Jump to content

TOSS (operating system)

From Alfawiki
Tri-Lab Operating System Stack (TOSS)
Company typeLinux distribution
IndustryHigh performance computing software
Headquarters
United States
Area served
National Nuclear Security Administration laboratories, NASA High-End Computing Capability Project
ProductsLinux distribution for HPC clusters

The Tri-Lab Operating System Stack (TOSS) is a Linux distribution derived from Red Hat Enterprise Linux (RHEL), created to establish a standardized software stack for high performance computing (HPC) clusters at laboratories under the National Nuclear Security Administration (NNSA). This operating system allows multiple smaller systems to operate together as a cohesive HPC environment.

Linux distribution

The term "tri-lab" signifies the three principal NNSA laboratories: Lawrence Livermore National Laboratory, Los Alamos National Laboratory, and Sandia National Laboratories.

TOSS serves as the operating system for NNSA infrastructures, including the El Capitan supercomputer and ARM-based architectures such as the ThunderX2 system on a chip (SoC). Additionally, in March 2022, the majority of systems within NASA's High-End Computing Capability Project, part of the NASA Advanced Supercomputing Division, transitioned to using TOSS.

This OS integrates numerous packages from the RHEL software repository and supplements them with additional RPMs compiled through Fedora's Koji build infrastructure. For workload scheduling and resource allocation, TOSS utilizes both SLURM and Flux.