<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; color: rgb(0, 0, 0); font-size: 14px; font-family: Calibri, sans-serif;"><div>Hi all,</div><div><br></div><div>During the upcoming MPI forum meeting in June we need to plan for the next set of locations and dates in 2017. The goal will, as always, be to a) find locations that are cost effective for the forum; b) times that don’t class with other HPC events; and c) to ensure the most people can come. For next year, though, we have a few anomalies that need to be discussed and so I am writing this email as a heads-up. If you want to respond with some early comments, please do so. Also, if you can’t make it to the meeting in June, but would like your voice heard, please send me email or respond to the group. We’ll take all of this into account during the discussion and decision in Bellevue.</div><div><br></div><div>The biggest anomaly is that EuroMPI is in Chicago next year. The exact dates are: September 25-28, 2017</div><div><br></div><div>Since EuroMPI was traditionally our 1 in 4 slot to be not in the US, we have to decide what do do – as I see it, we have three options:</div><ul><li>Not do any meeting outside the US next year – this will severely impact the ability to attend for some folks, especially from Europe, as far as I understand.</li><li>Pick one of the other meetings and go outside the US for that instead of the September meeting – without EuroMPI, this can severely impact US-based attendance. The suggestion in this case would be to combine the forum meeting with a large event that many may be traveling to anyway – ISC in Frankfurt (6/17-6/21) could fit that bill and RWTH Aachen in conjunction with JSC has tentative agreed to explore hosting us in Aachen the week before ISC (only about a 1-2 hour train ride between Aachen and Frankfurt and the facilities in Aachen have worked well for previous similar meetings) - thanks to Marc-Andre for helping explore this option!</li><li>We could stick with the schedule and go outside the US in September anyway (without overlapping with EuroMPI, of course :) ).</li></ul><div>If we hold the MPI forum meeting next September in conjunction with EuroMPI in Chicago, we have the additional problem that we likely need to leave a gap of a full weekend between the forum and the conference (based on space availability and having to avoid weekends) or pay extra. Is a co-location still useful in this case?</div><div><br></div><div>Aside from these issues, we’ll have the usual discussion of good locations – we had previously been hosted by Cisco in San Jose and various Microsoft locations (Chicago, Portland, and now Bellevue) as well as we’ll be in Dallas at an IBM site in December. Would anyone of these hosts be willing to host the forum again? SGI has also offered to host us in Eagan next year (thanks to all previous and current hosts!). Anyone else willing to host the forum in the US? </div><div><br></div><div>As an additional item to think about: in 2018, EuroMPI will again be outside the US and so we can go back to our normal routine. Additionally, though, SIAM-PP will be in Tokyo in the spring of 2018 and I was approached by the organizers whether we could co-locate the March forum meeting. The idea was to help each other increase attendance based on the observation that a good number of the regular MPI forum attendees were also part of SIAM-PP 2016, which was in Paris. Are we interested in pursuing this? If so, in addition or instead of EuroMPI?</div><div><br></div><div>Comments, Thoughts?</div><div><br></div><div>Thanks!</div><div><br></div><div>Martin</div><div><br></div><div><br></div><div><div style="font-family: Consolas; font-size: medium;">________________________________________________________________________</div><div style="font-family: Consolas; font-size: medium;">Martin Schulz, <a href="mailto:schulzm@llnl.gov">schulzm@llnl.gov</a>, <a href="http://scalability.llnl.gov/">http://scalability.llnl.gov/</a></div><div style="font-family: Consolas; font-size: medium;">CASC @ Lawrence Livermore National Laboratory, Livermore, USA</div><div><br></div></div></body></html>