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-ballo has quit [Ping timeout: 265 seconds]
K-ballo1 has joined #ste||ar
K-ballo1 is now known as K-ballo
Yorlik_ has joined #ste||ar
Yorlik has quit [Ping timeout: 264 seconds]
<gonidelis[m]>
HHN93: K-ballo so cppref proposes a bogus implementation? ;E
hkaiser has joined #ste||ar
hkaiser has quit [Quit: Bye!]
K-ballo1 has joined #ste||ar
K-ballo has quit [Ping timeout: 276 seconds]
K-ballo1 is now known as K-ballo
K-ballo has quit [Ping timeout: 276 seconds]
K-ballo has joined #ste||ar
K-ballo has quit [Ping timeout: 255 seconds]
K-ballo has joined #ste||ar
<K-ballo>
gonidelis[m]: not bogus, but suboptimal, yes
<gonidelis[m]>
damn
<satacker[m]>
But cppreference implementation has constexpr
<gonidelis[m]>
good one
<satacker[m]>
<satacker[m]> "`In constant expression and..." <- So this applies
<K-ballo>
it does, but it's not relevant here
<K-ballo>
there's a very specific case involving lifetime and self-identity that maters in constexpr, it should be tied to the related issue
<K-ballo>
lack of elision in constant evaluation is not a performance issue because, well.. compile time.. so you wouldn't care about it
<gonidelis[m]>
right
<gonidelis[m]>
what's that related issue you are referring to
<K-ballo>
the one that forbid NRVO in constant evaluation
K-ballo1 has joined #ste||ar
K-ballo has quit [Ping timeout: 276 seconds]
K-ballo1 is now known as K-ballo
K-ballo has quit [Remote host closed the connection]
K-ballo has joined #ste||ar
<pansysk75[m]>
How many/what kind of OS threads should i expect HPX to create in the distributed runtime?
<pansysk75[m]>
( If I remember correctly, in the non-distributed runtime, HPX utilizes one "startup" thread, k worker-threads (for --hpx:threads=k), and one thread that helps with shutdown. )