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
Yorlik_ has joined #ste||ar
Yorlik__ has quit [Ping timeout: 260 seconds]
hkaiser has quit [Quit: Bye!]
K-ballo has quit [Ping timeout: 250 seconds]
K-ballo has joined #ste||ar
Yorlik_ has quit [Ping timeout: 258 seconds]
Yorlik has joined #ste||ar
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 260 seconds]
Yorlik has joined #ste||ar
Yorlik_ has quit [Ping timeout: 260 seconds]
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 250 seconds]
Yorlik has joined #ste||ar
Yorlik_ has quit [Ping timeout: 240 seconds]
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 244 seconds]
Yorlik has joined #ste||ar
Yorlik_ has quit [Ping timeout: 260 seconds]
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 244 seconds]
hkaiser has joined #ste||ar
Yorlik has joined #ste||ar
Yorlik__ has joined #ste||ar
Yorlik_ has quit [Ping timeout: 260 seconds]
Yorlik has quit [Ping timeout: 240 seconds]
Yorlik_ has joined #ste||ar
Yorlik__ has quit [Ping timeout: 245 seconds]
Yorlik__ has joined #ste||ar
Yorlik_ has quit [Ping timeout: 245 seconds]
Yorlik has joined #ste||ar
Yorlik__ has quit [Ping timeout: 240 seconds]
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 240 seconds]
Yorlik has joined #ste||ar
Yorlik_ has quit [Ping timeout: 246 seconds]
<pansysk75[m]>
hkaiser: Do shared_futures have significant overhead over plain futures?
<pansysk75[m]>
in hpx, that is
Yorlik has quit [Ping timeout: 244 seconds]
Yorlik has joined #ste||ar
<K-ballo>
no, it's the same underlying thing
<K-ballo>
the difference is in get(), whether it moves or not
<pansysk75[m]>
ah ok that makes sense, thanks!
<hkaiser>
pansysk75[m]: none
Yorlik has quit [Ping timeout: 240 seconds]
Yorlik has joined #ste||ar
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 245 seconds]
Yorlik has joined #ste||ar
Yorlik_ has quit [Ping timeout: 240 seconds]
<hkaiser>
pansysk75[m]: yt?
<pansysk75[m]>
yes
<hkaiser>
I think I have resolved the assert
<hkaiser>
this was an unrelated issue that just manifested itself with this new mode of running threads
<pansysk75[m]>
hooray, I'm looking forward to see what that was about
<hkaiser>
the issue is that threads, when they are destroyed are pushed onto a terminated_threads list which is cleaned up later
<pansysk75[m]>
I'm working on the scan_partitioner, this scoped execution thing seems very similar to how senders-receivers are set up
<hkaiser>
but it could happen, that the same thread object is reused before it is cleaned up, so it ends up on that list twice in which case the assert will fire
<hkaiser>
pansysk75[m]: yes, there is some similarity
<pansysk75[m]>
pansysk75[m]: in the sense that you can set up a dependency chain using .then and avoid context switching
<pansysk75[m]>
and suspensions and stuff
<pansysk75[m]>
hkaiser: surprising that this only came up now, nice find