<html>
<body>
At 10:12 AM 6/20/2008, Richard Treumann wrote:<br><br>
<blockquote type=cite class=cite cite="">Of course - <br><br>
An assertion is a statement that the application <b>does not require</b>
some MPI standard feature or semantic guarantee. It is not a directive to
the MPI implementation. The implementation is free to provide that
feature or guarantee even if the application says it is not needed.
<br><br>
The story is a bit different for a helper library because the library is
logically a more or less opaque part of the application. If the caller of
MPI_INIT_ASSERTED says the application does not require something and
then uses a library that does require that feature or guarantee - the
library must raise an error or adjust its behavior to live within the
assertion.</blockquote><br>
While I understand the intention, am a bit worried about the<br>
implications. Imagine a long running application that loads<br>
a new physics module after hours of computation and this new<br>
module requires different assertions. If the only option it<br>
has is to fail, a lot of progress in the main application will<br>
get lost. The only alternative is for the application to never<br>
state any assertion since it does not know which modules it<br>
will load (often depends on the input deck) - and then the<br>
whole exercise will be pointless anyway.<br><br>
Also, tools often need very specific MPI features and can't live<br>
with many assertions (just taking from Rich's examples in the<br>
other emails: there is often a need to use wildcards or complex <br>
datatypes even if the application doesn't use it). Not being<br>
able to change this would basically eliminate the ability to<br>
use certain tools on certain applications (I realize that tools<br>
that run from the beginning can intercept MPI_Init and turn<br>
assertions off, but tools that attach can't).<br><br>
Hence, I think we need some way to change assertions at runtime<br>
(at very specific points only and as global operations) despite <br>
the extra complexity it will introduce.<br><br>
Martin<br><br>
<br><br>
<br><br>
<br>
<blockquote type=cite class=cite cite="">Dick Treumann - MPI Team/TCEM
<br>
IBM Systems & Technology Group<br>
Dept 0lva / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601<br>
Tele (845) 433-7846 Fax (845) 433-8363<br><br>
<br>
<tt>mpi3-subsetting-bounces@lists.mpi-forum.org wrote on 06/20/2008
12:58:03 PM:<br><br>
> Hi,</tt><br>
<tt>> </tt><br>
<tt>> Ignoring an assertion should be perfectly legal.</tt><br>
<tt>> </tt><br>
<tt>> Best regards.</tt><br>
<tt>> </tt><br>
_______________________________________________<br>
mpi3-subsetting mailing list<br>
mpi3-subsetting@lists.mpi-forum.org<br>
<a href="http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-subsetting" eudora="autourl">
http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-subsetting</a>
</blockquote>
<x-sigsep><p></x-sigsep>
_______________________________________________________________________<br>
Martin Schulz, schulzm@llnl.gov,
<a href="http://people.llnl.gov/schulz6" eudora="autourl">
http://people.llnl.gov/schulz6<br>
</a>CASC @ Lawrence Livermore National Laboratory, Livermore, USA
</body>
</html>