<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div>Very good. I forgot about ASYNCHRONOUS. So I think the problem is solved then. Copy-in/copy-out doesn't matter for blocking calls and the ASYNCHRONOUS attribute will be used on the non-blocking calls.</div><div><br></div><div>-craig</div><br><div><div>On Jun 12, 2009, at 11:28 AM, Jim Xia wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><br><tt><font size="2"><a href="mailto:mpi3-fortran-bounces@lists.mpi-forum.org">mpi3-fortran-bounces@lists.mpi-forum.org</a> wrote on 06/12/2009 12:52:00 PM:<br> <br> </font></tt> <br><tt><font size="2">> <br> > However, there was an earlier discussion raised by Jim about how a <br> > compiler might want to copy-in/copy-out even if for assumed-shape <br> > arrays. I think Jim's example had to do with copying vector sized <br> > objects even though the user is only using a portion of a vector.<br> > <br> > So does DIMENSION(..) restrict copy-in/copy-out?<br> </font></tt> <br> <br><tt><font size="2">I don't remember I raised discussion on this very topic, but this is a valid argument. In short, DIMENSION(..) alone will not restrict copy-in/copy-out. The most effective way to suppress copying is through VOLATILE/ASYNCHRONOUS attribute on the dummy argument.</font></tt> <br> <br><tt><font size="2">Thanks</font></tt> <br> <br><font size="2" face="sans-serif">Jim Xia<br> <br> XL Fortran Compiler Test<br> IBM Toronto Lab at 8200 Warden Ave, Markham, On, L6G 1C7<br> Phone (905) 413-3444 Tie-line 313-3444<br> email: <a href="mailto:jimxia@ca.ibm.com">jimxia@ca.ibm.com</a><br> D2/YF7/8200 /MKM<br> <br> </font><a href="http://www.ibm.com/software/awdtools/fortran/xlfortran"><font size="2" face="sans-serif">http://www.ibm.com/software/awdtools/fortran/xlfortran</font></a> <br>_______________________________________________<br>mpi3-fortran mailing list<br><a href="mailto:mpi3-fortran@lists.mpi-forum.org">mpi3-fortran@lists.mpi-forum.org</a><br>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-fortran<br></blockquote></div><br></body></html>