hkaiser changed the topic of #ste||ar to: The topic is '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/
hkaiser has quit [Ping timeout: 260 seconds]
hkaiser has joined #ste||ar
K-ballo has joined #ste||ar
Yorlik has quit [Read error: Connection reset by peer]
hkaiser has quit [Quit: bye]
nikunj97 has joined #ste||ar
nikunj97 has quit [Ping timeout: 258 seconds]
<heller> Wooot
* tarzeau turns off javascript to read it ...
<tarzeau> the full article must be bought, waiting for the hardcopy
<mdiers_> heller: I have read the article
<heller> cool!
<heller> I don't have a abo...
<heller> was it any good?
<mdiers_> are only four pages
<heller> He, I like the fact that someone writes about HPX in the first place ;)
<mdiers_> detlef uses the keyword hpx very often for the parallelization articles in the ct
<heller> Nice
nikunj has joined #ste||ar
weilewei has quit [Ping timeout: 260 seconds]
nikunj97 has joined #ste||ar
nikunj has quit [Ping timeout: 240 seconds]
Nikunj__ has joined #ste||ar
nikunj97 has quit [Ping timeout: 265 seconds]
nikunj has joined #ste||ar
Nikunj__ has quit [Ping timeout: 265 seconds]
rori has joined #ste||ar
nikunj97 has joined #ste||ar
nikunj has quit [Ping timeout: 268 seconds]
nikunj97 has quit [Ping timeout: 258 seconds]
hkaiser has joined #ste||ar
<heller> the introduction paragraphs sound strangely familiar ;)
<K-ballo> who is the author?
<K-ballo> oh, Detlef Wilkening
<hkaiser> heller: I don't care what they say as long they correctly spell our names ;-)
<heller> hkaiser: they don't even mention our names ;)
<hkaiser> sure they do: STE||AR Group
<heller> ah, yes
<heller> but "developed at LSU", which is not helping building my brand ;)
<hkaiser> well, true - that one is not correct
nikunj has joined #ste||ar
nikunj has quit [Ping timeout: 258 seconds]
hkaiser has quit [Quit: bye]
<heller> BTW, I'm going to be at the Prague c++ Meetup
<heller> That's the one that's happening during the committee meeting
<K-ballo> great!!!
<K-ballo> haven't seen you in a long time
<heller> Indeed
<heller> Will you be at the Meetup as well?
<K-ballo> I think it's planed as a committee meeting event?
<K-ballo> either way, yes, i'll be there
<heller> biddisco: you'll be in Prague as well, right?
<heller> Cool, a coworker of mine used to work with Hana, he'll be driving
<diehlpk_work> jbjnr, We have a call to dicuss about the SC20 paper.
hkaiser has joined #ste||ar
rori has quit [Quit: WeeChat 1.9.1]
Yorlik has joined #ste||ar
khuck has joined #ste||ar
<hkaiser> Yorlik: if you could please verify that your problem is fixed by #4315 we were able to merge it
<Yorlik> OK - I'll try
<Yorlik> Can I just cherry pick merge it into my 1.4.0 checkout?
<hkaiser> sure
diehlpk has joined #ste||ar
<diehlpk> HPX 1.4.0 does not build on Fedora since they updated some dependencies
<hkaiser> what compiler is that? what system?
<hkaiser> apparently its gcc 10.0.1, we do not test with that compiler, do we?
<hkaiser> simbergm: ^^?
<khuck> diehlpk: is there an octotiger call in 1 minute?
<diehlpk> khuck, yes
<diehlpk> I send a link to the mailing list
<diehlpk> jbjnr, yet?
<hkaiser> khuck: I'm looking into the swap issue, could be a problem on our side caused by some recent Blaze changes, not sure yet
<khuck> hkaiser: no problem, I am patiently awaiting the fix. :) So am I to understand the VT1/VT2 problem is only on POWER9? That kind of surprises me because at least VT1 is defined for all linux platforms
diehlpk has quit [Ping timeout: 268 seconds]
<khuck> maybe it's just a boost+blaze issue, I am fine with creating a sed script/command that will update blaze and blaze_tensor to replace VT1 and VT2 with something unique
<Yorlik> Dang - how do I cherry pick a PR? I tried "git cherry-pick 354f4d9ad5b28e2b10a05cfd86641e51a7fe9b83" but get a bad object error
<zao> You can fetch an arbitrary PR with `git fetch origin pull/ID/head:BRANCHNAME`
<zao> (with PR number as ID and arbitrary branch name)
<Yorlik> Thanks a ton !
<zao> I have to look that up every time I need it ^^
<Yorlik> Final command was: "git fetch origin pull/4315/head:master"
<Yorlik> hecking compile now
khuck_ has joined #ste||ar
<Yorlik> hkaiser: It's still broken after cherrypicking the PR into my 1.4.0 checkout
<Yorlik> Unresolved symbols
khuck has quit [Ping timeout: 260 seconds]
khuck_ has quit [Ping timeout: 260 seconds]
<simbergm> hkaiser diehlpk_work, gcc 10 isn't even out yet!? Anyway, it looks like a linker error... Not sure what would cause it
<simbergm> I'm back in the office on Thursday, can look at it then
<K-ballo> ups wrong window
<hkaiser> simbergm: the template is not instantiated, we might need to add its specializations explicitly
<simbergm> hkaiser ok, sounds good
<diehlpk_work> simbergm, this is fedora testing and they are plenty ahead with compilers
<diehlpk_work> simbergm, hkaiser We are fine and in the stable release HPX works. We just need to get things done for the upcoming release in April
khuck has joined #ste||ar
khuck has quit []
hkaiser has quit [Quit: bye]
weilewei has joined #ste||ar
hkaiser has joined #ste||ar
Yorlik has quit [Read error: Connection reset by peer]