hkaiser 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/ | GSoC: https://github.com/STEllAR-GROUP/hpx/wiki/Google-Summer-of-Code-%28GSoC%29-2020
nan11 has quit [Remote host closed the connection]
hkaiser has quit [Quit: bye]
nikunj has joined #ste||ar
weilewei has quit [Remote host closed the connection]
karame_ has quit [Remote host closed the connection]
bita has quit [Ping timeout: 244 seconds]
<mdiers[m]> ms: some time? i took two profile snapshots.
<ms[m]> mdiers: show me :)
diehlpk_work_ has joined #ste||ar
<zao> I'm getting "Bandwidth Limit Exceeded" on
diehlpk_work has quit [Ping timeout: 246 seconds]
<zao> (I know it's legacy docs, but still)
nikunj97 has joined #ste||ar
<zao> If I have OpenMP pragmas in a HPX async task, how bad is that?
<zao> Especially if I use HPX inside the vectorized loops?
Nikunj__ has joined #ste||ar
nikunj97 has quit [Ping timeout: 240 seconds]
<ms[m]> zao what pragmas? simd would be fine, anything else not
<zao> "omp parallel for" in this codebase
<ms[m]> bad idea (because of contention between the hpx and openmp runtimes)
Vir has quit [Remote host closed the connection]
<zao> I guess that the primary problem here is that the OpenMP threads can't run HPX tasks.
nikunj has quit [Read error: Connection reset by peer]
nikunj has joined #ste||ar
nikunj has quit [Ping timeout: 260 seconds]
nikunj has joined #ste||ar
Nikunj__ has quit [Quit: Leaving]
<heller1> You could use hpxmp
<ms[m]> hkaiser: heller do you have any further comments on the runtime and pragma once prs?
<nikunj> heller1: when can we have the call?
hkaiser has joined #ste||ar
<heller1> ms[m]: haven't looked, sorry
<heller1> nikunj: when would be most convenient to you?
<nikunj> heller1: anytime you want in general. I don't have online classes these days.
<heller1> nikunj: ok, how about today at around 9 my time?
<nikunj> Sounds good to me
<heller1> ok
nikunj has quit [Ping timeout: 240 seconds]
nikunj has joined #ste||ar
<K-ballo> addressing_service::register_counter_types is missing some using placeholders
<hkaiser> K-ballo: have a link?
nikunj has quit [Read error: Connection reset by peer]
nikunj has joined #ste||ar
<hkaiser> K-ballo: that's using bind_front, why placeholders?
<K-ballo> further down, the _1s and _2s
<hkaiser> ahh, funny that it works anyways
<hkaiser> thanks
<K-ballo> probably resolving to boost.bind globals
<K-ballo> no longer works with 1.73, although the globals are still on by default
rtohid has joined #ste||ar
<hkaiser> ok, I'll fix it
karame_ has joined #ste||ar
<hkaiser> K-ballo: see #4581
weilewei has joined #ste||ar
nikunj has quit [Ping timeout: 244 seconds]
nikunj has joined #ste||ar
nikunj has quit [Read error: Connection reset by peer]
nikunj has joined #ste||ar
bita has joined #ste||ar
<weilewei> hkaiser surprise, multi-threaded ring G algorithm seems generating correct results now, by 1) newly knowing a new parameter that can set G4 deterministic and 2) fixing broken default arguments related to thread_id and n_threads in DCA++. More verification will be followed
<hkaiser> weilewei: nice!
<weilewei> then using HPX to get rid of MPi_wait
<weilewei> hkaiser yea!!
