Explanation
What Version 1.2.0 Adds
What Version 1.2.0 Adds
- This dataset captures both tabular metadata and graph representations from deep learning training workflows, extracted via TensorFlow's XLA compiler.
TapisUI provides a research oriented frontend to interact with Tapis and tenant components. In this case, the ICICLE extension extends TapisUI with custom branding
The GNN Food Flow Portal is a Streamlit web app for exploring county-level U.S. food-flow predictions from the GNN FoodFlow Model. Version 1.2.0 includes the original parallel SCTG-specific model exploration workflow plus a new multi-task GNN what-if portal for one-to-one and one-to-many county scenario analysis.
A dataset designed to support AI-driven resource estimation like runtime prediction to support HPC scheduling optimization by leveraging compiler-level High-Level Optimizer (HLO) graph features and deep learning workload metadata.
Run the Portal Locally
How to Predict Training Time Using Metadata
View the main TapisUI wiki to learn how to deploy and test TapisUI extensions locally.
This tapis ui extension enables additional icicle specific branding and tabs on tapisui.
Explore Parallel Model Food Flows
Getting Started with the HLO Feature Dataset