comment on this article

Xilinx looks to revolutionise data centres

Xilinx has announced a new range of data centre products and solutions, including a new family of Alveo SmartNICs, smart world AI video analytics applications, and an accelerated algorithmic trading reference design for sub-microsecond trading.

Demanding and complex applications such as networking and AI analytics or financial trading, require low-latency and real-time performance. Achieving this level of performance has been limited to expensive and lengthy hardware development. However, with these new products and solutions, Xilinx said that it was looking to eliminate the barriers for software developers to quickly create and deploy software-defined, hardware accelerated applications on its Alveo accelerator cards.

“Data centers are transforming to increase networking bandwidth and optimise for workloads like artificial intelligence and real-time analytics,” said Salil Raje, executive vice president and general manager, Data Center Group at Xilinx. “These complex, compute-intensive and constantly-evolving workloads are pushing existing infrastructure to its limits and driving the need for fully composable, software-defined hardware accelerators that provide the adaptability to optimize today’s most demanding applications as well as the flexibility to quickly take on new workloads and protocols, and accelerate them at line rate.”

Xilinx's Alveo SN1000 is the industry’s first family of composable SmartNICs offering software-defined hardware acceleration for all function offloads. The SN1000 SmartNICs directly offload CPU intensive tasks to optimise networking performance, with an open architecture that can accelerate a broad range of network functions at line rate.

Using the Vitis Networking platform and industry standard, high-level programming languages such as P4, C, and C++, software developers will be able to create network functions, protocols, and applications that operate in hardware on the SmartNIC. Vitis Networking makes it possible to quickly and easily compose new, and tweak existing, network functions to handle new protocols and applications without replacing hardware, future proofing investments.

SN1000 SmartNICs provide software-defined hardware acceleration for a wide range of networking, security, and storage offloads, such as Open vSwitch and virtualization acceleration (Virtio.net). Security offloads include IPsec, kTLS and SSL/TLS and accelerated storage applications including Virtio.blk, NVMe over TCP, Ceph, and compression and crypto services.

Based on the Xilinx 16nm UltraScale+ architecture, the SN1000 family of SmartNICs are powered by the low-latency Xilinx XCU26 FPGA and a 16-core Arm processor. The SN1000 SmartNICs deliver dual-QSFP ports for 10/25/100Gb/s connectivity with leading small packet performance and a PCIe Gen 4 interconnect.

The first model in the family is the SN1022, which is offered in a full height, half length form factor in a 75W power envelope.

The Alveo SN1022 SmartNIC will be generally available in March 2021.

Xilinx has also launched an AI video analytics platform with an ecosystem of partner solutions built to accelerate the most complex and latency-sensitive AI video inferencing applications. The Xilinx smart world platform, powered by the Xilinx Video Machine-learning Streaming Server, delivers whole application acceleration and can support multiple neural networks on a single Alveo accelerator card at deterministic sub-100ms pipeline latency.

The result is the industry’s lowest TCO for demanding AI video analytics applications.

The Xilinx smart world ecosystem includes the following solutions:

  • Aupera is offering turnkey smart city and smart retail solutions that combine Aupera’s intelligent, video processing with Alveo accelerators.
  • Mipsology is providing a toolset for easy migration of existing AI applications from GPU-based architectures to the Alveo platform, as well as plug-and-play, high-performance AI inference acceleration.
  • DeepAI is delivering AI training at the edge on Alveo accelerators with up to a 10x performance per cost advantage compared to GPU-based solutions.

Achieving submicrosecond latency in algorithmic trading has traditionally required costly and time-consuming hardware development. The Vitis development platform now includes an accelerated algorithmic trading (AAT) reference design which gives software developers the ability to quickly and cost-effectively deliver sub-microscond trading performance without the need for custom hardware development.

AAT, implemented on Alveo accelerator cards, provides a modular design that includes all the necessary components for an end-to-end, low-latency trading solution. Each module can be customized using C and C++ in the Vitis platform to meet each firm’s specific needs.

The AAT reference design is now available at no cost for Alveo accelerator card customers.

Author
Neil Tyler

Comment on this article


Websites

http://www.xilinx.com

Companies

Xilinx Inc

This material is protected by MA Business copyright See Terms and Conditions. One-off usage is permitted but bulk copying is not. For multiple copies contact the sales team.

What you think about this article:


Add your comments

Name
 
Email
 
Comments
 

Your comments/feedback may be edited prior to publishing. Not all entries will be published.
Please view our Terms and Conditions before leaving a comment.

Related Articles

Terabox edge server

BittWare, a Molex company, and a supplier of enterprise-class FPGA accelerator ...

FPGAs come of age

Programmable logic devices have a range of aliases, but whatever you call them, ...