From jsquyres at [hidden] Tue Sep 1 08:50:54 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Tue, 1 Sep 2009 15:50:54 +0200 Subject: [Mpi-22] [MPI Forum] #146: Fix MPI_INIT description text In-Reply-To: <055.e9516f55b7bd4e5141b41cb71e5b0257@lists.mpi-forum.org> Message-ID: Rolf -- I don't understand. I *did* follow my own state diagram -- ticket #146 is done done done, so I resolved it in the "Ticket Complete" state. I attached the PDF for reference. You're saying that the ticket should be left open and just have its priority changed to "Text Committed". I disagree. The state diagram has the ticket state go to "Text Committed", not "Text Committed" followed by resolving it in "Text Committed" *again*. It was definitely my intention when making this state diagram that tickets should be *resolved* (i.e., closed) in with the "Text Committed" state. If there is a "Text Committed" priority (and I see that there is), I believe that to be a mistake. To be clear -- "Withdrawn", "Rejected", and "Deferred" are resolution (closing) states. They are not priorities. "Text Committed" was intended to be the same. Perhaps I'm just grouchy from jet lag. :-) On Sep 1, 2009, at 3:40 PM, MPI Forum wrote: > #146: Fix MPI_INIT description text > ------------------------------------------------- > +-------------------------- > Reporter: jsquyres > | Owner: jsquyres > Type: Text (only) changes > | Status: reopened > Priority: Ticket complete > | Milestone: 2009/07/27 Chicago > Version: MPI 2.2 > | Resolution: > Keywords: | > Implementation: Unnecessary > Author_bill_gropp: 0 | > Author_rich_graham: 0 > Author_adam_moody: 0 | > Author_torsten_hoefler: 0 > Author_dick_treumann: 0 | > Author_jesper_larsson_traeff: 0 > Author_george_bosilca: 1 | > Author_david_solt: 0 > Author_bronis_de_supinski: 0 | > Author_rajeev_thakur: 0 > Author_jeff_squyres: 0 | > Author_alexander_supalov: 0 > Author_rolf_rabenseifner: 0 | > ------------------------------------------------- > +-------------------------- > Changes (by RolfRabenseifner): > > * priority: Waiting for PDF reviews => Ticket complete > * status: closed => reopened > * resolution: Text committed => > > > Comment: > > Sory Jeff, our rule is open + ticket complete. > > Please see your own diagram. > > -- > Ticket URL: > > MPI Forum > MPI Forum > -- Jeff Squyres jsquyres_at_[hidden] * -------------- next part -------------- A non-text attachment was scrubbed... Name: MPI-2.2_ticket_states.pdf Type: application/pdf Size: 467281 bytes Desc: MPI-2.2_ticket_states.pdf URL: From rabenseifner at [hidden] Tue Sep 1 16:58:12 2009 From: rabenseifner at [hidden] (Rolf Rabenseifner) Date: Tue, 01 Sep 2009 23:58:12 +0200 Subject: [Mpi-22] [MPI Forum] #146: Fix MPI_INIT description text In-Reply-To: Message-ID: Jeff, I forward in the next mail Bill's answer to an earlier question on this topic. Currently, all 82 valid MPI-2.2 are kept as unclosed. They go from passed to wait pdf to complete. I expect that Bill will do the final step to close all 82 tickets when MPI-2.2 is done. Attached is your latest state diagram. Best regards Rolf On Tue, 1 Sep 2009 15:50:54 +0200 Jeff Squyres wrote: > Rolf -- > > I don't understand. I *did* follow my own state diagram -- ticket > #146 is done done done, so I resolved it in the "Ticket Complete" > state. I attached the PDF for reference. > > You're saying that the ticket should be left open and just have its > priority changed to "Text Committed". I disagree. > > The state diagram has the ticket state go to "Text Committed", not > "Text Committed" followed by resolving it in "Text Committed" > *again*. It was definitely my intention when making this state > diagram that tickets should be *resolved* (i.e., closed) in with the > "Text Committed" state. If there is a "Text Committed" priority >(and I see that there is), I believe that to be a mistake. > > To be clear -- "Withdrawn", "Rejected", and "Deferred" are >resolution (closing) states. They are not priorities. "Text >Committed" was intended to be the same. > > Perhaps I'm just grouchy from jet lag. :-) > > > > > > On Sep 1, 2009, at 3:40 PM, MPI Forum wrote: > >> #146: Fix MPI_INIT description text >> ------------------------------------------------- >> +-------------------------- >> Reporter: jsquyres >> | Owner: jsquyres >> Type: Text (only) changes >> | Status: reopened >> Priority: Ticket complete >> | Milestone: 2009/07/27 Chicago >> Version: MPI 2.2 >> | Resolution: >> Keywords: | >> Implementation: Unnecessary >> Author_bill_gropp: 0 | >> Author_rich_graham: 0 >> Author_adam_moody: 0 | >> Author_torsten_hoefler: 0 >> Author_dick_treumann: 0 | >> Author_jesper_larsson_traeff: 0 >> Author_george_bosilca: 1 | >> Author_david_solt: 0 >> Author_bronis_de_supinski: 0 | >> Author_rajeev_thakur: 0 >> Author_jeff_squyres: 0 | >> Author_alexander_supalov: 0 >> Author_rolf_rabenseifner: 0 | >> ------------------------------------------------- >> +-------------------------- >> Changes (by RolfRabenseifner): >> >> * priority: Waiting for PDF reviews => Ticket complete >> * status: closed => reopened >> * resolution: Text committed => >> >> >> Comment: >> >> Sory Jeff, our rule is open + ticket complete. >> >> Please see your own diagram. >> >> -- >> Ticket URL: >>> > >> MPI Forum >> MPI Forum >> > > > -- > Jeff Squyres > jsquyres_at_[hidden] Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner_at_[hidden] High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530 University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832 Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30) * -------------- next part -------------- A non-text attachment was scrubbed... Name: MPI-2.2_ticket_states.pdf Type: application/pdf Size: 467281 bytes Desc: MPI-2.2_ticket_states.pdf URL: From rabenseifner at [hidden] Tue Sep 1 16:59:10 2009 From: rabenseifner at [hidden] (Rolf Rabenseifner) Date: Tue, 01 Sep 2009 23:59:10 +0200 Subject: [Mpi-22] Fwd: Final state transition - was Re: [MPI Forum] #104: MPI_ARGV_NULL and MPI_ARGVS_NULL missing on p465:13-15. Message-ID: As answer to Jeffs mail, again with attached state diagram. --- the forwarded message follows --- attached mail follows: Thanks, Rolf. You are correct. Bill On Aug 25, 2009, at 2:53 AM, Rolf Rabenseifner wrote: > Hi all, > > based on our final state transition diagram, > the last state transition we are currently doing is: > > Priority: Waiting for PDF reviews --> Ticket complete > > This should be done by the ticket author (blue arrow), > and not by the chapter author (arrow is not black). > > We don't define to set the ticket to > Status: closed > Resolution: Text committed > > Therefore, I'll set my ticket back to > Status: reopened > > All othe completed tickets are in the same state, > i.e., Status "open" or "reopened", > and Priority "ticket complete". > > I hope that this is okay. > > Best regards > Rolf > >> From: Jeff Squyres >> Subject: Re: [Mpi-22] SVN committing MPI-2.2 latex >> Date: Fri, 12 Jun 2009 08:47:48 -0700 >> >> Ok, try this diagram. > ... >> Attachment: MPI-2.2 ticket states.pdf (463Kbytes) > > > On Tue, 25 Aug 2009 01:08:32 -0000 > "MPI Forum" wrote: >> #104: MPI_ARGV_NULL and MPI_ARGVS_NULL missing on p465:13-15. >> -------------------------------------------------- >> +------------------------- >> Reporter: RolfRabenseifner | >> Owner: RolfRabenseifner >> Type: Trivial text changes | >> Status: closed >> Priority: Ticket complete | >> Milestone: 2009/06/08 California >> Version: MPI 2.2 | >> Resolution: