English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent years have seen many successful applications of machine learning (ML)to facilitate fluid dynamic computations. As simulations grow, generating newtraining datasets for traditional offline learning creates I/O and storagebottlenecks. Additionally, performing inference at runtime requires non-trivialcoupling of ML framework libraries with simulation codes. This work offers asolution to both limitations by simplifying this coupling and enabling in situtraining and inference workflows on heterogeneous clusters. LeveragingSmartSim, the presented framework deploys a database to store data and MLmodels in memory, thus circumventing the file system. On the Polarissupercomputer, we demonstrate perfect scaling efficiency to the full machinesize of the data transfer and inference costs thanks to a novel co-locateddeployment of the database. Moreover, we train an autoencoder in situ from aturbulent flow simulation, showing that the framework overhead is negligiblerelative to a solver time step and training epoch.

In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD