TaskVine

TaskVine is our third-generation workflow system for building scalable data intensive applications that run on HPC clusters, cloud services, and other clusters.

TaskVine logo

TaskVine is a task scheduler for building large scale data intensive dynamic workflows that run on HPC clusters, GPU clusters, and commercial clouds. As tasks access external data sources and produce their own outputs, more and more data is pulled into local storage on workers. This data is used to accelerate future tasks and avoid re-computing exisiting results. Data gradually grows “like a vine” through the cluster. TaskVine is our third-generation workflow system, built on our twenty years of experience creating scalable applications in fields such as high energy physics, bioinformatics, molecular dynamics, and machine learning.

Related Publications

  1. Reshaping High Energy Physics Applications for Near-Interactive Execution Using TaskVine
    Barry Sly-Delgado, Ben Tovar, Jin Zhou, and Douglas Thain
    In ACM/IEEE Supercomputing, 2024
  2. Poster: Leveraging Intermediate Data Management with Parsl/TaskVine
    Colin Thomas and Douglas Thain
    In Greater Chicago Area Systems Research Workshop, 2024
  3. Poster: Reshaping High Energy Physics Applications for Near-Interactive Execution Using TaskVine
    Barry Sly-Delgado and Douglas Thain
    In Greater Chicago Area Systems Research Workshop, 2024
  4. TaskVine: Managing In-Cluster Storage for High-Throughput Data Intensive Workflows
    Barry Sly-Delgado, Thanh Son Phung, Colin Thomas, David Simonetti, Andrew Hennessee, Ben Tovar, and Douglas Thain
    In 18th Workshop on Workflows in Support of Large-Scale Science, 2023
  5. Poster: TaskVine: A User-Level Framework for Data Intensive Scientific Applications
    Douglas Thain
    In CSSI PI Meeting, 2023
  6. Poster: Mixed Modality Workflows in TaskVine
    David Simonetti, Ben Tovar, and Douglas Thain
    In ACM High Performance Distributed Computing, 2023

Acknowledgement

This work was supported in part by grant OAC #1931348 "CSSI Elements: Data Swarm: A User-Level Framework for Data Intensive Scientific Computing".