Intel has this week formally announced Frontera, an academic supercomputer that has been developed alongside Dell EMC. In the announcement, the company says Frontera will transform the computing capabilities of research projects with artificial intelligence (AI) tools.
Dell and Intel first revealed Frontera in August 2018, with development possible through a $60 million grant from the National Science Foundation (NSF). The supercomputer was designed to replace the Stampede2 academic computer at the University of Texas at Austin's Texas Advanced Computing Center (TACC).
Development was complete in June when the supercomputer was deployed, but only this week was it formally announced.
“The Frontera system will provide researchers computational and artificial intelligence capabilities that have not existed before for academic research,” said Intel vice president and general manager of Intel's extreme computing organization Trish Damkroger. “With Intel technology, this new supercomputer opens up new possibilities in science and engineering to advance research, including cosmic understanding, medical cures, and energy needs.”
Intel says Frontera is capable of previously unseen computational performance. At peak, the system can deliver 38.7 quadrillion floating point operations per second. This is easily the fastest supercomputer ever designed for academic use. It can handle research requirements such as big data, machine learning, and simulations.
“Featuring Dell EMC PowerEdge servers with 2nd Gen Intel Xeon Scalable processors, Frontera's 8008 compute nodes delivers peak performance of 38.75 petaflops. Frontera also features Intel Optane DC persistent memory to address the performance and memory capacity requirements of the diverse workloads run in the system, including scientific modeling and simulation, big data and artificial intelligence.”
Frontera's computational capabilities are delivered by 28-core second generation Intel Xeon Scalable CPUs working within Dell EMC PowerEdge servers. Nvidia nodes are also on tap. Intel built the processing units on its Advanced Vector Extensions 512 architecture, which allows double the number of FLOPS per clock.
“Frontera will provide scientists across the country with access to unprecedented computational modeling, simulation, and data analytics capabilities,” said NSF assistant director for computer and information science and engineering. “Frontera represents the next step in NSF's more than three decades of support for advanced computing capabilities that ensure the U.S. retains its global leadership in research frontiers.”