HPC via HTTP: Portable, Scalable Computing Using App
Containers and the Agave API
Presenters
Event Type
Tutorial
System Administration
TimeMonday, November 13th8:30am -
12pm
Location203
DescriptionSupercomputing matters. So does user experience.
Standing between the mainstream adoption of
supercomputing and a new generation of users is the
reality that the entry cost to using these systems, both
in terms of dollars and in time spent learning the
technology, has not significantly changed in the last 20
years. The rise of cloud computing only complicates the
learning curve further. Over the last 6 years, the
authors have been addressing this gap through the
development of a Science-as-a-Service platform enabling
users to go from their desktop, to their local data
center, to the cloud, and back without sacrificing their
existing tool chain or user experience.
In this tutorial, we combine best practices and lessons learned while on-boarding the last 70k new users to TACC's data center through the Agave Platform. Participants will walk through the process of scaling their application from a local environment to the Jetstream academic cloud and to an HPC at the Texas Advanced Computing Center. They will learn to use multiple container technologies to harmonize app execution between cloud and HPC resources, and they will learn to use modern APIs to orchestrate job execution, capture provenance information, and foster collaboration.
In this tutorial, we combine best practices and lessons learned while on-boarding the last 70k new users to TACC's data center through the Agave Platform. Participants will walk through the process of scaling their application from a local environment to the Jetstream academic cloud and to an HPC at the Texas Advanced Computing Center. They will learn to use multiple container technologies to harmonize app execution between cloud and HPC resources, and they will learn to use modern APIs to orchestrate job execution, capture provenance information, and foster collaboration.
Links
