Particle physics laboratory

National Laboratory and Los Alamos Pavilion Partner to Explore Scan Offloads to Computer Storage Arrays

Pavilion HyperOS with HyperParallel Flash Array enables analytical offloads

SAN JOSE, CA., May 25, 2022 /PRNewswire/ — Pavilion™ Data Systemsa leading provider of data analytics acceleration platforms and a pioneer of NVMe-Over-Fabrics (NVMe-oF), today announced a partnership with Los Alamos National Laboratories (LANL) to co -Develop and evaluate crawl acceleration by offloading crawl functions from server storage to the storage array, minimizing data movement by enabling data reduction near storage.

LANL moves its I/O from a file-based to a record-based or column-based, allowing analytics to be performed using tools from the Big Data/Analytics community. LANL has shown 1000X speedups on scanning functions by leveraging data reduction near storage devices via their DeltaFS technology. Developing standards and commercializing storage capabilities to help take advantage of storage-near analytics is at the heart of the Pavilion/LANL partnership.

“For decades, our large-scale physics simulations used file-based I/O because those simulations were suited for disk-based parallel file systems,” said Gary Grider, Head of the High Performance Computing Division at LANL. “File-based I/O had obscured the inherent data structure of these files. Moving to record/column-based I/O exposes the data structure, allowing for analysis. Leveraging Technology of the Big Data/Analytics community is a natural way to achieve this, and partnering with industry to explore this at an extreme scale is the basis of this partnership with Pavilion.”

“We are thrilled to partner with LANL on this high-performance innovation, as together we explore the use of HyperOS™ functionality to enable analyzes offloaded from large-scale scientific applications,” said Dario ZamarianPavilion CEO.

Pavilion HyperOS data processing algorithms combined with the performance density of the Pavilion HyperParallel™ Flash Array provide high-performance computing array capacity for large-scale analytical offloads.

About Los Alamos National Laboratory

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

Los Alamos strengthens 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 addressing issues related to energy, environment, infrastructure, health and global security issues.

About Pavilion Data Systems

Pavilion provides the data analytics acceleration platform that enables organizations to extract greater value from their data, faster, simpler and at scale. We are the perfect complement for AI/ML, HPC, analytics, edge and other data-driven workloads and the ideal data I/O platform for platforms GPU-based computing. The Pavilion HyperParallel Data Platform, powered by Pavilion HyperOS, delivers unmatched performance and density, ultra-low latency, and unlimited scalability and flexibility, giving customers unprecedented choice and control. Find out why Fortune 500 companies and federal government agencies choose Pavilion. To visit pavilion.ioand follow Pavilion on LinkedIn, Twitterand Facebook.

[email protected]

SPRINGS pavilion