Advanced Micro Devices is demonstrating its upcoming next-generation Opteron X APU running Fedora Linux, a move that company officials expect will help persuade more organizations to move their servers to the x86 APU architecture.
AMD is showing off the new server chip, code-named “Berlin,” at Red Hat Summit 2014 in San Francisco April 16. The Fedora Project is a community-based Linux distribution sponsored by Red Hat.
The Opteron X chips are the first server processors based on AMD’s accelerated processing unit (APU) technology—silicon with tightly integrated CPU and graphics technology on the same chip—and the first to offer Heterogeneous System Architecture (HSA) features, according to AMD officials. In addition, the demonstration offers a proof point in the efforts by AMD and other members of the HSA Foundation to build a strong software and service ecosystem around the architecture.
“As servers adapt to new and evolving workloads, it’s critical that the software ecosystem support the requirements of these new workloads,” Suresh Gopalakrishnan, corporate vice president and general manager of AMD’s Server Business Unit, said in a statement. “We are actively engaged with a broad set of partners in the data center software community who are bringing to market the software infrastructure to seamlessly enable x86 APU-based servers.”
The demonstration is aimed at convincing organizations interested in making the move to x86 APU servers but that might be reluctant to bring new software tools and platforms into their data centers, according to AMD officials.
Much of AMD’s work in the past around its APU technology focused on chips for desktop PCs, notebooks and, more recently, embedded systems. It’s now expanding into the server space as part of AMD’s heterogeneous computing push—creating computing platforms that leverage both CPUs and GPUs, depending on the workload, and the ability to easily move those workloads between the two. Proponents say heterogeneous processing will help companies meet the growing demand for more compute power and better energy efficiency in servers that is being fueled by such trends as cloud computing, big data, mobility, video and virtualization.
Roger Kay, principal analyst for Endpoint Technologies Associates, noted in a blog post in Forbes that systems-on-a-chip (SoCs) put much of the computing components—from the graphics and central processing to security, memory controller and I/O—on the same chip.
“In a unified architecture, all these elements are ‘aware’ of each other and balanced properly, which delivers benefits in both computing speed and power consumption,” Kay wrote. “Executing a task on the right sort of engine is faster and more efficient.”
Berlin and other AMD chips—such as “Kaveri,” for PCs—will be built on HSA Foundation specifications, which include the ability to view the GPU and the CPU as a single processor and to move the workloads to whichever one is needed. In addition, programmers will no longer need to be concerned with determining whether the software will run on the CPU or GPU; the system will make the decision. GPUs also will get more access to memory.
The HSA Foundation was launched in 2012 by AMD, ARM and other vendors to create standards for heterogeneous computing. At the company’s developer summit in November 2013, AMD officials and others spoke about the need to bring developers into the fold and create a software ecosystem that supports heterogeneous processing. Included in the demonstration at the Red Hat Summit will be new features developed in Project Sumatra, an open-source project with Oracle that enables Java developers to leverage the GPU capabilities in the APUs.
Having both Linux and Java running on the AMD APU platform will help showcase how HSA-based Opteron APUs can lead to server environments that efficiently process workloads in both general-purpose and multimedia environments, according to AMD officials. The chip vendor also will demonstrate software based on OpenCL and OpenGL running on Berlin.