On Wed, 23 Jan 2013, Kirk, Benjamin (JSC-EG311) wrote: > Are these ghosted vectors? > > Can't imagine how it could happen, but if the ghost indices are not > symmetric where they should be you could have processor m waiting on > a message from processor n that is not coming...
If something like this turns out to be the problem, we should probably revisit the "Workaround for a strange bug at large-scale" in one of the other PetscVector::localize() versions; an inconsistent send_list could explain why operator= was in your experience more robust than the manual scatter there too. --- Roy ------------------------------------------------------------------------------ Master Visual Studio, SharePoint, SQL, ASP.NET, C# 2012, HTML5, CSS, MVC, Windows 8 Apps, JavaScript and much more. Keep your skills current with LearnDevNow - 3,200 step-by-step video tutorials by Microsoft MVPs and experts. ON SALE this month only -- learn more at: http://p.sf.net/sfu/learnnow-d2d _______________________________________________ Libmesh-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/libmesh-users
