Using AmgX to Accelerate PETSc-Based CFD Codes
datasetposted on 18.05.2017 by Pi-Yueh Chuang, Lorena A. Barba
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
[This file set supplements the presentation by Pi-Yueh Chuang at 2016 GPU Technology Conference, on Thu. April 7th: see session S6355.]
Please cite as:
Chuang, Pi-Yueh; Barba, Lorena A. (2017): Using AmgX to Accelerate PETSc-Based CFD Codes. figshare.
The file set includes a Jupyter notebook that reports how we accelerated our PETSc-based CFD solver, PetIBM, with multi-GPU capability enabled through AmgX library. PETSc, developed by Argonne National Laboratory, is a toolkit for parallel scientific computing. AmgX is an NVIDIA library providing multigrid preconditioners and Krylov linear solvers. It features the capability of multi-GPU computing through MPI. We developed AmgXWrapper to couple PETSc and AmgX, so that we can easily integrate AmgX into PetIBM with less than 10 lines of code modification.
The links in references are:
* Video record of GTC 2016 presentation
* Rendered version of the notebook viewed on nbviewer
* GitHub repository of AmgXWrapper
* GitHub repository of PetIBM