<html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<p><br>
</p>
<div class="moz-cite-prefix">Il 15/07/21 14:15, Matthew Knepley ha
scritto:<br>
</div>
<blockquote type="cite" cite="mid:CAMYG4GnZrAcRaipgh9XNUKpoBxP1PSobVdMipkpF72t14OPMhg@mail.gmail.com">
<div dir="ltr">
<div dir="ltr">On Thu, Jul 15, 2021 at 6:39 AM Matteo Semplice
<<a href="mailto:matteo.semplice@uninsubria.it" moz-do-not-send="true">matteo.semplice@uninsubria.it</a>>
wrote:<br>
</div>
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0px 0px 0px
0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">
<div>
<p><br>
</p>
<div>Il 12/07/21 17:51, Matthew Knepley ha scritto:<br>
</div>
<blockquote type="cite">
<div dir="ltr">
<div dir="ltr">On Mon, Jul 12, 2021 at 11:40 AM Matteo
Semplice <<a href="mailto:matteo.semplice@uninsubria.it" target="_blank" moz-do-not-send="true">matteo.semplice@uninsubria.it</a>>
wrote:<br>
</div>
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0px
0px 0px 0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">
<div>
<p>Dear all,</p>
<p> I am experimenting with hdf5+xdmf output.
At <a href="https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.xdmf.org%2Findex.php%2FXDMF_Model_and_Format&data=04%7C01%7Cmatteo.semplice%40uninsubria.it%7Cfb0d540c87a64e4ea51d08d9478a4e9b%7C9252ed8bdffc401c86ca6237da9991fa%7C0%7C0%7C637619481622608977%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=sOQskFoMTHdOwjOec0d9npdw%2BiAVbar1SXBuU%2BH8xKc%3D&reserved=0" originalsrc="https://www.xdmf.org/index.php/XDMF_Model_and_Format" shash="COJ2W8d94F8Av8Nl7hPOHkHbcNK26tdZzSiNxaZ45Ahdx0RWbRHwMJ8I39rv8PF9wl1VQ1m6te6nGQSAJ58Qeu0aDwsR7wBYrdVDTM2bg58Fg5GuzCwYumyQatQx5JlygQhDGoEgHNtx2Y8cRBExojXzmIoesjWQnlLgo+lYCDc=" target="_blank" moz-do-not-send="true">https://www.xdmf.org/index.php/XDMF_Model_and_Format</a>
I read that "XDMF uses XML to store Light data
and to describe the data Model. Either HDF5<a rel="nofollow" href="https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.hdfgroup.org%2FHDF5&data=04%7C01%7Cmatteo.semplice%40uninsubria.it%7Cfb0d540c87a64e4ea51d08d9478a4e9b%7C9252ed8bdffc401c86ca6237da9991fa%7C0%7C0%7C637619481622618934%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=akFyfHE4BULSscevnO0MxjMhEByT3USoJFQKsikJSzg%3D&reserved=0" originalsrc="https://www.hdfgroup.org/HDF5" shash="umHxF55MUp5QVOFJQe5ottGXTW2kCspZ4TCWI15XANTRKsp+09sIxgq1dk+HLLYVp6Jr2mw+uebXPk92w8PXWB0W838N9oQyGGlnwehDPk0G5MzfhCYAZFTw+i7qKsXEGCttI40J68EzzXxL4kBCm6PdIQLE+wYwWlGsvcuh+bQ=" target="_blank" moz-do-not-send="true">[3]</a>
or binary files can be used to store Heavy
data. The data Format is stored redundantly in
both XML and HDF5."</p>
<p>However, if I call DMView(dmda,hdf5viewer)
and then I run h5ls or h5stat on the resulting
h5 file, I see no "geometry" section in the
file. How should I write the geometry to the
HDF5 file?<br>
</p>
<p>Here below is what I have tried.</p>
</div>
</blockquote>
<div>The HDF5 stuff is only implemented for DMPlex
since unstructured grids need to be explicitly
stored. You can usually just define the structured
grid in the XML</div>
<div>without putting anything in the HDF5. We could
write metadata so that the XML could be
autogenerated, but we have not done that.</div>
</div>
</div>
</blockquote>
<p>Thanks for the clarification. It shouldn't be hard to
produce the XML from my code.<br>
</p>
<p>Just another related question: if I call VecView in
parallel with the HDF5 viewer, I get a single output
file. Does this mean that data are gathered by one
process and written or it handles it smartly by
coordinating the output of all processes to a single
file?<br>
</p>
</div>
</blockquote>
<div>This is slightly more complicated than you would expect.
We have two implementations, one which uses MPI-IO, and one
which sends</div>
<div>data from each process to 0, which writes it out. It
turns out that MPI-IO is sometimes poorly supported or badly
implemented, so you need</div>
<div>the fallback.</div>
</div>
</div>
</blockquote>
<p>Thanks!<br>
</p>
<p>On my machine I am compiling from the git repo with
--download-hdf5, so I have some control, but on clusters I prefer
to use the available petsc.<br>
</p>
Is there a simple way to check which implementation is begin used in
a run? <br>
<p>Matteo<br>
</p>
<br>
</body>
</html>