Text committed >> Keywords: | >> Implementation: Unnecessary >> Author_bill_gropp: 0 | >> Author_rich_graham: 0 >> Author_adam_moody: 0 | >> Author_torsten_hoefler: 0 >> Author_dick_treumann: 0 | >> Author_jesper_larsson_traeff: 0 >> Author_george_bosilca: 0 | >> Author_david_solt: 0 >> Author_bronis_de_supinski: 0 | >> Author_rajeev_thakur: 0 >> Author_jeff_squyres: 1 | >> Author_alexander_supalov: 0 >> Author_rolf_rabenseifner: 0 | >> -------------------------------------------------- >> +------------------------- >> Changes (by jsquyres): >> >> * status: new => closed >> * resolution: => Text committed >> >> >> Comment: >> >> The changes Rolf made look good to me. I attached a new PDF, just >> in case >> anyone cares. >> >> Resolving this ticket to "text committed". >> >> -- >> Ticket URL: >> >> MPI Forum >> MPI Forum > > Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner_at_[hidden] > High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530 > University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832 > Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner > Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30) > _______________________________________________ > mpi-22 mailing list > mpi-22_at_[hidden] > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign _______________________________________________ mpi-22 mailing list mpi-22_at_[hidden] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 * -------------- next part -------------- A non-text attachment was scrubbed... Name: MPI-2.2_ticket_states.pdf Type: application/pdf Size: 467281 bytes Desc: MPI-2.2_ticket_states.pdf URL: From jsquyres at [hidden] Tue Sep 1 22:10:26 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Wed, 2 Sep 2009 06:10:26 +0300 Subject: [Mpi-22] Fwd: Final state transition - was Re: [MPI Forum] #104: MPI_ARGV_NULL and MPI_ARGVS_NULL missing on p465:13-15. In-Reply-To: Message-ID: I still disagree (the state diagrams you sent are exactly the same as the one I sent yesterday). What is the point of leaving the tickets open after their PDFs have been reviewed and the text has been successfully committed? You don't gain anything in terms of searchability of MPI 2.2 tickets, for example. All it does it make yet another step that has to be performed later. I repeat: it was definitely my intention that "Withdrawn", "Rejected", "Deferred", and "Text committed" were definitely *resolutions*, not *priorities*. The fact that there is a "Text committed" priority is a mistake. On Sep 2, 2009, at 12:59 AM, Rolf Rabenseifner wrote: > > As answer to Jeffs mail, again with attached state diagram. > > --- the forwarded message follows --- > > > From: "William Gropp" > Date: August 26, 2009 8:01:26 AM GMT+03:00 > To: "MPI 2.2" > Subject: Re: [Mpi-22] Final state transition - was Re: [MPI Forum] > #104:MPI_ARGV_NULL and MPI_ARGVS_NULL missing on p465:13-15. > Reply-To: "MPI 2.2" > > > Thanks, Rolf. You are correct. > > Bill > > On Aug 25, 2009, at 2:53 AM, Rolf Rabenseifner wrote: > > > Hi all, > > > > based on our final state transition diagram, > > the last state transition we are currently doing is: > > > > Priority: Waiting for PDF reviews --> Ticket complete > > > > This should be done by the ticket author (blue arrow), > > and not by the chapter author (arrow is not black). > > > > We don't define to set the ticket to > > Status: closed > > Resolution: Text committed > > > > Therefore, I'll set my ticket back to > > Status: reopened > > > > All othe completed tickets are in the same state, > > i.e., Status "open" or "reopened", > > and Priority "ticket complete". > > > > I hope that this is okay. > > > > Best regards > > Rolf > > > >> From: Jeff Squyres > >> Subject: Re: [Mpi-22] SVN committing MPI-2.2 latex > >> Date: Fri, 12 Jun 2009 08:47:48 -0700 > >> > >> Ok, try this diagram. > > ... > >> Attachment: MPI-2.2 ticket states.pdf (463Kbytes) > > > > > > On Tue, 25 Aug 2009 01:08:32 -0000 > > "MPI Forum" wrote: > >> #104: MPI_ARGV_NULL and MPI_ARGVS_NULL missing on p465:13-15. > >> -------------------------------------------------- > >> +------------------------- > >> Reporter: RolfRabenseifner | > >> Owner: RolfRabenseifner > >> Type: Trivial text changes | > >> Status: closed > >> Priority: Ticket complete | > >> Milestone: 2009/06/08 California > >> Version: MPI 2.2 | > >> Resolution: Text committed > >> Keywords: | > >> Implementation: Unnecessary > >> Author_bill_gropp: 0 | > >> Author_rich_graham: 0 > >> Author_adam_moody: 0 | > >> Author_torsten_hoefler: 0 > >> Author_dick_treumann: 0 | > >> Author_jesper_larsson_traeff: 0 > >> Author_george_bosilca: 0 | > >> Author_david_solt: 0 > >> Author_bronis_de_supinski: 0 | > >> Author_rajeev_thakur: 0 > >> Author_jeff_squyres: 1 | > >> Author_alexander_supalov: 0 > >> Author_rolf_rabenseifner: 0 | > >> -------------------------------------------------- > >> +------------------------- > >> Changes (by jsquyres): > >> > >> * status: new => closed > >> * resolution: => Text committed > >> > >> > >> Comment: > >> > >> The changes Rolf made look good to me. I attached a new PDF, just > >> in case > >> anyone cares. > >> > >> Resolving this ticket to "text committed". > >> > >> -- > >> Ticket URL: > >> 31> > >> MPI Forum > >> MPI Forum > > > > Dr. Rolf Rabenseifner . . . . . . . . . .. email > rabenseifner_at_[hidden] > > High Performance Computing Center (HLRS) . phone + > +49(0)711/685-65530 > > University of Stuttgart . . . . . . . . .. fax ++49(0)711 / > 685-65832 > > Head of Dpmt Parallel Computing . . . www.hlrs.de/people/ > rabenseifner > > Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30) > > _______________________________________________ > > mpi-22 mailing list > > mpi-22_at_[hidden] > > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 > > William Gropp > Deputy Director for Research > Institute for Advanced Computing Applications and Technologies > Paul and Cynthia Saylor Professor of Computer Science > University of Illinois Urbana-Champaign > > > > > _______________________________________________ > mpi-22 mailing list > mpi-22_at_[hidden] > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 > > > > -- Jeff Squyres jsquyres_at_[hidden] From wgropp at [hidden] Wed Sep 2 07:27:56 2009 From: wgropp at [hidden] (William Gropp) Date: Wed, 2 Sep 2009 07:27:56 -0500 Subject: [Mpi-22] [MPI Forum] #7: Function pointer typedefs: "_function" vs. "_fn" In-Reply-To: <055.58cd453f18b8b44d63ee673b465beb6f@lists.mpi-forum.org> Message-ID: <0BEAD0A8-5452-4827-8EE8-045F8365CCD6@illinois.edu> If you build the version with changes, all of the macros in the deleted or replaced code are still executed, which means that side- effects, such as index entries, are added. I checked the official version, and the only index entries for the _fn versions are from the deprecated discussion and the change log. Bill On Sep 2, 2009, at 5:27 AM, MPI Forum wrote: > #7: Function pointer typedefs: "_function" vs. "_fn" > --------------------------------------------------------- > +------------------ > Reporter: jsquyres > | Owner: jsquyres > Type: Enhancements to standard > | Status: assigned > Priority: Waiting for PDF reviews > | Milestone: 2009/07/27 Chicago > Version: MPI 2.2 > | Keywords: > Implementation: Completed | > Author_bill_gropp: 1 > Author_rich_graham: 0 | > Author_adam_moody: 0 > Author_torsten_hoefler: 0 | > Author_dick_treumann: 0 > Author_jesper_larsson_traeff: 0 | > Author_george_bosilca: 1 > Author_david_solt: 0 | > Author_bronis_de_supinski: 