CloudDatacentreInnovationResearchScienceServer

Tech Firms Handed $258m To Develop Exascale Supercomputer

Tom Jowitt is a leading British tech freelance and long standing contributor to TechWeek Europe

Large chunk of money handed to tech firms from US government to develop 1,000 petaflop supercomputer

The United States continues its quest for an exascale supercomputer, as it seeks to maintain its position in high-performance computing (HPC) research and development.

The US Department of Energy (DOE) said that it has awarded a research grant to a number for firms totalling $258 million (£202m) over a three-year period.

The tech firms involved in the Exascale Computing Project (ECP) will provide additional funding amounting to at least 40 percent of their total project cost, bringing the total investment to at least $430 million (£337m).

tianhe 2 supercomputer china milkywayExascale Supercomputer

It was back in July 2015 when then President Obama first signed an executive order for a high-performance computing (HPC) initiative in the United States.

That initiative, known as the National Strategic Computing Initiative (NSCI), is designed to help the United States develop the fastest supercomputer in the world capable of running at 1,000 petaflops or one exaflop.

That NSCI project is led by three US government departments, namely the Department of Energy (DOE), the Department of Defense (DOD), and the National Science Foundation (NSF).

But now the DOE has awarded over a quarter of a billion dollars to a number of tech firms to help the US government achieve its supercomputing ambition.

The tech firms awarded the money include Advanced Micro Devices (AMD), Cray, Hewlett Packard Enterprise (HPE), International Business Machines (IBM), Intel, and NVIDIA.

“The awardees will receive funding for research and development to maximize the energy efficiency and overall performance of future large-scale supercomputers, which are critical for US leadership in areas such as national security, manufacturing, industrial competitiveness, and energy and earth sciences,” the DOE said.

“Continued US leadership in high performance computing is essential to our security, prosperity, and economic competitiveness as a nation,” said Secretary Perry. “These awards will enable leading US technology firms to marshal their formidable skills, expertise, and resources in the global race for the next stage in supercomputing – exascale-capable systems.”

“The PathForward program is critical to the ECP’s co-design process, which brings together expertise from diverse sources to address the four key challenges: parallelism, memory and storage, reliability and energy consumption,” ECP Director Paul Messina said. “The work funded by PathForward will include development of innovative memory architectures, higher-speed interconnects, improved reliability systems, and approaches for increasing computing power without prohibitive increases in energy demand.”

Delivery Timeframe

The intention is for this ECP program to deliver at least one exascale-capable system by 2021. Intel previously predicted that it would be able to provide ‘exascale’ computing performance by 2020.

However this is a very tall order, because in order to develop a machine like this, these exascale machines will need to be 10 times faster and more energy efficient than today’s fastest supercomputers.

HPE meanwhile has said that at the heart of its exascale reference design is its Memory-Driven Computing, an architecture that puts memory, not processing, at the centre of the computing platform.

“We are excited at the opportunity to provide the technical blueprint for an exascale system that will process data faster than any supercomputer available today and enable a new era of computational and scientific capabilities,” said Bill Mannel, VP and general manager, HPC Segment Solutions, HPE.

“Our novel Memory-Driven Computing architecture combined with our deep expertise in HPC and robust partner ecosystem uniquely positions HPE to develop the first US exascale supercomputer and deliver against the PathForward program’s goals,” he said.

Arms Race

But there little doubt that the United States is currently locked into something of a supercomputing arms race with one of its chief rivals, namely China.

China currently has the world’s fast supercomputer with its Tianhe-2, which delivers 33.86 petaflops.

The United States is lagging behind, as its fastest supercomputer, the Cray Titan at the Oak Ridge National Laboratory, is thought to be only capable of 15 petaflops, and is ranked in third position behind two systems in China.

That said, the US has five of the 10 fastest computers in the world, and it does retain a global leadership in the actual application of high performance computing to national security, industry, and science.

But Exascale systems will be at least 50 times faster than the nation’s most powerful computers today, and typically would be capable of performing one million trillion floating-point operations per second.

Quiz: Think you know all about supercomputers?