The goal of the Argo project is to augment and optimize existing OS/R components for use in production HPC systems, providing portable, open source, integrated software that improves the performance and scalability of and that offers increased functionality to exascale applications and runtime systems.
We are developing software techniques to enable applications and runtime systems to make the best use of the capabilities of complex new memory types being incorporated into exascale node designs.
Dynamic power management is expected to be critical in the exascale era. We employ hierarchical power management that includes both system-global and node-local mechanisms and policies.
We divide physical resources on compute nodes into separate partitions called slices, separating individual components of parallel workloads, in addition to cordoning off system services.
Argo is a collaborative project between Argonne National Laboratory and Lawrence Livermore National Laboratory. It is funded by the U.S. Department of Energy as part of the Exascale Computing Project (ECP).