K-ballo 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/
nanmiao has joined #ste||ar
K-ballo has quit [Quit: K-ballo]
bita has quit [Ping timeout: 256 seconds]
hkaiser has quit [Quit: bye]
diehlpk_work_ has quit [Remote host closed the connection]
bita has joined #ste||ar
jehelset has joined #ste||ar
bita has quit [Ping timeout: 260 seconds]
jehelset has quit [Remote host closed the connection]
K-ballo has joined #ste||ar
hkaiser has joined #ste||ar
<gnikunj[m]>
hkaiser: yt?
<hkaiser>
gnikunj[m]: here
<gnikunj[m]>
are you free for a meet? We need to discuss further about bulk async and error handling.
<hkaiser>
gnikunj[m]: I didn't even have coffee yet ;-)
<gnikunj[m]>
I already feel sorry now ;-)
<gnikunj[m]>
let me know when you're free for a call
<hkaiser>
ok
<jedi18[m]1>
Hi! Could you please let me know of any other issues I could work if you find any? Thanks :)
<hkaiser>
jedi18[m]1: I will have a look at your PR today - thanks!
<hkaiser>
jedi18[m]1: ms[m] will be back next week (I would like for him to be ok with the changes), so we will start merging things then
<gnikunj[m]>
hkaiser: that reminds me. Kokkos meeting this tuesday, what time is it?
<jedi18[m]1>
Oh ok sure np, do let me know if there any other tasks I can do meanwhile
<gnikunj[m]>
like the one with Christian and Mikael
<hkaiser>
gnikunj[m]: 1pm CDT
<hkaiser>
ahh
<hkaiser>
that is Thursday 8.30am or so
<gnikunj[m]>
ok, then Mikael probably game me a wrong link. I'll have to talk to him on Monday when he returns.
<hkaiser>
gnikunj[m]: sorry, I'm still confused (no coffee)
<gnikunj[m]>
haha no pressure ;-)
<hkaiser>
you mean the one with Christian - that's Monday 10am
<gnikunj[m]>
won't make you think too hard ;-)
<gnikunj[m]>
yup, this is the one. Thanks. I had 5-6pm in the email. Had not clue about the timezone there :P
<gnikunj[m]>
so it's 9:30PM for me.
<hkaiser>
does that work?
<gnikunj[m]>
yes yes. I'll join for sure. Have to meet David Hollman as well. Saw his work on the executor stuff, should be nice to meet him too!
<hkaiser>
gnikunj[m]: it's Daisy Hollman now
<gnikunj[m]>
ohh so it went from David to Daisy. I'm sorry. I thought it was the other way round.
<gnikunj[m]>
what pronoun do I use btw? I don't want to offend.
<hkaiser>
gnikunj[m]: I will have to ask for a raincheck on meeting with you today
<hkaiser>
things came up that I need to tend to
<gnikunj[m]>
sure sure. If you're busy today, let's set up a meeting tomorrow?
<hkaiser>
can we play it by ear?
<gnikunj[m]>
sure, sounds good to me.
<hkaiser>
not sure how long you'll be available today, I might have some time later this afternoon (my time)
<gnikunj[m]>
I'm usually awake till 3am in the morning these days. So that would be 3:30PM for you.
<hkaiser>
ok
<hkaiser>
that might not be possible for me, then - let's try tomorrow
<gnikunj[m]>
ok
hkaiser has quit [Quit: bye]
bita has joined #ste||ar
<gonidelis[m]>
srinivasyadav227: jedi18 yt?
<jedi18[m]1>
Yep, Hi!
<srinivasyadav227>
yes
<gonidelis[m]>
jedi18: hey, in case you wanted to get involved in the algorithms adaptation projects I just uploaded a quick guide that might (certainly) seem helpful
<gonidelis[m]>
I started working last year just like you on HPX, in order to get accepted for GSoC
<gonidelis[m]>
so these are some realy really basic and helpful stuff on the adaptation game that you can't really find packed somewere in our wikis
<jedi18[m]1>
Thank you so much! I was looking into that issue
<gonidelis[m]>
jedi18: srinivasyadav227 great! So in case any of you really wants to get into this part of the library, this guide would serve you well. There is plenty of links/material/refs there. If you have any questions, suggestions or fixes on the "How to..." guide, please ping me here.
<jedi18[m]1>
Do you think it would possible for me to implement atleast one of these before gsoc starts?
<gonidelis[m]>
jedi18: I don't wanna boast, but with this guide, yes.
<gonidelis[m]>
if you really want to do this, just take an old adaptation PR and have this guide on the side
<gonidelis[m]>
go through the changes and understand where each bullet point/step refers to
<gonidelis[m]>
you will get familiar within a week tops
<gonidelis[m]>
so yes! if you want to, just take on a simple a algo and start playing. ask here if you need any help ;)
<jedi18[m]1>
Thanks a lot again! That helps a lot! I'll be sure to try that over the next few weeks
<srinivasyadav227>
gonidelis[m]: sure, thanks
<jedi18[m]1>
Oh ok great, I'll see your last year gsoc code to find the PRs?
<gonidelis[m]>
srinivasyadav227: jedi18 have fun. don't hesitate to ask. there is plenty of info to digest
<jedi18[m]1>
Oh ok I will! Thanks again!
<srinivasyadav227>
gonidelis[m]: this is one complete project for GSoC right?
<srinivasyadav227>
gonidelis: ok cool!, yea so there would be clash we both do the same right
<gonidelis[m]>
hm... not necessarily
<gonidelis[m]>
there are plenty of algos to get adapted but let's wait for hkaiser to tell
<gonidelis[m]>
you could work simultaneously on different algos
<srinivasyadav227>
oh, its like same project different algos?
<gonidelis[m]>
exactly
<gonidelis[m]>
there are no limitations
<gonidelis[m]>
don't look at it as a strict competition. we are basically looking for people who want to stay and really contribute and learn about the library
<gonidelis[m]>
if algorithms is your entry point, that's fine
<srinivasyadav227>
okay, cook! will look into
<srinivasyadav227>
it*
<gonidelis[m]>
there are like 15+ algos left to get adapted. so if you get accepted there will certainly be work to do
<srinivasyadav227>
<gonidelis[m] "don't look at it as a strict com"> yea yea, sure.. currently I was digging at datapar, and stuck at this, ;)
<gonidelis[m]>
noprob
<gonidelis[m]>
if that's your choice, then do it
<gonidelis[m]>
i just pinged both of you because this is like a more broader project to the one you implemented on your PRs with the segmented algos
<srinivasyadav227>
gonidelis: yea yea..thanks a lot! 🙂
<jedi18[m]1>
Yeah there is some overlap, I guess the segmented algos was a nice stepping point to this task, so this guide is perfect for me and helps a lot to move forward and contribute, so thanks a lot!
<gonidelis[m]>
jedi18: ;)
bita has quit [Ping timeout: 240 seconds]
K-ballo has quit [Remote host closed the connection]
K-ballo has joined #ste||ar
K-ballo has quit [Remote host closed the connection]
K-ballo has joined #ste||ar
K-ballo has quit [Remote host closed the connection]
hkaiser has joined #ste||ar
<hkaiser>
gonidelis[m]: thanks for the list of action items for the algorithms
<gonidelis[m]>
hkaiser hi guess it will be constantly improving
<gonidelis[m]>
I^^
<hkaiser>
yes
<gonidelis[m]>
Feel free to make changes if you want
<hkaiser>
ok, will do
jehelset has joined #ste||ar
jehelset has quit [Remote host closed the connection]