Latest Marvell Blog Articles

Posted on

Is IP over WDM finally here?

By Loi Nguyen, Executive Vice President, Cloud Optics Business Group

Some twenty years ago the concept of IP over Wavelength Division Multiplexing (WDM) was proposed as a way to simplify the optical infrastructures. In this vision, all optical networks are connected via point-to-point mesh networks with a router at the center. The concept was elegant, but never took off because the optical technology at the time was not able to keep up with the faster innovation cycle of CMOS, driven by Moore’s law. The larger form factor of WDM optics does not allow them to be directly plugged into a router port. Adopting a larger form factor on the router in order to implement IP over WDM in a massive scale would be prohibitively expensive.

For routers to interface with the networks, a “transponder” is needed, which is connected to a router via short-reach optics on one side and WDM optics to the network on the other. The market for transponders grew quickly to become a multi-billion-dollar market.

A Star is Born

About 10 years ago, I was building a team at Inphi, where I was a co-founder, to further develop a nascent technology called silicon photonics. SiPho, as it’s called, leverages commercial CMOS foundries to develop photonics integrated circuits (PIC) that integrate hundreds of components ranging from high-speed modulators and detectors to passive devices such as couplers, waveguides, monitoring diodes, attenuators and so on. We were looking for ideas and customers to bring silicon photonics to the marketplace.

Fortunately, good technology and market need found one another. A group of Microsoft executives had been considering IP over WDM to launch a new concept of “distributed data centers,” in which multiple data centers in a region are connected by high speed WDM optics using the same form factor as shorter reach “client optics” used in switches and routers. By chance, we met at ECOC 2013 in London for the initial discussion, and then some months later, a product that enabled IP over WDM at cloud scale was born.

Read More

Posted on

Thriving at Marvell with Trust, Respect, and Integrity

By Liz Du, Director, Marvell


Employees have demonstrated remarkable resiliency over the past few years, adjusting to new ways of working during an unprecedented global crisis. It forever changed how employees think about their workplaces, careers, and personal lives, giving them new perspectives on what really matters.

As a company, Marvell has also been evolving, tapping into employee experiences, and listening intently to their opinions on what makes Marvell a great place to work and how we can continuously improve. We were pleased to consistently hear appreciation for being able to experiment with cutting-edge technology, develop skills, and build products that help connect people all over the world.

But another pattern took shape in their commentary as they emphasized the importance of teammates and leaders, uttering words like transparency, integrity, and respect. We believe these adjectives are no coincidence. They are interrelated characteristics Marvell has purposefully cultivated to help employees thrive.

Read More

Posted on

Product security is paramount to us: A response to recent Cavium product security concerns 

By Raghib Hussain, President, Products and Technologies

To our Valued Customers:

Recently, reports have surfaced alleging that certain Cavium products included a “backdoor” for the National Security Agency (NSA). We assure you that neither Cavium nor Marvell have ever knowingly incorporated or retained any vulnerability or backdoor in our products.

Our products implement a suite of standards-based security algorithms like AES, 3DES, SHA etc. Prior to 2014, some of our software libraries included an algorithm for random number generation called Dual_EC_DRGB. This algorithm was one of four officially recommended at the time by the US National Institute for Standards and Technology (NIST) that our products implemented. In 2013, this algorithm was reported by the New York Times, The Guardian, and ProPublica to include a backdoor for the NSA. After we learned of the potential issue, Cavium removed this algorithm from its software libraries and has not included it in any product shipped since then. 

Importantly, the Dual_EC_DRGB algorithm was included in some of Cavium’s software libraries for our chip-level products, but not in the chips themselves.  As a result, while Cavium provided this algorithm (among many), the ultimate choice and control over the algorithms being used was managed by the equipment vendors integrating our products into their system level products. Many companies, not just Cavium, implemented the NIST standard algorithms including this algorithm. In fact, according to NIST’s historical validation data, approximately 80 different products with semiconductors from different vendors implemented this algorithm in some combination of hardware, software, and firmware before it was removed.

LiquidSecurity, Marvell’s cloud-optimized Hardware Secure Module (HSM) adapter, is a system-level product provided by Marvell, and previously Cavium, and these products have never included or implemented the Dual_EC_DRGB algorithm.

At Marvell, and previously at Cavium, maintaining the integrity and security of our products is paramount, and we continually invest in rigorous validations and updates. Although we believe our actions eliminated this particular vulnerability, new vulnerabilities may be created and exploited. Therefore, we have created robust processes to identify and address potential vulnerabilities in our chip designs and firmware. 

We assure you and our other partners that our products have been rigorously designed and tested to deliver unparalleled security and performance. 

Sincerely,

Raghib Hussain
President, Products & Technologies
(Previously co-founder of Cavium)

Posted on

Automotive Central Switches: The Latest Step in the Evolution of Cars

By Amir Bar-Niv, VP of Marketing, Automotive Business Unit, Marvell

When you hear people refer to cars as “data centers on wheels,” they’re usually thinking about how an individual experiences enhanced digital capabilities in a car, such as streaming media on-demand or new software-defined services for enhancing the driving experience.

But there’s an important implication lurking behind the statement. For cars to take on tasks that require data center-like versatility, they need to be built like data centers. Automakers in conjunction with hardware makers and software developers are going to have to develop a portfolio of highly specialized technologies that work together, based around similar architectural concepts, to deliver the capabilities needed for the software-defined vehicle while at the same time keeping power and cost to a minimum. It’s not an easy balancing act.

Which brings us to the emergence of a new category of products for the zonal architecture, specifically zonal and the associated automotive central Ethernet switches. Today’s car networks are built around domain localized networks: speakers, video screens and other infotainment devices link to the infotainment ECU, while powertrain and brakes are part of the body domain, and ADAS domain is based on the sensors and high-performance processors. Bandwidth and security can be form-fitted to the application.

Read More

Posted on

800G: An Inflection Point for Optical Networks

By Samuel Liu, Senior Director, Product Line Management, Marvell

Digital technology has what you could call a real estate problem. Hyperscale data centers now regularly exceed 100,000 square feet in size. Cloud service providers plan to build 50 to 100 edge data centers a year and distributed applications like ChatGPT are further fueling a growth of data traffic between facilities. Similarly, this explosive surge in traffic also means telecommunications carriers need to upgrade their wired and wireless networks, a complex and costly undertaking that will involve new equipment deployment in cities all over the world.

Weaving all of these geographically dispersed facilities into a fast, efficient, scalable and economical infrastructure is now one of the dominant issues for our industry.

Pluggable modules based on coherent digital signal processors (CDSPs) debuted in the last decade to replace transponders and other equipment used to generate DWDM compatible optical signals. These initial modular products didn’t offer the same performance as the incumbent solutions, and could only be deployed in limited use cases. These early modules, with their large form factors, had performance limitations and did not support the required high-density data transmission. Over time, advances in technology optimized the performance of pluggable modules, and CDSP speeds grew from 100 to 200 and 400 Gbps. Continued innovation, and the development of an open ecosystem, helped expand the potential applications.

Read More