0 > Author_rajeev_thakur: 0 | > Author_jeff_squyres: 0 > Author_alexander_supalov: 1 | > Author_rolf_rabenseifner: 1 > --------------------------------------------------------- > +------------------ > > Comment(by bronis): > > Perhaps I am just confused. Why do the *_fn items still appear in the > index in ticket7_all_except_inquiry.pdf? Is it outdated? > > I have a low bandwidth connection and I would like to avoid pulling > down > the current version of the whole document... > > It appears impossible to check the index without doing that but it > also > seems unlikely looking at the comment history that the old entries > have > been removed. > > PDF review of everything other than the index is OK. > > -- > Ticket URL: > > MPI Forum > MPI Forum William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign From wgropp at [hidden] Wed Sep 2 09:14:40 2009 From: wgropp at [hidden] (William Gropp) Date: Wed, 2 Sep 2009 09:14:40 -0500 Subject: [Mpi-22] MPI document review instructions for those at Helsinki meeting Message-ID: <1F510246-F50A-4C38-974A-57F5E2458B6C@illinois.edu> Here are the two slides that I presented about the review responsibilities. For those not at the Helsinki meeting, please feel free to look at any part of the document. Bill William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign * -------------- next part -------------- A non-text attachment was scrubbed... Name: final-mpi22-review-instructions.pdf Type: application/pdf Size: 54478 bytes Desc: final-mpi22-review-instructions.pdf URL: From traff at [hidden] Wed Sep 2 11:19:26 2009 From: traff at [hidden] (Jesper-Larsson Träff) Date: Wed, 2 Sep 2009 18:19:26 +0200 Subject: [Mpi-22] MPI document review instructions for those at Helsinki meeting In-Reply-To: <1F510246-F50A-4C38-974A-57F5E2458B6C@illinois.edu> Message-ID: <20090902161926.GA22390@fourier.it.neclab.eu> the current version in the repository is 447? Jesper On Wed, Sep 02, 2009 at 09:14:40AM -0500, William Gropp wrote: > Here are the two slides that I presented about the review > responsibilities. For those not at the Helsinki meeting, please feel > free to look at any part of the document. > Bill > > > > William Gropp > Deputy Director for Research > Institute for Advanced Computing Applications and Technologies > Paul and Cynthia Saylor Professor of Computer Science > University of Illinois Urbana-Champaign > > > > > _______________________________________________ > mpi-22 mailing list > mpi-22_at_[hidden] > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 * -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/x-pkcs7-signature Size: 3376 bytes Desc: smime.p7s URL: From wgropp at [hidden] Wed Sep 2 13:05:00 2009 From: wgropp at [hidden] (William Gropp) Date: Wed, 2 Sep 2009 13:05:00 -0500 Subject: [Mpi-22] MPI document review instructions for those at Helsinki meeting In-Reply-To: <20090902161926.GA22390@fourier.it.neclab.eu> Message-ID: <122767DC-EC94-4F1A-8325-DE7345F32F6C@illinois.edu> There are only a few minor differences between 442 and 447 (I've looked at the full diff). It is mostly a few additional fixes to spacing and correcting macro usage. The one visible change is array indices in the graph topology examples; there was a clear off-by-one error there. (Note to everyone: much as I'd like to improve the document, further fixes should be postponed until MPI-3.) Bill On Sep 2, 2009, at 11:19 AM, Jesper-Larsson Träff wrote: > > the current version in the repository is 447? > > Jesper > > On Wed, Sep 02, 2009 at 09:14:40AM -0500, William Gropp wrote: >> Here are the two slides that I presented about the review >> responsibilities. For those not at the Helsinki meeting, please feel >> free to look at any part of the document. >> Bill >> > > >> >> >> William Gropp >> Deputy Director for Research >> Institute for Advanced Computing Applications and Technologies >> Paul and Cynthia Saylor Professor of Computer Science >> University of Illinois Urbana-Champaign >> >> >> >> > >> _______________________________________________ >> mpi-22 mailing list >> mpi-22_at_[hidden] >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 > > William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign From wgropp at [hidden] Thu Sep 3 08:39:47 2009 From: wgropp at [hidden] (William Gropp) Date: Thu, 3 Sep 2009 08:39:47 -0500 Subject: [Mpi-22] MPI 2.2 Draft Standard Message-ID: Draft copies of the MPI 2.2 standard are available at http://www.mpi-forum.org/docs/mpi-2.2/ These are the versions on which we will vote on Friday (tomorrow). Assuming that we vote in the MPI 2.2 standard, these versions will be made available as MPI 2.2 from http://www.mpi-forum.org/docs/ . Bill William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign From jsquyres at [hidden] Fri Sep 4 04:05:05 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Fri, 4 Sep 2009 12:05:05 +0300 Subject: [Mpi-22] MPI-2.2 has passed Message-ID: <4904F88A-4A92-4E6B-960C-CBFF82AFBB22@cisco.com> Woo hoo! The final vote on the whole MPI-2.2 document was: - yes: 14 - no: 1 - abstain: 2 I'll post the full votes on meetings.mpi-forum.org soon; Bill will post the final final final documents on the mpi-forum.org web site soon. I have tagged SVN (/trunk/MPI-2.2_at_469 to /tags/MPI-2.2). I also added the official PDFs and .idx file to /tags/MPI-2.2. Congrats to all! -- Jeff Squyres jsquyres_at_[hidden] From jsquyres at [hidden] Fri Sep 4 04:06:00 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Fri, 4 Sep 2009 12:06:00 +0300 Subject: [Mpi-22] please sign up on MPI-3 list Message-ID: <09CEE604-CF9B-4A60-9187-7605CE624BEF@cisco.com> A reminder: we're about the dive deeply into MPI-3 discussions. You probably want to sign up on the MPI-3 general mailing list (just like we had the MPI-2.1 and MPI-2.2 mailing lists). Here's the signup page: http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-3 Mails to the MPI-3 list are archived are lists.mpi-forum.org (just like all other MPI Forum lists). Enjoy! -- Jeff Squyres jsquyres_at_[hidden] From wyu at [hidden] Fri Sep 4 04:11:34 2009 From: wyu at [hidden] (wyu_at_[hidden]) Date: Fri, 4 Sep 2009 09:11:34 +0000 Subject: [Mpi-22] [Mpi-forum] MPI-2.2 has passed In-Reply-To: <4904F88A-4A92-4E6B-960C-CBFF82AFBB22@cisco.com> Message-ID: <143699811-1252055496-cardhu_decombobulator_blackberry.rim.net-1217775763-@bda057.bisx.prodap.on.blackberry> Congratulation to all who have invested hard work and sweat to this. "Sent via BlackBerry from Smart" -----Original Message----- From: Jeff Squyres Date: Fri, 4 Sep 2009 12:05:05 To: ; MPI Forum Subject: [Mpi-forum] MPI-2.2 has passed Woo hoo! The final vote on the whole MPI-2.2 document was: - yes: 14 - no: 1 - abstain: 2 I'll post the full votes on meetings.mpi-forum.org soon; Bill will post the final final final documents on the mpi-forum.org web site soon. I have tagged SVN (/trunk/MPI-2.2_at_469 to /tags/MPI-2.2). I also added the official PDFs and .idx file to /tags/MPI-2.2. Congrats to all! -- Jeff Squyres jsquyres_at_[hidden] _______________________________________________ mpi-forum mailing list mpi-forum_at_[hidden] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum From jsquyres at [hidden] Mon Sep 7 09:18:15 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Mon, 7 Sep 2009 10:18:15 -0400 Subject: [Mpi-22] Fwd: [MPI Forum] #171: change MPI_C_BOOL external32 size to 1 byte In-Reply-To: <054.0427ad7d43bd1a9b43b313a808a63189@lists.mpi-forum.org> Message-ID: <9061A41D-8113-495A-BA04-5FF45071419E@cisco.com> Forwarding this on to the general MPI-2.2 list because I'd like to ask for clarifcation on the MPI-2.2 errata process (i.e., what *exactly* did we vote for on ticket #171?)