PAW is a comprehensive resource provisioning and workflow tool that automates the steps of
dynamically provisioning a large scale cluster environment in the cloud, executing a set of jobs or a custom workflow and, after the jobs have completed, de-provisioning the cluster environment in a single operation. A key characteristic of PAW is that it separates the provisioning of cluster resources in the cloud from the management of scientific workflow on these resources, which enables fine-grained decisions about performance and cost tradeoffs in a commercial cloud environment.

Related Publications:

• AWS Blog: Natural Language Processing at Clemson University – 1.1 Million vCPUs & EC2 Spot Instances
• MTAGS’17 paper: Brandon Posey, Christopher Gropp, Alexander Herzog, Amy Apon.
  “Automated Cluster Provisioning And Workflow Management for Parallel Scientific
  in the Cloud ”, 10th Workshop on Many-Task Computing on Grids and Supercomputer
  (MTAGS’17), held in conjunction with the International Conference for High Performance
  Computing, Networking, Storage, and Analysis (SC’17). Denver, November, 2017.

Supplemental Downloads

• Software and Template samples download: pawSourceCode.tar Users of PAW, please cite the MTAGS’17 paper (above).