aserio 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/
Matombo has quit [Remote host closed the connection]
<github> [hpx] hkaiser force-pushed resource_partitioner from 1242ec2 to 45d3cff: https://git.io/v7lfK
<github> hpx/resource_partitioner 45d3cff Hartmut Kaiser: Dynamic thread_pool footprint...
<github> [hpx] hkaiser pushed 16 new commits to master: https://git.io/v76z1
<github> hpx/master 39ed018 Taeguk Kwon: Avoid nested exception_list when handling exceptions in parallel algorithm.
<github> hpx/master 9a7b0ee Taeguk Kwon: Implement parallel::partition. And add docs for that.
<github> hpx/master 9689c3d Taeguk Kwon: Add unit tests for parallel::partition.
<K-ballo> when does GSoC end?
<hkaiser> end of August
<github> [hpx] hkaiser pushed 1 new commit to partitioned_vector: https://git.io/v76gM
<github> hpx/partitioned_vector 7b878c2 Hartmut Kaiser: Making header tests pass
<github> [hpx] K-ballo created pack-short-circuit (+1 new commit): https://git.io/v762o
<github> hpx/pack-short-circuit b472866 Agustin K-ballo Berge: Short-circuit all_of/any_of/none_of instantiations
<github> [hpx] K-ballo force-pushed pack-short-circuit from b472866 to f59faaf: https://git.io/v762b
<github> hpx/pack-short-circuit f59faaf Agustin K-ballo Berge: Short-circuit all_of/any_of/none_of instantiations
hkaiser has quit [Read error: Connection reset by peer]
EverYoung has quit [Ping timeout: 246 seconds]
eschnett has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
vamatya_ has joined #ste||ar
zbyerly__ has joined #ste||ar
zbyerly__ has quit [Ping timeout: 240 seconds]
vamatya_ has quit [Ping timeout: 248 seconds]
bikineev has quit [Remote host closed the connection]
bikineev has joined #ste||ar
bikineev_ has joined #ste||ar
bikineev has quit [Ping timeout: 268 seconds]
Matombo has joined #ste||ar
david_pfander has quit [Quit: david_pfander]
david_pfander has joined #ste||ar
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
bikineev_ has quit [Ping timeout: 258 seconds]
Matombo has quit [Remote host closed the connection]
bikineev has joined #ste||ar
bikineev has quit [Ping timeout: 258 seconds]
mcopik has joined #ste||ar
bikineev has joined #ste||ar
<github> [hpx] StellarBot pushed 1 new commit to gh-pages: https://git.io/v7ikS
<github> hpx/gh-pages 219d287 StellarBot: Updating docs
bikineev_ has joined #ste||ar
bikineev has quit [Read error: Connection reset by peer]
Matombo has joined #ste||ar
bikineev_ has quit [Ping timeout: 240 seconds]
Kiril_ has joined #ste||ar
Matombo has quit [Ping timeout: 240 seconds]
bikineev has joined #ste||ar
Matombo has joined #ste||ar
Matombo has quit [Ping timeout: 255 seconds]
<github> [hpx] AntonBikineev pushed 1 new commit to nondefault_ctor_ser: https://git.io/v7iGL
<github> hpx/nondefault_ctor_ser 2e90fd5 AntonBikineev: Reserving space before collection deserialization
hkaiser has joined #ste||ar
K-ballo has joined #ste||ar
bikineev has quit [Read error: No route to host]
bikineev has joined #ste||ar
<github> [hpx] hkaiser pushed 1 new commit to resource_partitioner: https://git.io/v7iCv
<github> hpx/resource_partitioner 5a05907 Hartmut Kaiser: More inspect happyness
<jbjnr> tut tut. "happiness"
<github> [hpx] hkaiser pushed 1 new commit to partitioned_vector: https://git.io/v7iCI
<github> hpx/partitioned_vector 73946c0 Hartmut Kaiser: Inspect error fix
<hkaiser> jbjnr: ok, thanks
<hkaiser> why not 'happieness', then?
<hkaiser> jbjnr: and should I rewrite the commit?
<jbjnr> just because english is highly irregular. No need to rewrite. We accept foriegn contributions :)
<jbjnr> Foreign even
<hkaiser> lol
<hkaiser> thanks
<jbjnr> multicultural - unlike trump's america soon.
<hkaiser> better than having 50% migrants
<jbjnr> all of usa is migrants
<hkaiser> indeed
<jbjnr> good point about the scheduler. who cares about the throttling one, now that we can add them in user code.
<hkaiser> yes
bikineev has quit [Ping timeout: 255 seconds]
david_pfander has quit [Quit: david_pfander]
Matombo has joined #ste||ar
mcopik has quit [Ping timeout: 260 seconds]
mcopik has joined #ste||ar
mcopik has quit [Ping timeout: 268 seconds]
eschnett has quit [Quit: eschnett]
<heller> hkaiser: jbjnr: you two are migrants
<hkaiser> sure we are
<hkaiser> the difference is we integrate with the local society
<jbjnr> At least I'm not German though.
<hkaiser> lol
<hkaiser> good one
<heller> lol
<jbjnr> My new neighbours are swiss german and they are so noisy. I want to move.