... Begin forwarded message: > From: "MPI Forum" > Date: September 7, 2009 10:13:23 AM EDT > Subject: Re: [MPI Forum] #171: change MPI_C_BOOL external32 size to > 1 byte > > #171: change MPI_C_BOOL external32 size to 1 byte > ------------------------------------------------------- > +-------------------- > Reporter: goodell > | Owner: > Type: Correction to standard > | Status: new > Priority: Had 1st vote > | Milestone: 2009/09/02 Helsinki > Version: MPI 2.2 errata > | Keywords: > Implementation: Unnecessary | > Author_bill_gropp: 0 > Author_rich_graham: 0 | > Author_adam_moody: 0 > Author_torsten_hoefler: 0 | > Author_dick_treumann: 0 > Author_jesper_larsson_traeff: 0 | > Author_george_bosilca: 0 > Author_david_solt: 0 | > Author_bronis_de_supinski: 0 > Author_rajeev_thakur: 1 | > Author_jeff_squyres: 0 > Author_alexander_supalov: 0 | > Author_rolf_rabenseifner: 0 > ------------------------------------------------------- > +-------------------- > > Comment(by jsquyres): > > After a little reflection, I'm a bit unclear on '''exactly''' what we > voted on for this ticket. > > Specifically, is this ticket a request to change the MPI-2.2 > latex? If > so, it is not in the proper form -- it should have the proper > sections for > all tickets. > > Or is this a ticket to add a bullet to the not-yet-created MPI-2.2 > errata > document? If so, I don't see clearly delineated what text > '''exactly''' > is going into the new errata document. > > To be more clear: I believe that the entire MPI-2.2 errata process > needs > to be laid out. It seems clear to me that we need ''both'' changes > to the > MPI-2.2 latex (for the 2.3 or 3.0 or whatever the next MPI version > document is) ''and'' a bullet for the MPI-2.2 errata document. Are > there > supposed to be two tickets; one for each item? Or should errata > tickets > have text for both documents (line-by-line changes compared to > MPI-2.2 > ''and'' a bullet item for the MPI-2.2 errata document)? > > I understand the urgency of this ticket, but I repeat something > that Bill > said many times in Helsinki: above all else, the process must be > preserved > (in this case: defined!). Pending clarification to the the MPI-2.2 > errata > process, we might need to reset the clock on this ticket. > > -- > Ticket URL: > > MPI Forum > MPI Forum > -- Jeff Squyres jsquyres_at_[hidden] * -------------- next part -------------- An HTML attachment was scrubbed... URL: From wgropp at [hidden] Mon Sep 7 09:57:51 2009 From: wgropp at [hidden] (William Gropp) Date: Mon, 7 Sep 2009 09:57:51 -0500 Subject: [Mpi-22] Fwd: [MPI Forum] #171: change MPI_C_BOOL external32 size to 1 byte In-Reply-To: <9061A41D-8113-495A-BA04-5FF45071419E@cisco.com> Message-ID: <5EC91CC3-EC75-4F9D-BF04-1819E384D4D3@illinois.edu> We *never* change the document LaTex with an errata vote. Errata items are collected into a separate document, which is updated as items are approved. The standard consists of the document plus approved errata items. This is the same process that was used with MPI 2.0. Errata items normally should reference the page/line number in the relevant document (in this case, the 2.2 document); in this particular case, the errata was created before the final line and page numbers were available, and the Forum agreed that it was better to fix this through the errata process rather than delay the MPI 2.2 document. In this particular case, the precise errata item is In MPI 2.2, on page 433, line 22, change MPI_C_BOOL 4 to MPI_C_BOOL 1 I've updated the description to reflect this, as we discussed before the vote. Once an item has been voted on twice, I will prepare a PDF containing these items and add that to the MPI Forum web site as official errata (again, this is what we did for MPI 2.0). The process of creating a new version of the document is not part of the errata process. Should another version be desired, the errata should be folded into it. That is what we did with MPI 2.1. Bill On Sep 7, 2009, at 9:18 AM, Jeff Squyres wrote: > --_004_9061A41D8113495ABA045FF45071419Eciscocom_ > Content-Type: multipart/alternative; > boundary="_000_9061A41D8113495ABA045FF45071419Eciscocom_" > > --_000_9061A41D8113495ABA045FF45071419Eciscocom_ > Content-Type: text/plain; charset="us-ascii" > Content-Transfer-Encoding: quoted-printable > > Forwarding this on to the general MPI-2.2 list because I'd like to > ask for = > clarifcation on the MPI-2.2 errata process (i.e., what *exactly* did > we vot= > e for on ticket #171?)... > > > Begin forwarded message: > > From: "MPI Forum" .org>> > Date: September 7, 2009 10:13:23 AM EDT > Subject: Re: [MPI Forum] #171: change MPI_C_BOOL external32 size to > 1 byte > > > #171: change MPI_C_BOOL external32 size to 1 byte > ------------------------------------------------------- > +-------------------= > - > Reporter: goodell > | = > Owner: > Type: Correction to standard > | = > Status: new > Priority: Had 1st vote > | = > Milestone: 2009/09/02 Helsinki > Version: MPI 2.2 errata > | = > Keywords: > Implementation: Unnecessary | > Author_b= > ill_gropp: 0 > Author_rich_graham: 0 | > Author_a= > dam_moody: 0 > Author_torsten_hoefler: 0 | > Author_dick= > _treumann: 0 > Author_jesper_larsson_traeff: 0 | > Author_georg= > e_bosilca: 0 > Author_david_solt: 0 | > Author_bronis_de= > _supinski: 0 > Author_rajeev_thakur: 1 | > Author_jef= > f_squyres: 0 > Author_alexander_supalov: 0 | > Author_rolf_rab= > enseifner: 0 > ------------------------------------------------------- > +-------------------= > - > > Comment(by jsquyres): > > After a little reflection, I'm a bit unclear on '''exactly''' what we > voted on for this ticket. > > Specifically, is this ticket a request to change the MPI-2.2 latex? > If > so, it is not in the proper form -- it should have the proper > sections for > all tickets. > > Or is this a ticket to add a bullet to the not-yet-created MPI-2.2 > errata > document? If so, I don't see clearly delineated what text > '''exactly''' > is going into the new errata document. > > To be more clear: I believe that the entire MPI-2.2 errata process > needs > to be laid out. It seems clear to me that we need ''both'' changes > to the > MPI-2.2 latex (for the 2.3 or 3.0 or whatever the next MPI version > document is) ''and'' a bullet for the MPI-2.2 errata document. Are > there > supposed to be two tickets; one for each item? Or should errata > tickets > have text for both documents (line-by-line changes compared to MPI-2.2 > ''and'' a bullet item for the MPI-2.2 errata document)? > > I understand the urgency of this ticket, but I repeat something that > Bill > said many times in Helsinki: above all else, the process must be > preserved > (in this case: defined!). Pending clarification to the the MPI-2.2 > errata > process, we might need to reset the clock on this ticket. > > -- > Ticket URL: 171#commen= > t:7> > MPI Forum > MPI Forum > > > -- > Jeff Squyres > jsquyres_at_[hidden] > > > --_000_9061A41D8113495ABA045FF45071419Eciscocom_ > Content-Type: text/html; charset="us-ascii" > Content-Transfer-Encoding: quoted-printable > > space; -webk= > it-line-break: after-white-space; ">Forwarding this on to the > general MPI-2= > .2 list because I'd like to ask for clarifcation on the MPI-2.2 > errata proc= > ess (i.e., what *exactly* did we vote for on ticket > #171?)...

