Network2

Why Your Network Needs Programmable NICs

April 9, 2021
Soaring demand for servers due to the rapid rise in data-center network traffic has also pushed demand for network interface controllers used to connect them. Thus, the need for a new class of NIC—a programmable SmartNIC.

What you’ll learn:

  • Changing trends and factors contributing to SmartNIC adoption.
  • Benefits of SmartNICs.
  • Decision-makers for SmartNICs.

New and emerging technologies are putting extraordinary pressure on networks in terms of uptime and performance: hyperscale architectures, cloud services, cybersecurity, AI, and others. Another factor this year has been the pandemic, which led people to the internet like never before for cloud-based business apps and services, as well as online ordering and entertainment.

This situation offers a great opportunity for SmartNICs—and particularly programmable SmartNICs—to demonstrate their worth. Organizations that use SmartNICs are reaping the benefits of this increased demand due to their ability to accelerate traffic and boost agility through programmability. SmartNICs will play an even more important role in networks as they evolve and expand.

Changing Trends and Factors

The volume of network traffic flowing into the data center is skyrocketing, primarily because of 5G mobile, cloud, edge, and IoT. Together, these unique megatrends are radically changing the way networks are built. The networks that support these new models all share common characteristics of moving to open, standard, low-cost server platforms to deliver the majority of applications and services. As the demand soars for servers, so does the number of network interface controllers (NICs) used to connect them. This creates the need for a new class of NIC, a programmable SmartNIC. 

Several other trends are responsible for upping the adoption of SmartNICs. One is the increase in performance requirements, including throughput PPS and Gb/s. There’s also lower latency for real-time applications and services in edge computing, and the need for improved security in a distributed cloud and edge network design.

Other factors are at play, too. There’s the need for operation, orchestration, and management for a massive number of network elements at scale. In addition, many more sessions and flows are needed amongst more users and applications. On top of that, there’s a requirement for feature velocity to keep up with the speed of innovation in software-defined networks.

The Benefits of SmartNICs

Central processing units (CPUs) are feeling a massive strain from the growing sophistication of cyberattacks and the coinciding growth in network traffic. One of the ways these systems are adapting is by offloading more of the packet-processing workload from the CPU to an FPGA-based SmartNIC.

By offloading networking processing workloads and tasks from server CPUs, SmartNICs boost server performance in cloud and private data centers. It’s not a new concept, but it’s being driven by the expansion in data-center network traffic. In fact, according to the analysts at Omdia, deployment of programmable NICs is seeing significant growth. They estimate that programmable NICs will proliferate for workloads like virtual switching and enforce software-defined networking (SDN) policies, surpassing $2.1 billion in revenue by 2024.

Decision Points for SmartNICs

It’s one thing to understand that SmartNICs hold significant value; it’s another to make a purchasing decision. You need to dig deeper before going on a spending spree. The process isn’t as simple as buying software and putting it on the server. You must understand your expectations of the software in terms of performance and number of users. You need to consider how it will scale. It will drive the hardware decisions that you put into your network.

To make the best decision, it’s crucial, of course, to understand your applications and users as well as the requirements for each. That’s partly because every application is a little different.

For instance, you could take applications A and B, put them both on a standard NIC, and A will work perfectly while B fails. So, you have to carefully evaluate each application’s or service’s needs, including how many users it needs to support simultaneously and its attributes. You must evaluate performance requirements, in terms of bandwidth and latency, and what kind of workload it involves. These considerations are key to ensuring you’re selecting the right solutions.

SmartNICs on the Horizon

The NIC market is expected to grow by more than 300% within the next five years. Most of the standard NICs will fall by the wayside as SmartNICs gain greater prominence. Adoption will increase simply because organizations need servers that can meet the demands of the services and applications they’re hosting. Refer to the recommendations above to develop the SmartNIC strategy that works best for your organization.

Sponsored Recommendations

TTI Transportation Resource Center

April 8, 2024
From sensors to vehicle electrification, from design to production, on-board and off-board a TTI Transportation Specialist will help you keep moving into the future. TTI has been...

Cornell Dubilier: Push EV Charging to Higher Productivity and Lower Recharge Times

April 8, 2024
Optimized for high efficiency power inverter/converter level 3 EV charging systems, CDE capacitors offer high capacitance values, low inductance (< 5 nH), high ripple current ...

TTI Hybrid & Electric Vehicles Line Card

April 8, 2024
Components for Infrastructure, Connectivity and On-board Systems TTI stocks the premier electrical components that hybrid and electric vehicle manufacturers and suppliers need...

Bourns: Automotive-Grade Components for the Rough Road Ahead

April 8, 2024
The electronics needed for transportation today is getting increasingly more demanding and sophisticated, requiring not only high quality components but those that interface well...

Comments

To join the conversation, and become an exclusive member of Electronic Design, create an account today!