Servers: The Right Compute
cancel
Showing results for 
Search instead for 
Did you mean: 

HPE Joins the DOE in the Race to Exascale Computing

BillMannel

 

Exascale computing is expected to dramatically increase our understanding of the world. As a PathForward vendor, HPE is working to extend the DOE’s hardware technology effort and develop a reference design for an exascale system.

In the digital age of innovation, technology is key to achieving the greatest possible speed, accuracy, and reliability required to succeed in today’s competitive global marketplace. Advancements in high performance computing (HPC) are enabling organizations across all industries to perform better, faster, and smarter than ever before. 

But is that enough?

The proliferation of billions of intelligent devices has made traditional operating systems no longer adequate to manage the sheer volume, velocity, and variety of Big Data. And with 5.5 million new devices connecting every day, the Internet of Things is placing a massive strain on even the most advanced supercomputers. The demand to process, share, store, and protect these massive datasets is leading developers to the next frontier of HPC development—exascale.

Exascale computing is crucial to managing future growth, research, and exploration. Capable of performing a million trillion operations per second, these next-generation machines will deliver unprecedented scale and processing capabilities to power the modern age. Exascale is expected to dramatically increase our understanding of the world and lead to the greatest scientific and technological breakthroughs of our time.

The question is, how do we get there?

Reaching exascale will require considerable advances in the hardware and software used to operate today’s supercomputers. As China, Japan, Russia, and other competitive nations make substantial investments in HPC, the U.S. is striving for maximum computing power and efficiency to ensure greater insights, economic vitality, national security, and competitive advantage in the years to come.

THE EXASCALE COMPUTING PROJECT

 In an effort to reach exascale, the Department of Energy (DOE) established a new project to facilitate rapid progress in the realm of HPC. The Exascale Computing PDOEBlog.jpgroject (ECP) targets the research and development of exascale machines, with the goal of delivering two complete systems by 2023. The DOE FastForward and DesignForward projects are the foundation for this initiative—FastForward focusing on memory, processing, and storage technologies and DesignForward implementing a fully integrated system to support extreme-scale computing.

The latest component of the ECP, the PathForward Initiative is geared toward the design and deployment of exascale-capable hardware.

HPE JOINING THE RACE

We are excited to announce that Hewlett Packard Enterprise (HPE) has been selected as one of four vendors for Phase I of Project PathForward. As a vendor, HPE is receiving a grant in order to extend the DOE’s hardware technology effort and develop a reference design for an exascale system.

This leap into exascale represents a significant milestone for HPE’s strategy, deep R&D capabilities, and pioneer efforts from HP Labs, as well as strong validation of HPE’s thought leadership and innovation in the HPC segment.

The HPE approach to exascale is focused on three areas of innovation: architecture, system technology, and technology ecosystem. Based on The Machine, our design boasts a memory-driven architecture that puts memory, not processing, at the center of the computing platform to realize levels of performance not found on the market today. This powerful framework addresses many concerns of exascale design, delivering application performance at scale, ensuring energy efficiency and sustainability, and increasing system reliability while reducing costs.

As part of the GenZ consortium, HPE is working to implement an industry-wide protocol which will increase the flexibility and workload optimization of the system architecture. This protocol, known as the next-generation memory interface (NGMI), is expected to dramatically increase throughput while mitigating energy usage and space consumption required by exascale.

THE FUTURE OF HIGH PERFORMANCE COMPUTING

Exascale computing promises to drive significant improvements to all industries and applications – enhancing weather and climate forecasting, oil and gas exploration, medical research, animation design, engineering design, remote simulation and data analysis, financial risk analysis, high-end equipment development, and more.

To learn more about the future of HPC and the capabilities of exascale, I invite you to follow me on Twitter at @Bill_Mannel.


Bill Mannel
VP & GM - HPC & AI Segment Solutions

twitter.gif @Bill_Mannel
linkedin.gif Bill-Mannel

0 Kudos
About the Author

BillMannel

As the Vice President and General Manager of HPC and AI Segment Solutions in the Data Center Infrastructure Group, I lead worldwide business and portfolio strategy and execution for the fastest growing market segments in HPE’s Data Center Infrastructure Group which includes the recent SGI acquisition and the HPE Apollo portfolio.

Comments
Mbithi

Good article