3 Hits in 4.2 sec

Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing [article]

Logan Ward, Ganesh Sivaraman, J. Gregory Pauloski, Yadu Babuji, Ryan Chard, Naveen Dandu, Paul C. Redfern, Rajeev S. Assary, Kyle Chard, Larry A. Curtiss, Rajeev Thakur, Ian Foster
2021 arXiv   pre-print
Methods that use machine learning (ML) to create proxy models of simulations show particular promise for guiding ensembles but are challenging to deploy because of the need to coordinate dynamic mixes  ...  of simulation and learning tasks.  ...  CONCLUSIONS We introduced Colmena, an open-source Python library for machine-learning-based steering of ensemble computations on HPC systems.  ... 
arXiv:2110.02827v1 fatcat:fp5lul5j3bcivjzy5qfvwxzxoe

ExaWorks: Workflows for Exascale [article]

Aymen Al-Saadi, Dong H. Ahn, Yadu Babuji, Kyle Chard, James Corbett, Mihael Hategan, Stephen Herbein, Shantenu Jha, Daniel Laney, Andre Merzky, Todd Munson, Michael Salim (+3 others)
2021 arXiv   pre-print
Exascale computers will offer transformative capabilities to combine data-driven and learning-based approaches with traditional simulation applications to accelerate scientific discovery and insight.  ...  Furthermore, we discuss how our project is working with the workflows community, large computing facilities as well as HPC platform vendors to sustainably address the requirements of workflows at the exascale  ...  We thank Rafael Ferreira da Silva and Henri Casanova of the Workflows-RI project for partnering to organize community summits.  ... 
arXiv:2108.13521v1 fatcat:y4qe4oxscbfhhkgydqz7lft3cq

Coupling streaming AI and HPC ensembles to achieve 100-1000x faster biomolecular simulations [article]

Alexander Brace, Igor Yakushin, Heng Ma, Anda Trifan, Todd Munson, Ian Foster, Arvind Ramanathan, Hyungro Lee, Matteo Turilli, Shantenu Jha
2022 arXiv   pre-print
Machine learning (ML)-based steering can improve the performance of ensemble-based simulations by allowing for online selection of more scientifically meaningful computations.  ...  We present DeepDriveMD, a framework for ML-driven steering of scientific simulations that we have used to achieve orders-of-magnitude improvements in molecular dynamics (MD) performance via effective coupling  ...  Acknowledgements: This article reports on work supported by the Exascale Computing Project (  ... 
arXiv:2104.04797v5 fatcat:vd6l3vyx2ngjtjv7wbdorqcgyu