UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

Xilinx at SC16

Cloud infrastructure is transforming. The decline of Moore’s Law and the exponential increase in computing for cloud services is driving the need for acceleration. Leaders in cloud computing are turning to FPGAs because of their hardware reconfigurability and range of applications they cover – something no other accelerator can do. Xilinx FPGAs provide the highest performance per watt and the lowest total cost of ownership of any FPGA available.

Join us at SC16 for a look at the Xilinx technology enabling compute, storage, and networking acceleration for data center applications, try out our Acceleration Developer Zone, and connect with Xilinx experts.

sc16-banner

During Exhibit Hours | Xilinx Booth

The following demos will be featured from Xilinx and its ecosystem throughout the show.

Accelerated Image Classification

This demo showcases Xilinx deep learning libraries by demonstrating image classification at highest throughput and power efficiency. Developers of cloud applications will be able to use this optimized Alexnet Network and reference implementation to begin accelerating deep learning applications from autonomous vehicles to cloud computing.

Dynamic Provisioning of FPGAs with OpenStack

In this demo, you will learn how FPGA resources can be provisioned and managed in OpenStack installations, the same way CPUs and GPUs can. OpenStack, the OS of the cloud, is an important tool to provision and deploy workloads to FPGA acceleration cards.

Virtualized Network Services with P4 Language

In this demo, Xilinx will demonstrate the orchestration of on-demand network services, implemented on a Xilinx FPGA-based smart NIC programmed with the high-level networking language P4.

Storage, Networking and Analytics Framework

This demo showcases the CAPI SNAP Framework enabling FPGA acceleration with ease. “SNAP”, short for “Storage, Networking, and Analytics Programming,” indicates that the framework enables accelerated analytics on data as it flows through the FPGA to/from the server.  As a result, computing moves closer to the data, providing higher performance at a lower cost while also lowering power consumption.

Database Acceleration Engine

This demo illustrates the use of Xilinx FPGAs in rENIAC’s Data Proxy Engine to accelerate Cassandra NoSQL databases without any software changes necessary. rENIAC’s Distributed Data Proxy Engine accelerates data stores (like NoSQL, SQL and Hadoop) and provides higher performance and significantly lower total cost of ownership. It delivers predictable 1/3-1/10 lower latency and up to 10x higher throughput.

Acceleration Developer Zone

During Exhibit Hours | Xilinx Booth

The Acceleration Developer Zone is a hands-on opportunity to learn about the evolution of FPGA programming models towards standard programming paradigms like OpenCL. In this self-paced interactive environment, the user will be able to learn how to optimize and debug a compute intensive algorithm to generate a custom accelerator using the compiler inside of the SDAccel™ Development Environment. Users can choose between learning about the Xilinx compiler tool chain for FPGAs, accelerator creation and optimization from a software designer’s view, and/or how to leverage FPGA accelerated libraries.

Booth Information

Booth #3640

Salt Palace Convention Center
Salt Lake City, UT

Monday, November 14
7:00PM - 9:00PM

Tuesday, November 15
10:00AM - 6:00PM

Wednesday, November 16
10:00AM - 6:00PM

Thursday, November 17
10:00AM - 3:00PM

Xilinx Conference Participation

Xilinx experts will be participating in the following sessions of interest throughout show.

Monday, November 14

9AM – 12:30PM

Second International Workshop on Heterogeneous High-Performance Reconfigurable Computing Workshop. http://h2rc.cse.sc.edu/index.html


Tuesday, November 15

4:15PM – 5PM

Introduction to Workload Acceleration Using FPGAs and Nimbix

Nimbix Booth #4072

Tuesday, November 15

5:30PM – 7PM

Birds of a Feather: Reconfigurable Supercomputing http://sc16.supercomputing.org/presentation/?id=bof107&sess=sess325


Wednesday, November 16,

9AM – 10AM

Xilinx Technology Briefing – Reconfigurable Acceleration in the Cloud Data Center

We are in the midst of a data explosion as cloud and IoT applications are generating more data at a rapidly escalating rate. Cloud providers are being pressed to move faster, be more agile and use data analytics and machine learning as ways to glean insight and offer more valuable services.  FPGA-based platforms that are programmable and reconfigurable can be hardware optimized for all major workloads, enabling cloud providers to shrink time to market for differentiated services and greatly increase their ‘feature velocity’ as new algorithms arise and business models change. In this briefing, the principles from Xilinx engineering and research will outline how cloud scale data centers can take advantage of a flexible, power efficient FPGA accelerator platform and a provide a look at the Xilinx technology roadmap ahead. After the briefing, the Xilinx technology team will be available for further discussion.

Location: Utah Museum of Contemporary Art (UMOCA) – Adjacent to the convention center

20 S. West Temple, Salt Lake City, UT 8101

View Map

Agenda:

8:15AM – Doors open, registration, coffee, continental breakfast

9:00AM – Welcome, technology briefing commences

Register Now

*This event is subject to seating availability. Registration required.

Wednesday, November 16

9AM – 10AM

Location: Utah Museum of Contemporary Art (UMOCA) – Adjacent to the convention center

20 S. West Temple, Salt Lake City, UT 8101

View Map

Reconfigurable Acceleration in the Cloud Data Center

We are in the midst of a data explosion as cloud and IoT applications are generating more data at a rapidly escalating rate. Cloud providers are being pressed to move faster, be more agile and use data analytics and machine learning as ways to glean insight and offer more valuable services.  FPGA-based platforms that are programmable and reconfigurable can be hardware optimized for all major workloads, enabling cloud providers to shrink time to market for differentiated services and greatly increase their ‘feature velocity’ as new algorithms arise and business models change. In this briefing, the principles from Xilinx engineering and research will outline how cloud scale data centers can take advantage of a flexible, power efficient FPGA accelerator platform and a provide a look at the Xilinx technology roadmap ahead. After the briefing, the Xilinx technology team will be available for further discussion.

Agenda:

8:15AM – Doors open, registration, coffee, continental breakfast

9:00AM – Welcome, technology briefing commences

Register Now

*This event is subject to seating availability. Registration required.

Xilinx Ecosystem Demonstrations

Xilinx technology-enabled demos will be in the following Xilinx ecosystem company booths at SC16.

Alpha Data – Booth 2607

ArrayFire – Booth 717

Bittware – Booth 3763

ClusterTech – Booth 3775

HP – Booth 1531

IBM – Booth 1018/1042

ICHEC – Booth 3460

Mellanox – Booth 2631

Metamako – Booth 547

Micron – Booth 4254

Nallatech – Booth 2214

Nimbix – Booth 4072

SmartIOPS – Booth 3447

Page Bookmarked