hkaiser changed the topic of #ste||ar to: STE||AR: Systems Technology, Emergent Parallelism, and Algorithm Research | stellar.cct.lsu.edu | HPX: A cure for performance impaired parallel applications | github.com/STEllAR-GROUP/hpx | Buildbot: http://rostam.cct.lsu.edu/ | Log: http://irclog.cct.lsu.edu/
khuck has quit [Remote host closed the connection]
khuck has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
khuck has quit [Ping timeout: 272 seconds]
eschnett has joined #ste||ar
anushi has joined #ste||ar
anushi_ has quit [Ping timeout: 240 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
anushi has quit [Quit: Bye]
Anushi1998 has quit [Ping timeout: 244 seconds]
Anushi1998 has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
Anushi1998 has quit [Ping timeout: 252 seconds]
eschnett has quit [Quit: eschnett]
eschnett has joined #ste||ar
eschnett has quit [Read error: No route to host]
eschnett has joined #ste||ar
hkaiser has quit [Quit: bye]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Read error: Connection reset by peer]
nikunj has quit [Ping timeout: 244 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
AnujSharma has joined #ste||ar
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
nanashi55 has quit [Ping timeout: 246 seconds]
nanashi55 has joined #ste||ar
jaafar has joined #ste||ar
mcopik has quit [Ping timeout: 245 seconds]
jbjnr has joined #ste||ar
jaafar has quit [Ping timeout: 252 seconds]
<jbjnr> (Although 76 fail is pretty bad, there are still 519 passes)
<jbjnr> aha. Looking at the fail outputs, I'd say that I didn't get the LD_LIBRARY_PATH right to pick up the components that were built as part of testing. The compilation was done on laptop and binaries copied across with some path name changes.
<jbjnr> so probably not as bad as 76 fails really
jbjnr has quit [Ping timeout: 240 seconds]
anushi has joined #ste||ar
anushi has quit [Remote host closed the connection]
jbjnr has joined #ste||ar
<simbergm> heller: cool!
<simbergm> did everything build successfully?
<simbergm> also, reminder about circleci/stellarbot ;)
<simbergm> gah, I keep misreading who writes messages
<simbergm> jbjnr: cool!
<simbergm> is this where you run martycam?
<jbjnr> Everything builds ok, but I spent a bit too long setting up the compiler toolchain, cos I wanted to try gcc 8 on the pi
<simbergm> and it was problematic I guess?
<jbjnr> Tonight I will try again with the fixes to the LD_LIBRARY_PATH etc
<jbjnr> looks like many thread suspend tests segfault
<jbjnr> problematic - yes I had issues with the libstdc++.so.6 and stuff like that, but It seems ok now
<simbergm> yep...
<simbergm> ok
<jbjnr> the thread suspend ones are yours?
<simbergm> yeah, at least the ones under tests.unit.resource
<simbergm> I've no clue what could be going wrong there though
<jbjnr> ok. I'll have to rebuild in debug mode and see what's going on. Was hoping you'd guess immediately what might be wrong :(
<simbergm> but maybe I should test it at home, there might be a bug that doesn't show up on linux again
<simbergm> I wish I could do that...
<simbergm> jbjnr: seems like HWLOC_MEMBIND_BYNODESET was introduced in 1.11.3, and I guess their version macro was messed up around those releases
<simbergm> I'll just check for < 2 to do it the old way
<jbjnr> have fun
<simbergm> I will!
<simbergm> (I do hate the macros as much as you do, but the world changes slowly...)
<simbergm> (#ifdefs)
<jbjnr> I would quite like to cmakeify hwloc and just build it as part of hpx :)
<jbjnr> (and jemalloc)
<simbergm> some people will love you, others will hate you
<simbergm> I'm not sure which one I will be yet
* zao shakes a fist at hwloc
<zao> jbjnr: Are there any silly cluster vendors that have a very special patched system-provided hwloc? Like I expect Cray to do.
<zao> Or the Power people.
david_pfander has joined #ste||ar
<jbjnr> zao: no idea, but I suspect no.
mcopik has joined #ste||ar
<heller> simbergm: what's cool?
<heller> the rasp-pi wasn't me ;)
nikunj has joined #ste||ar
<simbergm> I realized...
<simbergm> have you had time to play with your arm boards?
<jbjnr> I was pondering on the way to work whether I could setup a cross compiler toolchain on another machine and build nightlies that coukd then be run on the rpi ...
<jbjnr> is it worth the effort ...
<jbjnr> I could buy another pi and have it here at work! that'd simplify things :)
<jbjnr> quick ebay ....
<heller> i have 16 arm boards here
<heller> and the cross compilation setup
<heller> i just need to find the time to integrate it into our testing ;)
<jbjnr> ooh. I forgot you had tons
<jbjnr> got any spare?
<jbjnr> simbergm: I should have the hpx/opencv stuff running on the pi soon too :)
<simbergm> jbjnr: nice
<simbergm> I guess opencv already compiles without problems on arm?
