When your organization needs the resources of a high-performance computing system, speed is everything. Whether it’s a traditional HPC modeling and simulation workload or an emerging one like big data analytics or machine learning, time to insight depends on your ability to deploy a leading-edge system that supports the software you rely on and gives you scalability for the future.
At Intel, we understand these needs, and we are working to meet them with Intel Scalable System Framework (Intel SSF). Intel SSF uses recommended combinations of Intel hardware and software products to enable HPC systems to achieve exceptional performance and to efficiently and reliably scale to increasingly larger system sizes.
At the ISC High Performance conference in Frankfurt, which takes place June 19 – 23, we’re announcing the introduction of Intel SFF configurations for high-performance, balanced systems with broad application compatibility. These configurations use recommended combinations of components, including Intel® Xeon® processor E5-2600 v4 product family, Intel® Xeon Phi™ processors, Intel® Omni-Path Fabric, and Intel® Ethernet Adapters (1Gbit or higher). Get more specifics at intel.com/ssfconfigurations
Thanks to the continued support of our ecosystem partners, the momentum for Intel SFF is growing. At the ISC High Performance conference, we will also announce the growth of the Intel SSF ecosystem to 31 partners. This group includes 19 system providers and 12 independent software vendors.
Ultimately, Intel SFF will lead to a broad application catalog of tested HPC apps that the community can use with the confidence that the software will run well on a system using an Intel SSF configuration. This is one of the benefits of having validated system configurations that software developers can leverage to verify the performance of their applications.
And, of course, Intel SFF is gaining momentum from advances in foundational Intel technologies, including the new Intel® Xeon Phi™ processors (formerly code named Knights Landing). With up to 72 cores, these next-generation processors are built to deliver breakthrough performance for highly parallel workloads.
Let’s take an example from a groundbreaking HPC initiative. Intel Xeon Phi processors will be used in the next-generation Stampede 2 supercomputer at Texas Advanced Computing Center (TACC). The system will also incorporate a future generation of Intel Xeon processors. Stampede 2 will serve as a strategic national resource to provide HPC capabilities for thousands of researchers across the United States.
Stampede 2 will deliver peak performance of up to 18 petaflops. That’s more than twice the overall performance of the current Stampede system, which has run more than 7 million simulation and data analysis jobs for tens of thousands of users. Stampede 2 will be fueled by a just-announced $30 million award from the National Science Foundation and will be deployed by TACC in conjunction with partners Dell, Intel, and Seagate.
From my perspective, it’s particularly gratifying to see world-class supercomputing projects like TACC leveraging the technologies in Intel SSF to accelerate innovation across a wide range of research and development, from scientific theory to applied work that will bring near-term benefits to society as a whole. Every day, researchers working with TACC demonstrate how technology can fuel insight that drives big breakthroughs.
For a closer look at Intel Scalable System Framework, the Intel SSF Architecture Specification, and the latest Intel SSF reference designs, visit intel.com/ssf.