RapidIO.org announces ARM 64-bit Coherent Scale Out Task Group to Specify RapidIO as a Unified Coherent Fabric for Data Center Analytics and High Performance Computing

AMD and ARM join RapidIO.org to participate in the RapidIO specification development 

  AMD logo                 RapidIO logo ARM logo

Linley Processor Conference, Santa Clara, CA, October 22, 2014RapidIO.org, the organization that promotes and develops standards for the RapidIO interconnect architecture, announced today that AMD and ARM have joined the RapidIO.org community to collaborate with RapidIO.org member companies in the development of an open specification for multi-node / core coherent scale out of 64-bit ARM® processors using RapidIO as a coherent unified fabric.

Market and industry trends are changing the way enterprises and communications infrastructure carriers approach their data center and computing strategies. Many enterprises are looking to virtualization, fabric-based infrastructure and scalable modular designs as they explore how best to optimize their resources.  In order to meet this challenge, carriers have started to leverage datacenters to help create these services bridging the traditional gap between datacom and telecom networks to form a more unified network. This unified datacenter-network paradigm is being deployed by extending virtualization technologies such as software-defined networking (SDN) and Network Function Virtualization (NFV) into the carrier network domain delivering improved overall end-to-end network utilization and operational efficiencies.

This type of overall system flexibility is at the very core of RapidIO as the specification assumes there are multiple master, heterogeneous processors in a system needing to communicate with each other through shared memory, interrupts and messages.  Also, RapidIO based systems can include up to 64K processors, each with their own complete address space and supporting north/south, east/west peer-to-peer transactions within a RapidIO fabric.  Creating an open specification for multi-node / core coherent scale out of 64-bit ARM processors using RapidIO as a coherent unified fabric will extent the utility of RapidIO even further.

A dedicated ARM 64-bit Coherent Scale Out task group has been formed within the RapidIO.org Technical Working Group and includes the following founding task group member companies:

        • AMD, ARM, Cavium, Freescale, IDT, IIT Madras, Mercury Systems, Mobiveil, Texas Instruments and Xilinx.

“It is clear data center and performance critical computing customers in communications infrastructure and datacenter analytics applications require open, multi vendor, industry standards based, low latency multiprocessor unified fabrics” said Rick O’Connor, Executive Director of RapidIO.org, “We are very pleased to have the support of both AMD and ARM as they join our strong RapidIO.org ecosystem to help drive this important ARM 64-bit Coherent Scale Out initiative.”

“AMD is a technology leader in communications infrastructure, industrial automation, data center and high performance computing,” said Greg Shippen, Fellow and Chief Architect at AMD.  “We’re excited to participate in developing a specification for 64-bit ARM clusters over a unified RapidIO coherent scale out fabric.”

“As communications infrastructure technologies continue to merge with data center technologies there is an increasing need to build scalable heterogeneous systems,” said Charlene Marini, vice president of marketing, embedded segments, ARM. “We are proud to support this RapidIO initiative to specify a coherent scale out of ARM technology over RapidIO and further extend the ARM ecosystem into the broader infrastructure market.”

The RapidIO.org ARM 64-bit Coherent Scale Out Task Group is responsible for developing a specification for multicore cluster scale out of 64-bit ARM cores with the following functionality:

      • Coherent scale out of a few 10s to 100s cores & 10s of sockets
      • ARM AMBA® protocol mapping to RapidIO protocols
            • AMBA 4 AXI4/ACE mapping to RapidIO protocols
            • AMBA 5 CHI mapping to RapidIO protocols
      • Migration path from AXI4/ACE to CHI and future ARM protocols
      • Support for GPU/DSP floating point heterogeneous systems
      • HW hooks and definition to support RDMA, MPI, secure boot, authentication, SDN, Open Flow, Open Data Plane, etc

RapidIO.org is issuing an open industry call for participation in the ARM 64-bit Coherent Scale Out task group to companies interested in supporting the development of this important performance critical computing specification.

About RapidIO

The RapidIO unified fabric architecture, designed to be compatible with the most popular integrated host processors, communications processors, and digital signal processors, is a high-performance, packet-switched, interconnect fabric. RapidIO addresses performance critical computing needs in Data Center & HPC, Communications Infrastructure, Industrial Automation and Military & Aerospace markets offering high reliability, increased bandwidth, and low latency in an intra-system fabric. RapidIO provides chip-to-chip, board-to-board and shelf-to-shelf peer-to-peer connectivity at performance levels scaling to 100s of Gigabits per second and beyond. RapidIO.org, a non-profit corporation controlled by its members, directs the future development and drives the adoption of the RapidIO unified fabric architecture.  Learn more at www.rapidio.org.

About AMD

AMD (NYSE: AMD) designs and integrates technology that powers millions of intelligent devices, including personal computers, tablets, game consoles and cloud servers that define the new era of surround computing. AMD solutions enable people everywhere to realize the full potential of their favorite devices and applications to push the boundaries of what is possible. For more information, visit www.amd.com.

About ARM

ARM is at the heart of the world’s most advanced digital products. Our technology enables the creation of new markets and transformation of industries and society. We design scalable, energy efficient-processors and related technologies to deliver the intelligence in applications ranging from sensors to servers, including smartphones, tablets, enterprise infrastructure and the Internet of Things.

Our innovative technology is licensed by ARM Partners who have shipped more than 50 billion System on Chip (SoCs) containing our intellectual property since the company began in 1990. Together with our Connected Community, we are breaking down barriers to innovation for developers, designers and engineers, ensuring a fast, reliable route to market for leading electronics companies. Learn more and join the conversation at http://community.arm.com.

Tags: