hkaiser changed the topic of #ste||ar to: STE||AR: Systems Technology, Emergent Parallelism, and Algorithm Research | stellar-group.org | HPX: A cure for performance impaired parallel applications | github.com/STEllAR-GROUP/hpx | This channel is logged: irclog.cct.lsu.edu
diehlpk has joined #ste||ar
diehlpk has quit [Quit: Leaving.]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 268 seconds]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 268 seconds]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 252 seconds]
K-ballo has quit [Quit: K-ballo]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 268 seconds]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 252 seconds]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 268 seconds]
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 252 seconds]
diehlpk has joined #ste||ar
diehlpk has quit [Quit: Leaving.]
diehlpk has joined #ste||ar
hkaiser has quit [Quit: Bye!]
diehlpk has quit [Quit: Leaving.]
<dkaratza[m]> ms: could you please elaborate a bit on the mistake regarding the rows/cols when printing the matrices? because I thought i fixed it. I changed the print function: I replaced `std::cout << M[i * cols + j] << " ";` with `std::cout << M[i * rows + j] << " ";`
<dkaratza[m]> Is it still wrong?
<ms[m]> dkaratza: no, that one is good now
<ms[m]> `B[k * rowsA + j]` should be `B[k * rowsB + j]`
<ms[m]> if you try it out with `n != m != k` you'll probably see funky results
<dkaratza[m]> yes i noticed this was weird (rowsA used for matrix B)
<dkaratza[m]> ok i will fix that too
<ms[m]> dkaratza:
<ms[m]> 👍️
<ms[m]> that's why I suggested to have rowsR/colsR variables as well
<dkaratza[m]> alright!
<ms[m]> in principle a little matrix class would probably be nicest here, but I think it's nice to keep it simple in this case
<dkaratza[m]> ms[m]: I see..yes maybe its better not to complicate it, since we said its for demonstration purposes
<dkaratza[m]> ms: I also think I fixed the format, if you would like to check it. Is this what you wanted?
<ms[m]> dkaratza: yeah, I think that looks about right! if you ran clang-format on it then it's probably right ;)
<dkaratza[m]> ms[m]: great
<ms[m]> dkaratza: as a final request, would you mind squashing all the commits together into one commit? let me know if you need any help with that
<dkaratza[m]> ms[m]: i guess I need
<dkaratza[m]> haha
<ms[m]> :P
<ms[m]> do you have 5 minutes to do it now? we can do a quick call
<dkaratza[m]> sure
hkaiser has joined #ste||ar
K-ballo has joined #ste||ar
diehlpk has joined #ste||ar
hkaiser has quit [Quit: Bye!]
diehlpk_work has joined #ste||ar
<dkaratza[m]> ms: if I will try to make a new PR probably I will have conflicts later on because my last pr has not been merged yet
<dkaratza[m]> Should I wait first to me merged or its not a problem and I can go on?
<ms[m]> dkaratza: you can most likely go on
<ms[m]> are you thinking about the changes to the api docs? that will at least not conflict with the currently open pr
<ms[m]> dkaratza: btw, you should (force) push the sphinx_theme branch ;)
<dkaratza[m]> ms[m]: i already have
<dkaratza[m]> no?
<ms[m]> nope :P
<ms[m]> there are still 5 commits here: https://github.com/STEllAR-GROUP/hpx/pull/5645/commits
<K-ballo> you can make a PR against the branch of another PR, and then it gets automatically adjusted when the later is merged
nanmiao has quit [Quit: Client closed]
<dkaratza[m]> <ms[m]> "there are still 5 commits here..." <- oh I confused it
<dkaratza[m]> I also deleted the branch :)
<dkaratza[m]> but its ok, i fixed it
hkaiser has joined #ste||ar
nanmiao has joined #ste||ar
hkaiser has quit [Ping timeout: 252 seconds]
hkaiser_ has joined #ste||ar
diehlpk has quit [Quit: Leaving.]
hkaiser_ has quit [Ping timeout: 252 seconds]
nanmiao has quit [Quit: Client closed]
<pedro_barbosa[m]> Does HPXCL use NVRTC to compile or just NVCC?
diehlpk has joined #ste||ar
hkaiser has joined #ste||ar
diehlpk has quit [Quit: Leaving.]
diehlpk has joined #ste||ar
hkaiser has quit [Quit: Bye!]
hkaiser has joined #ste||ar
diehlpk has quit [Quit: Leaving.]
<hkaiser> jedi18[m]: https://cdash.cscs.ch/testDetails.php?test=59300224&build=202949, note the seed: 1638384086
diehlpk has joined #ste||ar
diehlpk has quit [Ping timeout: 252 seconds]
K-ballo has quit [Quit: K-ballo]
K-ballo has joined #ste||ar
diehlpk has joined #ste||ar