1) Message boards : News : The SixTrack team welcomes the LHC@Home volunteers at the CERN open days (Message 39967)
Posted 28 days ago by Profile Michael H.W. Weber
Post:
First of all the German Rechenkraft.net team would like to thank Ben Segal, Ian McIntosh, David Cameron and all the others involved for organizing both the ATLAS@home and the LHC@home booths which our team visited with 13 people on Saturday, 14th.

This time i'm the only one from Boinc Italy team. Maybe next time our teams could organize a joint venture :-)

Well, I thought about making it a joint visit together with other teams (and even non-DC-related people), because luckily we got a number of tickets for both days and, initially, it seemed that our team would not even use half of it. So, we globally invited people to join us via Twitter account announcements. In the end, however, we got no response at all but then found more and more people who became interested in joining us in our own team.

Michael.
2) Message boards : News : The SixTrack team welcomes the LHC@Home volunteers at the CERN open days (Message 39962)
Posted 29 days ago by Profile Michael H.W. Weber
Post:
First of all the German Rechenkraft.net team would like to thank Ben Segal, Ian McIntosh, David Cameron and all the others involved for organizing both the ATLAS@home and the LHC@home booths which our team visited with 13 people on Saturday, 14th.
Also, thanks a lot for the nice two special talks on Sixtrack and the 1 TB magnetic cartridges we all got as a gift.
Maybe it would be nice to post the PDF of the information leaflet we got at the talk somewhere here in the forum for download.

We had an amazing (!) weekend and many of us managed to visit all four underground detector sites. Several GB of photos and videos were recorded and of course we posted a first extract of all these marvellous impressions on our Twitter account - if you like, just take a look:

ATLAS detector
LHCb detector
LHCb high performance cluster & LHC liquid helium cooling tanks
CAST telescope to answer dark matter-related questions (search for axions from the sun)
ALICE detector (big bang-like event generator)
LHC accelerator tunnel (near the ALICE detector)
CMS detector

I was actually surprised how many people brought their entire families along including kids for which a lot of nice activities were provided, too. Excellent!
Of course, due to so many people, waiting times to enter the underground sites were ridiculously long: If I remember correctly, on the first day we waited almost 4 hours after entry at 9 am to only see the ATLAS detector for around 20 minutes. And this was located nearby, directly at the main entrance (resulting in people rushing there first, of course).

Although there was a nice app provided for the visitors, no free WiFi was available but internet access was essential to be able to see the waiting times for the detector sites. Many German providers appear to simply not broadcast around the CERN sites and the Eduroam cross-country university network could only be accessed after a device was identified over the CERN WiFi. For accessing the CERN network, however, one had to register and I was lucky that Ben approved my effort to do so rather quickly - thanks a lot for that, because only based on this we finally made it to all the remaining sites of interest on Sunday after more sophisticated app planning. ;-)
The app also appeared to consume quite some electricity, so people tended to use it savingly to be able to continue to use their smartphones for photography purposes.

I think, in order to easily recruit more distributed computing volunteers it would have been very helpful to setup the ATLAS@home booth directly next to the ATLAS waiting queue and have some people deliver LHC@home & subproject flyers. Just an idea... ;-)

Since CERN wanted to collect some statistical data of the individual site occupation by manual wristband scanning, people were unfortunately not only queueing up heavily at the site entrances but also at the exit areas - which really was quite annoying due to the caused delays. Maybe an RFID solution could help solve that problem next time?

All in all it was more than worth to travel the long distance from Germany to visit the CERN OpenDays.
A nice thing for the future would be a yellow VIP wristband for volunteer computing participants which should allow us to directly proceed to the underground sites - omitting the waiting queues of course... ;-)

Best regards,
Michael.
3) Message boards : ATLAS application : Uploads of finished tasks not possible since last night (Message 33877)
Posted 16 Jan 2018 by Profile Michael H.W. Weber
Post:
I have an ATLAS task not uploading since many, many days:

16.01.2018 08:55:48 | LHC@home | Started upload of WqtNDme5DvrnDDn7oo6G73TpABFKDmABFKDm8sHKDmABFKDmT56S3n_0_r205511374_ATLAS_result
16.01.2018 09:00:55 | LHC@home | Temporarily failed upload of WqtNDme5DvrnDDn7oo6G73TpABFKDmABFKDm8sHKDmABFKDmT56S3n_0_r205511374_ATLAS_result: transient HTTP error
16.01.2018 09:00:55 | LHC@home | Backing off 04:15:14 on upload of WqtNDme5DvrnDDn7oo6G73TpABFKDmABFKDm8sHKDmABFKDmT56S3n_0_r205511374_ATLAS_result

