Re: [hwloc-devel] Strange CPU topology numbering on dual socket ARM server with 2×ThunderX2 CN9975

On Sep 6, 2019, at 10:52 AM, Jirka Hladky mailto:jhla...@redhat.com>> wrote: You should avoid physical numbering at any cost. The trouble is that other Linux tools (like ps) are using the physical numbering. I will need to think about how to come around this. Use hwloc for everything! ;-)

Re: [hwloc-devel] Strange CPU topology numbering on dual socket ARM server with 2×ThunderX2 CN9975

FWIW / in addition to what Brice said: this is why hwloc also has "logical" ordering (in addition to the "physical" ordering). On Sep 6, 2019, at 10:07 AM, Brice Goglin mailto:brice.gog...@inria.fr>> wrote: Hello Jirka I don't think there's a bug here. physical_package_id don't have to be

[hwloc-devel] Fwd: [OMPI commits] Commit emails

FYI -- same applies for hwloc commit emails. Begin forwarded message: From: "Jeff Squyres \(jsquyres\) via ompi-commits" mailto:ompi-comm...@lists.open-mpi.org>> Subject: [OMPI commits] Commit emails Date: April 26, 2019 at 10:28:30 AM EDT To: "ompi-comm...@lists.open-mpi

Re: [hwloc-devel] C99 will be back soon

On Sep 28, 2017, at 8:41 AM, Brice Goglin wrote: > > Turns out Microsoft Visual Studio doesn't support most of C99 > (at least dynamic arrays and mixed declaration/code). Good lord; they don't even support mixing declarations/code? That... is unfortunate. > I am using

Re: [hwloc-devel] hwloc.m4: minor english fixes

ther, and I am pretty sure it's > not the first time it happens. There are no archives for this ML, do we > have a way to see the logs of the emailing script that runs on github ? > > Brice > > > > Le 08/02/2017 16:19, Jeff Squyres (jsquyres) a écrit : >> On Feb 7

Re: [hwloc-devel] hwloc.m4: minor english fixes

On Feb 7, 2017, at 11:48 AM, Samuel Thibault wrote: > >> -AC_MSG_WARN([*** and binding will not be support.]) >> +AC_MSG_WARN([*** and binding will likely not be supported.]) > > Well, it's not really "likely": unsupported systems really won't have >

Re: [hwloc-devel] Git: open-mpi/hwloc annotated tag hwloc-1.11.5 deleted. hwloc-1.11.5

On Nov 25, 2016, at 7:31 AM, Brice Goglin wrote: > > FWIW, I am trying to remove github automatic "release" tarballs from > the github page but it actually removes the corresponding git tag. > > Those releases are not autogen'ed, do not contain the doc, etc. > Users are

[hwloc-devel] Open MPI mail archives now back online

mail-archive.com now has all of the old Open MPI mail archives online. Example: https://www.mail-archive.com/users@lists.open-mpi.org/ https://www.mail-archive.com/devel@lists.open-mpi.org/ Note that there are two different ways you can permalink to messages on mail-archive: 1. Take

Re: [hwloc-devel] This list is suspended while migrating

We unfortunately ran into major issues while trying to migrate these lists, and have therefore restored them back on the Indiana U servers until we try the migration again. Sorry for the hassle folks; stay tuned! > On Jul 20, 2016, at 10:28 AM, Jeff Squyres (jsquyres) <jsquy...@cis

[hwloc-devel] This list is suspended while migrating

We are beginning the list migration process; this list will be suspended while it is in transit to a new home. We can't predict the exact timing of the migration -- hopefully it'll only take a few hours. See you on the other side! -- Jeff Squyres jsquy...@cisco.com For corporate legal

[hwloc-devel] This list is migrating!

