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!

Arm TechCon 2017

At Arm TechCon we will be showcasing our All Programmable Zynq® UltraScale™ MPSoCs and RFSoCs enabling smarter, connected and differentiated systems for your Embedded Vision and IoT applications. Join us at the show for a first-hand look and to connect with Xilinx technology experts.

During Exhibit Hours | Xilinx Booth
The following demos will be featured from Xilinx throughout the show.

Accelerated Machine Learning Image Recognition
Implemented in this Zynq UltraScale+ MPSoC is a convolutional neural network accelerating image recognition for an automotive application. The neural network is implemented on the integrated programmable logic and is customizable for different application requirements.

UltraHD Video Processing with Compression/Decompression
Integrated in the Zynq UltraScale+ MPSoC EV devices is a 4K multi-standard video codec capable of 8 simultaneous encode and decode streams at up to 60 frames per second. Enabled by a codec specific software stack, raw 4K video is compressed to H.265 standard and transmitted via Ethernet, decompressed, and displayed in this video conferencing example.

Accelerated Multi-sensor Image Processing
Utilizing the Zynq UltraScale+ MPSoC, this demonstration illustrates accelerated image processing with thermal imagery, visual images and voice print.  These three elements can be fused together to create a unique identification "signature" which can be used for security and other identification purposes. 

RF-DAC/ADC & SD-FEC RFSoC for Wireless, Cable, Radar
In this demonstration Xilinx showcases the capabilities of their Zynq UltraScale+ RFSoC family, which integrates multi-giga-sample-per-second RF data converters and soft-decision forward error correction (SD-FEC) into an All Programmable SoC architecture. Complete with an ARM® Cortex™-A53 processing subsystem and 16nm UltraScale+ programmable logic, the new family provides a comprehensive RF signal chain for wireless, cable access, test & measurement, radar, and other high performance, multi-channel Direct-RF applications.

Booth Information

Xilinx Booth #706
Santa Clara Convention Center
Santa Clara, CA

Wednesday, October 25
10:30 AM – 6:30 PM

Thursday, October 26
10:30 AM – 5:30 PM

Xilinx Conference Participation
Xilinx experts will be participating in the following product showcases.

Unprecedented Industry Collaboration Delivers Leading 7nm FinFET HPC Solutions
Thursday, October 26
11:30 AM – 12:30 PM

In this sponsored session, you will hear how Arm® and its Ecosystem partners delivered industry leading 7nm FinFET solutions to address applications of the High Performance Computing (HPC) segment.  With the increasing complexity of implementation at small geometries and more demanding product requirements and timelines, it is imperative that the Ecosystem collaborate closely to meet the most stringent system-level performance and power targets.  Speakers from TSMC®, Cadence®, Xilinx® and Arm will share details of this joint work and discuss key challenges and opportunities. Co-presented by: Arm, Cadence, TSMC and Xilinx.

IoT Cybersecurity for ARM-based Devices
Wednesday, October 25
2:30 PM – 3:20 PM

This talk will describe a new Arm-based solution to detect cyber vulnerabilities by monitoring analog side-channels (e.g. power consumption profiles or electromagnetic emissions) emitted during processor execution. Using machine learning to identify unique patterns not readily observable, combined with pattern recognition of authorized firmware this presentation illustrates an approach for instantly detecting any zero-day attack using an Arm-based Programmable SoC solution. This analysis approaches the cyber security problem from the lowest machine level, execution power emanations. Since any attack must ultimately use an IoT’s microprocessor to execute the attack, it is practically impossible to ‘sneak’ by power analysis techniques. 

 

このページをブックマークに追加