<heller> Noise cancelling technology? Something you could simulate on daint
<jbjnr> I had a water cannon in mind the other day. Much quicker and probably more likely to succeed
<jbjnr> heller: you should be on holiday. get off irc!
<K-ballo> is circleci broken?
<hkaiser> K-ballo: some affinity mask problems, they seem to have changed the underlying OS which reveals a problem in our affitiny masking code
<K-ballo> no, I mean circleci itself, I can't even access the build results
<jbjnr> nor can I
<K-ballo> all I get here is a spinner https://circleci.com/gh/STEllAR-GROUP/hpx
<jbjnr> oh no. it was my script disable add-on
<jbjnr> yup. spinner on that page
<K-ballo> can someone tell me the build number for my latest build?
<jbjnr> can it be guessed from here http://irclog.cct.lsu.edu/ste~b~~b~ar-dev/2017-08-08
<K-ballo> I just tried that, I think it's all buildbot and no circle
<hkaiser> cicleci works for me
<K-ballo> found it, from github's commit history
aserio has joined #ste||ar
eschnett has joined #ste||ar
hkaiser has quit [Quit: bye]
Kiril_ has quit [Quit: Page closed]
mcopik has joined #ste||ar
hkaiser has joined #ste||ar
heller has quit [Quit: http://quassel-irc.org - Chat comfortably. Anywhere.]
heller has joined #ste||ar
Matombo has quit [Remote host closed the connection]
hkaiser has quit [Quit: bye]
hkaiser has joined #ste||ar
<github> [hpx] hkaiser pushed 1 new commit to master: https://git.io/v7iFn
<github> hpx/master 899c58a Hartmut Kaiser: Remove more security leftovers
aserio has quit [Ping timeout: 258 seconds]
<github> [hpx] hkaiser pushed 1 new commit to master: https://git.io/v7iFA
<github> hpx/master 8719307 Hartmut Kaiser: Fix accidentally committed problem
aserio has joined #ste||ar
pree_ has joined #ste||ar
mbremer has joined #ste||ar
pree_ has quit [Read error: Connection reset by peer]
pree_ has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
K-ballo has joined #ste||ar
zbyerly__ has joined #ste||ar
vamatya_ has joined #ste||ar
aserio has quit [Ping timeout: 258 seconds]
<github> [hpx] hkaiser pushed 1 new commit to resource_partitioner: https://git.io/v7PUd
<github> hpx/resource_partitioner 466cc16 Hartmut Kaiser: Adding basic test for resource_partitioner...
<github> [hpx] hkaiser opened pull request #2806: Partitioned vector (master...partitioned_vector) https://git.io/v7PTL
Reazul has quit [Quit: Page closed]
bikineev has joined #ste||ar
<github> [hpx] hkaiser pushed 1 new commit to simple_base_lco: https://git.io/v7Ptn
<github> hpx/simple_base_lco 6e5fba6 Hartmut Kaiser: Merge branch 'master' into simple_base_lco
bikineev has quit [Ping timeout: 255 seconds]
<github> [hpx] hkaiser pushed 1 new commit to simple_base_lco: https://git.io/v7PtX
<github> hpx/simple_base_lco 4c9c6bc Hartmut Kaiser: Remove obsolete #includes
aserio has joined #ste||ar
EverYoung has joined #ste||ar
aserio has quit [Ping timeout: 276 seconds]
<github> [hpx] hkaiser created gentryx-master (+29 new commits): https://git.io/v7PZF
<github> hpx/gentryx-master 1416e1f Andreas Schäfer: reorder forward declarations to get rid of C++14-only auto return types
<github> hpx/gentryx-master 0c56fbc Andreas Schäfer: add test for C++14 auto compiler feature
<github> hpx/gentryx-master ee0f107 Andreas Schäfer: revert customization points, conditionally to the availability of C++14
bikineev has joined #ste||ar
zbyerly__ has quit [Ping timeout: 255 seconds]
zbyerly__ has joined #ste||ar
bikineev has quit [Remote host closed the connection]
Matombo has joined #ste||ar
aserio has joined #ste||ar
bikineev has joined #ste||ar
EverYoun_ has joined #ste||ar
EverYoung has quit [Ping timeout: 255 seconds]
zbyerly__ has quit [Read error: Connection reset by peer]
zbyerly_ has joined #ste||ar
hkaiser has quit [Quit: bye]
zbyerly_ has quit [Read error: Connection reset by peer]
zbyerly__ has joined #ste||ar
jakemp has joined #ste||ar
aserio has quit [Quit: aserio]
EverYoun_ has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
jakemp has quit [Ping timeout: 268 seconds]
mbremer has quit [Ping timeout: 260 seconds]
mbremer has joined #ste||ar
<mbremer> Can anyone help me? I'm trying to build hpx on a computer without HWLOC. I've set the following flag HPX_WITH_HWLOC=Off but I am still getting fatal errors where it seems cmake is trying to include hwloc headers
EverYoun_ has joined #ste||ar
<zao> mbremer: I believe that hwloc is, like Boost, required.
