q2112 PHY transceiver enables automakers to use one Ethernet switch to connect the multiple advanced features of tomorrow’s cars. Furthering our commitment to automotive innovation, in April 2016 we opened the Marvell Automotive Center of Excellence (ACE), a first-of-its-kind automotive networking technology development center. Located in Ettlingen, Germany, ACE aims to expand development and education efforts to advance the architecture of future connected, intelligent cars.

We showcased Marvell’s advanced auto connectivity solutions at the 2016 IEEE-SA Ethernet & IP @ Automotive Technology Day (E&IP@ATD) in Paris this past September, demonstrating how our technology supports multiple HD video streams with up to 4K resolution. Covering the exciting activities at E&IP@ATD, Tadashi Nezu of Nikkei wrote about our automotive connectivity leadership, noting that Marvell is rapidly coming to the forefront of the market. Nezu also lauded the Company for its early Ethernet development efforts, noting how Marvell quickly developed a solution compliant to the draft IEEE 802.3bp 1000BASE-T1 standard, before the specifications were even finalized.

Earlier this month, we presented our solutions at the heart of the world’s automotive development at the 3rd annual Automotive Ethernet Congress in Munich. Manfred Kunz, head of development at the ACE, spoke about automotive Ethernet security, while Christopher Mash, senior manager of automotive system architecture and field applications, co-presented with Bosch and Continental who shared their experience with the new 1000BASE-T1 technology. We showcased several automotive Ethernet solutions across nine customer booths, including the world’s first 1000Base-T1 Automotive Ethernet system, industry-leading intelligent security on the new 88Q5050 switch and a new platform demonstrating Marvell’s 10Gb capability for automotive.

The event was a success, drawing over 700 attendees, as well as speakers and exhibitors from over 20 countries.

Automotive Ethernet Congress, Munich, Germany

Automotive Ethernet Congress, Munich, Germany

As automotive technological developments continue to advance rapidly and data continues to play a fundamental role in advancing the future of connected cars, we look forward to continue innovating and collaborating with our auto partners to further accelerate car connectivity.

February 3rd, 2017

Super Bowl LI Scores a Touchdown on Tech

By Sander Arts, Interim VP of Marketing

With Super Bowl Sunday just around the corner, we’re reminded of last year’s game that took place just a few blocks away from Marvell’s campus in the heart of Silicon Valley. Taking inspiration from the locale, Super Bowl 50 was undoubtedly the most tech-savvy event to date. The Denver Broncos and Carolina Panthers played at Levi’s Stadium in Santa Clara, one of the most technologically advanced venues in the country and the first stadium to feature 40 gigabits per second of internet capacity. TechRepublic reported that there were 10.15 terabytes of data transferred across the network during the game, with cloud storage, social networking and web surfing accounting for the top three applications transferring data on Levi’s Wi-Fi network.  What was even more impressive was Levi Stadium’s mobile app which enabled attendees to order food and beverages in advance, find the shortest bathroom and concession lines and access game highlights in high-definition.

But where does the game go from here? With sports fans being more engaged and connected than ever, how can technology continue enhancing the fan experience for Super Bowl 51?

NRG Stadium, Houston, TX Source: Wikipedia

NRG Stadium, Houston, TX
Source: Wikipedia

This year, the mobile app worth cheering for is Fox Sports Go. For fans unable to watch the New England Patriots and Atlanta Falcons face off live in Houston on Sunday, they can still get up close to the game in virtual reality. Fox Sports will stream the game live on its app which can be viewed in VR using a Samsung Gear headset or Google Cardboard. The app’s “virtual suite” will offer viewers various viewpoints of the game – even those without a VR headset can experience the game in 360-degree video.

However, we can’t forget that for many viewers, the Super Bowl commercials are just as entertaining as the game itself. With the price of a 30-second ad reaching nearly $5 million this year, brands are, more than ever, using this opportunity to release some of the funniest, strangest and powerful ads to meet viewers’ high expectations. This Sunday, we’re especially looking forward to the technology commercials, such as the Kia Niro and Ford “Go Further” ads, which will highlight advancements in connected car technology. As consumers become increasingly interested in automotive technology, we can expect to see more Super Bowl commercials highlighting data and connectivity both this year and in the years to come.

