[MOAB-dev] pcomm::exchange_tags unpredicted behaviour on large mesh

[Grindeanu, Iulian R.]

take that back, it is reasonable to be about 3 times number of hexas.
________________________________________
From: moab-dev-bounces at mcs.anl.gov [moab-dev-bounces at mcs.anl.gov] on behalf of Grindeanu, Iulian R. [iulian at mcs.anl.gov]
Sent: Thursday, June 04, 2015 9:17 AM
To: Kanaev A.A.; moab-dev at mcs.anl.gov
Subject: Re: [MOAB-dev] pcomm::exchange_tags unpredicted behaviour on large     mesh

Hi Anton,
Is your mesh correct? Do you have a way of verifying it?
I mean, is it possible that some quads are duplicated, to start with? Or, before ghosting, can you do a check of adjacent faces (quads) to each of your hex elements?
you report 30 million quads on a 10 million hex mesh. Which is possible, if you have thin layers. Do you have a picture of your geometry, or some pictures of your mesh?
Iulian
________________________________________
From: moab-dev-bounces at mcs.anl.gov [moab-dev-bounces at mcs.anl.gov] on behalf of Kanaev A.A. [kanaev at ibrae.ac.ru]
Sent: Wednesday, June 03, 2015 7:15 PM
To: moab-dev at mcs.anl.gov
Subject: [MOAB-dev] pcomm::exchange_tags unpredicted behaviour on large mesh

Hello, MOAB-dev,

I have  10205296 hexa and  30736714 quads in my mesh
I read the mesh on 64 processors and exchange 1 layer of ghost cells with additional 2d entities
Then i exchange GLOBAL_ID tag data for quads
After exchange it looks like all quads have received new GLOBAL_ID tag value, it doesn't appear on smaller meshes
And there're two different quads with GLOBAL_ID = 30718357 on 41 proc after exchange (i think there're more doubles, that's just what i've spotted)

Small test program attached

The mesh is 3.9Gb, i hope that link works
https://drive.google.com/file/d/0B6upEZeL2DFWXzhYZjEzNGlQem8/view

Please check that on 64 processors

Anton