<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
Hi Folks,</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
<br>
</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
I finally got around to a to-do item for the MPI sessions WG. I’d said</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
I’d look through the MPI_T portion of the tools chapter of the standard</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
and see what consequences the MPI Sessions concept would have on that</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
section.</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
<br>
</div>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
I came up with the following short list:</div>
<ul>
<li><font face="Calibri,sans-serif">terminology collision. For performance variables, there is an
</font><font color="#454545" face="Helvetica"><span style="font-size: 12px;">MPI_T_pvar_session construct. However, it seems to me this is sufficiently distinct from what we’re proposing for sessions that there should not be an issue.</span></font></li><li><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px;">MPI_T_CVAR_GET_INFO </span><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px;">
</span><font color="#454545" face="Helvetica"><span style="font-size: 12px;">and MPI_T_CVAR_HANDLE_ALLOC. These have a handle to a MPI object argument. It is legal to pass MPI COMM WORLD/COMM SELF in as the argument. So we’d need to figure out how to handle
these cases in the context of an application that doesn’t explicitly call MPI_INIT or one of the other MPI functions that, according to our proposal, has the side effect of creating MPI_COMM_WORLD/SELF. One option might be to return </span></font><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px;">MPI_
T_ ERR_ CVAR_ SET_ NOT_ NOW error code.</span></li><li><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px; font-style: normal; font-weight: normal; text-decoration: none;">A similar problem exists for </span><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px;">MPI_T_PVAR_GET_INFO
and MPI_T_PVAR_HANDLE_ALLOC.</span><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px;"> Curiously, there is no analogous </span><span style="color: rgb(69, 69, 69); font-family: Helvetica; font-size: 12px;">MPI_T_ERR_PVAR_SET_NOT_NOW
error code.</span></li></ul>
<div style="color: rgb(0, 0, 0); font-family: Calibri, sans-serif; font-size: 14px;">
<div>
<div>That’s what I came up with for first order items that would be impacted by Sessions, beyond minor languages changes in the text to indicate, for instance, that a Session handle could be passed to MPI_T_CVAR_HANDLE_ALLOC, etc.</div>
<div><br>
</div>
<div>Howard</div>
<div><br>
</div>
<div><br>
</div>
<div>-- </div>
<div>Howard Pritchard</div>
</div>
<div>HPC-DES</div>
<div>Los Alamos National Laboratory</div>
<div><br>
</div>
</div>
</body>
</html>