Last year’s record-breaking data usage is just an example of how important Wi-Fi and connectivity have become in our fast-paced world, especially at events such as the Super Bowl where instant streaming and sharing play an essential role in the viewers’ experience. At last year’s game, 15.9 terabytes of data were transferred via Distributed Antenna System, which was 2.5 times the amount compared to the Super Bowl the year before. Will the record to be broken again this Sunday?

As we tune in to the biggest TV event of the year, we look forward to seeing how technology will up the ante at Super Bowl 51, from the amount of data being transferred to fans sharing their experience on social media, it’s sure to be a touchdown performance!

You can follow Sander Arts on Twitter @Sander1Arts

January 27th, 2017

Flashback Friday: How Santa Clara Valley Traded Fruit Trees for Silicon

By Sander Arts, Interim VP of Marketing

Before Silicon Valley became synonymous with high-tech and innovation, it was known as the “Valley of Heart’s Delight.” This expansive piece of land boasting acres of orchards just south of San Francisco would grow to become the future home to some of the world’s most innovative tech companies.

FlashbackFriday1

Looking back at the area’s history, it’s no surprise that it would someday inspire a culture where groundbreaking tech comes to life in a garage, college dorm room or even at a kitchen table. The story of Silicon Valley itself begins in a garage, with two Stanford grads William Hewlett and David Packard, who would later found Hewlett-Packard in 1939. Throughout the next decade, entrepreneurs and scientists would come to the Santa Clara Valley to explore radio, military and electronic technology, laying the groundwork for the future hotbed of innovation.

Birthplace

By 1953 notable tech companies began to officially establish ground in Santa Clara Valley with property in Stanford Industrial Park, closely followed by the area’s first semi company in 1956. With the Space Race in full force throughout the 1960s, the country experienced a heightened focus on the need for advanced silicon technologies and the valley began to take shape as the country’s hub for advanced high tech. Due to the sheer number of silicon companies in the park and growing attention on the semi industry, the area was officially coined “Silicon Valley” in an Electronic News series published in 1971.

Over the next 30 years, some of the world’s most groundbreaking technology companies would make their way to Silicon Valley. Marvell officially became a part of the phenomenon in 1995, right in the middle of the dot.com bubble. Since then, we’ve seen firsthand how the tech scene has grown exponentially through innovation and entrepreneurship. The startup mentality that originated in 1939 and which continues to boom in the 21st century inspires us to continue improving, innovating and challenging technology of today. At Marvell, we are confident in our vision for the future of silicon, data and cloud technologies and look forward to being a part of the next generation of great entrepreneurs, thinkers and tinkerers in Silicon Valley.

Marvell-campus

January 20th, 2017

The New Scaling Paradigm: Ethernet Port Extenders

By Michael Zimmerman, Vice President and General Manager, CSIBU

Over the last three decades, Ethernet has grown to be the unifying communications infrastructure across all industries. More than 3M Ethernet ports are deployed daily across all speeds, from FE to 100GbE. In enterprise and carrier deployments, a combination of pizza boxes — utilizing stackable and high-density chassis-based switches — are used to address the growth in Ethernet. However, over the past several years, the Ethernet landscape has continued to change. With Ethernet deployment and innovation happening fastest in the data center, Ethernet switch architecture built for the data center dominates and forces adoption by the enterprise and carrier markets. This new paradigm shift has made architecture decisions in the data center critical and influential across all Ethernet markets. However, the data center deployment model is different.
 