= >
Begin forwarded message:

interchange-newli= > ne">
margin-ri= > ght: 0px; margin-bottom: 0px; margin-left: 0px; "> face=3D"Helvetica" = > size=3D"5" color=3D"#000000" style=3D"font: 18.0px Helvetica; color: > #00000= > 0">From: style=3D"font: 1= > 8.0px Helvetica">"MPI Forum" < rg">mpi-22_at_[hidden]>
style=3D"margin-top= > : 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; > "> e=3D"Helvetica" size=3D"5" color=3D"#000000" style=3D"font: 18.0px > Helvetic= > a; color: #000000">Date: size=3D"5" = > style=3D"font: 18.0px Helvetica">September 7, 2009 10:13:23 AM EDT font> div>
0px; m= > argin-left: 0px; "> color=3D"#000000" st= > yle=3D"font: 18.0px Helvetica; color: #000000">Subject: font> face=3D"Helvetica" size=3D"5" style=3D"font: 18.0px > Helvetica">Re: [MPI= > Forum] #171: change MPI_C_BOOL external32 size to 1 byte div><= > div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; > margin= > -left: 0px; min-height: 14px; ">

#171: change MPI_C_BOOL > external3= > 2 size to 1 byte
> ------------------------------------------------------= > -+--------------------
> = > > Reporter= > : > goodell = > | > &= > nbsp > ;  > ; &nbs= > p; > Owner: = >   > ;  > ; >   >> ; &= > nbsp; > Type:&nbs= > p; Correction to standard | > = >   > ;  > ; &nb= > sp; Status: > new = >
> &nbs= > p > ;  > ; &= > nbsp; Priority: Had 1st > vote  = > ; | > = > > Mileston= > e: 2009/09/02 Helsinki
> = >   > ;  > ; &nb= > sp; Version: MPI 2.2 > errata = > | > &= > nbsp; > Keywords: = >   > ;  > ; &nb= > sp;
> &= > nbsp; Implementation: > Unnecessary= >   > ; | > &= > nbsp; > Author_bill_gro= > pp: > 0 &nbs= > p;
> &n= > bsp; Author_rich_graham: > 0 &= > nbsp > ;  > ; &nbs= > p; | >  = > ; Author_adam_moody: > 0  = > ;  > ; r> &nb William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign From jsquyres at [hidden] Tue Sep 8 12:06:04 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Tue, 8 Sep 2009 13:06:04 -0400 Subject: [Mpi-22] Fwd: [MPI Forum] #171: change MPI_C_BOOL external32size to 1 byte In-Reply-To: <5EC91CC3-EC75-4F9D-BF04-1819E384D4D3@illinois.edu> Message-ID: A few followups... 1. How is it delineated on the ticket exactly what the errata text is to be? I see that you indicated what it precisely is for *this* ticket, but is there a standard form for indicating *exactly* what the errata text is for other tickets? 2. Does a separate ticket need to be filed for MPI 3.0, or is it assumed that the errata change will *also* be applied to the MPI-3.0 latex? (you may have answered this implicitly via "We *never* change the document LaTex with an errata vote", but I wanted to be absolutely 100% crystal clear on this point) Thanks! On Sep 7, 2009, at 10:57 AM, William Gropp wrote: > We *never* change the document LaTex with an errata vote. Errata > items are collected into a separate document, which is updated as > items are approved. The standard consists of the document plus > approved errata items. This is the same process that was used with > MPI 2.0. Errata items normally should reference the page/line number > in the relevant document (in this case, the 2.2 document); in this > particular case, the errata was created before the final line and page > numbers were available, and the Forum agreed that it was better to fix > this through the errata process rather than delay the MPI 2.2 > document. In this particular case, the precise errata item is > > In MPI 2.2, on page 433, line 22, change > > MPI_C_BOOL 4 > > to > > MPI_C_BOOL 1 > > I've updated the description to reflect this, as we discussed before > the vote. > > Once an item has been voted on twice, I will prepare a PDF containing > these items and add that to the MPI Forum web site as official errata > (again, this is what we did for MPI 2.0). > > The process of creating a new version of the document is not part of > the errata process. Should another version be desired, the errata > should be folded into it. That is what we did with MPI 2.1. > > Bill > > On Sep 7, 2009, at 9:18 AM, Jeff Squyres wrote: > > > --_004_9061A41D8113495ABA045FF45071419Eciscocom_ > > Content-Type: multipart/alternative; > > boundary="_000_9061A41D8113495ABA045FF45071419Eciscocom_" > > > > --_000_9061A41D8113495ABA045FF45071419Eciscocom_ > > Content-Type: text/plain; charset="us-ascii" > > Content-Transfer-Encoding: quoted-printable > > > > Forwarding this on to the general MPI-2.2 list because I'd like to > > ask for = > > clarifcation on the MPI-2.2 errata process (i.e., what *exactly* did > > we vot= > > e for on ticket #171?)... > > > > > > Begin forwarded message: > > > > From: "MPI Forum" > .org>> > > Date: September 7, 2009 10:13:23 AM EDT > > Subject: Re: [MPI Forum] #171: change MPI_C_BOOL external32 size to > > 1 byte > > > > > > #171: change MPI_C_BOOL external32 size to 1 byte > > ------------------------------------------------------- > > +-------------------= > > - > > Reporter: goodell > > | = > > Owner: > > Type: Correction to standard > > | = > > Status: new > > Priority: Had 1st vote > > | = > > Milestone: 2009/09/02 Helsinki > > Version: MPI 2.2 errata > > | = > > Keywords: > > Implementation: Unnecessary | > > Author_b= > > ill_gropp: 0 > > Author_rich_graham: 0 | > > Author_a= > > dam_moody: 0 > > Author_torsten_hoefler: 0 | > > Author_dick= > > _treumann: 0 > > Author_jesper_larsson_traeff: 0 | > > Author_georg= > > e_bosilca: 0 > > Author_david_solt: 0 | > > Author_bronis_de= > > _supinski: 0 > > Author_rajeev_thakur: 1 | > > Author_jef= > > f_squyres: 0 > > Author_alexander_supalov: 0 | > > Author_rolf_rab= > > enseifner: 0 > > ------------------------------------------------------- > > +-------------------= > > - > > > > Comment(by jsquyres): > > > > After a little reflection, I'm a bit unclear on '''exactly''' what > we > > voted on for this ticket. > > > > Specifically, is this ticket a request to change the MPI-2.2 latex? > > If > > so, it is not in the proper form -- it should have the proper > > sections for > > all tickets. > > > > Or is this a ticket to add a bullet to the not-yet-created MPI-2.2 > > errata > > document? If so, I don't see clearly delineated what text > > '''exactly''' > > is going into the new errata document. > > > > To be more clear: I believe that the entire MPI-2.2 errata process > > needs > > to be laid out. It seems clear to me that we need ''both'' changes > > to the > > MPI-2.2 latex (for the 2.3 or 3.0 or whatever the next MPI version > > document is) ''and'' a bullet for the MPI-2.2 errata document. Are > > there > > supposed to be two tickets; one for each item? Or should errata > > tickets > > have text for both documents (line-by-line changes compared to > MPI-2.2 > > ''and'' a bullet item for the MPI-2.2 errata document)? > > > > I understand the urgency of this ticket, but I repeat something that > > Bill > > said many times in Helsinki: above all else, the process must be > > preserved > > (in this case: defined!). Pending clarification to the the MPI-2.2 > > errata > > process, we might need to reset the clock on this ticket. > > > > -- > > Ticket URL: > 171#commen= > > t:7> > > MPI Forum > > MPI Forum > > > > > > -- > > Jeff Squyres > > jsquyres_at_[hidden] > > > > > > --_000_9061A41D8113495ABA045FF45071419Eciscocom_ > > Content-Type: text/html; charset="us-ascii" > > Content-Transfer-Encoding: quoted-printable > > > > > space; -webk= > > it-line-break: after-white-space; ">Forwarding this on to the > > general MPI-2= > > .2 list because I'd like to ask for clarifcation on the MPI-2.2 > > errata proc= > > ess (i.e., what *exactly* did we vote for on ticket > > #171?)...


