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
hkaiser has joined #ste||ar
Yorlik_ has joined #ste||ar
Yorlik__ has quit [Ping timeout: 246 seconds]
hkaiser has quit [Quit: Bye!]
Yorlik_ has quit [Read error: Connection reset by peer]
Yorlik_ has joined #ste||ar
hkaiser has joined #ste||ar
hkaiser has quit [Quit: Bye!]
hkaiser has joined #ste||ar
hkaiser has quit [Quit: Bye!]
hkaiser has joined #ste||ar
K-ballo has quit [Ping timeout: 246 seconds]
K-ballo has joined #ste||ar
diehlpk_work has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
K-ballo has joined #ste||ar
<gonidelis[m]>
K-ballo: yt?
<K-ballo>
gonidelis[m]: here
<gonidelis[m]>
<gonidelis[m]> "but when i use gcc or llvm and i..." <- about this ? :P
<gonidelis[m]>
:) **
<K-ballo>
I don't have any context
<gonidelis[m]>
sorry
<gonidelis[m]>
i am curious what threading system is being used in g++ and clang when i used algo(std::execution::par, args...)
<K-ballo>
go check the source code
<gonidelis[m]>
arlight
<pansysk75[m]>
gonidelis: It's very likely it just runs sequentially, if you don't compile with intel tbb. The execution policy is just a hint. I remember I was confused when I was trying to benchmark parallel gcc in the past, without having tbb installed, because I got the same performance as sequential execution. But do check source, and tell us what you find
<gonidelis[m]>
damn son
<gonidelis[m]>
might as well be it
<K-ballo>
pedantic, it's not a hint, it's a user given guarantee
<K-ballo>
that guarantee enables the implementation to parallelize (run on corresponding execution engines), but places no requirements
<gonidelis[m]>
that's a political way to say "hint"
<K-ballo>
if the user gives an incorrect guarantee and the implementation does parallelize, crash burn
<K-ballo>
no, an incorrect hint doesn't result in crash and burn, it results in degraded performance
diehlpk_work has quit [Remote host closed the connection]