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/
eschnett_ has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] msimberg pushed 1 new commit to release: https://github.com/STEllAR-GROUP/hpx/commit/38ecfb0ec6cd2470c15bc64feb0b505310489ccc
<ste||ar-github> hpx/release 38ecfb0 Mikael Simberg: Merge remote-tracking branch 'origin/master' into release
ste||ar-github has left #ste||ar [#ste||ar]
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] msimberg tagged 1.2.0-rc1 at e43a66a: https://github.com/STEllAR-GROUP/hpx/commits/1.2.0-rc1
ste||ar-github has left #ste||ar [#ste||ar]
<simbergm> first rc out, you can keep opening prs to master or directly to release if you feel like it
<hkaiser> simbergm: many thanks!
<hkaiser> \o/
hkaiser has quit [Quit: bye]
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] StellarBot pushed 1 new commit to gh-pages: https://github.com/STEllAR-GROUP/hpx/commit/c08fa2d04750be151ce832b0ec4514272d82f2ee
<ste||ar-github> hpx/gh-pages c08fa2d StellarBot: Updating Sphinx docs
ste||ar-github has left #ste||ar [#ste||ar]
Anushi1998 has quit [Ping timeout: 272 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 272 seconds]
<simbergm> not too interesting, their conclusion is that hpx is not mature enough for their use case (not really hpc)
eschnett_ has quit [Quit: eschnett_]
<simbergm> jbjnr_ (IRC): if you see this in the morning, is this what your cuda pr was meant to fix: http://cdash.cscs.ch/viewConfigure.php?buildid=21702?
<simbergm> I thought it was but misread the pycicle statuses once again
nanashi55 has quit [Ping timeout: 272 seconds]
nanashi55 has joined #ste||ar
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 245 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 272 seconds]
<jbjnr_> simbergm: I see the error. It should have been fixed. I am puzzled (again)
<jbjnr_> aha. cmake 3.5.2 we need cmake 3.9 for the fix to work
<jbjnr_> That var wasn't added to FindCuda until later
<jbjnr_> Where should I add a note to say, cuda support requires 3.9 or better?
mcopik has quit [Ping timeout: 276 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 276 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 252 seconds]
david_pfander has joined #ste||ar
jaafar has quit [Ping timeout: 268 seconds]
<heller__> jbjnr_: to the prerequisite docs
<heller__> simbergm: well done!
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] biddisco created cuda_cmake_doc (+1 new commit): https://github.com/STEllAR-GROUP/hpx/commit/66cb96750a80
<ste||ar-github> hpx/cuda_cmake_doc 66cb967 John Biddiscombe: Note that cuda support requires cmake 3.9
ste||ar-github has left #ste||ar [#ste||ar]
Anushi1998 has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] biddisco opened pull request #3497: Note that cuda support requires cmake 3.9 (master...cuda_cmake_doc) https://github.com/STEllAR-GROUP/hpx/pull/3497
ste||ar-github has left #ste||ar [#ste||ar]
_diers_ has quit [Quit: _diers_]
_diers_ has joined #ste||ar
_diers_ has quit [Ping timeout: 246 seconds]
_diers_ has joined #ste||ar
Anushi1998 has quit [Ping timeout: 250 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Remote host closed the connection]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 244 seconds]
mcopik has joined #ste||ar
mcopik has quit [Ping timeout: 252 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 268 seconds]
Anushi1998 has joined #ste||ar
david_pfander has quit [Quit: david_pfander]
david_pfander has joined #ste||ar
Anushi1998 has quit [Ping timeout: 268 seconds]
david_pfander has quit [Quit: david_pfander]
david_pfander has joined #ste||ar
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 268 seconds]
Anushi1998 has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] biddisco closed pull request #3496: Disabling MPI's (deprecated) C++ interface (master...fixing_3475_v2) https://github.com/STEllAR-GROUP/hpx/pull/3496
ste||ar-github has left #ste||ar [#ste||ar]
mcopik has joined #ste||ar
<zao> simbergm: HPX has served well in making our broken cluster nodes reboot when compiling it :D
Anushi1998 has quit [Ping timeout: 245 seconds]
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] StellarBot pushed 1 new commit to gh-pages: https://github.com/STEllAR-GROUP/hpx/commit/dbd254fa6d0379b15a2f5115f1446ff5424da224
<ste||ar-github> hpx/gh-pages dbd254f StellarBot: Updating Sphinx docs
ste||ar-github has left #ste||ar [#ste||ar]
hkaiser has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] chinz07 closed pull request #3477: Fixing the scope of the imported MPI CMake variables (master...fixing_3475) https://github.com/STEllAR-GROUP/hpx/pull/3477
ste||ar-github has left #ste||ar [#ste||ar]
eschnett_ has joined #ste||ar
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 252 seconds]
Anushi1998 has joined #ste||ar
aserio has joined #ste||ar
eschnett_ has quit [Quit: eschnett_]
Anushi1998 has quit [Ping timeout: 246 seconds]
Anushi1998 has joined #ste||ar
eschnett_ has joined #ste||ar
<heller__> aserio: OB call today?