= > >
Begin forwarded message:

> interchange-newli= > > ne">
> margin-ri= > > ght: 0px; margin-bottom: 0px; margin-left: 0px; "> > face=3D"Helvetica" = > > size=3D"5" color=3D"#000000" style=3D"font: 18.0px Helvetica; color: > > #00000= > > 0">From: > style=3D"font: 1= > > 8.0px Helvetica">"MPI Forum" < > rg">mpi-22_at_[hidden]>
> style=3D"margin-top= > > : 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; > > "> > e=3D"Helvetica" size=3D"5" color=3D"#000000" style=3D"font: 18.0px > > Helvetic= > > a; color: #000000">Date: > size=3D"5" = > > style=3D"font: 18.0px Helvetica">September 7, 2009 10:13:23 AM EDT > font> > div>
> 0px; m= > > argin-left: 0px; "> > color=3D"#000000" st= > > yle=3D"font: 18.0px Helvetica; color: #000000">Subject: > font> > face=3D"Helvetica" size=3D"5" style=3D"font: 18.0px > > Helvetica">Re: [MPI= > > Forum] #171: change MPI_C_BOOL external32 size to 1 byte font> > div><= > > div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; > > margin= > > -left: 0px; min-height: 14px; ">

#171: change MPI_C_BOOL > > external3= > > 2 size to 1 byte
> > ------------------------------------------------------= > > -+--------------------
> > = > > > > Reporter= > > : > > goodell = > > | > > &= > > nbsp > > ;  > > ; &nbs= > > p; > > Owner: = > >   > > ;  > > ; >>   > > > > > ; &= > > nbsp; > > Type:&nbs= > > p; Correction to standard | > > = > >   > > ;  > > ; &nb= > > sp; Status: > > new = > >
> > &nbs= > > p > > ;  > > > ; &= > > nbsp; Priority: Had 1st > > vote  = > > ; | > > = > > > > Mileston= > > e: 2009/09/02 Helsinki
> > = > >   > > ;  > > ; &nb= > > sp; Version: MPI 2.2 > > errata = > > | > > &= > > nbsp; > > Keywords: = > >   > > ;  > > ; &nb= > > sp;
> > &= > > nbsp; Implementation: > > Unnecessary= > >   > > > ; | > > &= > > nbsp; > > Author_bill_gro= > > pp: > > 0 &nbs= > > p;
> > &n= > > bsp; Author_rich_graham: > > 0 &= > > nbsp > > ;  > > ; &nbs= > > p; | > >  = > > ; Author_adam_moody: > > 0  = > > ;  > > > ;  > ; > r> &nb > > William Gropp > Deputy Director for Research > Institute for Advanced Computing Applications and Technologies > Paul and Cynthia Saylor Professor of Computer Science > University of Illinois Urbana-Champaign > > > > > _______________________________________________ > mpi-22 mailing list > mpi-22_at_[hidden] > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 > -- Jeff Squyres jsquyres_at_[hidden] From wgropp at [hidden] Tue Sep 8 13:27:51 2009 From: wgropp at [hidden] (William Gropp) Date: Tue, 8 Sep 2009 13:27:51 -0500 Subject: [Mpi-22] Fwd: [MPI Forum] #171: change MPI_C_BOOL external32size to 1 byte In-Reply-To: Message-ID: <8B637A89-9596-4E7F-9C0E-140109AB88D1@illinois.edu> We've used a fairly open model, as long as it is clear what the change is. Typically, this is The section, page number(s) and line(s) in the MPI 2.2 standard that are affected The text being changed The replacement text. See the MPI 2.0 errata for another example. On MPI 3.0, it is too early to begin this process. We don't even know what chapters are in MPI 3.0; it is not clear that MPI 3.0 should be written as an epsilon delta from 2.2; I'd like to see MPI 3.0 written as coherent chapters, as we did in MPI 2.0. Bill On Sep 8, 2009, at 12:06 PM, Jeff Squyres wrote: > A few followups... > > 1. How is it delineated on the ticket exactly what the errata text is > to be? I see that you indicated what it precisely is for *this* > ticket, but is there a standard form for indicating *exactly* what the > errata text is for other tickets? > > 2. Does a separate ticket need to be filed for MPI 3.0, or is it > assumed that the errata change will *also* be applied to the MPI-3.0 > latex? (you may have answered this implicitly via "We *never* change > the document LaTex with an errata vote", but I wanted to be absolutely > 100% crystal clear on this point) > > Thanks! > > > > On Sep 7, 2009, at 10:57 AM, William Gropp wrote: > >> We *never* change the document LaTex with an errata vote. Errata >> items are collected into a separate document, which is updated as >> items are approved. The standard consists of the document plus >> approved errata items. This is the same process that was used with >> MPI 2.0. Errata items normally should reference the page/line number >> in the relevant document (in this case, the 2.2 document); in this >> particular case, the errata was created before the final line and >> page >> numbers were available, and the Forum agreed that it was better to >> fix >> this through the errata process rather than delay the MPI 2.2 >> document. In this particular case, the precise errata item is >> >> In MPI 2.2, on page 433, line 22, change >> >> MPI_C_BOOL 4 >> >> to >> >> MPI_C_BOOL 1 >> >> I've updated the description to reflect this, as we discussed before >> the vote. >> >> Once an item has been voted on twice, I will prepare a PDF containing >> these items and add that to the MPI Forum web site as official errata >> (again, this is what we did for MPI 2.0). >> >> The process of creating a new version of the document is not part of >> the errata process. Should another version be desired, the errata >> should be folded into it. That is what we did with MPI 2.1. >> >> Bill >> >> On Sep 7, 2009, at 9:18 AM, Jeff Squyres wrote: >> >>> --_004_9061A41D8113495ABA045FF45071419Eciscocom_ >>> Content-Type: multipart/alternative; >>> boundary="_000_9061A41D8113495ABA045FF45071419Eciscocom_" >>> >>> --_000_9061A41D8113495ABA045FF45071419Eciscocom_ >>> Content-Type: text/plain; charset="us-ascii" >>> Content-Transfer-Encoding: quoted-printable >>> >>> Forwarding this on to the general MPI-2.2 list because I'd like to >>> ask for = >>> clarifcation on the MPI-2.2 errata process (i.e., what *exactly* did >>> we vot= >>> e for on ticket #171?)... >>> >>> >>> Begin forwarded message: >>> >>> From: "MPI Forum" >> .org>> >>> Date: September 7, 2009 10:13:23 AM EDT >>> Subject: Re: [MPI Forum] #171: change MPI_C_BOOL external32 size to >>> 1 byte >>> >>> >>> #171: change MPI_C_BOOL external32 size to 1 byte >>> ------------------------------------------------------- >>> +-------------------= >>> - >>> Reporter: goodell >>> | = >>> Owner: >>> Type: Correction to standard >>> | = >>> Status: new >>> Priority: Had 1st vote >>> | = >>> Milestone: 2009/09/02 Helsinki >>> Version: MPI 2.2 errata >>> | = >>> Keywords: >>> Implementation: Unnecessary | >>> Author_b= >>> ill_gropp: 0 >>> Author_rich_graham: 0 | >>> Author_a= >>> dam_moody: 0 >>> Author_torsten_hoefler: 0 | >>> Author_dick= >>> _treumann: 0 >>> Author_jesper_larsson_traeff: 0 | >>> Author_georg= >>> e_bosilca: 0 >>> Author_david_solt: 0 | >>> Author_bronis_de= >>> _supinski: 0 >>> Author_rajeev_thakur: 1 | >>> Author_jef= >>> f_squyres: 0 >>> Author_alexander_supalov: 0 | >>> Author_rolf_rab= >>> enseifner: 0 >>> ------------------------------------------------------- >>> +-------------------= >>> - >>> >>> Comment(by jsquyres): >>> >>> After a little reflection, I'm a bit unclear on '''exactly''' what >> we >>> voted on for this ticket. >>> >>> Specifically, is this ticket a request to change the MPI-2.2 latex? >>> If >>> so, it is not in the proper form -- it should have the proper >>> sections for >>> all tickets. >>> >>> Or is this a ticket to add a bullet to the not-yet-created MPI-2.2 >>> errata >>> document? If so, I don't see clearly delineated what text >>> '''exactly''' >>> is going into the new errata document. >>> >>> To be more clear: I believe that the entire MPI-2.2 errata process >>> needs >>> to be laid out. It seems clear to me that we need ''both'' changes >>> to the >>> MPI-2.2 latex (for the 2.3 or 3.0 or whatever the next MPI version >>> document is) ''and'' a bullet for the MPI-2.2 errata document. Are >>> there >>> supposed to be two tickets; one for each item? Or should errata >>> tickets >>> have text for both documents (line-by-line changes compared to >> MPI-2.2 >>> ''and'' a bullet item for the MPI-2.2 errata document)? >>> >>> I understand the urgency of this ticket, but I repeat something that >>> Bill >>> said many times in Helsinki: above all else, the process must be >>> preserved >>> (in this case: defined!). Pending clarification to the the MPI-2.2 >>> errata >>> process, we might need to reset the clock on this ticket. >>> >>> -- >>> Ticket URL: >> 171#commen= >>> t:7> >>> MPI Forum >>> MPI Forum >>> >>> >>> -- >>> Jeff Squyres >>> jsquyres_at_[hidden] >>> >>> >>> --_000_9061A41D8113495ABA045FF45071419Eciscocom_ >>> Content-Type: text/html; charset="us-ascii" >>> Content-Transfer-Encoding: quoted-printable >>> >>> >> space; -webk= >>> it-line-break: after-white-space; ">Forwarding this on to the >>> general MPI-2= >>> .2 list because I'd like to ask for clarifcation on the MPI-2.2 >>> errata proc= >>> ess (i.e., what *exactly* did we vote for on ticket >>> #171?)...