16.01.2018 10:12:25 | LHC@home | Started upload of WqtNDme5DvrnDDn7oo6G73TpABFKDmABFKDm8sHKDmABFKDmT56S3n_0_r205511374_ATLAS_result
16.01.2018 10:12:47 | LHC@home | Temporarily failed upload of WqtNDme5DvrnDDn7oo6G73TpABFKDmABFKDm8sHKDmABFKDmT56S3n_0_r205511374_ATLAS_result: connect() failed
16.01.2018 10:12:47 | LHC@home | Backing off 03:54:55 on upload of WqtNDme5DvrnDDn7oo6G73TpABFKDmABFKDm8sHKDmABFKDmT56S3n_0_r205511374_ATLAS_result

Strangely, the ATLAS task data listed in my account is not consistent with the data displayed in my client: While tha task date is identical, download and due dates differ. The task was neither delivered on 15th of January by the server (instead many days earlier) nor has it to be complete on 23rd of January (but on 22nd).
Do you have a database problem?

Michael.
4) Message boards : Sixtrack Application : Inconclusive, valid/invalid results (Message 31322)
Posted 8 Jul 2017 by Profile Michael H.W. Weber
Post:
Is this topic related to the fact that the server has cancelled 8 tasks on 3 of my well-performing machines yesterday?

Michael.
5) Message boards : News : Network and server problems Sunday night (Message 30895)
Posted 20 Jun 2017 by Profile Michael H.W. Weber
Post:
The feeder is down again...

Michael.
6) Message boards : News : Network and server problems Sunday night (Message 30866)
Posted 19 Jun 2017 by Profile Michael H.W. Weber
Post:
...now it works again.

Michael.
7) Message boards : News : Network and server problems Sunday night (Message 30862)
Posted 19 Jun 2017 by Profile Michael H.W. Weber
Post:
The feeder is not running.
No tasks for any of the projects at present.

Michael.
8) Message boards : ATLAS application : ATLAS: Post never ending tasks here (Message 30852)
Posted 19 Jun 2017 by Profile Michael H.W. Weber
Post:
This machine completed a number of ATLAS tasks sucessfully requiring around 5000 to 6000 CPU seconds. I now have another task running for almost 24 hrs (!) with progress 99.999% and remainind time 00:00:00, which therefore is the next one that will never end (and hence is faulty):

https://lhcathome.cern.ch/lhcathome/workunit.php?wuid=71412840

Unlike the other one which I posted above, this one does NOT show an error message in the console view. Everything looks normal but that task appears dead.
With this task, however, I can't exclude an issue with network because I realized that the CERN server was down yesterday and some CERN WUs exchange data with the server during run time. So maybe that task stalled due to such an issue and therefore does not show any error message or event progress in the Virtualbox console view.
I just aborted it.

Michael.

P.S. Yes, I use an .xml file to set LHC to run 3 CPU ATLAS tasks with 4.9 GB RAM allowance. Only two tasks are allowed to be downloaded and only one of them can run at a time.
9) Message boards : ATLAS application : ATLAS: Post never ending tasks here (Message 30811)
Posted 17 Jun 2017 by Profile Michael H.W. Weber
Post:
... to continue a thread which I initiated over at ATLAS@home a long time back to classify problems with WUs for better analysis.

This is actually the first of these types of tasks which I encountered after the merging of ATLAS@home and LHC@home:

https://lhcathome.cern.ch/lhcathome/workunit.php?wuid=71030232

Michael.
10) Message boards : LHC@home Science : GPU Computing (Message 30678)
Posted 6 Jun 2017 by Profile Michael H.W. Weber
Post:
Any news?

Michael.
11) Message boards : Number crunching : SixTrack: Cross-OS validation = inconclusive results (Message 30536)
Posted 28 May 2017 by Profile Michael H.W. Weber
Post:
:)
Michael.
12) Message boards : Number crunching : SixTrack: Cross-OS validation = inconclusive results (Message 30529)
Posted 28 May 2017 by Profile Michael H.W. Weber
Post:
I do have completed and validated work units on several other projects. I know that is not an apples-to-apples comparison, but it still stands to reason that if the issue were hardware related, I would likely have several other failed results in other projects as well.

That is not necessarily the case.

