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/
<github> [hpx] hkaiser deleted speedup_feature_test at 01211d8: https://git.io/vHOuY
<github> [hpx] hkaiser pushed 1 new commit to master: https://git.io/vHOus
<github> hpx/master 96c8a4c Hartmut Kaiser: Merge pull request #2646 from STEllAR-GROUP/fixing_config_definitions...
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
EverYoung has quit [Ping timeout: 240 seconds]
patg has joined #ste||ar
pree has joined #ste||ar
<patg> has anyone seen parsa around ?
<patg> parsa[[w]]: yt?
hkaiser has quit [Quit: bye]
denis_blank has quit [Quit: denis_blank]
K-ballo has quit [Quit: K-ballo]
<patg> pree: are you here
pree_ has joined #ste||ar
pree has quit [Ping timeout: 260 seconds]
pree_ has quit []
pree has joined #ste||ar
pree has quit [Quit: Page closed]
pree has joined #ste||ar
bikineev has joined #ste||ar
zbyerly_ has quit [Ping timeout: 240 seconds]
pree has quit [Ping timeout: 260 seconds]
bikineev has quit [Remote host closed the connection]
pree has joined #ste||ar
bikineev has joined #ste||ar
david_pf_ has joined #ste||ar
heller_ has quit [Quit: http://quassel-irc.org - Chat comfortably. Anywhere.]
heller_ has joined #ste||ar
david_pfander has joined #ste||ar
david_pf_ has quit [Remote host closed the connection]
pree has quit [Ping timeout: 260 seconds]
david_pfander has quit [Ping timeout: 260 seconds]
pree has joined #ste||ar
bikineev 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
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
ajaivgeorge has joined #ste||ar
Matombo has quit [Remote host closed the connection]
bikineev has joined #ste||ar
Matombo has joined #ste||ar
K-ballo has joined #ste||ar
bikineev has quit [Ping timeout: 272 seconds]
hkaiser has joined #ste||ar
bikineev has joined #ste||ar
pree has quit [Ping timeout: 260 seconds]
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
hkaiser has quit [Read error: Connection reset by peer]
david_pf_ has joined #ste||ar
bikineev has quit [Remote host closed the connection]
pree has joined #ste||ar
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
pree has quit [Read error: Connection reset by peer]
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
hkaiser has joined #ste||ar
pree has joined #ste||ar
pree has quit [Read error: Connection reset by peer]
eschnett has quit [Quit: eschnett]
aserio has joined #ste||ar
pree has joined #ste||ar
<aserio> david_pf_, heller_, hkaiser, jbjnr, parsa[[w]], patg: Meeting in 5
pree has quit [Read error: Connection reset by peer]
<hkaiser> sec
<ajaivgeorge> hey, i am Ajai, working on the gsoc project on segmented algorithms. I am trying to create a segmented for_each_n with existing segmented for_each. The functor is getting hpx::detail::vector_value_proxy instead of the actual data type. Any idea why? Thanks in advance.
eschnett has joined #ste||ar
pree has joined #ste||ar
ajaivgeorge has quit [Quit: ajaivgeorge]
pree has quit [Client Quit]
ajaivgeorge has joined #ste||ar
david_pf_ has quit [Quit: david_pf_]
<hkaiser> ajaivgeorge: I can talk later but not now, sorry
<K-ballo> *function object
denis_blank has joined #ste||ar
<zao> K-ballo: funject!
<zao> :P
<K-ballo> technically not incorrect, at least
hkaiser has quit [Quit: bye]
<mcopik> ajaivgeorge: I believe the proxy represents a reference, a value is returned only for const access
<mcopik> Hartmut should be able to explain it better but I believe it is caused by the ability of reference to modify remote elements of a vector (i.e. elements not located on current locality)
<zao> Kind of like vector<bool>, but in no way at all? :)
<ajaivgeorge> @mcopik I am working on the partitioned_for_each unit test, added for_each_n to it. The for_each is able to dereference this properly, but the for_each_n fails. The functor gives the error operator++ is not available for vector_value_proxy. Can you look at the code after our call?
