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/
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
eschnett has joined #ste||ar
<K-ballo> heller: are you on the evolutionary reflectors?
<K-ballo> there's a surprisingly good thread on concepts
<K-ballo> titled "Generic programming must be generic"
zbyerly_ has quit [Remote host closed the connection]
zbyerly_ has joined #ste||ar
EverYoung has quit [Ping timeout: 246 seconds]
hkaiser has joined #ste||ar
hkaiser has quit [Quit: bye]
ajaivgeorge_ has quit [Ping timeout: 246 seconds]
ajaivgeorge_ has joined #ste||ar
zbyerly_ has quit [Remote host closed the connection]
zbyerly_ has joined #ste||ar
ajaivgeorge_ has quit [Ping timeout: 240 seconds]
ajaivgeorge_ has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
patg has joined #ste||ar
eschnett has quit [Quit: eschnett]
zbyerly_ has quit [Remote host closed the connection]
zbyerly_ has joined #ste||ar
zbyerly_ has quit [Quit: Leaving]
mars0000 has joined #ste||ar
mars0000 has quit [Quit: mars0000]
patg has quit [Quit: This computer has gone to sleep]
vamatya has joined #ste||ar
Matombo has joined #ste||ar
vamatya has quit [Ping timeout: 276 seconds]
Matombo has quit [Remote host closed the connection]
bikineev has joined #ste||ar
Matombo has joined #ste||ar
Matombo has quit [Ping timeout: 246 seconds]
Matombo has joined #ste||ar
<github> [hpx] StellarBot pushed 1 new commit to gh-pages: https://git.io/vQ9Ko
<github> hpx/gh-pages f2a7375 StellarBot: Updating docs
david_pfander 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]
bikineev has quit [Ping timeout: 255 seconds]
hkaiser has joined #ste||ar
hkaiser has quit [Quit: bye]
pree has joined #ste||ar
pree has quit [Ping timeout: 258 seconds]
pree has joined #ste||ar
K-ballo has joined #ste||ar
ajaivgeorge_ has quit [Quit: ajaivgeorge_]
mcopik has quit [Ping timeout: 240 seconds]
Matombo has joined #ste||ar
hkaiser has joined #ste||ar
eschnett has joined #ste||ar
<pree> parsa[w] : yt ?
hkaiser has quit [Quit: bye]
<heller> woo, metaclasses update
<heller> K-ballo: no, I am currently only subscribed to parallel
mcopik has joined #ste||ar
<heller> linking clang is taking a HUGE amount of memory ...
aserio has joined #ste||ar
pree has quit [Ping timeout: 260 seconds]
patg has joined #ste||ar
patg is now known as patg[w]]
patg[w]] is now known as patg[w]
zbyerly_ has joined #ste||ar
pree has joined #ste||ar
Matombo has quit [Ping timeout: 246 seconds]
zbyerly_ has quit [Remote host closed the connection]
zbyerly_ has joined #ste||ar
zbyerly_ has quit [Remote host closed the connection]
zbyerly_ has joined #ste||ar
<patg[w]> aserio: see pm
<heller> david_pfander: so, the octotiger master branch is even failing on circle-ci
Matombo has joined #ste||ar
<heller> so yeah, this would be your first source to look at
<david_pfander> heller: we only got 4GB on CircleCI, that has been a big problem forever
<david_pfander> heller: even during compilation
<heller> didn't the test run once?
<david_pfander> heller: a very long time ago
<david_pfander> heller: I changed the number of compiling processes from 4 to 2 to 1 ...
<david_pfander> heller: same of the threads of the moving_star example
<david_pfander> heller: I fixed it from time to time, but 4GB is simply little memory
<heller> this worked
<heller> so during the runs we did for the GB paper, it seemed to have worked nicely. What changed?
<david_pfander> heller: so? it was 3 month ago
akheir has joined #ste||ar
<heller> What changed?
<david_pfander> heller: no idea, I didn't commit anything to master, except for circle ci changes
<david_pfander> heller: I wanted to merge master into my branch, this is when I noted the current problem
<heller> so, since it worked once. It's a strong indication that the circle-ci infrastructure is not at fault here
<david_pfander> heller: I agree
<heller> 1) The false positive (starting with build #340) should have been fixed early on
<heller> 2) People commiting to master should take a closer look to it
<heller> 3) Fix once your build failed
<david_pfander> heller: I absolutely agree, but "people" didn't do that
<heller> that's why I suggested a git bisect, to identify the bad commit, fix it ASAP, and communicate the importance of the CI testing
<heller> I don't think we have a memory inside of HPX
<heller> I am pretty certain (and your observation is backing off here) is that the rebalancing code currently in place is just broken
<david_pfander> heller: very likely, as HPX + my branch works fine
<heller> which is what dominic was working on recently
<heller> let me dig out the commit I know works
<heller> 336e35d60fe5f11e6af098ca82e5ed8e3d02175f
<heller> this should work
<heller> Jun 14
zbyerly_ has quit [Ping timeout: 276 seconds]
<david_pfander> heller: can you add that to the octotiger issue? and assign Dominic?
