<div dir="ltr"><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)">I want to write a distributed variable to a file and the way the <br></div><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)">data is distributed is fairly random with respect to the ordering on the file. <br><br></div><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)">It seems like I can do several things from each task in order to write the data -<br><br></div><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)"><ol><li>I can specify several blocks of code using start and count and make mulitple calls on each task to ncmpi_bput_vara_all</li><li>I can define an MPI derived type and make a single call to ncmpi_bput_var_all on each task</li><li>I (think I) can use ncmpi_bput_varm_all and specify an imap (btw: the pnetcdf users guide has this interface wrong)<br></li></ol></div><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)">Are any of these better from a performance standpoint?<br><br>Thanks,<br></div><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)"><br></div><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:rgb(56,118,29)"><br><br clear="all"></div><br>-- <br><div dir="ltr"><div><div><div>Jim Edwards<br><br></div><font size="1">CESM Software Engineer<br></font></div><font size="1">National Center for Atmospheric Research<br></font></div><font size="1">Boulder, CO</font> <br></div>
</div>