<jbjnr> not tested yet, but will try today. Can set a build going now as the cross compiler is on the laptop
mcopik has quit [Ping timeout: 252 seconds]
<heller> jbjnr: you can order the suitcase for 650 euros ;)
<jbjnr> suitcase?
<jbjnr> photos please
<jbjnr> How do I pay!
<jbjnr> I want one. Right now
<jbjnr> It looks awesome
<heller> ;)
<zao> That's cheaper than I thought.
<heller> it is awesome
<heller> well, 650 is just the labor
<heller> 2.5k is the hardware
<heller> sorry
<jbjnr> 2.5k - each pi only cost 40CHF - how many are there?
<zao> Ah :)
<heller> it's not a pi
<zao> Note that those are fancypants ARM boards, not pies.
<jbjnr> well, nearly a pi
<heller> those are 8 core ARM64 (one piece is around 100, IIRC)
<heller> there are 17 on board, one is the head node
<jbjnr> ok. sounds about right then
<heller> plus an integrated ethernet switch, the cables, power unit, suitcase
<jbjnr> why in particular did you buy this? what is the project?
<heller> it's the demonstrator for allscale
<heller> simbergm: will StellarBot still push to gh-pages or do we want everything being handled by circle?
<simbergm> heller: I was just interested in StellarBot the github user to handle it with circleci
<simbergm> but I don't keeping it the way it is with rostam either
<heller> alright, that's a different beast, IIRC
<simbergm> don't mind
<heller> nah, if we can handle it on Circle, that's superb
<simbergm> would be nice to have
<simbergm> I'm not going to set it up now, but it could eventually handle release tags as well and we'd just host it all on gh pages
AnujSharma has quit [Ping timeout: 252 seconds]
<heller> simbergm: what would be cool is if we'd just have sub directories: release, master, PR-XXXX
<heller> have an index pointing to the releases and master
<heller> and delete the PR ones once the PR has been merged
AnujSharma has joined #ste||ar
<heller> and then the tags as well, of course
<simbergm> yeah, that's more or less what I had in mind as well minus the PRs
<simbergm> not sure how we'd clean them up
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] StellarBot pushed 1 new commit to gh-pages: https://github.com/STEllAR-GROUP/hpx/commit/c356308d372023a090ce3bc609655f7105a56c28
<ste||ar-github> hpx/gh-pages c356308 StellarBot: Updating docs
ste||ar-github has left #ste||ar [#ste||ar]
AnujSharma has quit [Ping timeout: 250 seconds]
mcopik has joined #ste||ar
<jbjnr> what have you demonstrated on the suitcase arm box?
AnujSharma has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] msimberg opened pull request #3456: Add #ifdefs to topology.cpp to support old hwloc versions again (master...hwloc-version-checks) https://github.com/STEllAR-GROUP/hpx/pull/3456
ste||ar-github has left #ste||ar [#ste||ar]
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] msimberg closed pull request #3454: Fixing warnings related to silent conversion of size_t --> int16_t (master...fixing_warnings) https://github.com/STEllAR-GROUP/hpx/pull/3454
ste||ar-github has left #ste||ar [#ste||ar]
K-ballo has joined #ste||ar
mcopik has quit [Ping timeout: 250 seconds]
<heller> jbjnr: resiliency by unplugging one of the boxes. The demo isn't ready yet ;)
mcopik has joined #ste||ar
mcopik_ has joined #ste||ar
mcopik has quit [Read error: Connection reset by peer]
<heller> simbergm: I need to mess with your branch to test the StellarBot ssh key stuff
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] sithhell created msimberg-sphinx (+3 new commits): https://github.com/STEllAR-GROUP/hpx/compare/930d366493fe^...e21d3df42b72
<ste||ar-github> hpx/msimberg-sphinx 930d366 Mikael Simberg: Add sphinx documentation
<ste||ar-github> hpx/msimberg-sphinx 61e988e Mikael Simberg: Remove boostbook documentation...
<ste||ar-github> hpx/msimberg-sphinx e21d3df Thomas Heller: Merge branch 'sphinx' of git://github.com/msimberg/hpx into msimberg-sphinx
ste||ar-github has left #ste||ar [#ste||ar]
<simbergm> heller: the sphinx branch? go ahead
<simbergm> but I think I need to reopen it, I think the ssh keys won't be accessible from forked repos (good)
<simbergm> oh wait, you're already on it
eschnett has quit [Quit: eschnett]
aserio has joined #ste||ar
nikunj has quit [Quit: brb]
Anushi1998 has joined #ste||ar
eschnett has joined #ste||ar
AnujSharma has quit [Ping timeout: 252 seconds]
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] StellarBot pushed 1 new commit to gh-pages: https://github.com/STEllAR-GROUP/hpx/commit/7a63f4922e1e75017576c725814e461a3c00c66e
<ste||ar-github> hpx/gh-pages 7a63f49 Mikael Simberg: Updating Sphinx docs
ste||ar-github has left #ste||ar [#ste||ar]
<heller> simbergm: cool, it seemed to work!