<heller> dominic should be aware of that ...
<heller> that commit is the result of a bug he thought was in HPX
<heller> I am going to rerun the circle-ci tests now to get a better feeling of the state of the repository
bikineev has joined #ste||ar
bikineev has quit [Read error: Connection reset by peer]
bikineev has joined #ste||ar
pree has quit [Ping timeout: 260 seconds]
pree has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
mars0000 has joined #ste||ar
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
akheir has quit [Remote host closed the connection]
K-ballo has joined #ste||ar
bikineev has quit [Ping timeout: 248 seconds]
K-ballo has quit [Quit: K-ballo]
<parsa[w]> merci beaucoup
K-ballo has joined #ste||ar
EverYoung has quit [Ping timeout: 246 seconds]
mars0000 has quit [Quit: mars0000]
ajaivgeorge has joined #ste||ar
bikineev has joined #ste||ar
ajaivgeorge has quit [Remote host closed the connection]
<heller> K-ballo: he, you too don't want to get involved in that goto discussion ;)?
ajaivgeorge has joined #ste||ar
<K-ballo> heller: vinnie is just reacting to the title of the paper
<heller> after he said: "you know, there has been a rebuttal" i decided to step back
<heller> yeah, it's difficult to tell him he is wrong...
ajaivgeorge_ has joined #ste||ar
hkaiser has joined #ste||ar
david_pfander has quit [Ping timeout: 240 seconds]
ajaivgeorge has quit [Ping timeout: 246 seconds]
<hkaiser> aserio: yt?
EverYoung has joined #ste||ar
ajaivgeorge_ has quit [Quit: ajaivgeorge_]
<heller> aserio: wash wants to help with the asplos adoption
<aserio> hkaiser: yes
<aserio> heller: ok :)
<hkaiser> aserio: hey
<aserio> I will let him know when I get the repo set up
<aserio> hkaiser: hey
<hkaiser> I guess heller's comment just now answers my question ;)
<heller> aserio: please do
<aserio> hkaiser: did you make it home?
<hkaiser> sitting in ATL right now
<aserio> fun lol
<hkaiser> indeed, at least they had no objections to me getting back in ...
<aserio> hkaiser: do you care if I set up the ASPLOS in our document repo
<hkaiser> aserio: why should I?
<aserio> getting you back in ?
<hkaiser> into the country
<aserio> hkaiser: we had it separated
<hkaiser> for the GB, yah
<aserio> previous work was in the GB repo
<hkaiser> well, make it separate if you think it's a better solution
<aserio> I would prefer it with the other papers
<hkaiser> ok
<hkaiser> fine by me
<aserio> but I was not entirely clear if if posed other issues
<hkaiser> we didn't make it, so no secrecy needed
<aserio> ok
<hkaiser> heller: pls see my comment to #2740
<hkaiser> aserio, heller: btw: https://github.com/LLNL/spack/pull/4709
<heller> hkaiser: \o/
<aserio> :0
<aserio> hkaiser: does patg know?!?
<hkaiser> aserio: I'd assume so, patg[w] ^^
<heller> "I'd be strongly opposed to that. HPX5 is a dead project, and HPX3 was a badly chosen name selected in the context of a particular funded project. HPX itself was always named this way and all the public records go under this name."
<heller> hkaiser: ^^ haha
<hkaiser> ;)
<aserio> It's true!
<heller> ncie that no one disagrees with that statement ;)
<hkaiser> nod
<heller> do you know the guy who is proposing it?
<hkaiser> proposing what?
<heller> the HPX spack package
<hkaiser> he's at LANL
<heller> no, junghans did the ebuild, the PR is from another person
<heller> arg
<heller> I am totally confused
<hkaiser> he is the one at the Mardi Conf a couple years back telling us about the summer project where they compared a bunch of runtimes
<heller> this writing business is killin gme
<hkaiser> heller: sure it's him
<heller> yeah ... sorry
<hkaiser> he's still embarrassed appently ;)
<heller> aserio: the reason why I am not answering to the book email is because I guess I need some distance to the current writing before I am ready to take on another one of those large text production tasks ;)
<heller> he
<aserio> diehlpk_work: ^^
<heller> so all this is coming at a very unfortunate timepoint for me ;)
<hkaiser> heller: just 'contribute' one of your chapters ;)
<heller> all of them!
