aserio 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/
Smasher has quit [Remote host closed the connection]
EverYoung has quit [Read error: Connection reset by peer]
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
EverYoun_ has joined #ste||ar
EverYoung has quit [Read error: Connection reset by peer]
EverYoun_ has quit [Remote host closed the connection]
EverYoung has joined #ste||ar
EverYoung has quit [Ping timeout: 255 seconds]
EverYoung has joined #ste||ar
EverYoung has quit [Remote host closed the connection]
hkaiser has quit [Quit: bye]
EverYoung has joined #ste||ar
EverYoung has quit [Ping timeout: 265 seconds]
EverYoung has joined #ste||ar
EverYoung has quit [Ping timeout: 276 seconds]
jaafar has quit [Ping timeout: 240 seconds]
hkaiser has joined #ste||ar
hkaiser has quit [Quit: bye]
anushi has joined #ste||ar
anushi has quit [Remote host closed the connection]
nanashi55 has quit [Ping timeout: 256 seconds]
nanashi55 has joined #ste||ar
anushi has joined #ste||ar
EverYoung has joined #ste||ar
EverYoung has quit [Ping timeout: 255 seconds]
Anushi1998 has joined #ste||ar
anushi has quit [Ping timeout: 255 seconds]
K-ballo has quit [Quit: K-ballo]
Anushi1998 is now known as anushi
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
<github>
hpx/master 7f4a8bc Mikael Simberg: Add optional scheduler_mode parameter to create_thread_pool
<github>
hpx/master daf2a8d Mikael Simberg: Merge pull request #3230 from msimberg/create-thread-pool...
jaafar has quit [Ping timeout: 260 seconds]
<jbjnr_>
simbergm: any progress on any of the cleanup thread_map branches etc that you are aware of?
<jbjnr_>
I wiuld like to finish that, by looking into the stack use/reuse
<simbergm>
jbjnr_: no, I haven't seen any branches for thread_map cleanup so don't know and I tried to poke heller about the lazy thread init branch
<simbergm>
my understanding of stack reuse so far is that the recycle thread stuff should go (at least with stacksize-specific heaps), and the stack reuse should go into the context implementations
<simbergm>
but I understand the context/coroutine implementations still quite badly
david_pfander has joined #ste||ar
<jbjnr_>
simbergm: ok, there are no branches for thread_map cleanup directly, but we created a couple of brnaches for the lazy_init and the removal of wait_or_add_new - I wondered if they had been touched. I presume not. I'll rebase them onto master and start on them again.
<jbjnr_>
I want to also improve the scheduler to use numa aware allocations for the queues etc.
<simbergm>
jbjnr_: yeah, no progress on those (not sure when you last checked)
<simbergm>
lazy thread init may be missing some things in the non-linux implementations and wait or add new passed all tests on pycicle at least, don't know if you still have that one test hanging?
<simbergm>
I guess you will see soon...
<simbergm>
jbjnr_: I'm testing a pycicle version which lets one set the cmake build type
<simbergm>
I've changed the submitted site and build names, do you mind that?
<jbjnr_>
no. they are not important. only for display
<simbergm>
thread_queues should get allocated by the thread that is using it
<jbjnr_>
correct. (and bound to the numa domain using it)
<simbergm>
and by should I mean that happens right now on master
<simbergm>
but the shared_priority_scheduler might do it differently though...