<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=us-ascii">
<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;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
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:0cm;
margin-right:0cm;
margin-bottom:0cm;
margin-left:36.0pt;
font-size:11.0pt;
font-family:"Aptos",sans-serif;
mso-ligatures:standardcontextual;}
span.EmailStyle21
{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:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;}
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:\F0B7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
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:-18.0pt;
font-family:"Courier New";}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
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:-18.0pt;
font-family:"Courier New";}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
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:-18.0pt;
font-family:"Courier New";}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l1
{mso-list-id:1330865320;
mso-list-template-ids:-1598621860;}
@list l1:level1
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:36.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level2
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:72.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level3
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:108.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level4
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:144.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level5
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:180.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level6
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:216.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level7
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:252.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level8
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:288.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level9
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:324.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
ol
{margin-bottom:0cm;}
ul
{margin-bottom:0cm;}
--></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-GB" link="#467886" vlink="#96607D" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Hi all,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">WORDS to capture our discussion on Monday 29th Jan.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">The MPI_Comm_create_from_group procedure must handle some difficult cases:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">3. the potential for the additional MPI processes to fail during the operation<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">1. failed before the operation<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">2. different groups at different processes<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">There are several sub-cases here:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">b) procA's group contains procB but procB's does not include procA<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">We have two broad categories of approach here:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">- any problem results in an error, return immediately without creating the output communicator<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">- 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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">We probably want a resilient algorithm that doesn’t have dreadful scaling.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">3. failures during the operation<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Resilient algorithm:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Be eager to help: Always listen for incoming protocol messages related to communicator creation.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Attempt communication with your direct children;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"> 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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"> 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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Attempt communication with your parent;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"> 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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"> 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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Assume it all worked beautifully but execute MPI_Comm_agree to make certain.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"> if new failure detected, update the local group, update the local detector, start again<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"> if the agreement succeeds without discovering new failures, we're done!<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">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 style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Best wishes,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Dan.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US" style="font-family:"Calibri",sans-serif;mso-ligatures:none">From:</span></b><span lang="EN-US" 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"><o:p> </o:p></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Hi Howard/all,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Here is the simple code I was talking about in the meeting today:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">// general high-level optimistic application<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">void main() {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session session;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session_Init(MPI_INFO_NULL, MPI_ERRORS_ARE_FATAL, &session);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group group;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group_from_session_pset(session, "mpi://world", &group);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Comm comm;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Comm_create_from_group(group, &comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> ret = do_stuff_with_comm(comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> if (MPI_SUCCESS == ret) {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Comm_disconnect(&comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session_Finalize(&session);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> break;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> } else {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> panic();<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> }<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">}<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">// general high-level pragmatic application<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">void main() {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> // additional code<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> while (1) {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session session;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session_Init(MPI_INFO_NULL, MPI_ERRORS_RETURN, &session);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group world, failed, group;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group_from_session_pset(session, "mpi://world", &world);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> // additional code<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session_get_proc_failed(session, &failed); // new API, seems easy to do<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group_difference(world, failed, &group);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group_free(&world);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group_free(&failed);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Comm comm;<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Comm_create_from_group(group, &comm); // <-- the detail-devils live here<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Group_free(&group);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> ret = do_stuff_with_comm(comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Comm_disconnect(&comm);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> MPI_Session_Finalize(&session);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> if (MPI_SUCCESS == ret) {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> break; // all done!<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> } else if (MPI_ERR_PROC_FAILED == ret) {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> continue; // no more panic<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> }<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> // additional code<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US"> } // end while<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Courier New";mso-fareast-language:EN-US">}<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Best wishes,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Dan.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US" style="font-family:"Calibri",sans-serif;mso-ligatures:none">From:</span></b><span lang="EN-US" 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"><o:p> </o:p></p>
<p class="MsoNormal"><span lang="EN-US">Hi Folks,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Let’s meet on 1/29 to continue discussions related to sessions and FT.
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">I think what will help is to consider several use cases and implications.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Here are some I have<o:p></o:p></span></p>
<ul style="margin-top:0cm" type="disc">
<li class="MsoListParagraph" style="margin-left:0cm;mso-list:l0 level1 lfo3"><span lang="EN-US">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></span></li><li class="MsoListParagraph" style="margin-left:0cm;mso-list:l0 level1 lfo3"><span lang="EN-US">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></span></li><li class="MsoListParagraph" style="margin-left:0cm;mso-list:l0 level1 lfo3"><span lang="EN-US">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></span></li></ul>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">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></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">For those with access, the ULFM slice 1 PR is at
<a href="https://github.com/mpi-forum/mpi-standard/pull/947">https://github.com/mpi-forum/mpi-standard/pull/947</a><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Thanks,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Howard<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<div>
<p class="MsoNormal"><span lang="EN-US" style="font-family:"Calibri",sans-serif;mso-ligatures:none">-------<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" 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:129.6pt">
<td width="76" valign="top" style="width:56.95pt;padding:0cm 5.4pt 0cm 5.4pt;height:129.6pt">
<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@01DA552F.F06648F0" alt="signature_61897647"></span><span style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-ligatures:none"><o:p></o:p></span></p>
</td>
<td width="290" valign="top" style="width:217.55pt;padding:0cm 5.4pt 0cm 5.4pt;height:129.6pt">
<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://www.instagram.com/losalamosnatlab/"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none;text-decoration:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_4" src="cid:image002.png@01DA552F.F06648F0" alt="signature_1672648044"></span></b></a><a href="https://twitter.com/LosAlamosNatLab"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none;text-decoration:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_3" src="cid:image003.png@01DA552F.F06648F0" alt="signature_2067890307"></span></b></a><a href="https://www.linkedin.com/company/los-alamos-national-laboratory/"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none;text-decoration:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_2" src="cid:image004.png@01DA552F.F06648F0" alt="signature_1942525183"></span></b></a><a href="https://www.facebook.com/LosAlamosNationalLab/"><b><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#0B1A8C;mso-ligatures:none;text-decoration:none"><img border="0" width="27" height="27" style="width:.2812in;height:.2812in" id="Picture_x0020_1" src="cid:image005.png@01DA552F.F06648F0" alt="signature_882949974"></span></b></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 lang="EN-US" style="font-family:"Calibri",sans-serif;mso-ligatures:none"><o:p> </o:p></span></p>
</div>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
</div>
</body>
</html>