<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;" class="">
Thanks Howard, that captures most things I can remember.<br class="">
<div class=""><br class="webkit-block-placeholder">
</div>
<div class="">
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
If we get more time tomorrow, should we go through non-chap10 changes (my preference - none of that has been presented yet) or work on fixing some of the feedback from today (get a head-start on prep for the next virtual meeting)?</div>
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
<br class="Apple-interchange-newline">
Cheers,</div>
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
Dan.</div>
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
—<br class="">
Dr Daniel Holmes PhD<br class="">
Applications Consultant in HPC Research<br class="">
<a href="mailto:d.holmes@epcc.ed.ac.uk" class="">d.holmes@epcc.ed.ac.uk</a><br class="">
Phone: +44 (0) 131 651 3465<br class="">
Mobile: +44 (0) 7940 524 088<br class="">
Address: Room 2.09, Bayes Centre, 47 Potterrow, Central Area, Edinburgh, EH8 9BT</div>
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
—</div>
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.</div>
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant-caps: normal; font-weight: normal; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
—</div>
</div>
<br class="">
<div>
<blockquote type="cite" class="">
<div class="">On 5 Dec 2018, at 18:03, Pritchard Jr.,<span class="Apple-tab-span" style="white-space:pre">
</span>Howard via mpiwg-sessions <<a href="mailto:mpiwg-sessions@lists.mpi-forum.org" class="">mpiwg-sessions@lists.mpi-forum.org</a>> wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; font-size: 14px; font-family: Calibri, sans-serif;" class="">
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Hi Folks,</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Notes from the Sessions reading at 12/5/18 forum:</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Dan gives some background about PR #55 as is. He says we’ve got enough changes that aren’t ticket 0 that this really shouldn’t be called a reading.</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">We’ve added 7271 lines and subtracted 1004. A lot of this is moving around. Move all the getting processes started into chapter 10.</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Wesley asks about dynamic being incompatible with peer to peer – Dan says no, can be mixed. Tony is getting us confused. How to do Sessions</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">outside of MPI? Looking for using sessions concepts for more general job startup. Aurelian asks about how we get groups from nothing – Dan</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">says we aren’t getting groups from nothing – hence the runtime process set notion.</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Martin says we should be more careful about Process vs MPI Process – but this is in places we’ve not changed for sessions in most cases.</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Some discussion of the use of the term Session and “Peer to Peer” - should we use some others?</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">List of things brought up during the reading/plenary</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class=""><br class="">
</div>
<ul class="">
<li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Martin wants to drop “unless the application explicitly calls MPI_INIT” in page 416, lines 46-47. Add valid as an adjective to MPI COMM WORLD in this section. </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">We need to fix the second paragraph of 10.1 to better integrate the dynamic process model back into the 3 models for process creation</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">fix 10.1 subtitle!</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">page 417 line 22 add Window or File</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">water down line 45 on page 416 or remove</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">question about MPC-MPI MPI process is a thread model from Aurelian and Martin. We need to think about this – maybe add a blurb in the pset definition</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Maybe move last paragraph in 10.4 up to intro part of chapter and reword a bit. remove backward compatible?</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">swap 10.4.1 with 10.4.2.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">page 418 line 1 remove use of “runtime” in that first, todo: decide if we want to mandate or highly recommend
<a href="mpi://UNIVERSE" class="">mpi://UNIVERSE</a> and <a href="mpi://comm" class="">
mpi://comm</a> type <a href="http://shared.no" class="">shared.no</a> examples.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">make clearer what’s going on with lines 4-5, what exactly is a pset. define semantically? </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">some discussion of groups and getting groups from psets</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">key is mandatory for all process sets - Jeff Squyres thinks this needs more verbiage.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">add some more discussion about the flags bit mask to MPI Session init.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">fix f08 binding for MPI_Session_init flags should be TYPE(MPI_Flags), check other f08 bindings too where INTEGER should be replaced with a TYPE</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">could we use info arg to MPI_Session_init rather than flags</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">use tools cvar/pvar approach for psets and their lengths</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">replace MPI_Errhandler with MPI_Session_errhandler in multiple places</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">add text for thread level support </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Aurelian asks about thread safety for things like data type manipulation, etc. This needs to go with the info ops before MPI Init discussion.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">an advice to users about sessions and how implementations may use them – Dan talks about isolation and multiplexing, grouping of communicators. </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">should we call Sessions Enclaves? </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">pre-defined info keys</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">options naming for sessions? Nathan asked about this.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">communicator inherits uri as its name idea</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">need to add local to the description of MPI_Session_init</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">be consistent with capitalization of session/enclave Martin says put MPI in front of Enclave or Session</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">function name for MPI_Session_init line 46 on page 418</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">make session handle in out to MPI_Session_finalize </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">need a lot more text – use analogous not equivalent, should we add a drop-all-resources type of call that frees all resources associated with a session. Collective. Files, windows, communicators,
groups get leaned up</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">MPI Session get num sets replace pset_name with npsets or something like this,</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">same issue with get_psetlen </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">could we replace all this with an in/out info object</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">definitely need to keep the figure</li><li class=""><font face="Calibri,sans-serif" style="font-size: 14px;" class="">rework chapter describing </font><span style="font-size: 11px; font-family: Helvetica;" class="">MPI_SESSION_GET_NTH_PSET
</span><font face="Calibri" class="">about room for NULL terminator etc. Check MPI T and info</font></li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">in the code example title add a reference to chapter six functions.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">question about where the example would block </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">verbiage about session finalize associated with the example</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">uniqueness of uri (Jeff says don’t use this!!!) across sets of processes, suggestion and advice to users for MPI_Create_comm_from_group
<a href="gov://llnl" class="">gov://llnl</a> thingy </li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">Tony is talking about doing state transitions.</li><li style="font-size: 14px; font-family: Calibri, sans-serif;" class="">should we rename MPI_GROUP_FROM_SESSION_PSET . maybe return MPI GROUP EMPTY if not valid pset name?</li></ul>
<div class="">Howard</div>
<div class=""><br class="">
</div>
<div style="font-size: 14px; font-family: Calibri, sans-serif;" class="">
<div class="">
<div class="">-- </div>
<div class="">Howard Pritchard</div>
</div>
<div class="">B Schedule</div>
<div class="">HPC-ENV</div>
<div class="">
<div style="margin: 0in 0in 0.0001pt; font-size: 11pt;" class="">Office 9, 2<sup class="">nd</sup> floor Research Park<o:p class=""></o:p></div>
<div style="margin: 0in 0in 0.0001pt; font-size: 11pt;" class="">TA-03, Building 4200, Room 203</div>
</div>
<div class="">Los Alamos National Laboratory</div>
<div class=""><br class="">
</div>
</div>
</div>
_______________________________________________<br class="">
mpiwg-sessions mailing list<br class="">
<a href="mailto:mpiwg-sessions@lists.mpi-forum.org" class="">mpiwg-sessions@lists.mpi-forum.org</a><br class="">
https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions<br class="">
</div>
</blockquote>
</div>
<br class="">
</body>
</html>