Short version = The server for this mailing list will be migrating sometime soon (the exact timing is not fully predictable). Three things you need to know: 1. We'll send a "This list is now closed for migration" last message when the migration starts 2. We'll send a "This list is

Re: [hwloc-devel] Using Hwloc in LLVM OpenMP

On May 18, 2015, at 3:03 PM, Brice Goglin wrote: > > (3) it won't replace autotools since we have autotools-projects embedding > hwloc. if we can have both autotools and cmake without too much trouble, I > guess it's ok Since cmake likely won't be the main

Re: [hwloc-devel] Lhwloc1 duplicate symbol issue

On Mar 25, 2015, at 4:14 PM, Brice Goglin wrote: > > Looks like I missed something in the OMPI discussion: > When you say symbol, do you mean asm label? > include/private/cpuid-x86.h: Assembler messages: > include/private/cpuid-x86.h:40: Error: symbol `Lhwloc1' is already

Re: [hwloc-devel] Coverity

On Feb 14, 2015, at 8:57 AM, Brice Goglin wrote: >> Brice: do you have a nightly coverity submission script running somewhere? > > No, I just run it manually from time to time. Do you want it to run automated? We can run the script at IU. -- Jeff Squyres

[hwloc-devel] Coverity

I added a bunch of components into the hwloc coverity setup, as well as a dummy model file (so that coverity doesn't complain that hwloc is not fully configured). Brice: do you have a nightly coverity submission script running somewhere? -- Jeff Squyres jsquy...@cisco.com For corporate legal

Re: [hwloc-devel] Git: open-mpi/hwloc branch master updated. 85ea6e4acc456d398fa995d671960ccc0dff0d42

FWIW, here's the difference between a root and non-root run on a system with a Cisco VIC: Root XML contains additional PCI data: And the usNIC VFs have a link speed: (the non-root run has "0.0" for the link speed: > On Jan 10, 2015, at 5:42 AM,

Re: [hwloc-devel] upcoming feature removal

On Nov 4, 2014, at 9:10 AM, Brice Goglin wrote: >> - pu_children >> - io_children >> - misc_children > > OK but what does "pe" stand for? did you mean "pu" to match our PU objects? I said "pu_children". Really. I didn't edit the text above and make it look like I

Re: [hwloc-devel] upcoming feature removal

On Nov 3, 2014, at 5:49 AM, Brice Goglin wrote: > * don't put I/O objects in "normal" children since it confuses programs > consulting the children list. rather place them under a dedicated child > pointer special objects such as Misc may go there as well. If you're going

Re: [hwloc-devel] hwloc version number

Errr... I got the patch slightly wrong. The one added line should include the ".$HWLOC_RELEASE_VERSION" at the end. You get the idea... On Oct 1, 2014, at 8:50 PM, Jeff Squyres (jsquyres) <jsquy...@cisco.com> wrote: > We just changed the version numbering scheme ove

[hwloc-devel] hwloc version number

We just changed the version numbering scheme over in OMPI to always be "a.b.c", even if c==0. Do we want the same thing in hwloc? Right now, hwloc uses the old OMPI versioning scheme -- it's "a.b.c", except when c==0, and then the version is "a.b". It's a pretty simple change: diff --git

Re: [hwloc-devel] Using hwloc to detect Hard Disks

On Sep 22, 2014, at 6:55 PM, Brice Goglin wrote: >> HWLOC already provides similar info for processors and mother boards, so it >> seemed a natural extension of current capabilities to provide it for other >> system elements. > > Disk vendor/model is easy to add from

[hwloc-devel] One more Github-inspired change...

I forgot to mention: now that the hwloc-svn list was renamed to hwloc-commits, I have disallowed anyone from posting to it. Only the gitdub mailer is allowed to post to that list. Replied to such posts are automatically directed to hwloc-devel. But note that github offers nice code

[hwloc-devel] hwloc now 100% at Github

hwloc's git repo has been at Github for a long now. As of this morning: - hwloc's tickets are now Github issues https://github.com/open-mpi/hwloc/issues - hwloc's wiki is now on the Github wiki https://github.com/open-mpi/hwloc/wiki - hwloc's git diff emails are being fired via gitdub (not

Re: [hwloc-devel] Migrate Trac tickets -> Github issues

Cool. I'm going to wait until I hear from Brice (I think he might be traveling?); I don't want to spam him with a zillion emails. On Sep 12, 2014, at 7:58 AM, Samuel Thibault <samuel.thiba...@inria.fr> wrote: > Jeff Squyres (jsquyres), le Fri 12 Sep 2014 10:44:03 +, a écrit :