<mcopik> ajaivgeorge: sure, I'll do it
<K-ballo> *function object
<mcopik> ajaivgeorge: can you give me (a link to gist or pastebin would be sufficient) to exact error with template stack?
pree has joined #ste||ar
mcopik has quit [Ping timeout: 260 seconds]
taeguk has joined #ste||ar
bikineev has joined #ste||ar
ajaivgeorge has quit [Quit: ajaivgeorge]
mcopik has joined #ste||ar
hkaiser has joined #ste||ar
akheir has joined #ste||ar
ajaivgeorge has joined #ste||ar
<github> [hpx] hkaiser pushed 1 new commit to master: https://git.io/vH3Ha
<github> hpx/master 744467f Hartmut Kaiser: Fixing recent patch to config definitions
mcopik has quit [Ping timeout: 258 seconds]
<github> [hpx] hkaiser pushed 1 new commit to master: https://git.io/vH3QC
<github> hpx/master 6941187 Hartmut Kaiser: Making optional all Boost specific configuration constants
bikineev has quit [Ping timeout: 258 seconds]
bikineev has joined #ste||ar
eschnett has quit [Quit: eschnett]
eschnett has joined #ste||ar
<github> [hpx] K-ballo force-pushed drop-vs2013 from 9f5b326 to 44d8c58: https://git.io/vHJsA
<github> hpx/drop-vs2013 912e310 Agustin K-ballo Berge: Remove support for VS2013
<github> hpx/drop-vs2013 a10fa1b Agustin K-ballo Berge: Mark C++11 defaulted functions as required
<github> hpx/drop-vs2013 12b43b8 Agustin K-ballo Berge: Mark C++11 noexcept as required
pree has quit [Ping timeout: 240 seconds]
<zao> K-ballo: Hooray!
<K-ballo> it's been a long battle
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
EverYoun_ has joined #ste||ar
EverYoung has quit [Ping timeout: 260 seconds]
denis_blank has quit [Quit: denis_blank]
aserio has quit [Ping timeout: 258 seconds]
eschnett has quit [Quit: eschnett]
EverYoung has joined #ste||ar
EverYoun_ has quit [Ping timeout: 240 seconds]
pree has joined #ste||ar
mcopik has joined #ste||ar
bikineev_ has joined #ste||ar
bikineev has quit [Read error: Connection reset by peer]
bikineev_ has quit [Read error: Connection reset by peer]
bikineev has joined #ste||ar
pree has quit [Ping timeout: 245 seconds]
pree has joined #ste||ar
bikineev has quit [Read error: Connection reset by peer]
bikineev has joined #ste||ar
<hkaiser> heller_: yt?
<hkaiser> jbjnr: I think I found some dubious code which could be responsible for the occasional hangs in the LF pp
<K-ballo> hkaiser: do inspect checks run on any header/source file found within a directory?
<hkaiser> by default yes
<K-ballo> thinking how core-only checks would look like
aserio has joined #ste||ar
pree has quit [Quit: AaBbCc]
pree has joined #ste||ar
<pree> Could anyone provide me a short description of what components :: server ::runtime_support will do ?
<pree> thank you
<github> [hpx] K-ballo force-pushed range from d435472 to c15cd60: https://git.io/voasb
<github> hpx/range 1f04dcf Agustin K-ballo Berge: Add C++11 range utilities
<github> hpx/range 00f07c1 Agustin K-ballo Berge: Cleanup acquire traits, replace boost::range with util/range in their implementation, patch broken whens
<github> hpx/range 474a409 Agustin K-ballo Berge: Replace core boost::range with util/range, remove redundant parallel traits
<zao> pree: Where would you start looking to find out?
<pree> zao While looking at copying functionalities for components
<github> [hpx] hkaiser created fixing_parcel_await (+1 new commit): https://git.io/vHsBX
<github> hpx/fixing_parcel_await 4218539 Hartmut Kaiser: This patch makes sure that all parcels in a batch are properly handled...
<github> [hpx] hkaiser opened pull request #2652: This patch makes sure that all parcels in a batch are properly handled (master...fixing_parcel_await) https://git.io/vHsBD
<hkaiser> pree: runtime_support is a 'all except the kitchen sink' type doing a lot of things
pree has quit [Ping timeout: 258 seconds]
<hkaiser> it handles a lot of the functionalities a locality exposes to other localities, such as creation of component instances
<hkaiser> this type needs a serious refactoring at some point
pree has joined #ste||ar
<pree> thank you hkaiser
<K-ballo> I dream of a mayor refactoring into layers
eschnett has joined #ste||ar
<hkaiser> K-ballo: nod, I agree that'd be good
<hkaiser> things have grown to intertwined
<github> [hpx] hkaiser pushed 1 new commit to fixing_parcel_await: https://git.io/vHs0J
<github> hpx/fixing_parcel_await d490a92 Hartmut Kaiser: Making sure every parcel is handled only once
pree has quit [Ping timeout: 240 seconds]
<heller_> hkaiser: I am back
pree has joined #ste||ar
<heller_> hkaiser: just commented
<heller_> hkaiser: parcels might indeed get preprocessed twice.