<hkaiser> even better
<heller> I got 126 pages, single line spacing, A4 paper, no figures already
<hkaiser> showing off - huh?
<heller> hkaiser: you keep me busy with PRs? I keep you busy with grading it :P
<hkaiser> whatever it takes, get this thing done!
<heller> ;)
<heller> on it
<heller> introduction and conclusion tomorrow!
<heller> next week: result generation. the week after: polishing
<aserio> Yay!
<heller> (was about to make a bad joke about poland)
<heller> time to call it a day I guess
<diehlpk_work> heller, What about when I write the half page abstracts out of your thesis for the book?
<heller> I didn't even realize we need to provide a half page abstract right now ;)
hkaiser has quit [Quit: bye]
<diehlpk_work> We need for each chapter half page abstract, estimated pages, number of figures, and number of colored figures
<heller> do we have a publisher now?
<diehlpk_work> CRC Press is till interested, but the want to see this outline to decide
<diehlpk_work> All others do not want to publish the book
<heller> ok
<diehlpk_work> They do not publish books for C++ anymore or reduced their work there
<heller> O'reilly?
<diehlpk_work> and Springer never replied
bikineev has quit [Remote host closed the connection]
patg[w] has quit [Quit: Leaving]
<diehlpk_work> O'reilly is more for applied books and tutorials
<heller> so?
<heller> Practical Asynchronous Distributed Programming in C++ using HPX
<heller> s/Practical/Applied/
<heller> ;)
<heller> I think that could fit quite well
<diehlpk_work> Yes, or if we want to write more details about the concept of HPX and underlying techniques
<diehlpk_work> O.reilly would be more applied and CRC press more for academics
<diehlpk_work> Funny one of the gsoc students asked for a hpx book in his evaluation
<heller> if you don't ask, you never know ;)
<diehlpk_work> And I do not know if 0'reilly allows editors and contributors
<diehlpk_work> Ok, I will ask them
<diehlpk_work> With the title you suggested
<diehlpk_work> My concern is that the CRC press book would give us more credit for our academic career
K-ballo1 has joined #ste||ar
K-ballo has quit [Ping timeout: 260 seconds]
K-ballo1 is now known as K-ballo
pree has quit [Ping timeout: 260 seconds]
mars0000 has joined #ste||ar
pree has joined #ste||ar
eschnett has quit [Ping timeout: 240 seconds]
eschnett has joined #ste||ar
pree has quit [Ping timeout: 260 seconds]
pree has joined #ste||ar
pree has quit [Client Quit]
<github> [hpx] atrantan opened pull request #2758: Remove various warnings detected by clang 5.0 (master...master) https://git.io/vQQq9
bikineev has joined #ste||ar
titzi has quit [Ping timeout: 258 seconds]
diehlpk_work has quit [Quit: Leaving]
titzi has joined #ste||ar
<aserio> heller: I think it would be possible to re-use most of the GB paper for ASPLOS
aserio has quit [Quit: aserio]
Matombo has quit [Remote host closed the connection]
eschnett has quit [Read error: Connection reset by peer]
eschnett has joined #ste||ar
EverYoun_ has joined #ste||ar
EverYoung has quit [Ping timeout: 246 seconds]
mars0000 has quit [Quit: mars0000]
Matombo has joined #ste||ar
bikineev has quit [Remote host closed the connection]
EverYoun_ has quit [Remote host closed the connection]
Matombo has quit [Remote host closed the connection]
zbyerly_ has joined #ste||ar
EverYoung has joined #ste||ar
hkaiser has joined #ste||ar
<github> [hpx] hkaiser deleted fixing_2747 at a5a7c6f: https://git.io/vQQrt
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
<wash> hkaiser, heller: I think we can reuse all of it
<wash> more or less
<hkaiser> wash: all of what?
<github> [hpx] hkaiser pushed 1 new commit to simple_base_lco: https://git.io/vQQou
<github> hpx/simple_base_lco 6430975 Hartmut Kaiser: Leave managed base_lco_with_value the default
eschnett has quit [Quit: eschnett]
<wash> hkaiser: Well, I think we have a paper that is written and pretty polished, so i think we should just tweak it a bit for the conference
<wash> yes?
<wash> improve it where we can but no need to write something from scratch
<hkaiser> ahh yes, sure
<hkaiser> I missed the context
<wash> ah :p
<wash> hkaiser: are you back home?
<hkaiser> yah, just arrived