hkaiser changed the topic of #ste||ar to: STE||AR: Systems Technology, Emergent Parallelism, and Algorithm Research | stellar-group.org | HPX: A cure for performance impaired parallel applications | github.com/STEllAR-GROUP/hpx | This channel is logged: irclog.cct.lsu.edu
K-ballo1 has joined #ste||ar
K-ballo has quit [Ping timeout: 240 seconds]
K-ballo1 is now known as K-ballo
hkaiser has quit [Ping timeout: 240 seconds]
hkaiser has joined #ste||ar
Yorlik_ has joined #ste||ar
tufei has joined #ste||ar
Yorlik has quit [Ping timeout: 240 seconds]
hkaiser has quit [Ping timeout: 240 seconds]
HHN93 has joined #ste||ar
HHN93 has quit [Quit: Client closed]
K-ballo1 has joined #ste||ar
K-ballo has quit [Ping timeout: 246 seconds]
K-ballo1 is now known as K-ballo
tufei has quit [Remote host closed the connection]
tufei has joined #ste||ar
hkaiser has joined #ste||ar
hkaiser has quit [Quit: Bye!]
hkaiser has joined #ste||ar
<Aarya[m]>
<zao> "The build system you've got..." <- Any ideas how to resolve this
<pansysk75[m]>
hkaiser: Are parcels sent from one locality to one other locality received in the same order they are sent?
<pansysk75[m]>
I found an issue regarding migration failures, and it has to do with remote actions being executed in different order in the receiving-locality than they were triggered from the caller-locality.
<K-ballo>
are they actually synchronized?
<pansysk75[m]>
Not explicitly, I don't think so
<pansysk75[m]>
at least not with any standard synchronization primitives like condition variables, futures etc
<K-ballo>
they're just sent one after the other on the same "thread"?
<K-ballo>
I would not expect any guarantees, but I don't know for sure
<pansysk75[m]>
K-ballo: Yes, this is the case
<pansysk75[m]>
One thread in each locality also
hkaiser_ has joined #ste||ar
hkaiser has quit [Ping timeout: 250 seconds]
<hkaiser_>
pansysk75[m]: there is no guarantee that the parcel sequence is the same on the sender and the receiver
hkaiser_ has quit [Client Quit]
<zao>
Aarya[m]: You might have some luck with CMake's `linker_language` property for the target, which might make it link through the C++ compiler.
<zao>
CMake normally knows the language of dependencies that are built in the same project or imported from exported targets, but in this case it may not be aware and just link the static library of hpxc (which I assume are C bindings to HPX) and the HPX shared library.
<zao>
Key to static libraries is that when you link them in, you need to link all their dependencies, which implicitly includes the C++ runtime if they're in C++ and you're in a different language.
<Aarya[m]>
hm hm
K-ballo has quit [Ping timeout: 240 seconds]
K-ballo has joined #ste||ar
hkaiser has joined #ste||ar
K-ballo has quit [Ping timeout: 265 seconds]
K-ballo has joined #ste||ar
tufei has quit [Remote host closed the connection]