Newswise — LOS ALAMOS, N.M., Aug. 2, 2021- As the HPC community enters an era in which computation can be offloaded to storage devices, it is important to explore the mechanisms for using and programming these processing offloads. To this end, Los Alamos National Laboratory  and NGD Systems are partnering through Los Alamos’ Efficient Mission Centric Computing Consortium (EMC3) to explore scalable computational storage offloads for ultrascale High Performance Computing (HPC) simulation environments. 

“Computational storage devices become a key source of acceleration when we are able to directly interpret the data within the storage device,” said Brad Settlemyer, senior scientist in Los Alamos’ HPC Design Group. “With that component in place, near-storage analytics unleashes massive speedups via in-device reduction and fewer roundtrips between the device and host processors.”

Computational offloads using both in-network processing and near-storage compute are becoming an important part of both scale-up and scale-out computing, with future scaling requirements virtually requiring programmable elements along the data path to achieve performance efficiency goals.

“NGD’s versatile computational storage platform makes it easy to try new concepts for offloading functions to near storage,” said Vladimir Alves, chief technology officer at NGD Systems. “By offering an OS-based storage device, with on-board applications processors in our NVMe SSD ASIC solution, we offer partners like Los Alamos the ability to try many different paths to a more complete solution with a simple and seamless programming and device management model.”

In addition to the effort to explore computational storage offloads, Los Alamos has partnered with NGD Systems to focus on building a curriculum for a set of summer internship programs in using NGD’s Newport Computational Storage Drives to accelerate data analytics.

“Los Alamos is happy to see the evolution of computational offloads towards standards-based computational storage technology, and is hopeful explorations into use cases for this technology will bear fruit for the HPC and at-scale computing environments,” said Gary Grider, HPC division leader at Los Alamos.  “We look forward to continued partnership with NGD Systems in efficient computing via the Efficient Mission Centric Computing Consortium.”

About the collaboration

This collaborative effort is sponsored by Los Alamos’ EMC3, which focuses on applying efficient computing architectures, system components, and environments to the real-world workload mixes that result from mission-centric work. This focus on efficiency seeks to improve application performance, workflows, and code efforts for better exploitation of current and future systems and workflow software and computer platforms, while maintaining a proper balance of compute, memory size, memory bandwidth and latency, performance, and I/O throughout. 

EMC3 has nearly 20 members now, including national and international partners. 

About Los Alamos National Laboratory (www.lanl.gov):

Los Alamos National Laboratory, a multidisciplinary research institution engaged in strategic science on behalf of national security, is operated by Triad a public service oriented, national security science organization equally owned by its three founding members: Battelle Memorial Institute (Battelle), The Texas A&M University System (TAMUS), and The Regents of the University of California (UC) for the Department of Energy’s National Nuclear Security Administration.

Los Alamos enhances national security by ensuring the safety and reliability of the U.S. nuclear stockpile, developing technologies to reduce threats from weapons of mass destruction, and solving problems related to energy, environment, infrastructure, health, and global security concerns.

About NGD Systems: (www.NGDSystems.com)

NGD Systems enables infrastructure success and growth by delivering the industry’s most innovative Computational Storage NVMe SSDs in the largest capacity and most power-efficient storage products available. This provides an increase in system-level performance for near-real-time processing at the edge where data is generated. The Newport Platform uses a patented In-Situ Processing solution, to radically reduce the bandwidth required to analyze mass data sets and reduces the strain on customer infrastructure. NGD Systems’ Computational Storage products enable compute anywhere without moving data from storage devices, overcoming challenges that current system architectures cannot solve. NGD Systems’ breakthrough technology is ideal for hyperscale environments, edge computing and AI/data analytic applications.

Founded in 2013 with headquarters in Irvine, Calif., NGD Systems has focused its breakthrough technology will fundamentally change the IT Industry by bringing compute to storage in ways never implemented before.

LA-UR-21-27450