<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
{font-family:Wingdings;
panose-1:5 0 0 0 0 0 0 0 0 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Aptos;
panose-1:2 11 0 4 2 2 2 2 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Aptos",sans-serif;
mso-ligatures:standardcontextual;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#467886;
text-decoration:underline;}
p.MsoListParagraph, li.MsoListParagraph, div.MsoListParagraph
{mso-style-priority:34;
margin-top:0in;
margin-right:0in;
margin-bottom:0in;
margin-left:.5in;
font-size:11.0pt;
font-family:"Aptos",sans-serif;
mso-ligatures:standardcontextual;}
span.EmailStyle20
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:366417539;
mso-list-type:hybrid;
mso-list-template-ids:-1973804472 67698689 67698691 67698693 67698689 67698691 67698693 67698689 67698691 67698693;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Symbol;}
@list l0:level2
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:"Courier New";}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Wingdings;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Symbol;}
@list l0:level5
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:"Courier New";}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Wingdings;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Symbol;}
@list l0:level8
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:"Courier New";}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Wingdings;}
@list l1
{mso-list-id:575286445;
mso-list-template-ids:1630832032;}
@list l1:level1
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level2
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:1.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level3
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:1.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level4
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:2.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level5
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:2.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level6
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:3.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level7
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:3.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level8
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:4.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level9
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:4.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
ol
{margin-bottom:0in;}
ul
{margin-bottom:0in;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#467886" vlink="#96607D" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif">Thanks Dan. I added this to the 01/29/24 webex notes<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif"><a href="https://github.com/mpiwg-sessions/sessions-issues/wiki/2024-01-29-webex">https://github.com/mpiwg-sessions/sessions-issues/wiki/2024-01-29-webex</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif">Howard<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span lang="EN-GB" style="font-size:12.0pt;font-family:"Calibri",sans-serif;color:black;mso-ligatures:none">From:
</span></b><span lang="EN-GB" style="font-size:12.0pt;font-family:"Calibri",sans-serif;color:black;mso-ligatures:none">mpiwg-sessions <mpiwg-sessions-bounces@lists.mpi-forum.org> on behalf of MPI Sessions working group <mpiwg-sessions@lists.mpi-forum.org><br>
<b>Reply-To: </b>MPI Sessions working group <mpiwg-sessions@lists.mpi-forum.org><br>
<b>Date: </b>Thursday, February 1, 2024 at 10:02 AM<br>
<b>To: </b>MPI Sessions working group <mpiwg-sessions@lists.mpi-forum.org>, Aurelien Bouteiller <bouteill@icl.utk.edu><br>
<b>Cc: </b>"Holmes, Daniel John" <daniel.john.holmes@intel.com><br>
<b>Subject: </b>[EXTERNAL] Re: [mpiwg-sessions] Sessions WG - meet 1/29/24<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif;mso-ligatures:none"><o:p> </o:p></span></p>
</div>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Hi all,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">WORDS to capture our discussion on Monday 29th Jan.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The basic idea in the example code I gave is to detect process fail-stop faults, shrink the active communicator to exclude the failed processes, and then carry on.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The while loop captures the "carry on" part, only exit when we hit the break statement (or we suffer a process fail-stop fault).<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The additional code block captures the "shrink" part by creating a new communicator that excludes failed processes.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The MPI_Group_from_session_pset calls will all produce identical groups, even after processes have failed. This is a local procedure and there's no reason for it to return an error.