[hwloc-devel] Migrate Trac tickets -> Github issues

Samuel / Brice -- I did a test import of hwloc's Trac tickets to githib -- what do you think? https://github.com/ompiteam/hwloc-test-ticket-import/issues If you like it, I'll re-do the import over to the main hwloc repo, and we can then fully abandon Trac. There will be one important

Re: [hwloc-devel] Stop updating Trac wiki (Github migration)

Yoinks! Autocomplete in my email client sent this to the wrong list... hwloc conversion is already done. This message was meant for the main Open MPI developers list, not the hwloc list. Sorry for the noise... On Sep 9, 2014, at 12:03 PM, Jeff Squyres (jsquyres) <jsquy...@cisco.com>

[hwloc-devel] Stop updating Trac wiki (Github migration)

As part of our migration to Github, there are three main things to convert: 1. SVN -> Git 2. Trac wiki -> Github markdown 3. Track tickets -> Github issues I have a good automated solution for #1; that can be run whenever we're ready to switchover. I used an 80% automated solution for #2

[hwloc-devel] Fwd: [OMPI svn-full] svn:open-mpi r32675 - in trunk/opal/mca/hwloc/hwloc191/hwloc: include/hwloc src

Brice -- Did you see this? The issue is that ipmi.h has a #define for "uint64". :-( So this isn't hwloc's fault at all, but it's a change we had to make in OMPI so that ORCM can have a topology-aware IPMI module. Begin forwarded message: > From: > Subject:

[hwloc-devel] hwloc wiki on github

The hwloc wiki -- all 5 pages of it :-) -- is now officially on github: https://github.com/open-mpi/hwloc/wiki The Trac wiki is now deprecated. (...conversion of Trac tickets is still in the works...) -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to:

[hwloc-devel] Migrating Trac wiki and tickets to Github

As part of moving the final OMPI SVN repo to Github, we're also converting the Trac wiki and tickets. I have a first attempt at converting the hwloc trac wiki to Github's Markdown: https://github.com/jsquyres/hwloc-test/wiki If this looks good (from a conversion standpoint -- at least some

Re: [hwloc-devel] --enable-plugins broken

Good enough; thanks for the refresher. :) Sent from my phone. No type good. > On Aug 18, 2014, at 2:07 PM, "Brice Goglin" <brice.gog...@inria.fr> wrote: > > Le 18/08/2014 20:37, Jeff Squyres (jsquyres) a écrit : >> I notice that --enable-plugins seems

[hwloc-devel] --enable-plugins broken

I notice that --enable-plugins seems to be broken -- it always ends in: configure: WARNING: Plugin support requested, but could not find ltdl.h configure: error: Cannot continue if you don't have libltdl installed. Is this intentional? I.e., have we already relied on an external libltdl? Or

Re: [hwloc-devel] patch to execute command when using hwloc-bind --get

How about displaying a warning if --get is specified but a command to execute is also specified? Sent from my phone. No type good. > On Aug 13, 2014, at 5:22 AM, "John Donners" wrote: > > Hi Brice, > >> On 13-08-14 10:46, Brice Goglin wrote: >> Hello, >> >> Can

[hwloc-devel] PATCH: Mark fd as close-on-exec

Any objections to this patch? In OMPI, we're seeing this fd leak into child processes. diff --git a/src/topology-linux.c b/src/topology-linux.c index e934d4c..8c5fba1 100644 --- a/src/topology-linux.c +++ b/src/topology-linux.c @@ -4601,6 +4601,13 @@ hwloc_linux_component_instantiate(struct

[hwloc-devel] Slowly moving to git

As many of you have noticed, we've been moving more repositories from SVN to git. This email is a summary of where we are and what the (current) overall plan is. So far, the following repos are hosted in the Open MPI community at github: 1. hwloc (integrated with Trac at IU) 2. hwloc-debian

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

E" ls -lf $distdir/README On Apr 7, 2014, at 6:04 PM, Brice Goglin <brice.gog...@inria.fr> wrote: > My jenkins does make distcheck on some Linux and only make check on > others, so it should be fine on my side. > > Brice > > > > > Le 08/0

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

-h -f - doc/doxygen-doc | tar -x -C > /home/ci/hwloc-gitclone/build/hwloc-gitclone -f - > tar: /dev/rmt/0: No such file or directory > > > > Le 07/04/2014 23:29, Jeff Squyres (jsquyres) a écrit : >> --- a/config/distscript.sh >> +++ b/config/distscript.sh >> @

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

On Apr 7, 2014, at 5:06 PM, "Jeff Squyres (jsquyres)" <jsquy...@cisco.com> wrote: > Ok, lemme look at tar -- there's a canonical way to copy dir trees with tar; > let me look it up... Does this work for you? It seems to do the Right Thing for me on OS X and Linux.

