Hello Jørgen, great. If you have access to a super computer it would be very interesting to know, how the recently implemented new versions of GMRes and CG (that implement overlapping of gobal reductions with matrix-vector multiplications) perform in comparison to the standard versions in terms of scaling. These algorithms are in PETSc 3.4 and later if I remember correctly.
That's just a suggestion though. Best, Robert -----"Opm" <[email protected]> wrote: ----- To: [email protected] From: Jørgen Kvalsvik Sent by: "Opm" Date: 01/26/2015 12:36 Subject: [OPM] Thesis: PETSc integration and performance measurements Hi, The tl;dr about me can be found in my previous introduction at: http://www.opm-project.org/pipermail/opm/2014-October/000664.html I have now started my master's thesis project, which briefly is to integrate PETSc into OPM and measure performance for real applications with different algorithms, also possibly on the GPU. As some of you may have noticed, I have already submitted a couple of pull requests for PETSc integration into opm-core. I am open for any suggestions and feedback regarding this work, and I will make sure to publish progress reports and findings through the spring. Sincerely, Jørgen Kvalsvik _______________________________________________ Opm mailing list [email protected] http://www.opm-project.org/mailman/listinfo/opm "This e-mail with attached documents is only for the addressee indicated above. The e-mail and documents may contain confidential information. If you are not the correct addressee or are responsible for transfer of this e-mail with attached documents to the correct addressee, any copying or further transfer of information contained herein is expressly forbidden. If you have received this e-mail by mistake, you are kindly requested to immediately inform me thereof by e-mail and delete the e-mail and the received documents." http://www.iris.no _______________________________________________ Opm mailing list [email protected] http://www.opm-project.org/mailman/listinfo/opm
