Explaining the QSFP-DD Data Center Interconnect Standard


Reading time ( words)

The explosion in data center activity shows no signs of abating. Cisco’s latest Visual Networking Index (VNI) study projects annual global IP traffic will reach 4.8 zettabytes per year by 2022 after breaking one zettabyte just three years ago. Worldwide traffic will triple over the next five years, reaching 50 GB per capita. The VNI study anticipates 28.5 billion networked devices by 2022, up from 18 billion in 2017, with 82% of all data flow due to video viewing.

According to Cisco’s report, most IP traffic either originates or terminates in data centers. Yet as massive as the flows between centers are becoming, the data managed within those same facilities is going even higher. All of this activity means that “hyperscale” is the word of the future. Roughly one-quarter of all servers installed in 2016 went to hyperscale facilities, but that number will grow to almost one-half by next year. Other advances that are heavily impacting the modern data center is the rise in 400-Gbps technology, the expansion of cloud computing, and how virtual data centers, machine learning, and AI are all driving change.

To meet the pressing need for high signal integrity, lower latency, lower insertion loss, and higher density data transmission, transceivers and modules capable of supporting 400 Gbps are quickly being developed. At the forefront is the Quad Small Form Factor Pluggable-Double Density (QSFP-DD) system— the most advanced interconnect standard yet. Defining form factors and performance specifications for this new standard is the QSFPDD Multi-Source Agreement (MSA) comprised of leading data center equipment and component suppliers.

To read this entire article, which appeared in the September 2019 issue of SMT007 Magazine, click here.

Share

Print


Suggested Items

Book Excerpt: The Printed Circuit Assembler’s Guide to Smart Data, Chapter 1

12/30/2020 | Sagi Reuven and Zac Elliott, Siemens Digital Industries Software
Accurate data is required to adjust processes and to ensure quality over time. This is difficult because not all data is in the same format, and not all sensors perform the same over time. How do you know what the best data to collect is and how to filter out the junk data from useful or smart data? This is not an easy task when the interfaces to data collection sources are complex, and they do not speak the same language, often requiring the vendor’s help to get data out of the machine and then spending time normalizing the data to turn it into something useful. This is a challenge for companies trying to set up a custom data collection system themselves.

Book Excerpt: The Printed Circuit Assembler’s Guide to Smart Data

12/16/2020 | Sagi Reuven and Zac Elliott, Siemens Digital Industries Software
Whenever we discuss data, keep in mind that people have been collecting data, verifying it, and translating it into reports for a long time. And if data is collected and processes are changed automatically, people still will be interpreting and verifying the accuracy of the data, creating reports, making recommendations, solving problems, tweaking, improving, and innovating. Whatever data collection system is used, any effort to digitalize needs to engage and empower the production team at the factory. Their role is to attend to the manufacturing process but also to act as the front line of communications and control.

Siemens and Computrol: Achieving Operational Excellence in Electronics Manufacturing

12/02/2020 | I-Connect007 Editorial Team
I-Connect007’s Happy Holden and Nolan Johnson speak with Zac Elliott, technical marketing engineer at Siemens Digital Industries Software, and Farid Anani, VP of operations at Computrol, about how to achieve operational excellence in electronics manufacturing. They start by discussing the dynamic wherein automation projects may initially create islands of automation and the need to eventually connect those islands to achieve even greater operational efficiencies. The discussion then moves to how to make the data smarter and more useful for analysis and optimization.



Copyright © 2021 I-Connect007. All rights reserved.