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

t; >make dist works when building out-of-source if $srcdir/doc/doxygen-doc >is a symlink to builddir/doc/doxygen-doc. >But it actually fails to copy the doxygen-doc tree because it >doesn't dereference the symlink. Fix that. > > Brice > > > > > Le 07/04/

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

range. > > Brice > > > > Le 07/04/2014 22:05, Jeff Squyres (jsquyres) a écrit : >> Right -- I've done that (i.e., if I do "make doc" again, it does nothing >> because it's already done). And "make dist" works fine. >> >> But &quo

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

(but a little bit harder to use :)) > > Brice > > > Le 07/04/2014 21:37, Jeff Squyres (jsquyres) a écrit : >> I just pushed 143e27248f928797e2e8532747386c67c9f8d873, which converted >> distscript.csh to distscript.sh. >> >> If it works well on master, we

Re: [hwloc-devel] GIT: hwloc branch master updated. 0e6fe307c10d47efee3fb95c50aee9c0f01bc8ec

I just pushed 143e27248f928797e2e8532747386c67c9f8d873, which converted distscript.csh to distscript.sh. If it works well on master, we can pull it to the v1.9 branch. I notice that "make distcheck" is broken, however -- when it goes to "make dist" in the expanded tarball, I get the following

Re: [hwloc-devel] Use of

Sweet; thanks. On Jan 10, 2014, at 12:25 PM, Brice Goglin <brice.gog...@inria.fr> wrote: > Looks like we're good. > Brice > > > > Le 10/01/2014 18:05, Jeff Squyres (jsquyres) a écrit : >> K, will do. >> >> On Jan 10, 2014, at 12:00 PM, Bri

Re: [hwloc-devel] Use of

K, will do. On Jan 10, 2014, at 12:00 PM, Brice Goglin <brice.gog...@inria.fr> wrote: > Push it to master, we'll what regression testing at > https://ci.inria.fr/hwloc/job/master-1-check/ thinks about it > Brice > > > > "Jeff Squyres (jsquyres)" &

[hwloc-devel] Use of

Brice / Samuel -- In http://www.open-mpi.org/community/lists/devel/2014/01/13619.php, Paul Hargrove found this compiler warning: - On OpenBSD the header malloc.h exists, but is NOT intended to be used: -bash-4.2$ grep -B2 'is obsolete' make.log CC bind.lo In file included from

Re: [hwloc-devel] GIT: hwloc branch master updated. c05fc46fa58d792b13b6b4aec30d7a81877185f4

I'll investigate. On Nov 7, 2013, at 12:37 AM, Brice Goglin wrote: > Jeff, > This mail looks strange. The actual diff and commit message is missing. > Also we got a commit mail for HEAD for some reason. > Brice > > > > Le 07/11/2013 09:35, MPI Team a écrit : >> The

[hwloc-devel] Git branch emails

Ok, sorry for the bazillion emails you just got, but the email script should now send out notices for all commits on all branches now. -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/

Re: [hwloc-devel] late git commit email

you have to explicit > enable them on github? > > Brice > > > > Le 06/11/2013 15:30, Jeff Squyres (jsquyres) a écrit : >> There was a disk problem on the IU server where the git commit message came >> from. >> >> It was ju

[hwloc-devel] late git commit email

There was a disk problem on the IU server where the git commit message came from. It was just fixed, which is why we got the commit email so late. -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/

Re: [hwloc-devel] Relationship between Cario and X11

On Nov 1, 2013, at 11:54 AM, Samuel Thibault wrote: > We could avoid Xutil.h and keysym.h by disabling the case KeyPress part, > but I'd rather not: people will wonder why they don't have keyboard > shortcut, and finding out from ./configure output will not be easy. >

