<div dir="ltr"><div dir="ltr">On Sun, Mar 17, 2019 at 8:02 PM Jeff Hammond <<a href="mailto:jeff.science@gmail.com">jeff.science@gmail.com</a>> wrote:<br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr">When this was written, I was convinced that Dursi was wrong about everything because one of the key arguments against MPI was fault-intolerance, which I was sure was going to be solved soon. However, LLNL has done everything in their power to torpedo MPI fault-tolerance in MPI-4 for the past 3+ years and I am no longer optimistic about MPI's ability to grow outside of traditional HPC because of the forum's inability to take fault-tolerance seriously. It's also unclear that we can get by without it in a post-exascale world.</div></blockquote><div><br></div><div>I am interested to hear that. I have never thought much of the software fault tolerance argument. First, I do not think people will</div><div>buy machines that fail all the time. Second, I do not think software fault tolerance is a very promising avenue, looking at the failure</div><div>of standardization on almost everything.</div><div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div>Jeff</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sun, Mar 17, 2019 at 4:33 PM Matthew Knepley via petsc-dev <<a href="mailto:petsc-dev@mcs.anl.gov" target="_blank">petsc-dev@mcs.anl.gov</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div dir="ltr">On Sun, Mar 17, 2019 at 5:34 PM Jed Brown via petsc-dev <<a href="mailto:petsc-dev@mcs.anl.gov" target="_blank">petsc-dev@mcs.anl.gov</a>> wrote:<br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">"Smith, Barry F. via petsc-dev" <<a href="mailto:petsc-dev@mcs.anl.gov" target="_blank">petsc-dev@mcs.anl.gov</a>> writes:<br>
<br>
> I stubbled on this today; I should have seen it years ago.<br>
<br>
<a href="https://lists.mpich.org/pipermail/devel/2015-April/000536.html" rel="noreferrer" target="_blank">https://lists.mpich.org/pipermail/devel/2015-April/000536.html</a><br>
<br>
<a href="https://twitter.com/KpDooty/status/585763759777574912" rel="noreferrer" target="_blank">https://twitter.com/KpDooty/status/585763759777574912</a><br>
<br>
Proposing, as replacements for MPI, systems with no successful libraries<br>
is a strange hill to die on. I'd like a system with more flexible<br>
process management and better support/conventions for interactive<br>
environments (where interrupts and programming bugs are common). That<br>
would help reduce impedance mismatch between MPI and the likes of Spark<br>
and Dask. Any discussion of such tools should include an explanation of<br>
why MPI has been/is used by machine learning groups including Watson,<br>
Baidu, Bing, and OpenAI.<br>
</blockquote></div><br clear="all"><div>I wasted 30s skimming this. I should has used that to recognize the author as a member of the FLASH team before reading.</div><div><br></div><div> Matt</div><div><br></div>-- <br><div dir="ltr" class="gmail-m_2271486078005890830gmail-m_953154836599926641gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener</div><div><br></div><div><a href="http://www.cse.buffalo.edu/~knepley/" target="_blank">https://www.cse.buffalo.edu/~knepley/</a><br></div></div></div></div></div></div></div></div>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail-m_2271486078005890830gmail_signature">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></div>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener</div><div><br></div><div><a href="http://www.cse.buffalo.edu/~knepley/" target="_blank">https://www.cse.buffalo.edu/~knepley/</a><br></div></div></div></div></div></div></div></div>