= >>>
Begin forwarded message:

>> interchange-newli= >>> ne">
>> margin-ri= >>> ght: 0px; margin-bottom: 0px; margin-left: 0px; ">>> face=3D"Helvetica" = >>> size=3D"5" color=3D"#000000" style=3D"font: 18.0px Helvetica; color: >>> #00000= >>> 0">From: >> style=3D"font: 1= >>> 8.0px Helvetica">"MPI Forum" <>> rg">mpi-22_at_[hidden]>
>> style=3D"margin-top= >>> : 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; >>> ">>> e=3D"Helvetica" size=3D"5" color=3D"#000000" style=3D"font: 18.0px >>> Helvetic= >>> a; color: #000000">Date: >> size=3D"5" = >>> style=3D"font: 18.0px Helvetica">September 7, 2009 10:13:23 AM EDT>> font>>> div>
>> 0px; m= >>> argin-left: 0px; ">>> color=3D"#000000" st= >>> yle=3D"font: 18.0px Helvetica; color: #000000">Subject: >> font>>> face=3D"Helvetica" size=3D"5" style=3D"font: 18.0px >>> Helvetica">Re: [MPI= >>> Forum] #171: change MPI_C_BOOL external32 size to 1 byte> font>>> div><= >>> div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; >>> margin= >>> -left: 0px; min-height: 14px; ">

#171: change MPI_C_BOOL >>> external3= >>> 2 size to 1 byte
>>> ------------------------------------------------------= >>> -+--------------------
>>> = >>> >>> Reporter= >>> : >>> goodell = >>> | >>> &= >>> nbsp >>> ;  >>> ; &nbs= >>> p; >>> Owner: = >>>   >>> ;  >>> ; >>>   >>> >>> >> ; &= >>> nbsp; >>> Type:&nbs= >>> p; Correction to standard | >>> = >>>   >>> ;  >>> ; &nb= >>> sp; Status: >>> new = >>>
>>> &nbs= >>> p >>> ;  >>> >> ; &= >>> nbsp; Priority: Had 1st >>> vote  = >>> ; | >>> = >>> >>> Mileston= >>> e: 2009/09/02 Helsinki
>>> = >>>   >>> ;  >>> ; &nb= >>> sp; Version: MPI 2.2 >>> errata = >>> | >>> &= >>> nbsp; >>> Keywords: = >>>   >>> ;  >>> ; &nb= >>> sp;
>>> &= >>> nbsp; Implementation: >>> Unnecessary= >>>   >>> >> ; | >>> &= >>> nbsp; >>> Author_bill_gro= >>> pp: >>> 0 &nbs= >>> p;
>>> &n= >>> bsp; Author_rich_graham: >>> 0 &= >>> nbsp >>> ;  >>> ; &nbs= >>> p; | >>>  = >>> ; Author_adam_moody: >>> 0  = >>> ;  >>> >> ;  >> ; >> r> &nb >> >> William Gropp >> Deputy Director for Research >> Institute for Advanced Computing Applications and Technologies >> Paul and Cynthia Saylor Professor of Computer Science >> University of Illinois Urbana-Champaign >> >> >> >> >> _______________________________________________ >> mpi-22 mailing list >> mpi-22_at_[hidden] >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 >> > > > -- > Jeff Squyres > jsquyres_at_[hidden] > > _______________________________________________ > mpi-22 mailing list > mpi-22_at_[hidden] > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign From rlgraham at [hidden] Wed Sep 9 14:04:11 2009 From: rlgraham at [hidden] (Graham, Richard L.) Date: Wed, 09 Sep 2009 15:04:11 -0400 Subject: [Mpi-22] Fwd: [MPI Forum] #171: change MPI_C_BOOL external32size to 1 byte In-Reply-To: <8B637A89-9596-4E7F-9C0E-140109AB88D1@illinois.edu> Message-ID: Also, for 3.0 I am going to want to have tickets for each of the changes we make, so we can track them, and be sure not to inadvertently miss changes. Rich On 9/8/09 2:27 PM, "William Gropp" wrote: We've used a fairly open model, as long as it is clear what the change is. Typically, this is The section, page number(s) and line(s) in the MPI 2.2 standard that are affected The text being changed The replacement text. See the MPI 2.0 errata for another example. On MPI 3.0, it is too early to begin this process. We don't even know what chapters are in MPI 3.0; it is not clear that MPI 3.0 should be written as an epsilon delta from 2.2; I'd like to see MPI 3.0 written as coherent chapters, as we did in MPI 2.0. Bill On Sep 8, 2009, at 12:06 PM, Jeff Squyres wrote: > A few followups... > > 1. How is it delineated on the ticket exactly what the errata text is > to be? I see that you indicated what it precisely is for *this* > ticket, but is there a standard form for indicating *exactly* what the > errata text is for other tickets? > > 2. Does a separate ticket need to be filed for MPI 3.0, or is it > assumed that the errata change will *also* be applied to the MPI-3.0 > latex? (you may have answered this implicitly via "We *never* change > the document LaTex with an errata vote", but I wanted to be absolutely > 100% crystal clear on this point) > > Thanks! > > > > On Sep 7, 2009, at 10:57 AM, William Gropp wrote: > >> We *never* change the document LaTex with an errata vote. Errata >> items are collected into a separate document, which is updated as >> items are approved. The standard consists of the document plus >> approved errata items. This is the same process that was used with >> MPI 2.0. Errata items normally should reference the page/line number >> in the relevant document (in this case, the 2.2 document); in this >> particular case, the errata was created before the final line and >> page >> numbers were available, and the Forum agreed that it was better to >> fix >> this through the errata process rather than delay the MPI 2.2 >> document. In this particular case, the precise errata item is >> >> In MPI 2.2, on page 433, line 22, change >> >> MPI_C_BOOL 4 >> >> to >> >> MPI_C_BOOL 1 >> >> I've updated the description to reflect this, as we discussed before >> the vote. >> >> Once an item has been voted on twice, I will prepare a PDF containing >> these items and add that to the MPI Forum web site as official errata >> (again, this is what we did for MPI 2.0). >> >> The process of creating a new version of the document is not part of >> the errata process. Should another version be desired, the errata >> should be folded into it. That is what we did with MPI 2.1. >> >> Bill >> >> On Sep 7, 2009, at 9:18 AM, Jeff Squyres wrote: >> >>> --_004_9061A41D8113495ABA045FF45071419Eciscocom_ >>> Content-Type: multipart/alternative; >>> boundary="_000_9061A41D8113495ABA045FF45071419Eciscocom_" >>> >>> --_000_9061A41D8113495ABA045FF45071419Eciscocom_ >>> Content-Type: text/plain; charset="us-ascii" >>> Content-Transfer-Encoding: quoted-printable >>> >>> Forwarding this on to the general MPI-2.2 list because I'd like to >>> ask for = >>> clarifcation on the MPI-2.2 errata process (i.e., what *exactly* did >>> we vot= >>> e for on ticket #171?)