<hkaiser> good job!
mcopik has joined #ste||ar
mcopik has quit [Client Quit]
akheir has joined #ste||ar
akheir1 has joined #ste||ar
akheir has quit [Ping timeout: 244 seconds]
nikunj97 has joined #ste||ar
nikunj has quit [Read error: Connection reset by peer]
nikunj has joined #ste||ar
nikunj has quit [Ping timeout: 260 seconds]
nikunj has joined #ste||ar
nikunj has quit [Read error: Connection reset by peer]
nikunj has joined #ste||ar
nan11 has joined #ste||ar
nikunj has quit [Ping timeout: 246 seconds]
nikunj has joined #ste||ar
nikunj has quit [Ping timeout: 240 seconds]
nikunj has joined #ste||ar
<nikunj97> heller1, what platform do we use for the call?
<heller1> I don't care
<heller1> Zoom is fine
<heller1> Or whereby
<nikunj97> I don't have zoom account? Can you create a link?
<nikunj97> ? -> .
<heller1> one sec
<heller1> nikunj97: let's try that: https://meet.jit.si/STEIIAR-Group (I think it only works fine in non firefox browsers
<weilewei> diehlpk_work_ do you know where can I find the list of accepted workshops in SC?
<diehlpk_work_> weilewei, On the submission form
<diehlpk_work_> I had to login, make a new submission, and I could see the list of accepted workshops
<diehlpk_work_> I found PAW-AMT and PMBS for my paper
<weilewei> diehlpk_work_ thanks I see now. I didn't find one on SC webpage, but now in submission page
<diehlpk_work_> Same here, I could nto find them on the SC page
<bita> hkaiser, I apologize I couldn't test this: https://github.com/STEllAR-GROUP/hpx/pull/4561 the problem does not occur in windows and on docker starting from the hpx image it is not possible (or I am not aware how) to use a branch
<bita> I'll try to test it on Rostam later
<hkaiser> bita: sure, no worries
<heller1> diehlpk_work_: where did you login and is our workshop accepted?
<diehlpk_work_> heller1, Our workshop was rejected with the same old reason
<heller1> not enough science?
<diehlpk_work_> For the login
<diehlpk_work_> heller1, Check your phone, since I cna not send you a private message on irc
<hkaiser> bita: should work, yes
<bita> thank you
<rtohid> hkaiser: I just requested the transfer.
<hkaiser> rtohid: here is the new link: https://github.com/STEllAR-GROUP/phyfleaux
<hkaiser> please let me know if you can't access it etc
<rtohid> hkaiser: thanks! sure.
<K-ballo> what's phyfleaux?
<hkaiser> ask rtohid
<diehlpk_work_> sounds French
<rtohid> K-ballo: in its infancy, but the goal is to analyze decorated python functions and map them to appropriate backends- including code generation, scheduling, ...
<rtohid> for now we are focusing on nested loops that can be modeled as polyhedral, and use tiramisu to apply transformations.
<rtohid> in case you want to check it out, see https://github.com/STEllAR-GROUP/phyfleaux/tree/demo-merge, it has the latest changes.
<K-ballo> now I want tiramisu..
<K-ballo> heh, not what I had in mind :P
<rtohid> the following file has good deal of information: https://github.com/Tiramisu-Compiler/tiramisu/blob/master/include/tiramisu/core.h
<K-ballo> although that does look interesting
<rtohid> what did you have in mind?
<rtohid> if you don't mind me asking :)
<K-ballo> the italian dessert
<rtohid> ahhhhhh! Oops!
nikunj97 has quit [Ping timeout: 260 seconds]
akheir1 has quit [Quit: Leaving]
bita has quit [Ping timeout: 240 seconds]
<hkaiser> karame_: here is the new repository link: https://github.com/STEllAR-GROUP/docker-containers
bita has joined #ste||ar
<hkaiser> let me know if you don't have access etc.
shahrzad has joined #ste||ar
shahrzad has quit [Ping timeout: 244 seconds]
karame_ has quit [Quit: Ping timeout (120 seconds)]
shahrzad has joined #ste||ar
rtohid has left #ste||ar [#ste||ar]
bita has quit [Ping timeout: 240 seconds]
shahrzad has quit [Ping timeout: 244 seconds]