How Data Centers are Different

Ethernet-ExtendersEthernet port deployment in data centers tends to be uniform, the same Ethernet port speed whether 10GbE, 25GbE or 50GbE is deployed to every server through a top of rack (ToR) switch, and then aggregated in multiple CLOS layers. The ultimate goal is to pack as many Ethernet ports at the highest commercially available speed onto the Ethernet switch, and make it the most economical and power efficient. The end point connected to the ToR switch is the server NIC which is typically the highest available speed in the market (currently 10/25GbE moving to 25/50GbE). Today, 128 ports of 25GbE switches are in deployment, going to 64x 100GbE and beyond in the next few years. But while data centers are moving to higher port density and higher port speeds, and homogenous deployment, there is still a substantial market for lower speeds such as 10GbE that continues to be deployed and must be served economically. The innovation in data centers drives higher density and higher port speeds but many segments of the market still need a solution with lower port speeds with different densities. How can this problem be solved?
 

Bridging the Gap

Fortunately, the technology to bridge lower speed ports to higher density switches has existed for several years. The IEEE standards codified the 802.1br port extender standard as the protocol needed to allow a fan-out of ports from an originating higher speed port. In essence, one high end, high port density switch can fan out hundreds or even thousands of lower speed ports. The high density switch is the control bridge, while the devices which fan out the lower speed ports are the port extenders.
 

Why Use Port Extenders

In addition to re-packaging the data center switch as a control bridge, there are several unique advantages for using port extenders:

  1. Port extenders are only a fraction of the cost, power and board space of any other solution aimed for serving Ethernet ports.
  2. Port extenders have very little or no software. This simplified operational deployment results in the number of managed entities limited to only the high end control bridges.
  3. Port extenders communicate with any high-end switch, via standard protocol 802.1br. Additional options such as Marvell DSA, or programmable headers are possible.)
  4. Port extenders work well with any transition service: 100GbE to 10GbE ports, 400GbE to 25GbE ports, etc.
  5. Port extenders can operate in any downstream speed: 1GbE, 2.5GbE, 10GbE, 25GbE, etc.
  6. Port extenders can be oversubscribed or non-oversubscribed, which means the ratio of upstream bandwidth to downstream bandwidth can be programmable from 1:1 to 1:4 (depending on the application). This by itself can lower cost and power by a factor of 4x.

 
 
Port-Extenders

 

Marvell Port Extenders

Marvell has launched multiple purpose-built port extender products, which allow fan-out of 1GbE and 10GbE ports of 40GbE and 100GbE higher speed ports. Along with the silicon solution, software reference code is available and can be easily integrated to a control bridge. Marvell conducted interoperability tests with a variety of control bridge switches, including the leading switches in the market. The benchmarked design offers 2x cost reduction and 2x power savings. SDK, data sheet and design package are available. Marvell IEEE802.1br port extenders are shipping to the market now. Contact your sales representatives for more information.

 

January 18th, 2017

The Four Most Exciting Wireless Audio Trends

By Jawad Haider, Senior Product Marketing Manager of Wireless Connectivity Business Unit

As chips are becoming smaller and more powerful, the wireless audio market is continuing to rapidly grow. According to MarketsandMarkets, the wireless audio industry is expected to reach $54.07 billion by 2022, at a CAGR of 23.2 percent between 2016 and 2022. High performance, low power wireless and Bluetooth/ Bluetooth Low Energy (BLE) solutions have been key enablers of the growth of wireless audio, providing the technology for companies to develop connected audio solutions that have the throughput and range needed for high-resolution wireless, integrated with the extended battery life consumers expect for portable devices.

Multi-channel and multi-room wireless audio solutions are two key trends that have seen an increase in consumer adoption. However, to enable consumers to seamlessly stream their favorite tunes throughout their homes, there are a few key technological challenges with range and synchronization that must be addressed.

Marvell’s newest Avastar® wireless connectivity solutions make range limitations a thing of the past for many home and enterprise audio applications. Marvell’s high performance and low power Avastar combos incorporate Dynamic Multi-Hop Relay (DMHR) Technology to connect up to 15 devices in a daisy-chain fashion, extending the range of traditional Wi-Fi networks 15 times from 40m to almost 600m in a typical home. Additionally, Marvell has enabled other exciting features, such as connecting up to 31 clients to a speaker or sound bar which acts as a soft access point.