<aserio> heller__: yes in 2 min
<heller__> k
<jbjnr_> aserio: should I join?
<jbjnr_> and how
<aserio> I will primitively being adding people via Skype
<aserio> jbjnr_, heller__: ^^
<jbjnr_> I do not have skype on linux
<jbjnr_> so, no me
<heller__> mine just crashed. hooray
<jbjnr_> mine stopped working about 6 months ago
<heller__> skypeforlinux works fine for me
hkaiser has quit [Quit: bye]
<jbjnr_> aserio: heller__ I've install skypeforlinux, try adding me please
<aserio> Ok, one second
<heller__> jbjnr_: just did
eschnett_ has quit [Quit: eschnett_]
eschnett_ has joined #ste||ar
<aserio> jbjnr_: please see pm
Anushi1998 has quit [Ping timeout: 260 seconds]
diehlpk has joined #ste||ar
<diehlpk> The Ste||ar group is now present on orcid
<heller__> are lco descriptions ever set from outside of the current thread?
<heller__> or is this about the retrieval of the thing?
david_pfander has quit [Ping timeout: 276 seconds]
<simbergm> jbjnr_ (IRC): thanks, I didn't realize I was using such an old cmake, will change that asap
<simbergm> (thanks for the fix btw)
<simbergm> heller__ (IRC): thanks for posting the rc on slack!
<simbergm> I might add that to the release procedure
eschnett_ has quit [Quit: eschnett_]
eschnett_ has joined #ste||ar
jaafar has joined #ste||ar
Anushi1998 has joined #ste||ar
aserio has quit [Ping timeout: 250 seconds]
mcopik has quit [Ping timeout: 260 seconds]
Anushi1998 has quit [Ping timeout: 276 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Read error: Connection reset by peer]
Anushi1998 has joined #ste||ar
aserio has joined #ste||ar
eschnett_ has quit [Quit: eschnett_]
<heller__> K-ballo: is inline in front a function always equivalent to mean "weak linkage"?
Anushi1998 has quit [Remote host closed the connection]
<heller__> i guess its called internal linkage in standard speak
<K-ballo> mmh, I thought those were different
<K-ballo> I'd say yes, but I'm not 100% sure there are no corner interactions with enclosing namespaces, extern C, etc
<heller__> ok
<heller__> it goes away when I either define hpx_main inside of src/hpx_main.cpp inline or with __attribute__((weak))
<K-ballo> inline will silence it, don't know about fixing it
<K-ballo> where is hpx_main defined if not in hpx_main.cpp ?
<heller__> in the user application
Anushi1998 has joined #ste||ar
<K-ballo> oh, I think I misparsed the above statement then
eschnett_ has joined #ste||ar
<heller__> so essentially it is: We know that we are violating the ODR, but whenever it is already defined, discard what we had before
<heller__> I think both __attribute__((weak)) and inline do what I want here
<heller__> just wanted to double check
<heller__> the failures are gone at least and the executable works as expected
<K-ballo> inline would mean pick whichever, doesn't weak mean prefer a non-weak def?