Re: [hwloc-devel] Relationship between Cario and X11

, there's extra X11 goodies that can be used) Is that correct? Or do we *require* all 3 header files for X11 support? On Nov 1, 2013, at 11:20 AM, "Jeff Squyres (jsquyres)" <jsquy...@cisco.com> wrote: > Ya -- working on a new patch, too. > > > On Nov 1, 201

Re: [hwloc-devel] Relationship between Cario and X11

Ya -- working on a new patch, too. On Nov 1, 2013, at 11:10 AM, Brice Goglin <brice.gog...@inria.fr> wrote: > Can you first find out which header and library contains XOpenDisplay() > on your Mac? > > Brice > > > > Le 01/11/2013 16:01, Jeff Squyres (jsquy

Re: [hwloc-devel] Relationship between Cario and X11

to be independent of Cairo and GL (and therefore only once, and include the AC_DEFINE for HWLOC_HAVE_X11)? On Nov 1, 2013, at 10:53 AM, Samuel Thibault <samuel.thiba...@inria.fr> wrote: > Jeff Squyres (jsquyres), le Fri 01 Nov 2013 15:12:31 +0100, a écrit : >> Cool. Does the following patch

Re: [hwloc-devel] Relationship between Cario and X11

not found, Cairo/X11 back-end disabled]) - hwloc_cairo_happy=no -fi - - CFLAGS=$CFLAGS_save - LIBS=$LIBS_save - fi fi if test "x$hwloc_cairo_happy" = "xyes"; then On Nov 1, 2013, at 10:07 AM, Samuel Thibault <samuel.thiba.

[hwloc-devel] Relationship between Cario and X11

I notice that we have an explicit dependency between Cairo and X11 in configure: - if test "x$enable_X11" != "xyes"; then AC_MSG_WARN([X11 headers not found, Cairo/X11 back-end disabled]) hwloc_cairo_happy=no fi - Is there any reason for this? I ask

Re: [hwloc-devel] [open-mpi/hwloc] f21cd7: linux/mic: add a MICSerialNumber info attribute wh...

Yeah; we're working on it. Github's emails kinda suck. Brice sent me his openmx git email script today; I'm going to try to get that hosted at IU. On Oct 17, 2013, at 1:17 PM, Samuel Thibault wrote: > Brice Goglin, le Thu 17 Oct 2013 19:10:05 +0200, a écrit : >>

[hwloc-devel] github hwloc repo reset

I chatted w/ Brice in IM: the github/open-mpi/hwloc repo ***has been completely reset*** and now reflects all the correct information. If you have any clones of the original githib/open-mpi/hwloc repo, either be *exceedingly* careful in pulling down new stuff, or, probably simpler/better: just

Re: [hwloc-devel] New git repo attempt

On Oct 3, 2013, at 12:31 PM, Brice Goglin wrote: > The master branch looks good to me, and the list of branches looks fine too. Good. > v1.7 misses the last git commits, but I guess you didn't update it yet. Yes; I replayed on the master, but not v1.7 yet. I'll go do

[hwloc-devel] New git repo attempt

I did the conversion again, and then added the commits that we've put on github since the original conversion (but I squashed most of them). I put the resulting repo here: https://github.com/jsquyres/hwloc-convert-again Does this look ok to everyone? If so, I can kill the existing

Re: [hwloc-devel] nightly snapshot tarballs now available

On Oct 3, 2013, at 6:41 AM, Brice Goglin wrote: > It was likely moved to the attic. If svn2git doesn't find it, that's > fine, I still have it in my archives in case we ever want it (very > unlikely). Ah, ok. -- Jeff Squyres jsquy...@cisco.com For corporate legal

Re: [hwloc-devel] nightly snapshot tarballs now available

On Oct 2, 2013, at 12:47 PM, Brice Goglin wrote: > I can do it (assuming the "hwloc-svn-conversion" git tree it uptodate). > But I need somebody to create the ompi/hwloc-debian repo on github and > give us credentials. Done. > The only important one is "cuda". > Most

Re: [hwloc-devel] git / nightly builds

Sorry for the delay in replying. On Sep 29, 2013, at 10:32 AM, Brice Goglin wrote: > Now why do we still need a call to git-describe in get_version.sh? Isn't > this script supposed to just read what distscript.csh did? (which would > mean that "if test -z

