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/ | GSoC2018: https://wp.me/p4pxJf-k1
nikunj has quit [Quit: Leaving]
diehlpk has joined #ste||ar
K-ballo has quit [Ping timeout: 245 seconds]
twwright_ has quit [Quit: twwright_]
K-ballo has joined #ste||ar
hkaiser has joined #ste||ar
twwright_ has joined #ste||ar
mcopik has quit [Ping timeout: 260 seconds]
twwright_ has quit [Quit: twwright_]
jaafar has joined #ste||ar
hkaiser has quit [Quit: bye]
diehlpk has quit [Ping timeout: 260 seconds]
K-ballo has quit [Quit: K-ballo]
jaafar_ has joined #ste||ar
jaafar has quit [Ping timeout: 264 seconds]
jaafar_ has quit [Ping timeout: 248 seconds]
jaafar_ has joined #ste||ar
jaafar_ has quit [Ping timeout: 264 seconds]
jaafar_ has joined #ste||ar
nanashi55 has quit [Ping timeout: 245 seconds]
nanashi55 has joined #ste||ar
jaafar_ has quit [Ping timeout: 256 seconds]
jaafar_ has joined #ste||ar
anushi has joined #ste||ar
anushi has quit [Ping timeout: 276 seconds]
Anushi1998 has joined #ste||ar
anushi has joined #ste||ar
jaafar_ has quit [Quit: Konversation terminated!]
Anushi1998 has quit [Read error: Connection reset by peer]
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
twwright_ has joined #ste||ar
twwright_ has quit [Quit: twwright_]
Anushi1998 has joined #ste||ar
mcopik has joined #ste||ar
tianyi has quit [Remote host closed the connection]
tianyi has joined #ste||ar
rtohid has joined #ste||ar
rtohid has quit [Read error: Connection reset by peer]
anushi has quit [Read error: Connection reset by peer]
anushi has joined #ste||ar
hkaiser has joined #ste||ar
anushi has quit [Remote host closed the connection]
anushi has joined #ste||ar
jakub_golinowski has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 268 seconds]
K-ballo has joined #ste||ar
mcopik has quit [Ping timeout: 245 seconds]
david_pfander has joined #ste||ar
eschnett has quit [Quit: eschnett]
hkaiser has quit [Quit: bye]
Anushi1998 has joined #ste||ar
david_pfander has quit [Ping timeout: 256 seconds]
mcopik has joined #ste||ar
mcopik has quit [Ping timeout: 248 seconds]
hkaiser has joined #ste||ar
eschnett has joined #ste||ar
mcopik has joined #ste||ar
akheir has joined #ste||ar
david_pfander has joined #ste||ar
<M-ms>
Hey jakub_golinowski, all good with the tests?
<jakub_golinowski>
M-ms, hello - I am running them right now
mbremer has joined #ste||ar
<jakub_golinowski>
They were failing initially because I did not have the separate OpenCV repo with the testdata
<jakub_golinowski>
now I specified the environment variable with path to the test directory and it should be ok now
<M-ms>
Ok, good to hear
<M-ms>
And all good with your teeth...?
<M-ms>
So from tomorrow and Saturday I might be harder to reach but you can still leave questions here (if needed) and I'll try to answer when I have time
<M-ms>
Without from
<jakub_golinowski>
M-ms, I feel quite OK now and started to eat normal meals today but I needed some rest as the surgery included drilling through my bone.
<jakub_golinowski>
Also while waiting for the test to run I plotted the result of the Sunday experiment with the newest version of the hpx backend where there is no differentiation between handling nstripes.
<M-ms>
Ouch, sounds nasty...
<M-ms>
And how does it look?
<M-ms>
Is it in the repo?
<jakub_golinowski>
it is not yet because I want to do some rebasing on these commits
<M-ms>
I'm afraid that gap to the other backends can't be fixed without going deeper into hpx, but it's good to see where we are compared to the others
<jakub_golinowski>
For now the only surprise is that HPX is performing sligtly worse for nstripes=-1 and 0 than for the nstripes form range (5-99)
<jakub_golinowski>
Later tonight I will run the benchmark over the whole nstripes range to verify if it is flat for the new hpx backend
<jakub_golinowski>
Also, the speedups are done versus one sequential run (with repetitions to capture the uncertainty) on pthreads with completely different code executed (sequentialMandelbrot function)
<hkaiser>
jakub_golinowski: what hpx API do you use for the parallelization?
<jakub_golinowski>
hkaiser, hpx::parallel_for
<hkaiser>
I assume with the default chunking policy
<nikunj97>
hkaiser, yt?
<jakub_golinowski>
hkaiser, yes, ultimately we decided to use the default chunking policy in all cases
nikunj1997 has joined #ste||ar
<jakub_golinowski>
however the nstripes allows for some level of control over chunking by overwriting the range passe to hpx::parallel_for and then for each loop body execution overwriting the sub_range(i, i+1) to the real subrange of the whole range
nikunj97 has quit [Ping timeout: 256 seconds]
mbremer has quit [Quit: Page closed]
mbremer has joined #ste||ar
<mbremer>
@hkaiser: are you ready for the call?
twwright has quit [Read error: Connection reset by peer]
twwright has joined #ste||ar
Anushi1998 has quit [Quit: Bye]
<hkaiser>
mbremer: sorry, I missed the time
<hkaiser>
ready now - skype?
nikunj1997 has quit [Quit: Leaving]
anushi has quit [Read error: Connection reset by peer]
anushi has joined #ste||ar
anushi has quit [Ping timeout: 245 seconds]
anushi has joined #ste||ar
anushi has quit [Remote host closed the connection]
mbremer has quit [Quit: Page closed]
mcopik has quit [Ping timeout: 255 seconds]
<K-ballo>
how do I connect to rostam again? is it rostam.cct.lsu.edu:22 ?
anushi has joined #ste||ar
eschnett has quit [Quit: eschnett]
nikunj has joined #ste||ar
david_pfander has quit [Ping timeout: 256 seconds]
diehlpk has joined #ste||ar
jaafar has joined #ste||ar
<bibek>
K-ballo: rostam.cct.lsu.edu port is 8000 not 22
<K-ballo>
aaah, that was it! thanks bibek
galabc has joined #ste||ar
anushi has quit [Ping timeout: 256 seconds]
anushi has joined #ste||ar
<bibek>
K-ballo: you are welcome.
anushi has quit [Remote host closed the connection]
anushi has joined #ste||ar
katywilliams has joined #ste||ar
<katywilliams>
For the performance data generated by running ALS on MovieLens.csv, which files do the line numbers correspond to? E.g. for access-variable/num_users(23, 40), the 23 corresponds to the ... (.py file? .physl file?)
<hkaiser>
katywilliams: depends on what you used to run the code
<hkaiser>
if the initial code was .py, then this should refer to that
<nikunj>
hkaiser, need a bit of help
zura has quit [Quit: Leaving]
<katywilliams>
@hkaiser thanks!
katywilliams has quit [Quit: Lost terminal]
<diehlpk>
hkaiser, see pm
Anushi1998 has joined #ste||ar
galabc has quit [Ping timeout: 255 seconds]
hkaiser has quit [Quit: bye]
shahrzad has quit [Remote host closed the connection]