We should guarantee that it never returns errors of class MPI_ERR_PROC_FAILED.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The MPI_Session_get_proc_failed calls give a snapshot of the knowledge contained in the local detector. There is no communication or nonlocal dependence here. This is a (new) local
procedure and there's no reason for it to return an error. We should guarantee that it never returns errors of class MPI_ERR_PROC_FAILED.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The group manipulation procedures are existing MPI and will work exactly the same as they always have done. These are local procedures and there's no reason for them to return
an error. We should guarantee that they never return errors of class MPI_ERR_PROC_FAILED.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The devils are always in the details. The details in this case are all in the implementation of MPI_Comm_create_from_group.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">The MPI_Comm_create_from_group procedure must handle some difficult cases:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">1. the potential for failed processes to exist in the group that is passed in by the calling MPI process<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">2. the potential for the group passed in to be different to the groups passed in by other MPI processes<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">3. the potential for the additional MPI processes to fail during the operation<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">1. failed before the operation<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">If this MPI process attempts to communicate with a failed process, it's detector must eventually detect that, otherwise it is broken!<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">This means that the failure of the other MPI process is discovered during the operation -- see point (3).<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">2. different groups at different processes<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">There are several sub-cases here:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">a) procA's group includes procB but procB has failed (any time before procA communicates with it)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">b) procA's group contains procB but procB's does not include procA<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">c) procA's group contains procB and procC but procB's group includes procA but does not include procC<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">d) procA's group and procB's group are identical but one of them later discovers an (a|b|c) problem<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Current shrink implementations rely on shared knowledge of the survivors so each involved process can independently create the same spanning tree as all the other involved processes.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">This simplifies the design and results in a better worst-case performance scaling, at least asymptotically [ED: pls check]<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">All of the above sub-cases can happen during a shrink operation, so intuitively this is no worse than that.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">We have two broad categories of approach here:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">- any problem results in an error, return immediately without creating the output communicator<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">- any FT problem is dealt with internally; some kind of best-effort communicator is created<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">We probably want a resilient algorithm that doesn’t have dreadful scaling.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">3. failures during the operation<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">We can just do an agreement at the end to catch failures that happen after the critical moment when other processes communicate with it.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Resilient algorithm:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Start optimistic: Create a spanning tree from the group members you have been given in the call.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Be eager to help: Always listen for incoming protocol messages related to communicator creation.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Attempt communication with your direct children;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"> if new failure detected, update the local group, update the local detector, fix the spanning tree (skip that child, but add that child's children as your direct children)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"> if a child reports a different group (compare hashes), figure out the difference, update the local detector, fix the spanning tree (recreate it using only uncontacted undead
processes)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Attempt communication with your parent;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"> if new failure detected, update the local group, update the local detector, fix the spanning tree (skip the parent, but add that parent's parent as your direct parent)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"> if the parent reports a different group (compare hashes), figure out the difference, update the local detector, fix the spanning tree (recreate it using only uncontacted undead
processes)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Assume it all worked beautifully but execute MPI_Comm_agree to make certain.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"> if new failure detected, update the local group, update the local detector, start again<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"> if the agreement succeeds without discovering new failures, we're done!<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Best-case asymptotic scaling is O(log(p)), a spanning tree traversal of P processes.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Worst-case O(sum_i=1,p-1(log(p-i)) < O(p log(p)), no more than p-1 tree traversals with a shrinking tree size.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Best wishes,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Dan.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-family:"Calibri",sans-serif;mso-ligatures:none">From:</span></b><span style="font-family:"Calibri",sans-serif;mso-ligatures:none"> mpiwg-sessions <mpiwg-sessions-bounces@lists.mpi-forum.org>