Re: [hwloc-devel] nightly snapshot tarballs now available

On Sep 28, 2013, at 10:05 AM, Brice Goglin wrote: > The only things that we're still missing as far as I know are: > * the debian repository as explained above (by the way, beware that > branches are not under branches/ in there) Sorry for the delay in replying -- I suck

Re: [hwloc-devel] git / nightly builds

On Sep 28, 2013, at 4:47 PM, Paul Hargrove wrote: > I am watching with intense interest, as GASNet will be moving to git on Nov 1. > Could you give me a pointer to where I can get copies all the scripts that > you guys use for nightly tarballs, commit emails and such? > I'll

Re: [hwloc-devel] git / nightly builds

On Sep 28, 2013, at 8:12 AM, Brice Goglin wrote: >> Let's go through the use cases of what we want: >> >> 1. "make dist" in a developer's git clone. This should make a "hwloc-> describe>.tar.*. > > This is actually the critical point, see below. > >> 2. make a nightly

Re: [hwloc-devel] commit messages

> > Le 28/09/2013 14:19, Jeff Squyres (jsquyres) a écrit : >> This sounds good. Can you add this to the trac wiki? >> >> (e.g., MPICH did something like this when they converted to git) >> >> >> On Sep 28, 2013, at 8:15 AM, Brice Goglin <brice.g

Re: [hwloc-devel] commit messages

This sounds good. Can you add this to the trac wiki? (e.g., MPICH did something like this when they converted to git) On Sep 28, 2013, at 8:15 AM, Brice Goglin wrote: > Let's discuss some rules for commit messages. I used svn propedit often > in the past, that's not

Re: [hwloc-devel] git / nightly builds

On Sep 28, 2013, at 4:41 AM, Brice Goglin wrote: > I am having lots of problems when switching the regression testing stuff > (jenkins) to git, mostly because of make dist. Actually it worked 2 days > ago, no it breaks because hwloc-unknown.tar.* remain after make

[hwloc-devel] nightly snapshot tarballs now available

Ok, the infrastructure is now updated. I've generated the first snapshot tarballs in http://www.open-mpi.org/software/hwloc/nightly/. Nightly snapshots for <=v1.6 have all been removed. Git is fully open for business. Enjoy. -- Jeff Squyres jsquy...@cisco.com For corporate legal

Re: [hwloc-devel] git / nightly builds

On Sep 27, 2013, at 9:43 AM, Brice Goglin wrote: > I don't think so. I am planning to only update the regression testing > for v1.7 as well. K. > BUT what if the stable OMPI 1.6 needs a hwloc fix? Should we keep the > hwloc v1.5 branch open? E... let's cross that

[hwloc-devel] git / nightly builds

I'd say that git and the new Trac are now fully open for business. I might still do some shifting around of tags (see below), but otherwise, I think everything is just about ready. I'm revamping make_dist_script and the nightly build script; I should finally be able to commit those today, if

[hwloc-devel] Git status

The conversion to the new git repo is done, as is the conversion of Trac: https://github.com/open-mpi/hwloc https://git.open-mpi.org/trac/hwloc/timeline Commit messages have been edited to include new Git hashes for each old SVN "r" reference (e.g.,

[hwloc-devel] Quiet time for github/trac conversion

DongInn and I are set to do the final SVN -> git (i.e., github) hwloc transition. Here's what will happen: 1. Everyone immediately ceases all hwloc SVN and trac activity (i.e., now) 2. DongInn will set hwloc SVN and trac to read-only 3. Jeff will do the final SVN -> git (github) conversion 4.

Re: [hwloc-devel] Git testing of hwloc

onal tests. > > Brice > > > > Le 23/09/2013 20:36, Jeff Squyres (jsquyres) a écrit : >> Did you guys want to try to git commits and see them affect trac, etc.? >> >> I'm thinking that getting you 2 guys happy with the github <--> trac >> in

[hwloc-devel] Nightly tarballs

The nightly tarballs were broken for a few days after IU moved the build machine to a different server. They should now be fixed -- the OMPI 1.9 tarball was generated a few minutes ago; the others are being built right now. -- Jeff Squyres jsquy...@cisco.com For corporate legal information