bikineev has quit [Remote host closed the connection]
<hkaiser> heller_: they got sent twice as well
<heller_> hkaiser: how would I reproduce it
<heller_> hkaiser: added another comment why preprocessing might indeed happen more than once, or twice
bibek_desktop has quit [Quit: Leaving]
<hkaiser> heller_: no idea, biut just think about it: pass 3 parcels through parcel_await, all of them have futures
<hkaiser> then the first parcel_await::apply gets restarted at idx 0, the second at idx 1 and so on
<heller_> yes, it has to get restarted at idx 0
<heller_> to go over the parcel again, to check the state of the future
<hkaiser> right
<hkaiser> but I see now that they wouldn't get sent twice as the idx_ is shared amongst the three invocations of apply and the apply() calls would execute sequentially
<hkaiser> I will remove the second commit from the PR
<hkaiser> the first commit is still valid, though
<hkaiser> done
<heller_> ok
bibek_desktop has joined #ste||ar
<github> [hpx] hkaiser force-pushed fixing_parcel_await from d490a92 to 4218539: https://git.io/vHsaG
<heller_> hkaiser: the first comment still applies
eschnett has quit [Ping timeout: 240 seconds]
<hkaiser> yes
<hkaiser> that one
<hkaiser> heller_: if preprocess needs to be kept alive, then the split_gid map will be a zombie after the first parcel
<hkaiser> so in any case, something is wrong with the existing code
<heller_> so what is it you want to fix here?
<heller_> ahh, preprocess_.split_gids_ is bogus after the first parcel, indeed
<hkaiser> this move creates problems for all but the first parcel: https://github.com/STEllAR-GROUP/hpx/blob/master/src/runtime/parcelset/detail/parcel_await.cpp#L60
<heller_> right
<heller_> it should just be reseted after the first parcel, not put in a zombie state, good catch
<heller_> so HPX_ASSERT(parcel[idx].split_gids_.empty()); swap(parcel[idx].split_gids_, preprocess_.split_gids_);
<heller_> i guess
<K-ballo> /hpx/tests/performance/network/network_storage/network_storage.cpp:693:31: warning: moving a temporary object prevents copy elision [-Wpessimizing-move]
<K-ballo> transfer_buffer_type buffer(std::move(f.get()));
<K-ballo> jbjnr: git-blame says that ^ is yours
<heller_> hkaiser: that explains some effects I am seeing though
denis_blank has joined #ste||ar
<hkaiser> heller_: feel free to reuse the PR I created
<github> [hpx] K-ballo opened pull request #2653: Drop support for VS2013 (master...drop-vs2013) https://git.io/vHsKm
<heller_> hkaiser: I'll play around with it for sure
<heller_> hkaiser: as it is, it will create more problems, i believe
<heller_> having those things unit tested would be just great..
<heller_> hkaiser: resource manager test appears to be failing at the moment
hkaiser has quit [Quit: bye]
pree has quit [Ping timeout: 240 seconds]
pree has joined #ste||ar
hkaiser has joined #ste||ar
pree has quit [Ping timeout: 272 seconds]
<hkaiser> heller_: do you plan to fix this parcel_await problem?
hkaiser has quit [Read error: Connection reset by peer]
hkaiser has joined #ste||ar
hkaiser has quit [Read error: Connection reset by peer]
hkaiser has joined #ste||ar
<hkaiser> heller_: could you explain why the parcel needs to store the split gids?
<hkaiser> also, assuming this is required, what split gids should a parcel store, just the one which will be sent with this parcel?
<hkaiser> I have no idea how this is supposed to work :/
EverYoun_ has joined #ste||ar
akheir has quit [Remote host closed the connection]
EverYoung has quit [Ping timeout: 245 seconds]
EverYoun_ has quit [Ping timeout: 255 seconds]
bikineev has joined #ste||ar
pree has joined #ste||ar
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
pree has quit [Ping timeout: 272 seconds]
pree has joined #ste||ar
aserio has quit [Quit: aserio]
pree has quit [Ping timeout: 272 seconds]
pree has joined #ste||ar
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
pree has quit [Ping timeout: 272 seconds]
bikineev has quit [Remote host closed the connection]
pree has joined #ste||ar
heller_ has quit [Quit: http://quassel-irc.org - Chat comfortably. Anywhere.]
heller_ has joined #ste||ar
pree has quit [Ping timeout: 272 seconds]
EverYoun_ has joined #ste||ar
EverYoung has quit [Ping timeout: 246 seconds]
EverYoun_ has quit [Ping timeout: 240 seconds]
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
pree has joined #ste||ar
pree has quit [Ping timeout: 272 seconds]
pree has joined #ste||ar
Matombo has quit [Remote host closed the connection]
Matombo has joined #ste||ar
pree has quit [Ping timeout: 272 seconds]
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