Large scale in transit computation of quantiles for ensemble runs
From MaRDI portal
Publication:6318544
arXiv1905.04180MaRDI QIDQ6318544FDOQ6318544
Authors: Alejandro Ribés, Théophile Terraz, B. Iooss, Yvan Fournier, Bruno Raffin 
Publication date: 10 May 2019
Abstract: The classical approach for quantiles computation requires availability of the full sample before ranking it. In uncertainty quantification of numerical simulation models, this approach is not suitable at exascale as large ensembles of simulation runs would need to gather a prohibitively large amount of data. This problem is solved thanks to an on-the-fly and iterative approach based on the Robbins-Monro algorithm. This approach relies on Melissa, a file avoiding, adaptive, fault-tolerant and elastic framework. On a validation case producing 11 TB of data, which consists in 3000 fluid dynamics parallel simulations on a 6M cell mesh, it allows on-line computation of spatio-temporal maps of percentiles.
This page was built for publication: Large scale in transit computation of quantiles for ensemble runs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6318544)
