Xilinx is now part ofAMDUpdated Privacy Policy

OCP Virtual Summit

Booth Highlights

OCP Summit has gone virtual! We welcome you to join us to learn how Xilinx’s compute, networking and storage platforms are powering the evolution of real-time computing.

Please visit our virtual booth from May 12-15. Our team will be available to chat with you live as you view our virtual demos, answer questions about our line of Alveo® accelerator cards, and participate in our industry talks.

We hope to see you at OCP!


Demo Title Description
OpenCompute Accelerator Module (OAM) Xilinx will demonstrate a Proof of Concept OpenCompute Accelerator Module (OAM) that leverages an UltraScale+ VU37P FPGA with 8GB of HBM memory and supports seven 25Gbps x8 links to enable rich inter-module system topologies.
  • Proof of Concept leveraging UltraScale+ VU37P FPGA with 8GB of HBM memory
  • Seven 25Gbps x8 links enable rich inter-module system topologies
  • Compliant with Open Accelerator Infrastructure (OAI)
Enabling Real-Time Healthcare with TigerGraph and Alveo® U50

In this demo, we will showcase the calculation of real-time healthcare data via the TigerGraph recommendation engine, powered by Alveo® U50 accelerator cards.

  • Get critical insights in less than one tenth of a second
  • Calculate data for up to 10M patients in under 35 ms with a single Alveo® U50 card (100x faster than CPU)
  • Calculate data for up to 50M patients in under 50 ms with multiple Alveo® U50 card (400x faster than CPU)


Demo Title Description
Virtual Switching Offload on FPGA-Based SmartNICs

In this demo, we will show how server hypervisor virtual switching function is offloaded and accelerated on an FPGA-based SmartNIC, greatly reducing the server CPU burden and reclaiming resources that can be monetized to run more applications. At the same time, we will show how the data bottleneck to the server is opened up, now that the SmartNIC is processing data at a much higher throughput.

  • Hypervisor virtual switching function offloaded and accelerated on an FPGA-based SmartNIC
  • Reduces server CPU burdens and reclaims resources to run more applications
  • Eliminates server bottlenecks to process data at higher throughputs


Demo Title Description
Accelerated Analytics & Business Intelligence with Alveo® and Samsung SmartSSD®

In this demo, technology partner Bigstream demonstrates how Caltrans created a dashboard map to analyze Bay Area traffic intensity with seamless acceleration of Parquet queries up to 3X, utilizing Alveo® accelerator cards and Samsung SmartSSD® drives.

  • 2X – 30X acceleration with Alveo
  • Zero code change for data analysts with Bigstream’s Hyper-Acceleration layer
  • Reduced TCO – More analytics performed with given infrastructure
  • CPU Offload – Expensive operations executed on Samsung SmartSSD® drives
  • Scalable Acceleration – Multiple SmartSSD® drives

Booth Information

Xilinx Booth (live on May 12)

May 12 - 15, 2020

Xilinx Talks

Finding the Goldilocks Zone in Data Center Networking

Date/Time: On-demand
Presenter: Scott Schweitzer, Accelerator Marketing, Data Center Group, Xilinx

Software Defined Networking has transformed Data Center Networking in several profound ways.  First, it has broken down traditional boundaries of where functionality exists across network elements.  Second, it has vastly increased the functional richness and diversity of features available to data center operators.  And third, it has made possible for the first time the development and deployment of new networking features at the speed of software.

But this transformation has also brought about massive technical challenges and unanswered questions.  What    is the most optimal way to partition networking functionality across switches, NICs, and Server CPUs?  When and where does it make sense to apply acceleration techniques?  What types of acceleration technologies provide the best performance while maintaining the flexibility and development agility required by SDN?

In case you haven’t noticed, many players in the networking industry have set out to tackle some of these difficult problems.  This is creating a renaissance in domain specific networking architectures.   In this session we will present Xilinx’s vision regarding this important new trend and explain how FPGA technology will play an important and critical role.


New Era of Software-Defined Networking and Storage Infrastructure

Date/Time:  Thursday,  May 14 @10:00am - 10:30am
Presenter: Jamon Bowen, Product Marketing Director, Xilinx

Software Defined Networking and computational storage is transforming data center infrastructure in several profound ways.  As compute migrates out to the NIC and where the data lives in storage, a whole new set of domain-specific architectures are being created and deployed.   In this session, we will present Xilinx’s vision regarding this important new trend and explain how FPGA technology will play an important and critical role.