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/
<K-ballo>
no, I want to benchmark some hpx changes
<jbjnr>
k
<jbjnr>
(just curious)
jgolinowski has joined #ste||ar
hkaiser has quit [Quit: bye]
<diehlpk_work>
simbergm, Could you mention nikunj changes in the release note? HPXCL and blazemark were working with hpx 1.1 and with his changes everything was not working anymore and needed some fixes
<diehlpk_work>
It was working at the beginning of this year before your changes were commited.
hkaiser has joined #ste||ar
aserio has quit [Ping timeout: 250 seconds]
<simbergm>
diehlpk_work: yeah, I'll mention that, it's probably the biggest single feature in this release
<simbergm>
but if it's still causing problems I might consider turning it off by default for the release
<diehlpk_work>
It is more that stuff worked with 1.1 is not working anymore
<diehlpk_work>
After doing some changes it is working again
<diehlpk_work>
Or to say it in a different way this change is not 100% compatible with HPX 1.1
<diehlpk_work>
I think we should definitely highlight this change and may provide some pitfalls
<simbergm>
yeah
<simbergm>
do you know what the problem was in this case?
<diehlpk_work>
For HPXCL is was the the tenry point was named hpx_main and this what not handled by his changes. I had to use main and it was working again
<diehlpk_work>
For blazemark, I am still debugging
<simbergm>
are you able to pass in any hpx options on the commandline (for the blaze example) or is everything unknown?
<diehlpk_work>
Currently everything is unkown, because commandline args are parsed by blaze and all related not to blaze are unknown. I found the line of codes causing the error within blaze. And also discussed with Klaus how to fix it
<diehlpk_work>
I am not sure why it was working with HPX 1.1 and stopped working know
<diehlpk_work>
I only looked briefly into it yesterday night, because Sharizad reported a bug for blazemark
<diehlpk_work>
I will invest more time today or tomorrow. I have to finish some benchmarks for a paper
aserio has joined #ste||ar
aserio has quit [Ping timeout: 250 seconds]
hkaiser has quit [Quit: bye]
david_pfander has quit [Ping timeout: 252 seconds]
hkaiser has joined #ste||ar
hkaiser has quit [Read error: Connection reset by peer]
hkaiser has joined #ste||ar
akheir has joined #ste||ar
hkaiser has quit [Ping timeout: 240 seconds]
hkaiser has joined #ste||ar
aserio has joined #ste||ar
bibek has quit [Quit: Konversation terminated!]
bibek has joined #ste||ar
<nikunj>
diehlpk_work, I will have to look into hpxcl and blazemark cmakelist to identify the reason for it's failure. I have a quiz tomorrow, so I'll check it after the quiz.
<nikunj>
It will most likely be due to flags that do not get added. I'll have to look into detail if that's not the case
<diehlpk_work>
nikunj, Sure, take your time
hkaiser has quit [Read error: Connection reset by peer]