Although microprocessors based on the Arm architecture are prevalent in cellphones, automobile electronics, and other embedded applications, they have failed to provide the performance needed to make them viable for high-performance computing applications.
One of the first supercomputers - Astra - is predicted to be deployed at Sandia National Laboratories in late summer. This supercomputer uses processors that are based on the Arm design in a large-scale, high-performance computing platform.
Now, the U.S. Department of Energy’s National Nuclear Security Administration has declared that Astra, which is the first of a promising series of sophisticated architecture prototype platforms, will be installed as part of the Vanguard program. Under this program, the viability of evolving high-performance computing architectures will be evaluated as production platforms in order to support NNSA’s goal to improve and maintain the effectiveness, security, and safety of the U.S. nuclear stockpile.
The Astra supercomputer will be based on the newly announced Cavium Inc.’s ThunderX2 64-bit Arm-v8 microprocessor. The platform will precisely include 2,592 compute nodes, of which each node is a 28-core, dual-socket and will be at a hypothetical peak of over 2.3 petaflops, which are comparable to 2.3 quadrillion (thousand trillion) floating-point operations (FLOPS), or calculations, for every second. Although being the fastest is not one of the objectives of the Vanguard program or Astra in general, just one Astra node is about one hundred times faster when compared to a contemporary Arm-based cellphone.
“One of the important questions Astra will help us answer is how well does the peak performance of this architecture translate into real performance for our mission applications,” states Mark Anderson, program director for NNSA’s Advanced Simulation and Computing program, which funds Astra.
A First Step for Vanguard
Emerging architectures come with many challenges. Since the NNSA has not previously deployed high-performance computing platforms based on Arm processors, there are gaps in the software that must be addressed before considering this technology for future platforms much larger in scale than Astra.
Scott Collis, Director of Sandia’s Center for Computing Research
As part of a multiple lab association, scientists expect continually enhancing Astra and future platforms.
Sandia researchers partnering with counterparts at Los Alamos and Lawrence Livermore national laboratories expect to develop an improved software-and-tools environment that will enable mission codes to make increasingly effective use of Astra as well as future leadership-class platforms. The Vanguard program is designed to allow the NNSA to take prudent risks in exploring emerging technologies and broadening our future computing options.
Ken Alvin, Senior Manager of Sandia’s extreme scale computing group
The Astra supercomputer will be deployed at Sandia in an extended portion of the building, which initially housed the novel Red Storm supercomputer.
In addition, the Astra platform will be deployed in association with Hewlett Packard Enterprise and Westwind Computer Products Inc.
“Astra, like Red Storm, will require a very intimate collaboration between Sandia and commercial partners,” states James Laros, Vanguard project lead. “In this case, all three NNSA defense labs will work closely with Westwind, HP Enterprise, Arm, Cavium and the wider high-performance computing community to achieve a successful outcome of this project.”
The name Astra comes from the Latin phrase “per aspera ad astra,” which means “through difficulties to the stars.”
“The development of a scalable Arm platform based on the HPE Apollo 70 will become a key resource to expand the Arm high-performance computing ecosystem. Westwind is honored to be entrusted by Sandia, in its continued commitment to developing small businesses here in New Mexico, to implement such an important project.”
— Steve Hull, president of Westwind Computer Product
“By delivering the world’s largest Arm-based supercomputer featuring the HPE Apollo 70 platform, a purpose-built architecture that includes advanced performance and storage capabilities, we are enabling the U.S. Department of Energy and National Nuclear Security Administration to power innovative solutions for energy and national security uses.”
— Mike Vildibill, vice president of the Advanced Technology Group at HPE
“Arm has been deeply engaged with Sandia National Laboratories working to comprehend and deliver on the needs of the high-performance computing community. We are eager to support the Vanguard program as a key milestone deployment for Arm and our partners, delivering on a shared vision to spur innovation in this critical domain.”
— Drew Henry, senior vice president and general manager of Arm’s Infrastructure Business Line
“Cavium is pleased to partner with Sandia National Laboratories to enable the Arm-v8-based high-performance computing cluster as part of the Vanguard program. Vanguard is an additional proof point regarding readiness and maturity of ThunderX2 processors for large-scale deployments and will further accelerate the entire computing ecosystem on the Arm server architecture.”
— Gopal Hegde, vice president and general manager of the Data Center Processor Group at Cavium
Source – http://www.sandia.gov/