Breaking down barriers and empowering software developers to unleash the performance of Xilinx FPGAs. That’s our mission at Xilinx Data Center Group.

In this video Pej Roshan (Xilinx VP of Marketing DCG) explains how the products and solutions in the 2021 DCG spring launch deliver software-defined hardware acceleration for datacenter networking offloads, AI video analytics, and algorithmic trading.

Learn more about the products and solution in the Xilinx DCG spring launch here:

Xilinx Alveo SN1000 family of composable SmartNICs with Vitis Networking

Xilinx Smart World video AI analytics platform and solutions ecosystem

Xilinx Advanced Algorithmic Trading

Xilinx App Store

Xilinx Vitis

Get the latest Xilinx news in your inbox

Innovation is recognized when it disrupts a market. Network Interface Cards (NICs) have existed since the 1980s, and around the turn of the century, various companies began innovating in this area. Their initial focus was on High-Performance Computing (HPC). While businesses ran on Ethernet, the most powerful HPC clusters in the world were created using Myrinet or Infiniband. The NICs for these networks were architected to bypass the operating system (OS) kernel and communicate directly with HPC applications delivering substantially greater performance. To make this happen, these NICs applied extensive computational resources at the edge of the network, enabling them to offload common communications tasks from the host CPU.

These HPC NICs laid the groundwork for what then became Ethernet NICs with built-in kernel bypass for electronic trading in all the world's stock markets. Over time these platforms further evolved into what has become SmartNICs or Data Processing Units (DPUs). With the emergence of Hyperscalers and Cloud Service Providers (CSPs), Xilinx has idenfied three things that have hampered the adoption of SmartNICs:

1. Programmability
2. Composability
3. Portability

Xilinx's approach of providing a software-defined, hardware-accelerated platform lends itself perfectly to addressing these three issues.

The most critical AI video analytics applications are the ones that protect human health, preserve human life, and secure property, and complex applications like that need deterministic low latency performance. Not only that, but their complexity can be extremely hardware intensive, which can challenge organizational budgets.

The low latency performance and massive parallel processing capabilities of Xilinx Alveo accelerator cards make them the perfect foundation on which to build these critical applications, and today Xilinx launched an AI video analytics platform, built on Alveo, with an ecosystem of partner solutions built to accelerate the most complex and latency-sensitive AI video inferencing applications.