<b>On Behalf Of </b>Holmes, Daniel John via mpiwg-sessions<br>
<b>Sent:</b> Monday, January 29, 2024 4:13 PM<br>
<b>To:</b> MPI Sessions working group <mpiwg-sessions@lists.mpi-forum.org>; Aurelien Bouteiller <bouteill@icl.utk.edu><br>
<b>Cc:</b> Holmes, Daniel John <daniel.john.holmes@intel.com><br>
<b>Subject:</b> Re: [mpiwg-sessions] Sessions WG - meet 1/29/24<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Hi Howard/all,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Here is the simple code I was talking about in the meeting today:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">// general high-level optimistic application<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">void main() {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session session;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session_Init(MPI_INFO_NULL, MPI_ERRORS_ARE_FATAL, &session);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group group;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group_from_session_pset(session, "mpi://world", &group);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Comm comm;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Comm_create_from_group(group, &comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> ret = do_stuff_with_comm(comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> if (MPI_SUCCESS == ret) {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Comm_disconnect(&comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session_Finalize(&session);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> break;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> } else {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> panic();<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> }<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">}<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">// general high-level pragmatic application<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">void main() {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> // additional code<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> while (1) {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session session;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session_Init(MPI_INFO_NULL, MPI_ERRORS_RETURN, &session);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group world, failed, group;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group_from_session_pset(session, "mpi://world", &world);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> // additional code<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session_get_proc_failed(session, &failed); // new API, seems easy to do<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group_difference(world, failed, &group);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group_free(&world);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group_free(&failed);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Comm comm;<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Comm_create_from_group(group, &comm); // <-- the detail-devils live here<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Group_free(&group);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> ret = do_stuff_with_comm(comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Comm_disconnect(&comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> MPI_Session_Finalize(&session);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> if (MPI_SUCCESS == ret) {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> break; // all done!<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> } else if (MPI_ERR_PROC_FAILED == ret) {<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> continue; // no more panic<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> }<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> // additional code<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New""> } // end while<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Courier New"">}<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Best wishes,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif">Dan.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-family:"Calibri",sans-serif"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-family:"Calibri",sans-serif;mso-ligatures:none">From:</span></b><span style="font-family:"Calibri",sans-serif;mso-ligatures:none"> mpiwg-sessions <<a href="mailto:mpiwg-sessions-bounces@lists.mpi-forum.org">mpiwg-sessions-bounces@lists.mpi-forum.org</a>>
<b>On Behalf Of </b>Pritchard Jr., Howard via mpiwg-sessions<br>
<b>Sent:</b> Thursday, January 25, 2024 6:07 PM<br>
<b>To:</b> MPI Sessions working group <<a href="mailto:mpiwg-sessions@lists.mpi-forum.org">mpiwg-sessions@lists.mpi-forum.org</a>><br>
<b>Cc:</b> Pritchard Jr., Howard <<a href="mailto:howardp@lanl.gov">howardp@lanl.gov</a>><br>
<b>Subject:</b> [mpiwg-sessions] Sessions WG - meet 1/29/24<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal">Hi Folks,<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Let’s meet on 1/29 to continue discussions related to sessions and FT.
<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">I think what will help is to consider several use cases and implications.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Here are some I have<o:p></o:p></p>
<ul style="margin-top:0in" type="disc">
<li class="MsoListParagraph" style="margin-left:0in;mso-list:l0 level1 lfo3">App using sessions to init/finalize and create at least one initial communicator with MPI_Comm_create_from_group, but also wants to use methods available in slice1 of ULFM proposal
to shrink/repair communicators. Are there any problems?<o:p></o:p></li><li class="MsoListParagraph" style="margin-left:0in;mso-list:l0 level1 lfo3">App using sessions to init/finalize and create at least one initial communicator with MPI_Comm_create_from_group, and wants to use methods available in slice 1 of ULFM proposal to
create new group from a pset and create a new communicator<o:p></o:p></li><li class="MsoListParagraph" style="margin-left:0in;mso-list:l0 level1 lfo3">App using sessions to init/finalize, etc. and when a fail-stop error is detected destroy the session, create a new session query for process sets, etc. and start all over.
