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/ | GSoC2018: https://wp.me/p4pxJf-k1
nikunj has quit [Read error: Connection reset by peer]
nikunj has joined #ste||ar
Anushi1998 has quit [Quit: Leaving]
<nikunj>
I'm writing blogs for every week of GSoC coding period, you can give it a read to know more about what I did in the following week. Here is the link for the same: https://medium.com/gsoc18-with-ste-ar-group
nikunj has quit [Quit: Leaving]
hkaiser has quit [Quit: bye]
david_pfander has joined #ste||ar
kisaacs has quit [Ping timeout: 245 seconds]
kisaacs has joined #ste||ar
gablab has joined #ste||ar
<gablab>
Hi I'm currently trying to install hpxML on the rostam clusters
kisaacs has quit [Ping timeout: 245 seconds]
<gablab>
I managed to build hpx but now I need to build the ClangTool
david_pfander has quit [Ping timeout: 260 seconds]
mbremer has joined #ste||ar
kisaacs has joined #ste||ar
aserio has joined #ste||ar
hkaiser has quit [Quit: bye]
kisaacs has quit [Ping timeout: 252 seconds]
akheir has joined #ste||ar
tianyi has joined #ste||ar
RostamLog has joined #ste||ar
diehlpk has joined #ste||ar
tianyi has quit [Remote host closed the connection]
kisaacs has joined #ste||ar
diehlpk has quit [Ping timeout: 252 seconds]
hkaiser has joined #ste||ar
parsa has joined #ste||ar
parsa has quit [Quit: Zzzzzzzzzzzz]
aserio has quit [Ping timeout: 260 seconds]
Anushi1998 has joined #ste||ar
<mbremer>
@hkaiser: Have you taken a peek at my email?
nikunj has joined #ste||ar
aserio has joined #ste||ar
<hkaiser>
mbremer: still trying to grasp things
<mbremer>
Things in general or just my things?
<hkaiser>
heh good question
<hkaiser>
I do not fully understand what's going on yet
<hkaiser>
especially that the component after migration continues with the same time step
<hkaiser>
this looks like a problem on your end
churli has joined #ste||ar
<mbremer>
Hmm. Yeah I figured. Any ideas? I'm still under the impression that the nested parallelism is causing problems.
<hkaiser>
in what sense?
<mbremer>
Well the component only has one action `Step()` but there are several kind of asynchronous calls in `Step()`
<hkaiser>
ok
<hkaiser>
and step returns before those are finished?
<mbremer>
Well step returns the associated futures.
<hkaiser>
ok, then things make sense
<mbremer>
Aha!
<hkaiser>
the migration is prevented by pinning the object
<hkaiser>
it is unpinned once the Step() function returns
<hkaiser>
that is a good and interesting finding
<hkaiser>
the pinning should be left in place until the retunred future becomes ready
<mbremer>
Yes, this is what I was hoping would happen.
<hkaiser>
I think that could explain why the object is migrated in the middle of things
<mbremer>
That's what would make the most sense to me.
<mbremer>
Would you like me to make a minimial Working example and open an issue?
<hkaiser>
give me a sec
<hkaiser>
mbremer: yah, please create a ticket
<hkaiser>
I'll try to come up with a workaround for you and with a general purpose solution asap
<mbremer>
ok. Yeah, sounds good. I can try making a test, that just takes the current migration test and change the action to reflect my use case.
AnujSharma has quit [Ping timeout: 245 seconds]
zura has joined #ste||ar
AnujSharma has joined #ste||ar
<hkaiser>
mbremer: for now I'd suggest that you call pin() on the base class of your component before returning and attach a continuation to the returned future that calls unpin()
<hkaiser>
mbremer: from what I see from the code there is no pinning being done at all, currently :/
<hkaiser>
doh!
<mbremer>
Hahah :) best workaround yet!
<mbremer>
Let me try that actually real quick. That should be straightforward enough.