Diagram showing a daisy-chain wireless audio setup

Diagram showing a daisy-chain wireless audio setup

To make every microsecond of audio count, Marvell’s Avastar solutions provide cutting-edge audio synchronization across devices and rooms. Combining Marvell’s advanced Wi-Fi technology, support for the 802.11mc standard, and hardware time-stamping synchronization algorithms developed by our partners, Avastar delivers best-in-class smart connected solutions.

Another key trend in the wireless audio space, is the emergence of voice assisted products like Amazon Echo and Google Home. Marvell is working closely with all voice-enabled ecosystems to be at the forefront of technology enablement for this new category of products.

From portable speakers to advanced soundbar systems, Marvell’s advanced wireless technology is embedded in many of the most popular audio products on the market today. To learn more about Marvell’s wireless solutions, please visit: www.marvell.com/wireless. You can also read more about wireless trends and standards in my Q&A with Electronic Design’s Bill Wong http://electronicdesign.com/wifi/qa-what-s-new-wireless-audio-market.

January 18th, 2017

Marvell on the Move as Devices are Getting Smarter and the Volume of Data is Exploding

By Sander Arts, Interim VP of Marketing

MOVE_Fast
We are only a couple of weeks into the New Year and already have a glimpse of how the industry will take shape in 2017 and beyond. It has been a ritual for the Marvell team, and most major players in the technology ecosystem, to start the first week of the year showcasing the cutting-edge solutions of today and tomorrow at CES. This year, the Las Vegas expo floor showed us that everyday objects, as well as cars, are getting smarter and are taking on new capabilities, signaling new demands for the industry to address.

Say “Hello” to the Car of the Future

The race to fully autonomous cars continues with new automotive tech ranging from improved sensors for Advanced Driver Assistance Systems (ADAS) to new displays and infotainment systems. Automakers introduced the integration of cloud-based voice assistants, which is bound to revolutionize the way we will interact with our cars.

Virtual Reality Wants to Get Real

Virtual reality (VR) developers focused on creating better content and tools to bring VR to the mainstream. Companies shared plans for gesture tracking and untethered headsets to deliver immersive experiences for gaming, entertainment and enterprise applications. In the near future, we can expect access to more VR, augmented reality (AR) and mixed reality (MR) content and experiences, such as shopping in virtual retail stores.

The AI of Everything

While automotive tech and VR continued to have a big presence at CES like in past years, artificial intelligence (AI) was one of the stars of the show. We saw more devices—beyond robots and smartphones—touting AI capabilities as automakers and home appliance manufacturers showcased exciting voice control integrations in cars, fridges, washing machines, TVs and more.

Amid all of the hype around the technologies that took center stage at this year’s CES, it was clear that data remains at the heart of our connected world. With advancements in connectivity comes the explosion of digital traffic as data is created, accessed, stored and moved to the cloud by billions of connected devices, appliances, cars, enterprises and more. Autonomous cars, VR and AI all depend on high bandwidth video and data to deliver smart and seamless experiences for consumers.

MOVE_Reliably

 

At CES Marvell demonstrated how we are enabling the ecosystem to overcome its toughest data storage and network bandwidth challenges with our advanced solutions for the cloud, automotive, industrial, enterprise and consumer markets. Our automotive Ethernet physical layer (PHY) transceiver provides the robust 1000BASE-T1 connectivity needed to distribute data between the multiple advanced in-vehicle systems of tomorrow’s cars.

As data is moved and stored from consumer devices to the cloud, data centers can take advantage of our support for a range of Ethernet technology speeds for even greater accessibility, including our Prestera® switches, Alaska® Ethernet transceivers and ARMADA® 64-bit ARM-based modular SoC families for 10 Gigabit Ethernet (GbE), 25 GbE and 40 GbE. We also demonstrated at CES our recently announced 25GbE end-to-end data center solution which underscores our commitment to delivering high performance, cost-effective and energy-efficient computing solutions to keep up with today’s increasing bandwidth demands.

What we saw at CES validates the work we do at Marvell, providing industry-leading solutions that help our customers move and store data fast, securely, reliably and efficiently across a wide range of applications, systems and platforms. For whatever new demands and challenges the market brings in 2017, Marvell is on the Move.