<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1">
</head>
<body text="#000000" bgcolor="#FFFFFF">
Hi All,<br>
<br>
We have the prototype implementation for the nonblocking collective
I/O routines provided by Dr. Edgar Gabriel and his student
(Vishwanath Venkatesan). The implementation provides a prototype for
implementing the following routines:<br>
<ul>
<li>MPI_File_iread_all</li>
<li>MPI_File_iwrite_all</li>
<li>MPI_File_iread_at_all</li>
<li>MPI_File_iwrite_at_all</li>
</ul>
<p>We did not implement, however the nonblocking counterpart for
shared file pointer collective operations:<br>
</p>
<ul>
<li>MPI_File_iread_ordered</li>
<li>MPI_File_iwrite_ordered</li>
</ul>
<p>The reason is that the entire shared file pointer operations are
not implemented within the MPI-I/O framework used. That being
said, we can provide the pseudo code for the operations,
since in reality there is
nothing fundamentally difficult if we have a shared file pointer
and
the other nonblocking routines available. <br>
</p>
<p>Would anyone on this list object to the idea of just providing
the pseudo code implementation for the shared file pointer
routines (i.e. postpone voting on the ticket till we have a
prototype implementation which would likely not be in the MPI-3.0
time frame anymore)?</p>
Thanks,<br>
Mohamad<br>
</body>
</html>