Okay, that's a good point. But it should be an integer in fortran shouldn't it? Anyway, thanks for the fix. <br><br><div class="gmail_quote">On Thu, Nov 15, 2012 at 12:51 PM, Wei-keng Liao <span dir="ltr"><<a href="mailto:wkliao@ece.northwestern.edu" target="_blank">wkliao@ece.northwestern.edu</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">By the way, MPI_Request is an opaque object in MPICH, not an integer.<br>
So you probably is printing a pointer address.<br>
IBM may choose to implement it as an integer. Anyway, the right way to<br>
use it is to define the requests as MPI_Request type.<br>
<div class="im HOEnZb"><br>
Wei-keng<br>
<br>
On Nov 15, 2012, at 1:42 PM, Jim Edwards wrote:<br>
<br>
</div><div class="HOEnZb"><div class="h5">> Ah but there is no fortran definition of NC_REQ_NULL, so it's still an issue.<br>
><br>
> On Thu, Nov 15, 2012 at 12:37 PM, Jim Edwards <<a href="mailto:jedwards@ucar.edu">jedwards@ucar.edu</a>> wrote:<br>
> So this program illustrates the problem:<br>
><br>
> #include <mpi.h><br>
> #include <stdio.h><br>
> #include <pnetcdf.h><br>
><br>
> int main()<br>
> {<br>
> printf("%d %d\n",MPI_REQUEST_NULL,NC_REQ_NULL);<br>
> }<br>
><br>
><br>
> On Cray systems using pgi compiler:<br>
><br>
> ./a.out<br>
> 738197504 -1<br>
><br>
> I can try using NC_REQ_NULL instead of MPI_REQUEST_NULL in my program, but I'm afraid that's just going to cause this problem to manifest in a different way.<br>
><br>
><br>
><br>
><br>
> On Thu, Nov 15, 2012 at 11:34 AM, Jim Edwards <<a href="mailto:jedwards@ucar.edu">jedwards@ucar.edu</a>> wrote:<br>
> On Cray systems the MPI constant MPI_REQUEST_NULL resolves to 738197504<br>
> but passing this value into nonblocking.c results in an error:<br>
><br>
> Error: no such request ID = 738197504<br>
><br>
><br>
> I think that this is an error in parallel-netcdf ncmpii_wait.<br>
><br>
> On the ibm aix system MPI_REQUEST_NULL resolves to -1 and nonblocking.c seems to handle it correctly.<br>
><br>
><br>
> --<br>
> Jim Edwards<br>
><br>
> CESM Software Engineering Group<br>
> National Center for Atmospheric Research<br>
> Boulder, CO<br>
> <a href="tel:303-497-1842" value="+13034971842">303-497-1842</a><br>
><br>
><br>
><br>
><br>
> --<br>
> Jim Edwards<br>
><br>
> CESM Software Engineering Group<br>
> National Center for Atmospheric Research<br>
> Boulder, CO<br>
> <a href="tel:303-497-1842" value="+13034971842">303-497-1842</a><br>
><br>
><br>
><br>
><br>
> --<br>
> Jim Edwards<br>
><br>
> CESM Software Engineering Group<br>
> National Center for Atmospheric Research<br>
> Boulder, CO<br>
> <a href="tel:303-497-1842" value="+13034971842">303-497-1842</a><br>
><br>
<br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br><pre>Jim Edwards<br><br><br></pre><br>