<heller__> you are right
<heller__> so inline could actually trigger an ODR violation, while weak is marking the version which we don't want
<heller__> in case of a conflict
aserio has quit [Ping timeout: 250 seconds]
mcopik has joined #ste||ar
aserio has joined #ste||ar
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] sithhell force-pushed sithhell-patch-1 from 4cf1c10 to a54dba4: https://github.com/STEllAR-GROUP/hpx/commits/sithhell-patch-1
<ste||ar-github> hpx/sithhell-patch-1 75fcf98 Thomas Heller: Changing base Docker image for the HPX image
<ste||ar-github> hpx/sithhell-patch-1 1b0e74b Thomas Heller: Fixing Clang7 linker issues
<ste||ar-github> hpx/sithhell-patch-1 a54dba4 Thomas Heller: Fixing warnings popping up with clang 7:...
ste||ar-github has left #ste||ar [#ste||ar]
<heller__> aserio: see pm
<heller__> aserio: I am lost. Where do I find the MovieLens data file?
Anushi1998 has quit [Ping timeout: 276 seconds]
Anushi1998 has joined #ste||ar
<heller__> but none of the csv files works with ALS
<heller__> als_csv
<heller__> {what}: read_x(6, 15): file_read_csv:: wrong data format /home/inf3/heller/ml-20m/movies.csv:0: HPX(unhandled_exception)
<heller__> this is what I get
<heller__> so I am a little bit lost there
<heller__> which MovieLens_20m.csv is the regression tester using?
hkaiser has joined #ste||ar
<heller__> hkaiser: hey
<hkaiser> hey heller__
<heller__> hkaiser: Do you happen to know where to get the MovieLens_20m.csv file from?
<heller__> used for als_csv
<zao> Seems to be expecting a ton of comma-separated doubles?
<heller__> yeah
<heller__> the csv files you find online regarding movie lens, only have 3 to 4 columns
<heller__> and fails
aserio has quit [Ping timeout: 272 seconds]
<heller__> the files I found also don't correlate with that one here: https://github.com/STEllAR-GROUP/phylanx/blob/master/examples/algorithms/datasets/MovieLens.csv
<heller__> those are the ones I found: https://grouplens.org/datasets/movielens/
hkaiser has quit [Ping timeout: 276 seconds]
hkaiser has joined #ste||ar
<hkaiser> heller__: I don't know, Bibek should be able to tell
<heller__> I'll ask him
diehlpk has quit [Ping timeout: 276 seconds]
<zao> Took a peek inside stellargroup/phylanx_base:prerequisites, couldn't find any CSVs there.
<heller__> nope
<heller__> it is hidden somewhere on rostam
<heller__> now I wonder what the actual relation to the real dataset is
<heller__> yay. aborted due to illegal instruction
<zao> Heaven knows where khuck runs their buildbot.
<hkaiser> zao: on his machines
<zao> Handy :)
<zao> Enough sleuthing from my side, back to writing presentation material I don't want to make :)
<heller__> good luck
aserio has joined #ste||ar
<aserio> heller__: give me a second
<heller__> aserio: got it
<heller__> now failing differntly at runtime ;)
shahrzad has joined #ste||ar
shahrzad_ has joined #ste||ar
<aserio> heller__: if you have further questions feel free to ask shahrzad
<heller__> shahrzad: hey, I was wondering how you created the movielens files. They don't seem to match with the cvs files to be found on the internets
<shahrzad_> Hi, I was just emailing you about that
<heller__> great
<shahrzad_> so I used a code to create the current dataset out of the original dataset to use it as the input of the algorithm
<heller__> ok
<heller__> just wondering
<heller__> did you ever run into illegal instruction errors?