<mbremer>
@hkaiser: Cool! So the migration happens at the right time now. Still getting a segfault, but this I think really is my problem.
parsa has joined #ste||ar
nikunj97 has joined #ste||ar
parsa has quit [Quit: Zzzzzzzzzzzz]
nikunj has quit [Ping timeout: 245 seconds]
zura has quit [Quit: Leaving]
nikunj1997 has joined #ste||ar
nikunj97 has quit [Read error: Connection reset by peer]
AnujSharma has quit [Ping timeout: 252 seconds]
aserio has quit [Ping timeout: 260 seconds]
diehlpk has joined #ste||ar
david_pfander has joined #ste||ar
nikunj1997 has quit [Ping timeout: 248 seconds]
diehlpk has quit [Remote host closed the connection]
aserio has joined #ste||ar
diehlpk has joined #ste||ar
diehlpk has quit [Remote host closed the connection]
diehlpk has joined #ste||ar
nanashi64 has joined #ste||ar
nanashi55 has quit [Ping timeout: 240 seconds]
nanashi64 is now known as nanashi55
diehlpk has quit [Ping timeout: 252 seconds]
Anushi1998 has quit [Ping timeout: 245 seconds]
<mbremer>
@hkaiser: I opened the issue. In the meantime, I'll just use the work around. Thanks!
kisaacs has quit [Ping timeout: 260 seconds]
david_pfander has quit [Ping timeout: 245 seconds]
churli has quit [Ping timeout: 252 seconds]
jaafar_ has joined #ste||ar
Anushi1998 has joined #ste||ar
kisaacs has joined #ste||ar
nikunj1997 has joined #ste||ar
hkaiser has quit [Quit: bye]
<nikunj1997>
heller: yt?
Anushi1998 has quit [Read error: Connection reset by peer]
kisaacs has quit [Ping timeout: 256 seconds]
nikunj1997 has quit [Ping timeout: 256 seconds]
kisaacs has joined #ste||ar
david_pfander has joined #ste||ar
hkaiser has joined #ste||ar
churli has joined #ste||ar
kisaacs has quit [Ping timeout: 252 seconds]
diehlpk has joined #ste||ar
parsa has joined #ste||ar
kisaacs has joined #ste||ar
david_pfander has quit [Ping timeout: 245 seconds]
<diehlpk>
hkaiser, Do you know what Zhara exactly changed for the hpxml repo?
akheir has quit [Quit: Leaving]
<hkaiser>
diehlpk: no, sorry
<diehlpk>
Ok, I think I got it
<diehlpk>
We have now a submodule for hpx
<diehlpk>
So we can just clone the master from hpx and we do not need to store a copy of hpx within hpxml
<diehlpk>
In hpxml are only the additional files and once we tell cmake to compile hpx with hpxml these addtional file are included
aserio has quit [Quit: aserio]
<diehlpk>
hkaiser, Can I add thes option to hpx cmake?
<diehlpk>
This is the only think I need to commit to hpx master
david_pfander has joined #ste||ar
hkaiser has quit [Ping timeout: 260 seconds]
nikunj has joined #ste||ar
hkaiser has joined #ste||ar
hkaiser has quit [Ping timeout: 260 seconds]
gablab has joined #ste||ar
<gablab>
Hi
<gablab>
oups
<zao>
Hello!
<gablab>
:D
hkaiser has joined #ste||ar
<diehlpk>
gablab, I am working on the hpxml issues
<diehlpk>
hkaiser, Forget what I wrote, I found a much better solution
david_pfander has quit [Ping timeout: 245 seconds]
<gablab>
thank you diehlpk
nikunj has quit [Ping timeout: 245 seconds]
nikunj has joined #ste||ar
<nikunj>
hkaiser: yt?
david_pfander has joined #ste||ar
parsa has quit [Quit: Zzzzzzzzzzzz]
<github>
[hpx] hkaiser created init_logging (+1 new commit): https://git.io/vhvUx
<github>
hpx/init_logging 74d1fd9 Hartmut Kaiser: Make sure logging is up and running while modules are being discovered....
<github>
[hpx] hkaiser opened pull request #3326: Make sure logging is up and running while modules are being discovered. (master...init_logging) https://git.io/vhvTe