<simbergm> heller: almost... did it manually from circleci but should be able to get it to work automatically
<simbergm> it was waiting for a "yes" while cloning the gh-pages branch with ssh
<simbergm> thanks for adding the keys!
<simbergm> (key)
<heller> Ah, ok
<heller> simbergm: how do we avoid the "yes"?
<heller> simbergm: also, did it require to set the user name and email?
<zao> Maybe these would help in known_hosts?
<zao> hrm, maybe not.
<zao> Haven't found any help page with the actual signatures.
<simbergm> ssh-keyscan -H github.com seems to give me what we need
<heller> simbergm: will you continue on the branch I created?
<heller> You could also just cherry pick my commit
<simbergm> heller: hmm, wait, is something different other than the warnings commit from master?
<simbergm> I could keep it around just to test, it should work on the branch you created and fail on mine
<heller> simbergm: the depth of the clone and the add ssh keys stuff
<heller> It still hangs due to the "yes" thing
<simbergm> yeah, I didn't change anything yet
<simbergm> heller: but do you mean you changed something in the circleci config (keys and depth)?
<heller> Yes, the key in circle and the depth in the cmake file
<simbergm> and yeah, we should set user and email as well
<zao> simbergm: while technically sufficient, it also ruins the whole security idea about having known signatures of servers :)
<simbergm> zao: I know, but we can hardcode it ;)
<simbergm> if it changes and we know github actually changed their keys we can update it
hkaiser has joined #ste||ar
hkaiser has quit [Client Quit]
hkaiser has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] msimberg pushed 1 new commit to msimberg-sphinx: https://github.com/STEllAR-GROUP/hpx/commit/88b9a7b9a66d76a133e175158e1477092c74a6b7
<ste||ar-github> hpx/msimberg-sphinx 88b9a7b Mikael Simberg: Add GitHub public key and git username/email to CircleCI docs push stage
ste||ar-github has left #ste||ar [#ste||ar]
<simbergm> heller: what I was trying to say is that I can't see your changes to the config
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] hkaiser pushed 1 new commit to fixing_warnings: https://github.com/STEllAR-GROUP/hpx/commit/764f535f1f9a5789816129fef1f4e4c469ea6b99
<ste||ar-github> hpx/fixing_warnings 764f535 Hartmut Kaiser: Fixing more size_t -> int16_t (and similar) warnings
ste||ar-github has left #ste||ar [#ste||ar]
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] hkaiser opened pull request #3457: Fixing more size_t -> int16_t (and similar) warnings (master...fixing_warnings) https://github.com/STEllAR-GROUP/hpx/pull/3457
ste||ar-github has left #ste||ar [#ste||ar]
anushi has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] msimberg pushed 1 new commit to msimberg-sphinx: https://github.com/STEllAR-GROUP/hpx/commit/eddbec6539190c63da8689a44f69a6b6570f495c
ste||ar-github has left #ste||ar [#ste||ar]
<ste||ar-github> hpx/msimberg-sphinx eddbec6 Mikael Simberg: TEMP: Disable tests on CircleCI
Anushi1998 has quit [Ping timeout: 272 seconds]
aserio has quit [Ping timeout: 250 seconds]
aserio has joined #ste||ar
AnujSharma has joined #ste||ar
AnujSharma has quit [Max SendQ exceeded]
AnujSharma has joined #ste||ar
david_pfander has quit [Ping timeout: 246 seconds]
eschnett has quit [Quit: eschnett]
jaafar has joined #ste||ar
eschnett has joined #ste||ar
aserio has quit [Ping timeout: 252 seconds]
nikunj has joined #ste||ar
<hkaiser> K-ballo: the simple_loop test is fixed now (fixing_simple_loop branch)
<K-ballo> alright, I'll give it another try
anushi has quit [Quit: Bye]
Anushi1998 has joined #ste||ar
mcopik_ has quit [Ping timeout: 244 seconds]
nikunj has quit [Remote host closed the connection]
nikunj has joined #ste||ar
eschnett has quit [Quit: eschnett]
aserio has joined #ste||ar
eschnett has joined #ste||ar
aserio1 has joined #ste||ar
aserio has quit [Ping timeout: 240 seconds]
aserio1 is now known as aserio
mcopik_ has joined #ste||ar
aserio has quit [Ping timeout: 252 seconds]
AnujSharma has quit [Ping timeout: 246 seconds]
jaafar_ has joined #ste||ar
jaafar has quit [Ping timeout: 252 seconds]
jaafar_ is now known as jaafar
hkaiser has quit [Quit: bye]
aserio has joined #ste||ar
eschnett has quit [Quit: eschnett]
<heller> simbergm: stupid me, forgot to actually commit the changes
<K-ballo> hkaiser: works
aserio has quit [Quit: aserio]
hkaiser has joined #ste||ar
anushi has joined #ste||ar
Anushi1998 has quit [Ping timeout: 245 seconds]
parsa[[w]] has quit [Read error: Connection reset by peer]
jbjnr has quit [Read error: Connection reset by peer]