SUNNYVALE, CA — (Marketwired) — 05/13/13 — (NYSE: AMD) today announced availability of servers based on its AMD Open 3.0 specification, defined as part of the Open Compute Project, delivering workload versatility and performance equal to competing proprietary OEM servers at significantly lower cost. In comparison to benchmarks running virtual desktop infrastructure (VDI), the AMD Open 3.0-based system supported just as many virtual desktops and reduced total cost of ownership (TCO) by 57 percent: $4,589 versus $10,669 for just a single server. This cost effectiveness translates into a dramatic reduction in cost per virtual desktop, from $91.19 to only $38.24 per desktop. More details on the findings are available and will be discussed at a roundtable event tomorrow in New York City and other select cities. The servers will be available through distributor partners.
“Global IT organizations have the difficult task of choosing between price and performance when investing in servers,” said Bob Ogrey, cloud evangelist and fellow, AMD. “We don-t believe organizations have to compromise one for the other. Using systems based on the AMD Open 3.0 specification — the first open source, modular platform for the masses — enables high performance and energy efficiency at a reasonable price, making it the best choice for organizations.
In May 2012 AMD released the AMD Open specification, and in January 2013 demonstrated systems based on this specification for the first time. Systems are now in full production and available through a number of technology partners including Avnet Inc., Hyve, Penguin Computing and ZT Systems. The system is part of AMD-s work with the and demonstrates AMDs commitment to open industry standards, delivering the right solutions for the right problems. With the ideal combination of power, space and cost, this tailored solution is the foundation for Open Compute Server 3.0.
Powered by the high performance AMD Opteron 6300 Series processor, AMD Open 3.0 systems can be installed in all standard 19″ rack environments without modification, as well as in Open Rack environments, and managed openly using standards such as Systems Management Architecture for Server Hardware (SMASH) from the Distributed Management Task Force (DMTF). The motherboard is 16″ x 16.7″ and designed to fit into 1U, 1.5U, 2U or 3U rack height servers. It features two AMD Opteron 6300 Series processors, each with 12 memory sockets, allowing up to 384GB of DDR3 DRAM (four channels with three DIMMs each,) 6 Serial ATA (SATA) connections per board, one dual channel gigabit Ethernet NIC with integrated management, up to four PCI Express® expansion slots, one serial port, two USB ports and a mezzanine connector for custom module solutions such as the Mellanox I/O module or Broadcom management module. Specific PCI Express card support is dependent on usage case and chassis height.
AMD Open 3.0 enables substantial flexibility, efficiency and operating cost by simplifying motherboard design with a single base product to address multiple enterprise workloads, including high-performance computing, virtual desktop infrastructure, cloud, infrastructure and storage. This innovative design is optimized to eliminate features typically over-provisioned in traditional server offerings. The platform is designed to easily enable IT professionals to customize the server to meet specific workload requirements. Learn more about AMD-based Open Compute .
AMD, along with Broadcom, Quanta and others, will host an invitation-only customer and partner roundtable on May 14 in New York City. Please email if you are interested in attending.
AMD (NYSE: AMD) is a semiconductor design innovator leading the next era of vivid digital experiences with its ground-breaking AMD Accelerated Processing Units (APUs) that power a wide range of computing devices. AMD-s server computing products are focused on driving industry-leading cloud computing and virtualization environments. AMD-s superior graphics technologies are found in a variety of solutions ranging from game consoles, PCs to supercomputers. For more information, visit
You must be logged in to post a comment Login