Xilinx and its Ecosystem Showcase Compute, Storage, and Networking Acceleration for Data Center and HPC Applications at SC14

News provided by

Xilinx, Inc.

Nov 12, 2014, 07:20 ET

SAN JOSE, Calif., Nov. 12, 2014 /PRNewswire/ -- Xilinx, Inc. (NASDAQ: XLNX) today announced it will showcase, together with its ecosystem, compute, storage, and networking acceleration for Data Center and HPC applications at Supercomputing 2014. Through a series of demonstrations and presentations, Xilinx and its ecosystem will highlight FPGA-based solutions demonstrating new and industry-leading capabilities that can enable rapid innovation and accelerated deployment in the Data Center. To learn more, visit Xilinx at booths #3903 and 4003, November 17 – 20, 2014 at the Ernest N. Morial Convention Center, New Orleans, Louisiana. 

Logo - http://photos.prnewswire.com/prnh/20020822/XLNXLOGO

Presentations/Panel Participation:

  • Tuesday 11/18 at 5:30 p.m., Room 393-94-95 – Reconfigurable Supercomputing
  • Tuesday, 11/18 at 10:00 a.m., Micron booth #1949 – The Benefits of Xilinx® UltraScale™ Devices for HMC

In-Booth Demonstrations by Xilinx and its Alliance Members – Booths #3903 and #4003:

  • Key Value Store Application Acceleration
    Leveraging the Alpha Data ADM-PCIE-7V3 board, this demonstration is a broadly applicable key value store workload acceleration engine (i.e. Memcached and NoSQL) that delivers significant performance/watt acceleration at substantially lower latency.
  • NVMe Flash Storage Platform Featuring a Kintex-7 FPGA
    This demonstration is an NVMe-based flash storage solution running on a Xilinx® Kintex®-7 FPGA development platform. The solution showcases a fully compliant NVMe spec 1.1 interface.
  • Low Latency 25G/50G Ethernet MAC Connectivity Solution
    This demonstration utilizes two Virtex® UltraScale™ VCU107 boards communicating over four channels of 25G Ethernet through 5 meters of direct attached copper cable and two QSFP+ modules. The low latency 25GE MAC supports the 25G Ethernet Consortium specification.
  • Low Latency TOE for Network Acceleration from Alliance Member Intilop
    Demonstration features Intilop's 16 to 16,394 Simultaneous Connections TCP & UDP Offload Engine (TOE & UOE) and 10G MAC soft IP core running on the Alpha Data ADM-PCIE-7V3 card.
  • Software Defined Development Environment for OpenCL
    Demonstration of Xilinx's software defined development environment enabling the compilation of OpenCL applications into binaries ready for execution on FPGA devices using a standard programming environment.
  • Software Defined Development Environment for Xilinx Virtex-7 Devices
    Demonstration of OpenCL applications featuring the Alpha-Data ADM-PCIE-7V3 board based on the All Programmable Virtex-7 FPGA for the highest performance at the lowest possible power envelope.
  • Software Defined Development Environment for Kintex-7 Devices
    Demonstration featuring the Pico Computing M505-K325T acceleration board based on the All Programmable Kintex-7 FPGA, delivering unparalleled fanless performance for under 20W.

Xilinx Technology-enabled Demonstrations Throughout the SC14 Show floor:
The following Xilinx Alliance Program members will showcase a Xilinx-based technology demonstration in their SC14 booths:

  • Alpha Data – Booth #3803
    Demonstration features Alpha Data's industry-leading FPGA accelerator boards for network processing including the KU3 UltraScale card with dual 40GbE / PCIe Gen3 x16, and the 7V3 Virtex-7 card with dual 10GbE / PCIe Gen3 x8. 
  • Auviz Systems – Alpha Data Booth #3803
    Demonstrating functions from Auviz Systems' computer vision and image processing middleware IP, AuvizCV, created using Xilinx's software defined development environment for OpenCL.
  • Convey Computer – Emerging Technology Booth ET11
    Demonstrating high level programming for Convey's Virtex-7 FPGA-based Wolverine line of high performance coprocessors, with the Convey Personality Development Toolset and the Xilinx software defined development environment for OpenCL.
  • The Dini Group – Booth #528
    Showcasing scalable Kintex-7 and Virtex-7 FPGA-based solutions for high performance computing featuring the DNK7_F5PCIe board.
  • Invea-Tech – Booth #3923
    Demonstrating the world's first HPC 100GE transmit/receive data stream on xR4 PCI-e cards based on Virtex-7 HT FPGAs with 28Gbps transceivers using a commodity server.
  • Micron – Booth #1949
    Hosting HMC interoperability demos featuring Open-Silicon and Pico Computing IP on Virtex UltraScale devices.
  • Nallatech – Booth #1332
    Showcasing Nallatech's PCI-287n with dual Kintex-7 FPGAs for high performance computing and network processing applications.
  • Pico Computing – Booth # 3233
    Demonstrations include Xilinx's software defined development environment for OpenCL running in a Kontron 2U with Pico Computing's Kintex-7-powered acceleration module; Hybrid Memory Cube (HMC) IP running on Xilinx's Virtex UltraScale VCU109 device; and Pico Computing's new EX-850 Virtex UltraScale board integrating eight HMCs devices.

About Xilinx
Xilinx is the world's leading provider of All Programmable FPGAs, SoCs and 3D ICs. These industry-leading devices are coupled with a next-generation design environment and IP to serve a broad range of customer needs, from programmable logic to programmable systems integration. For more information, visit www.xilinx.com.

#1463
#AAB852
© Copyright 2014 Xilinx, Inc. Xilinx, the Xilinx logo, Artix, ISE, Kintex, Spartan, Virtex, Vivado, Zynq, and other designated brands included herein are trademarks of Xilinx in the United States and other countries. All other trademarks are the property of their respective owners.

Xilinx
Silvia E. Gianelli
(408) 626-4328
[email protected]

SOURCE Xilinx, Inc.

Related Links

http://www.xilinx.com