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/
eschnett_ has quit [Quit: eschnett_]
eschnett_ has joined #ste||ar
eschnett_ has quit [Quit: eschnett_]
hkaiser has quit [Quit: bye]
aserio has joined #ste||ar
aserio has quit [Client Quit]
jbjnr__ has joined #ste||ar
jbjnr_ has quit [Ping timeout: 260 seconds]
nanashi55 has quit [Ping timeout: 240 seconds]
nanashi55 has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
K-ballo has joined #ste||ar
anushi has joined #ste||ar
anushi has quit [Remote host closed the connection]
<simbergm>
heller: do you know why apply creates a task immediately (i.e. run_now = true)? was playing around with the future_overhead test and expected apply to be at least as fast as async but it's not because of that
<heller>
no
<heller>
probably historic
<simbergm>
ok, thanks
<heller>
simbergm: so you are saying that async tasks are not run immediately and apply tasks are and that creates a performance problem?
<simbergm>
heller: yeah, but I don't know if it's a problem anywhere else
<simbergm>
in the future_overhead test 1. using apply is slower because all the tasks are created on the same thread and 2. mmap fails if you try to launch 10000 or 100000 tasks because it tries to create all the stacks at once
<heller>
ok
<heller>
simbergm: I guess the lazy task init would fix it ...
<heller>
i really have to get that going...
<heller>
I am still caught up in that EU project...
<simbergm>
yeah, that would remove the problem completely
<simbergm>
I might just change true to false for the release...
<heller>
ok
<heller>
when do we plan the RC?
<heller>
we have to fix the migrate test as well...
<simbergm>
I was hoping to do it still this week, after I've merged the sphinx docs
<heller>
#3484 are important as well
<heller>
is*
<heller>
do you know if John is working on that?
<heller>
I might give it a whirl
<simbergm>
slack activity would suggest that he's looking into it
<simbergm>
we can still fix bugs after the rc but there doesn't seem to be any new features left to go in except that I know john wants his guided executor in the release
<simbergm>
heller: don't know if you've looked at rostam lately but I asked about partitioned vector because of that...
<simbergm>
is the usual thing just to split translation units to lower memory usage? without completely changing the code that is
<heller>
yes ...
<heller>
but that's just fighting the symptoms
<simbergm>
yeah, that's why I'm asking :/ my google-fu hasn't given me any other reasonable suggestions
<ste||ar-github>
hpx/fix_3484 d67efc7 John Biddiscombe: Use BUILD_INTERFACE generator expression to fix cmake flag exports
ste||ar-github has left #ste||ar [#ste||ar]
ste||ar-github has joined #ste||ar
<ste||ar-github>
[hpx] biddisco opened pull request #3485: Use BUILD_INTERFACE generator expression to fix cmake flag exports (master...fix_3484) https://github.com/STEllAR-GROUP/hpx/pull/3485
<ste||ar-github>
hpx/demangle_helper 4734f58 John Biddiscombe: Move type info into hpx::debug namespace and add print helper functions
<ste||ar-github>
hpx/demangle_helper 9ee87e6 John Biddiscombe: Fix demangle_helper review comments
<ste||ar-github>
hpx/demangle_helper e7f4f5e John Biddiscombe: Move debug demangle_helper etc into util::debug namespace/dir
ste||ar-github has left #ste||ar [#ste||ar]
eschnett_ has joined #ste||ar
<nikunj97>
simbergm, I am free this weekend. I will review the docs for any grammatical mistake. Also, I think it would be a nice idea to add examples for some basic functions (I haven't read complete docs so I'm not sure if it includes any).
hkaiser has quit [Quit: bye]
eschnett_ has quit [Quit: eschnett_]
aserio has joined #ste||ar
<simbergm>
nikunj97: nice, thanks
<simbergm>
it includes some but probably not enough
<simbergm>
I might go ahead and merge it before you have time to look at it to make sure I have all the circleci/gh pages stuff set up correctly but you can open a pr later on with corrections or just tell me
<simbergm>
and there are many things that could be added, this is just meant to be a start
<nikunj97>
simbergm, sure go ahead and merge the PR. I'll add one later.
<nikunj97>
Reading the docs will update me with every feature. I can add a few examples myself just to understand how things are running :)
<ste||ar-github>
hpx/msimberg-patch-1 723795b Mikael Simberg: Fix launch_process test...
ste||ar-github has left #ste||ar [#ste||ar]
eschnett_ has joined #ste||ar
hkaiser has joined #ste||ar
<nikunj97>
hkaiser, see pm please
aserio has quit [Ping timeout: 252 seconds]
patgr has joined #ste||ar
<patgr>
Is Dominic around?
<hkaiser>
patgr: yes, he sits across the hallway from here
<patgr>
I guess I'll email him. I'm not sure how he made the paper without the markups and Alice wants to submit it today or tomorrow
<patgr>
hkaiser: can you nudge him to respond to the email?
<hkaiser>
will do
<patgr>
Thank you
<hkaiser>
patgr: done
david_pfander has quit [Ping timeout: 250 seconds]
<heller>
hkaiser: I'd be available from now on
<hkaiser>
heller: sorry, I have another meeting in 5 minutes :/
<hkaiser>
can we move our meeting to tomorrow, please?
<heller>
hkaiser: ok, what do you suggest?
<heller>
sure thing
<hkaiser>
thank you
<hkaiser>
bad planning on my end
<heller>
no problem
<heller>
allows me to fall asleep right away :P
<heller>
or try to fix the cmake mess...
<K-ballo>
jbjnr__: did you figure out the template-id issue?
aserio has joined #ste||ar
aserio1 has joined #ste||ar
aserio has quit [Ping timeout: 250 seconds]
aserio1 is now known as aserio
akheir has joined #ste||ar
aserio has quit [Quit: aserio]
hkaiser has quit [Quit: bye]
aserio has joined #ste||ar
aserio has quit [Ping timeout: 252 seconds]
aserio has joined #ste||ar
hkaiser has joined #ste||ar
<jbjnr__>
K-ballo: yes. I figured it out. I had somehow messed up a copy paste into my stuff and once I removed a bit of nonsense code, the problem went away
RostamLog has joined #ste||ar
patgr has quit [Quit: Leaving]
eschnett_ has quit [Quit: eschnett_]
nikunj97 has quit [Remote host closed the connection]
nikunj has joined #ste||ar
aserio has quit [Quit: aserio]
aserio has joined #ste||ar
aserio has quit [Client Quit]
nikunj has quit [Remote host closed the connection]