Re: [hwloc-devel] Git testing of hwloc

AM, Jeff Squyres (jsquyres) <jsquy...@cisco.com> wrote: > Added both of you. > > On Sep 7, 2013, at 2:52 AM, Samuel Thibault <samuel.thiba...@inria.fr> wrote: > >> Jeff Squyres (jsquyres), le Sat 07 Sep 2013 00:04:13 +0200, a écrit : >>> What ar

[hwloc-devel] nightly builds failed

IU moved the nightly build cron jobs to a new machine today, and they failed. I'm manually running the build cron jobs on the old build machine (eddie) right now. I've alerted IU to what I think the error was in the move; hopefully they'll be able to fix it over the weekend. -- Jeff Squyres

Re: [hwloc-devel] Git testing of hwloc

Added both of you. On Sep 7, 2013, at 2:52 AM, Samuel Thibault <samuel.thiba...@inria.fr> wrote: > Jeff Squyres (jsquyres), le Sat 07 Sep 2013 00:04:13 +0200, a écrit : >> What are your github IDs? > > sthibaul > > Samuel > ___

[hwloc-devel] Git testing of hwloc

Brice / Samuel -- We seem to be in pretty good shape: - github commits work as expected - we're getting emails sent upon pushes to github - DongInn got the "refs #X" and "closes #X" stuff working (i.e., putting tokens in git commit messages affects Trac tickets -- see

Re: [hwloc-devel] [mpich-core] hwloc-1.6.x tainted with GPL?

On Sep 6, 2013, at 10:50 AM, Pavan Balaji wrote: > Aha! I was never happier to be wrong. :-) Woohoo! > > Thanks for the clarification. No problem. Go smack your partner for not doing their due diligence properly. :-) > FWIW, I said that you guys have LGPL-2.1 code, so

Re: [hwloc-devel] hwloc-1.6.x tainted with GPL?

On Sep 6, 2013, at 10:30 AM, Pavan Balaji wrote: > The mpich-3.0.x series was released with hwloc-1.6.x. One our of partners > just brought it to our attention that this version of hwloc has LGPL-2.1 code > in src/libltdl. Because GPL violations are quite serious, I want

[hwloc-devel] Migrating www.open-mpi.org

All -- Our hosting provider will be migrating www.open-mpi.org to a new machine on Wednesday. See message below for details. Begin forwarded message: From: DongInn Kim > Subject: Migrating

Re: [hwloc-devel] upcoming cleaning of headers and doc sections

Just to throw in a wildcard... You could also make hwloc.h be pretty minimal, and #include a bunch of others. You could divide sub-.h files by: - types - section / functionality - ...? On Jul 18, 2013, at 8:09 AM, Brice Goglin wrote: > FYI, I recently got a lot of

Re: [hwloc-devel] [hwloc-svn] [open-mpi/hwloc] 3ae99c: Fix a memory leak of the info array when mergin...

This was a test email post from github (we're exploring various options for migrating hwloc from svn to git). There might be more test emails over time; bear with us. On Jul 11, 2013, at 9:06 AM, Samuel Thibault wrote: > Branch: refs/heads/master > Home:

Re: [hwloc-devel] Move to git?

.fr> wrote: > Do you have any svn/git plan in the very near future? I will have a > couple fixes to push in the next days. So if you're going to switch to > git soon, please let me know, I'll wait and commit later. > > Brice > > > > Le 04/06/2013 12:14, Jeff S

Re: [hwloc-devel] First plugin namespace issue report

On Jun 4, 2013, at 11:12 PM, Brice Goglin wrote: > This code has to be in the plugin for real, it obviously cannot be > shared in the hwloc core, but putting it in a static inline in > hwloc/plugins.h may still be OK? I've written a Haiku in honor of the occasion:

Re: [hwloc-devel] First plugin namespace issue report

On Jun 4, 2013, at 9:55 AM, Brice Goglin wrote: >> One option might be to try to lt_dlsym one of the hwloc symbols that you >> know you'll need in the plugin (or any public hwloc symbol, for that >> matter). If ltdl_sym gets NULL back for the hwloc global symbol, then

Re: [hwloc-devel] First plugin namespace issue report

On Jun 4, 2013, at 5:22 AM, Brice Goglin wrote: > I take that back. Topology flags come too late, plugins are loaded > during the first topology_init(). Bummer. > We're back to things like "export HWLOC_PLUGINS_PATH=/none" Perhaps add a pre-init API to set flags like

Re: [hwloc-devel] First plugin namespace issue report

On Jun 4, 2013, at 5:11 AM, Brice Goglin wrote: > 2) custom test with ltdl: The program just silently fails to load hwloc > symbols. Equivalent to passing the topology flag above. One option might be to try to lt_dlsym one of the hwloc symbols that you know you'll need

Re: [hwloc-devel] Move to git?

