Demo Includes Cache Coherent Acceleration for NFV Platforms
DENVER — (BUSINESS WIRE) — November 13, 2017 — The CCIX™ Consortium today announced the first industry demonstration of a CCIX product at the SC17 Conference in Denver, Colorado. The Consortium is missioned to develop and promote adoption of an industry standard specification that enables coherent interconnect technologies between general-purpose processors and acceleration devices.
This first CCIX product demo will show cache coherent packet forwarding acceleration for network function virtualization (NFV) platforms, based on a CCIX capable CPU and Xilinx FPGA CCIX accelerator. CCIX greatly simplifies the data movement architecture between host and accelerators, resulting in faster movement of data. The demonstration will take place at the Xilinx booth no. 681, all week, during exhibit hours.
Additionally, to learn more about the CCIX Consortium, at the Mellanox Technologies Theater (booth 653) on Thursday, November 16 at 2:00 pm, Jon Masters of Red Hat will present an overview of the CCIX technology.
“The industry’s first demonstration of CCIX is a major step toward broader adoption of CCIX, which aims to enhance performance, efficiency, and scalability for the next generation of high-performance, artificial intelligence, cloud, telco and other data centers,” said Gilad Shainer, CCIX president. “By leveraging the large eco-system of PCIe®, CCIX provides users with the capabilities to analyze more data faster and to gain a competitive advantage on one side, while minimizing the cost of new technology adoption.”
“We are excited to highlight the capabilities offered by CCIX at the Supercomputing’17 Conference,” said Gaurav Singh, CCIX Chairman. “The demo we will be showcasing at the Xilinx booth represents a true milestone for the future of data center system design and CCIX specification implementation and adoption.”
“One of the biggest advantages of CCIX is that it builds on the existing PCIe infrastructure, which dramatically reduces the cost and risk of integrating it with existing products,” said Jeff Defilippi, senior product manager, Infrastructure Line of Business, Arm and CCIX Consortium treasurer. “Additionally, CCIX-based systems enable cache coherent driverless acceleration and speeds of up to 25 GT/s that are needed in today’s cloud and edge computing solutions.”
About the CCIX Specification
The CCIX specification enables seamless system integration between processors such as x86, Arm and POWER and all accelerator types, including FPGAs, GPUs, network accelerators, and storage adaptors - even custom ASICs can be incorporated into a CCIX topology. CCIX also gives system designers the flexibility to choose the right combination of heterogeneous components from many different vendors to deliver optimized configurations for the data center.
About CCIX Consortium, Inc.
CCIX was founded to enable a new class of interconnect focused on emerging acceleration applications such as machine learning, network processing, storage off-load, in-memory database and 4G/5G wireless technology. The standard allows processors based on different instruction set architectures to extend the benefits of cache coherent, peer processing to a number of acceleration devices including FPGAs, GPUs, network/storage adapters, intelligent networks, and custom ASICs. CCIX simplifies the development and adoption by extending well-established data center hardware and software infrastructure. This ultimately allows system designers a seamlessly integrate the right combination of heterogeneous components to address their specific system needs. For more information, please visit https://www.ccixconsortium.com/.
Rachel Weikum, +1-503-970-4869