<shahrzad_> no
<heller__> hmm
<shahrzad_> are you using openblas?
<shahrzad_> the openblas on Rostam is compiled for Haswell architecture
<shahrzad_> if you run it on Marwin it will fail
<heller__> I am running on my own machine
<heller__> but yeah ... I guess it has something to do with blas/lapack
<K-ballo> zao: what will you be presenting?
<zao> K-ballo: One of my colleagues volunteered me for an internal 1h seminar on stuff.
<zao> Last week I talked about containers and singularity to assorted site staff. This friday I'm talking about the module system and how we build software.
<heller__> shahrzad: btw, the paths don't expand '~'
<heller__> yup: 0x00007ffff3614004 in dgemm_oncopy () from /opt/apps/spack/opt/spack/linux-debian8-x86_64/gcc-8.1.0/openblas-0.3.0-s7hm7f4sy3xcfpieqwnxmpdvzioninrf/lib/libopenblas.so.0
<heller__> shahrzad: I guess the first number in the output is the runtime?
mbremer has joined #ste||ar
<heller__> hkaiser: is there any other benchmark I might want to look into?
<heller__> so yes, it is my openblas installation ...
<heller__> great
<hkaiser> heller__: we have 3 or 4 algorithms written up using Python, PhySL, and C++ for comparisions
<heller__> ok
<heller__> hkaiser: I wanted to look into the issue with the set_thread_lco_description
<hkaiser> ok
<hkaiser> good move
<heller__> So I wanted to reproduce Kevin's numbers ...
<heller__> 900 seconds is just too long for a quick turnaround though
<heller__> something like 10 seconds might be better there ;)
<hkaiser> you can use als with almost any data size
<heller__> I don't even know what als stands for :/
<hkaiser> ALS == alternating least square
<heller__> ok
<heller__> how do I alternate the problem size?
<hkaiser> make it smaller ;-)
<hkaiser> use less columns or rows
<hkaiser> (see command line options)
<heller__> ok, that's something to start with
<hkaiser> heller__: shahrzad can help with every question here, it's her code
aserio has quit [Quit: aserio]
<heller__> hkaiser: the move to clang7 should be good now
<heller__> except for the usual...
Anushi1998 has quit [Ping timeout: 246 seconds]
Anushi1998 has joined #ste||ar
<heller__> hkaiser: which test do you usually run for profiling?
Anushi1998 has quit [Ping timeout: 244 seconds]
Anushi1998 has joined #ste||ar
Anushi1998 has quit [Ping timeout: 252 seconds]
Anushi1998 has joined #ste||ar
<hkaiser> heller__: Kevin runs the ALS and LRA algorithms on a nightly bases and collects perf data
Anushi1998 has quit [Ping timeout: 246 seconds]
Anushi1998 has joined #ste||ar
<heller__> hkaiser: I mean you personally
<hkaiser> that's more fine-grain
<hkaiser> heller__: also see the same on advanced_indexing branch
<heller__> ok
<heller__> hkaiser: any specific options?
<hkaiser> no options
<hkaiser> I mostly use it with vtune to understand where are the overheads
eschnett_ has quit [Quit: eschnett_]
Anushi1998 has quit [Ping timeout: 245 seconds]
jaafar has quit [Ping timeout: 252 seconds]
<hkaiser> what's fibhash?
<hkaiser> and yes, this benchmark will probably not give you more than parallelism for 2 cores
<heller__> hkaiser: just pushed
ste||ar-github has joined #ste||ar
<ste||ar-github> [hpx] sithhell created fibhash (+2 new commits): https://github.com/STEllAR-GROUP/hpx/compare/44de39e47042^...ca6f5ec288c7
<ste||ar-github> hpx/fibhash 44de39e Thomas Heller: Removing superfluous checks
<ste||ar-github> hpx/fibhash ca6f5ec Thomas Heller: Improving spinlook pool by using a multiplicative fibonacci based hash
ste||ar-github has left #ste||ar [#ste||ar]
<hkaiser> interesting