On Jun 4, 2013, at 3:38 AM, Brice Goglin wrote: >> I'd like to explore converting all the old SVN log message mentions of >> "r" to git hashes. git-svn doesn't do that, right? > > No it doesn't afaik, and that would be nice. I know that MPICH went through this

Re: [hwloc-devel] Move to git?

On Jun 4, 2013, at 3:23 AM, Brice Goglin wrote: > When I switched Open-MX and KNEM from SVN to GIT, I basically just > pushed my git-svn clone. But I had to manually convert some svn > tags/branches. IIRC, the main reason is that git-svn has a strange way > to name svn

Re: [hwloc-devel] plugins inside plugin broken, as expected

On Jun 3, 2013, at 11:11 AM, Samuel Thibault wrote: > If only plugins and the core use these functions, the application does > not have to use -lhwloc-helper at all. If the application uses them > (e.g. bitmap functions), then it would have to use -lhwloc-helper, > but

Re: [hwloc-devel] Move to git?

ect to encounter along the way. On Jun 3, 2013, at 11:17 PM, Brice Goglin <brice.gog...@inria.fr> wrote: > +1000 ! > I already use git-svn for most of my hwloc work. But I still need svn for > backports, and that wastes a lot of my time. > Brice > > > "Jeff Squy

[hwloc-devel] Move to git?

We're having a discussion (again :-) ) about moving OMPI to a DVCS. The short conclusion of the long conversation is: the OMPI dev community would be much more comfortable moving to a DVCS if they could see some success with other OMPI projects (e.g., hwloc and/or MTT). Would hwloc be

Re: [hwloc-devel] hwloc embedding vs libltdl

On May 9, 2013, at 8:55 AM, Brice Goglin wrote: > +Although hwloc plugins may be used in embedded mode, the embedder > +project will have to manually setup libltdl in its build system so > +that hwloc can load its plugins. > +Also, embedders should avoid using their own

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r5606 - trunk

Does this patch fix it? It's not clear to me from the LT docs whether you're supposed to call LT_LANG multiple times or LT_LANG with multiple languages, but this patch below seems to run the libtool C++ configury: Index: configure.ac

Re: [hwloc-devel] hwloc embedding vs libltdl

On May 8, 2013, at 4:16 PM, Brice Goglin wrote: > But this issue is only in the embedders (OMPI), not in the embeddee > (hwloc), right? Yes. > I can get plugins to work in tests/embedded by adding 2 lines to its > configure.ac (see the attached patch, which also removes

Re: [hwloc-devel] hwloc embedding vs libltdl

I don't think libltdl has a .pc. :( Sent from my phone. No type good. On May 8, 2013, at 2:26 AM, "Brice Goglin" <brice.gog...@inria.fr<mailto:brice.gog...@inria.fr>> wrote: Le 08/05/2013 02:47, Jeff Squyres (jsquyres) a écrit : How's this patch? The only question I hav

Re: [hwloc-devel] hwloc embedding vs libltdl

1. Ok. 2. My thoughts were preventing hwloc from going thru some of the pain that OMPI went thru w embedding. Libibverbs has the same problem. If you have middleware that uses plugins that, in turn, uses plugins, it's a bit complicated to support fully static builds properly (OMPI and hwloc

Re: [hwloc-devel] hwloc embedding vs libltdl

How's this patch? The only question I have is: how do we figure out what libraries to put in the .pc file in the --disable-shared --enable-static case? On May 7, 2013, at 8:24 PM, Samuel Thibault <samuel.thiba...@inria.fr> wrote: > Jeff Squyres (jsquyres), le Wed 08 May 2013 02:21

  1   2   >