<o:p></o:p></li></ul>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">We should also consider the behavior of MPI_Comm_create_from_group if a process failure occurs while creating a new communicator. The ULFM slice 1 discusses behavior of MPI_COMM_DUP and process failure. We’d probably want similar behavior
for MPI_Comm_create_from_group.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">For those with access, the ULFM slice 1 PR is at <a href="https://urldefense.com/v3/__https:/github.com/mpi-forum/mpi-standard/pull/947__;!!Bt8fGhp8LhKGRg!FQpQE-vRq0MA4P6dPrB5NsdiFgWQ-SLsy4uZvj3iVjVrKNb62cGBeVOefebRWqLjS2k6t4cm7x7F3EOd__pmTvxOY531RGi2Og$">
https://github.com/mpi-forum/mpi-standard/pull/947</a><o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Thanks,<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Howard<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-ligatures:none">-------<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-ligatures:none"><o:p> </o:p></span></p>
<table class="MsoNormalTable" border="0" cellspacing="0" cellpadding="0" width="366" style="width:274.5pt;border-collapse:collapse">
<tbody>
<tr style="height:1.8in">
<td width="76" valign="top" style="width:56.95pt;padding:0in 5.4pt 0in 5.4pt;height:1.8in">
<p class="MsoNormal"><span style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-ligatures:none"><img border="0" width="55" height="55" style="width:.5729in;height:.5729in" id="Picture_x0020_5" src="cid:image001.png@01DA550B.22A71F30" alt="signature_61897647"><o:p></o:p></span></p>
</td>
<td width="290" valign="top" style="width:217.55pt;padding:0in 5.4pt 0in 5.4pt;height:1.8in">
<p class="MsoNormal"><b><span style="font-size:12.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none">Howard Pritchard<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:"Arial",sans-serif;color:#545961;mso-ligatures:none">Research Scientist<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:"Arial",sans-serif;color:#545961;mso-ligatures:none">HPC-ENV<o:p></o:p></span></b></p>
<p class="MsoNormal"><span style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-ligatures:none"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none">Los Alamos National Laboratory<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><a href="mailto:howardp@lanl.gov"><span style="color:#0563C1">howardp@lanl.gov</span></a><o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><o:p> </o:p></span></b></p>
<p class="MsoNormal"><a href="https://urldefense.com/v3/__https:/www.instagram.com/losalamosnatlab/__;!!Bt8fGhp8LhKGRg!FQpQE-vRq0MA4P6dPrB5NsdiFgWQ-SLsy4uZvj3iVjVrKNb62cGBeVOefebRWqLjS2k6t4cm7x7F3EOd__pmTvxOY51FDX5_rQ$"><span style="color:windowtext;text-decoration:none"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_4" src="cid:image002.png@01DA550B.22A71F30" alt="signature_1672648044"></span></b></span></a><a href="https://urldefense.com/v3/__https:/twitter.com/LosAlamosNatLab__;!!Bt8fGhp8LhKGRg!FQpQE-vRq0MA4P6dPrB5NsdiFgWQ-SLsy4uZvj3iVjVrKNb62cGBeVOefebRWqLjS2k6t4cm7x7F3EOd__pmTvxOY50FHS6vlA$"><span style="color:windowtext;text-decoration:none"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_3" src="cid:image003.png@01DA550B.22A71F30" alt="signature_2067890307"></span></b></span></a><a href="https://urldefense.com/v3/__https:/www.linkedin.com/company/los-alamos-national-laboratory/__;!!Bt8fGhp8LhKGRg!FQpQE-vRq0MA4P6dPrB5NsdiFgWQ-SLsy4uZvj3iVjVrKNb62cGBeVOefebRWqLjS2k6t4cm7x7F3EOd__pmTvxOY52DYZVlLg$"><span style="color:windowtext;text-decoration:none"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_2" src="cid:image004.png@01DA550B.22A71F30" alt="signature_1942525183"></span></b></span></a><a href="https://urldefense.com/v3/__https:/www.facebook.com/LosAlamosNationalLab/__;!!Bt8fGhp8LhKGRg!FQpQE-vRq0MA4P6dPrB5NsdiFgWQ-SLsy4uZvj3iVjVrKNb62cGBeVOefebRWqLjS2k6t4cm7x7F3EOd__pmTvxOY53yhqaiAg$"><span style="color:windowtext;text-decoration:none"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_1" src="cid:image005.png@01DA550B.22A71F30" alt="signature_882949974"></span></b></span></a><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none"><o:p></o:p></span></b></p>
</td>
</tr>
</tbody>
</table>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-ligatures:none"><o:p> </o:p></span></p>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>