<zao> (unless possibly on macOS, if the docs are right)
EverYoung has quit [Ping timeout: 246 seconds]
<mbremer> zao: Thanks. I'll just install it. I did get this cmake error "CMake Error at cmake/HPX_Message.cmake:43 (message): ERROR: Hwloc could not be found and HPX_WITH_HWLOC=ON, please specify HWLOC_ROOT to point to the correct location or set HPX_WITH_HWLOC to OFF"
eschnett has quit [Quit: eschnett]
<mbremer> I find that then maybe a little misleading. But thank you nonetheless!
<zao> Someone[TM] probably should look into where it's actually required nowadays and probably set up some hard gates around it.
<zao> If you're bored you could file a bug :)
<mbremer> Haha sure thing. Will do.
hkaiser has joined #ste||ar
pree_ has quit [Quit: AaBbCc]
<K-ballo> it is optional, but strongly encouraged (opt out), is it not?
bikineev has quit [Remote host closed the connection]
<zao> K-ballo: Listed under "required" on both Linux and Windows, mentions that it's optional on macOS.
<zao> Prose above seems to just strongly encourage it.
<zao> And the build output from MB shows that it's being used regardless of what you set the CMake WITH knob to.
<zao> hkaiser: Running a build on the PV-affected system, hopefully it completes.
<zao> The fans sound like they're going to take off, and I have no picture on the screen :)
<zao> hkaiser: Initial results are same, at least one test fails as before.
<zao> tests/unit/parallel/segmented_algorithms/CMakeFiles/partitioned_vector_transform_reduce_test_exe.dir/partitioned_vector_transform_reduce.cpp.o: In function `hpx::const_local_vector_iterator<int, std::vector<int, std::allocator<int> > >::local()':
<zao> /home/zao/stellar/hpx/hpx/components/containers/partitioned_vector/partitioned_vector_segmented_iterator.hpp:409: undefined reference to `hpx::server::partitioned_vector<int, std::vector<int, std::allocator<int> > >::cbegin() const'
<zao> tests/unit/parallel/segmented_algorithms/CMakeFiles/partitioned_vector_transform_reduce_test_exe.dir/partitioned_vector_transform_reduce.cpp.o: In function `hpx::const_local_vector_iterator<double, std::vector<double, std::allocator<double> > >::local()':
<zao> /home/zao/stellar/hpx/hpx/components/containers/partitioned_vector/partitioned_vector_segmented_iterator.hpp:409: undefined reference to `hpx::server::partitioned_vector<double, std::vector<double, std::allocator<double> > >::cbegin() const'
mbremer has quit [Ping timeout: 260 seconds]
Matombo has quit [Remote host closed the connection]
<hkaiser> zao: circleci does not show any of those problems
<hkaiser> what could be different?
<zao> It's about as stock a debian 9.1 installation as you can get.
<hkaiser> gcc?
<zao> cmake 3.7.2, gcc 6.3.0 20170516 (Debian 6.3.0-18), hwloc and gperftools, all from package.
<hkaiser> ok
<hkaiser> cicleci is clang-based
<zao> Boost 1.64 with C++14 flags, HPX -DHPX_WITH_CXX14=ON
<hkaiser> zao: something is fishy with your boost detection - even if that is unrelated
<zao> That stuff has been going on forever, IIRC.
<hkaiser> I have never seen this before :/
<hkaiser> nor does it show on circleci, for instance
<zao> What CMake is CCI on?
<hkaiser> uhh
<hkaiser> we should add that to the cmake output
jbjnr_ has joined #ste||ar
jbjnr has quit [Ping timeout: 246 seconds]
jbjnr_ is now known as jbjnr
EverYoun_ has quit [Remote host closed the connection]
<zao> Building with clang now, for parity.
<zao> Assuming that the machine doesn't burn up due to full-speed GPU fans, because Linux.
<zao> clang build on the same box seems fine.
<zao> Three failed tests, tests.unit.parallel.distributed.tcp.partitioned_vector_target, tests.unit.serialization.serialization_partitioned_vector, tests.unit.host_.block_allocator
<zao> Last one ate over 8G of memory before timing out.
<zao> Middle one said 'partitioned_vector' not registered.
<zao> First one on some component hogwash, let's see if I can get the logs.
<hkaiser> but no linker errors at least
<zao> correct
<hkaiser> nod
<zao> started a build for reference on another machine, foss/2017a Boost/1.61.0 hwloc/1.11.5 CMake/3.8.0
<zao> (foss/2017a has GCC 6.3.0)
<hkaiser> ok
<zao> Not sure how well the Boost will fare, but time will tell.
<hkaiser> zao: the serialization test has been fixed on master at least, so 2 failin gones
<hkaiser> and the block_allocator test is unrelated
<zao> hkaiser: Link is hosed on work box as well.
<zao> Need to view the raw file for the build log, as it's too polluted by Boost deprecations.
<zao> Oh well, sleep.
<zao> Hopefully there's some semblance of useful info in there somewhere.
<zao> At least it's reproducible outside of my home machine, and it builds in like 11 minutes :)
<zao> (note that there's two build invocations in the log, one without any target and one for 'tests')