<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 14 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-reply;
font-family:"Calibri","sans-serif";
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri","sans-serif";}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></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="blue" vlink="purple">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">Thanks, Barry and Jeff! I will pass the word on about MPI-4. I was at the last FASTMath meeting and I do recall that you were at least wondering whether a
shared memory model was needed, but I didn’t realize that you had ripped all of the threading code out of PETSc. For what it’s worth, I am on board with you about the all “MPI” model. I don’t see a compelling reason that MPI+X is needed (especially if you
allow for MPI to evolve into “MPI”), but since we already support MPI+X in hypre, it’s not a huge deal for us to continue along that path with everybody else.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">Thanks again.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">-Rob<o:p></o:p></span></p>
<p class="MsoNormal"><a name="_MailEndCompose"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"><o:p> </o:p></span></a></p>
<div style="border:none;border-left:solid blue 1.5pt;padding:0in 0in 0in 4.0pt">
<div>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:"Tahoma","sans-serif"">From:</span></b><span style="font-size:10.0pt;font-family:"Tahoma","sans-serif""> Jeff Hammond [mailto:jeff.science@gmail.com]
<br>
<b>Sent:</b> Tuesday, January 12, 2016 12:36 PM<br>
<b>To:</b> Barry Smith<br>
<b>Cc:</b> Falgout, Rob; Yang, Ulrike Meier; PETSc<br>
<b>Subject:</b> Re: [petsc-dev] thread communicator<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<p class="MsoNormal">Rob:<o:p></o:p></p>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">You might be interested in the MPI-4 endpoints proposal. It should allow MPI communicators to act as thread communicators.<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">Jeff<o:p></o:p></p>
</div>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<p class="MsoNormal">On Tue, Jan 12, 2016 at 12:33 PM, Barry Smith <<a href="mailto:bsmith@mcs.anl.gov" target="_blank">bsmith@mcs.anl.gov</a>> wrote:<o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:12.0pt"><br>
Rob,<br>
<br>
I guess you missed the last FASTMath meeting. We have stopped all work on using threads a long time ago because we never saw an improvement in performance and it was a pain to maintain. We even ripped the thread code out of PETSc so currently we are back
to being an all "MPI" model.<br>
<br>
Barry<br>
<br>
So far we haven't lost all our funding :-)<br>
<br>
<br>
<br>
> On Jan 11, 2016, at 12:28 PM, Falgout, Rob <<a href="mailto:falgout2@llnl.gov">falgout2@llnl.gov</a>> wrote:<br>
><br>
> Hi Barry,<br>
><br>
> What is the latest on the thread communicator idea you guys were working on? We are having discussions here with a variety of folks (application and library developers as well as vendors) about similar ideas, so I’d like to bring your work into the mix.
Let me know. Thanks!<br>
><br>
> -Rob<br>
><br>
> Robert D. Falgout<br>
> Center for Applied Scientific Computing<br>
> Lawrence Livermore National Laboratory<br>
> P.O. Box 808, L-561, Livermore, CA 94551<br>
> Phone - (925) 422-4377, Email - <a href="mailto:rfalgout@llnl.gov">rfalgout@llnl.gov</a>, Web -
<a href="http://people.llnl.gov/falgout2" target="_blank">http://people.llnl.gov/falgout2</a><o:p></o:p></p>
</div>
<p class="MsoNormal"><br>
<br clear="all">
<o:p></o:p></p>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<p class="MsoNormal">-- <o:p></o:p></p>
<div>
<p class="MsoNormal">Jeff Hammond<br>
<a href="mailto:jeff.science@gmail.com" target="_blank">jeff.science@gmail.com</a><br>
<a href="http://jeffhammond.github.io/" target="_blank">http://jeffhammond.github.io/</a><o:p></o:p></p>
</div>
</div>
</div>
</div>
</body>
</html>