... >>> >>> >>> Begin forwarded message: >>> >>> From: "MPI Forum" >> .org>> >>> Date: September 7, 2009 10:13:23 AM EDT >>> Subject: Re: [MPI Forum] #171: change MPI_C_BOOL external32 size to >>> 1 byte >>> >>> >>> #171: change MPI_C_BOOL external32 size to 1 byte >>> ------------------------------------------------------- >>> +-------------------= >>> - >>> Reporter: goodell >>> | = >>> Owner: >>> Type: Correction to standard >>> | = >>> Status: new >>> Priority: Had 1st vote >>> | = >>> Milestone: 2009/09/02 Helsinki >>> Version: MPI 2.2 errata >>> | = >>> Keywords: >>> Implementation: Unnecessary | >>> Author_b= >>> ill_gropp: 0 >>> Author_rich_graham: 0 | >>> Author_a= >>> dam_moody: 0 >>> Author_torsten_hoefler: 0 | >>> Author_dick= >>> _treumann: 0 >>> Author_jesper_larsson_traeff: 0 | >>> Author_georg= >>> e_bosilca: 0 >>> Author_david_solt: 0 | >>> Author_bronis_de= >>> _supinski: 0 >>> Author_rajeev_thakur: 1 | >>> Author_jef= >>> f_squyres: 0 >>> Author_alexander_supalov: 0 | >>> Author_rolf_rab= >>> enseifner: 0 >>> ------------------------------------------------------- >>> +-------------------= >>> - >>> >>> Comment(by jsquyres): >>> >>> After a little reflection, I'm a bit unclear on '''exactly''' what >> we >>> voted on for this ticket. >>> >>> Specifically, is this ticket a request to change the MPI-2.2 latex? >>> If >>> so, it is not in the proper form -- it should have the proper >>> sections for >>> all tickets. >>> >>> Or is this a ticket to add a bullet to the not-yet-created MPI-2.2 >>> errata >>> document? If so, I don't see clearly delineated what text >>> '''exactly''' >>> is going into the new errata document. >>> >>> To be more clear: I believe that the entire MPI-2.2 errata process >>> needs >>> to be laid out. It seems clear to me that we need ''both'' changes >>> to the >>> MPI-2.2 latex (for the 2.3 or 3.0 or whatever the next MPI version >>> document is) ''and'' a bullet for the MPI-2.2 errata document. Are >>> there >>> supposed to be two tickets; one for each item? Or should errata >>> tickets >>> have text for both documents (line-by-line changes compared to >> MPI-2.2 >>> ''and'' a bullet item for the MPI-2.2 errata document)? >>> >>> I understand the urgency of this ticket, but I repeat something that >>> Bill >>> said many times in Helsinki: above all else, the process must be >>> preserved >>> (in this case: defined!). Pending clarification to the the MPI-2.2 >>> errata >>> process, we might need to reset the clock on this ticket. >>> >>> -- >>> Ticket URL: >> 171#commen= >>> t:7> >>> MPI Forum >>> MPI Forum >>> >>> >>> -- >>> Jeff Squyres >>> jsquyres_at_[hidden] >>> >>> >>> --_000_9061A41D8113495ABA045FF45071419Eciscocom_ >>> Content-Type: text/html; charset="us-ascii" >>> Content-Transfer-Encoding: quoted-printable >>> >>> >> space; -webk= >>> it-line-break: after-white-space; ">Forwarding this on to the >>> general MPI-2= >>> .2 list because I'd like to ask for clarifcation on the MPI-2.2 >>> errata proc= >>> ess (i.e., what *exactly* did we vote for on ticket >>> #171?)...


= >>>
Begin forwarded message:

>> interchange-newli= >>> ne">
>> margin-ri= >>> ght: 0px; margin-bottom: 0px; margin-left: 0px; ">>> face=3D"Helvetica" = >>> size=3D"5" color=3D"#000000" style=3D"font: 18.0px Helvetica; color: >>> #00000= >>> 0">From: >> style=3D"font: 1= >>> 8.0px Helvetica">"MPI Forum" <>> rg">mpi-22_at_[hidden]>
>> style=3D"margin-top= >>> : 0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; >>> ">>> e=3D"Helvetica" size=3D"5" color=3D"#000000" style=3D"font: 18.0px >>> Helvetic= >>> a; color: #000000">Date: >> size=3D"5" = >>> style=3D"font: 18.0px Helvetica">September 7, 2009 10:13:23 AM EDT>> font>>> div>
>> 0px; m= >>> argin-left: 0px; ">>> color=3D"#000000" st= >>> yle=3D"font: 18.0px Helvetica; color: #000000">Subject: >> font>>> face=3D"Helvetica" size=3D"5" style=3D"font: 18.0px >>> Helvetica">Re: [MPI= >>> Forum] #171: change MPI_C_BOOL external32 size to 1 byte> font>>> div><= >>> div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; >>> margin= >>> -left: 0px; min-height: 14px; ">

#171: change MPI_C_BOOL >>> external3= >>> 2 size to 1 byte
>>> ------------------------------------------------------= >>> -+--------------------
>>> = >>> >>> Reporter= >>> : >>> goodell = >>> | >>> &= >>> nbsp >>> ;  >>> ; &nbs= >>> p; >>> Owner: = >>>   >>> ;  >>> ; >>>   >>> >>> >> ; &= >>> nbsp; >>> Type:&nbs= >>> p; Correction to standard | >>> = >>>   >>> ;  >>> ; &nb= >>> sp; Status: >>> new = >>>
>>> &nbs= >>> p >>> ;  >>> >> ; &= >>> nbsp; Priority: Had 1st >>> vote  = >>> ; | >>> = >>> >>> Mileston= >>> e: 2009/09/02 Helsinki
>>> = >>>   >>> ;  >>> ; &nb= >>> sp; Version: MPI 2.2 >>> errata = >>> | >>> &= >>> nbsp; >>> Keywords: = >>>   >>> ;  >>> ; &nb= >>> sp;
>>> &= >>> nbsp; Implementation: >>> Unnecessary= >>>   >>> >> ; | >>> &= >>> nbsp; >>> Author_bill_gro= >>> pp: >>> 0 &nbs= >>> p;
>>> &n= >>> bsp; Author_rich_graham: >>> 0 &= >>> nbsp >>> ;  >>> ; &nbs= >>> p; | >>>  = >>> ; Author_adam_moody: >>> 0  = >>> ;  >>> >> ;  >> ; >> r> &nb >> >> William Gropp >> Deputy Director for Research >> Institute for Advanced Computing Applications and Technologies >> Paul and Cynthia Saylor Professor of Computer Science >> University of Illinois Urbana-Champaign >> >> >> >> >> _______________________________________________ >> mpi-22 mailing list >> mpi-22_at_[hidden] >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 >> > > > -- > Jeff Squyres > jsquyres_at_[hidden] > > _______________________________________________ > mpi-22 mailing list > mpi-22_at_[hidden] > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 William Gropp Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign _______________________________________________ mpi-22 mailing list mpi-22_at_[hidden] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-22 From jsquyres at [hidden] Thu Sep 10 13:34:25 2009 From: jsquyres at [hidden] (Jeff Squyres) Date: Thu, 10 Sep 2009 14:34:25 -0400 Subject: [Mpi-22] Fwd: [all-osl-users] OSL server reboots In-Reply-To: <4AA94218.4060204@osl.iu.edu> Message-ID: Except for www.mpi-forum.org, all MPI Forum web, SVN, and Trac services will be disrupted at the time indicated below. I'm guessing the outage will only last a few minutes. Begin forwarded message: > From: "Kim, DongInn" <> > Date: September 10, 2009 2:14:48 PM EDT > Subject: [all-osl-users] OSL server reboots > > Hi, > > We need to have the newer kernels installed on the OSL server > machines for the security concerns but they need to be rebooted to > put them into effect. > > The systems which need to be rebooted are: > > gibson > milliways > rontok > sourcehaven > wowbagger > frogstar > magrathea > > The downtime of systems would be at 8:00AM to 9:00AM on Friday, > September 11, 2009 due to the rebooting. > - 5:00am-6:00am Pacific US time > - 6:00am-7:00am Mountain US time > - 7:00am-8:00am Central US time > - 8:00am-9:00am Eastern US time > - 12:00pm-1:00pm GMT > > Please let me know if you have any problems or questions about this > outage. > > Regards, > > -- > - DongInn > > -- Jeff Squyres jsquyres_at_[hidden]