A new system architecture from Intel promises to bring high performance computing to more enterprise workloads. The company said that the new technology will make high performance capabilities (HPC) available to more industries and more types of users.
The new Omni-Path architecture (OPA) is a series of upgrades to the chipmaker’s Scalable System Framework (SSF). Intel added that Omni-Path improves the performance of HPC applications for entry level to large-scale HPC clusters.
The framework combines next-generation Intel Xeon processors and Intel Xeon Phi processors, Intel OPA, silicon photonics, innovative memory technologies, and the Intel Lustre parallel file system, along with the ability to efficiently integrate them into a broad spectrum of system solutions, the company said.
Designed specifically for HPC, the Intel Omni-Path Host Fabric Interface (Image: Omni-Path OPA HFI) uses an advanced connectionless design that delivers performance that scales with high node and core counts, making it the ideal choice for the most demanding application environments, according to the company.
If Intel’s claims are true, Omni-Path could make supercomputing capabilities available to almost any user. Once only available to governments and university researchers doing work on complex problems like genome sequencing, supercomputing has gradually expanded as the computing demands of other sectors have grown.
A New Era of Supercomputing?
The advent of big data analytics and the workloads that accompany them have only increased the demand for supercomputing abilities in industries such as financial services and healthcare.
"We're entering a new era in which supercomputing is being transformed from a tool for a specific problem to a general tool for many," said Charlie Wuischpard, vice president and general manager of HPC Platform Group at Intel. "System-level innovations in processing, memory, software and fabric technologies are enabling system capabilities to be designed and optimized for different usages, from traditional HPC to the emerging world of big data analytics and everything in between."
SSF will make it possible to increase accessibility to HPC by allowing more scalable, flexible, and balanced HPC systems to be built, according to the company. The framework will also help simplify the procurement, deployment, and management of HPC systems for workloads such as data-driven analytics, visualization, and machine learning.
The new SSF architecture helps run divergent workload types that stress different parts of a system, such as compute, memory, I/O, etc., by optimizing the performance of a variety of workloads. SSF will also provide a consistent platform for HPC system deployments in cloud environments.
New Processor on the Way
The company also has its server partners onboard. Companies such as Dell, Cray, Fujitsu Systems Europe, Lenovo, and other server manufacturers will be announcing the launch of new switches and server platforms based on Intel’s new SSF architecture next year. Volume shipments are expected to begin in the first quarter of 2016. For its part, Intel will be providing partners with reference architectures, designs and validation tools.
Intel also announced that preproduction versions of its new Xeon Phi processors are already running in several supercomputing-class systems. Cray has a system currently running multiple customer applications in preparation for the supercomputer deployments at Los Alamos (Trinity system) and NERSC (Cori system). Systems using the Xeon Phi processors are also already installed at CEA (the French Alternative Energies and Atomic Energy Commission) and at Sandia National Laboratories.
Intel expects more than 50 system providers to have the Xeon Phi product family-based systems in the market when the processor officially launches.
Read more on: Intel
, Big Data
, Enterprise IT
, Technology News
, Top Tech News