Intel Demos Future of HPC and Artificial Intelligence Capabilities

As new digital economies continue to rise across industries from biomedicine research to autonomous driving, generating a plethora of data, there is a great demand for high-performance computing (HPC) to advance systems for scalability and agility to support optimal data use in compute, storage, memory, network and security.


At the 2017 International Supercomputing Conference (ISC 17), Intel demonstrated that to manage these diverse workloads efficiently, HPC systems will need to evolve to enable new levels of performance, scalability, memory bandwidth and I/O capabilities. Intel discussed how new approaches to HPC system design and flexible delivery models are enabling users to get more value from HPC than ever before.

At ISC 17, Intel disclosed its latest developments to further advance HPC systems and transform new experiences for supercomputing users. Intel explained how its upcoming Intel® Xeon® Scalable processors, with significant per-core performance enhancements and other advancements, support a wide range of workloads. Through its integration of the Intel® Advanced Vector Extensions 512 (Intel® AVX-512), the platform generates 2X FLOPs/clock-cycle peak improvements, offering a boost to performance for demanding use.1 Intel AVX-512 combined with improvements in cores, cache and memory, delivers up to 2.27x more performance than today’s Intel Xeon processor E5 v4 (formerly codenamed Broadwell)2, and up to 8.2x more double precision GFLOPS/second when compared to a 4-year old Intel Xeon processor E5 family in the installed base.3 In addition, the Intel® Omni-Path Architecture (Intel® OPA), a high-bandwidth and low-latency fabric for performance optimization, is integrated with the Intel Xeon Scalable processors to deliver the performance for today’s HPC workloads and ability to scale to tens of thousands of nodes while benefiting from improved total cost of ownership.

Intel also announced Intel’s SDVis Appliance (Software Defined Visualization Appliance), an integrated turnkey solution based on an open standard foundation that allows HPC users to gain benefits of a developed software ecosystem without having to construct the hardware system themselves or work with vendors to customize the configuration.

Intel made significant advancements in the Top500 list of supercomputers with 110 new systems including three systems based on the upcoming Intel Xeon Scalable processors. The industry’s rapid adoption of Intel OPA continues to accelerate with 36 percent more Top500 systems than the previous list issued November 2016. In addition, systems utilizing Intel OPA in the June 2017 Top500 list have delivered a 54 percent increase in performance as a result.

At the show, Intel’s HPC experts Rajeeb (Raj) Hazra and Patricia (Trish) A. Damkroger delivered a joint keynote sharing Intel’s plans to further advance HPC systems with built-in high-performance data analytics by combining traditional HPC with artificial intelligence (AI). They explained that by integrating Intel’s upcoming products targeted for AI applications, HPC systems can deliver faster workloads at a lower cost. Intel’s commitment is to transform HPC to become a key foundation for driving new digital services and experiences, while delivering reliability and efficiency.

Following the keynote, Pradeep Dubey, an Intel Fellow at Intel Labs, discussed in-depth the growing value of AI and Intel’s AI technology portfolio, which is accelerating adoption across a broad range of industries.

In addition, Intel showcased the following technologies for high-performance computing and artificial intelligence at its booth #F-930:

•Drug screening with artificial intelligence powered by Intel® Xeon Phi™ processors
•Intel Xeon Phi processor developer access program
•Software-defined visualization tools to increase efficiency
•Intel field programmable gate arrays enabling efficient CPU access to pooled storage