I have two GPUs that work error-free with all tested DC projects, except for one. AND: On one of these cards, that project incompatibility has not even been there from the very beginning. It started after about half a year of constant computation. Hardware-wise, still no flaws can be detected. But something on that equipment must have changed over time and it did not appear to be just dust accumulation causing overheating - as judged on the basis of chip temperature sensors.

Vice-versa, there are hardware testing programs which may output potential failures (e.g. GPU RAM) but these appear false-positives as despite the reported issue, the DC results produced with those boards are successfuly cross-validated. However, it might e.g. also be that some projects use more RAM than others such that a faulty area on the memory chips is only used by some DC apps.
Another possibility: With a very popular Linux distribution, for quite a while, simply a faulty CPU-RAM test was delivered, and so on...

All possible... I use many machines, CPUs and GPUs, for more than 15 years in distributed computing on a 24/7 basis. So, I have seen quite a few apparently strange things in this respect. One of the problems with an accurate diagnosis on a scientific basis is the fact that many DC projects often just are not very helpful because they do not care about a proposed single users issue.
One example: Currently I have a machine which used to contribute to a DC project for more than a year using its GTX 770 card. From one day to the other that machine ceased receiving work for no obvious reason. To date, the project leader board did not manage to help solving the problem. Well, its their project and they now have one constantly contributing machine less.

Michael.
13) Message boards : CMS Application : CMS Tasks Failing (Message 30523)
Posted 27 May 2017 by Profile Michael H.W. Weber
Post:
Two CMS tasks failing after 10 min; each on a different host, once Windows, once Linux:

https://lhcathome.cern.ch/lhcathome/result.php?resultid=144126716
https://lhcathome.cern.ch/lhcathome/result.php?resultid=144113647

Michael.
14) Message boards : Number crunching : SixTrack: Cross-OS validation = inconclusive results (Message 30522)
Posted 27 May 2017 by Profile Michael H.W. Weber
Post:
Thank you Eric for looking into it in such great detail.

:)
Michael.

P.S.: Generally, none of my machines is overclocked.
15) Message boards : Number crunching : SixTrack: Cross-OS validation = inconclusive results (Message 30510)
Posted 27 May 2017 by Profile Michael H.W. Weber
Post:
Good morning! :)
Please check out this inconclusive SixTrack result where the server tried to compare a Windows vs. a Linux result:

https://lhcathome.cern.ch/lhcathome/workunit.php?wuid=69568938

Isn't it correct that different OS may yield slightly different numerical results for the same calculation and therefore it is advised to only cross-compare / validate Windows vs. Windows and Linux vs. Linux (as is the case for validation of only AMD vs. AMD and Intel vs. Intel CPU results for reasons of different float number rounding)?
If this is the case, WUs to be validated by redundant computation should only be handed out to the same OS, otherwise computational ressources are going to be wasted.

Michael.
16) Message boards : LHC@home Science : GPU Computing (Message 30504)
Posted 26 May 2017 by Profile Michael H.W. Weber
Post:
Well we have tried GPUs and results are not brilliant to say the least.

So, then what GPUs have been tested and what was the speed increase factor vs. electricity consumption?

I know very well from our own RNA World DC project that there is plenty of code which simply does not benefit from porting to GPUs at all.

Michael.
17) Message boards : LHC@home Science : GPU Computing (Message 30499)
Posted 26 May 2017 by Profile Michael H.W. Weber
Post:
SixTrack already runs on arm.

I just saw on the application page that, indeed, on May 4th a SixTrack ARM client for both Linux- and Android-on-ARM was released in beta status.

If you had announced this on both the LHC@home main page plus in the BOINC clients info panel, a lot more people might already have known and helped testing it.

Michael.

[edit]: Well, it seems testing isn't an option as at least currently no work for that ARM app appears available.
18) Message boards : News : SixTrack News - May 2017 (Message 30497)
Posted 26 May 2017 by Profile Michael H.W. Weber
Post:
Very good! Thanks a lot for the feedback.

The more we get the impression something meaningful is being done with our computational efforts, the more support you may expect.

Michael.
19) Message boards : LHC@home Science : GPU Computing (Message 30491)
Posted 25 May 2017 by Profile Michael H.W. Weber
Post:
Well, I think maybe ARM might even be interested in funding a student for a few months to port code to MALI GPU to demonstrate their GPUs capabilities in the context of a significant project (SixTRack/LHC/CERN: outreach!) if this is not an intersting enough topic for some Google Summer of code student...

Michael.
20) Message boards : LHC@home Science : GPU Computing (Message 30488)
Posted 25 May 2017 by Profile Michael H.W. Weber
Post:
In case the LHC@home team would like to wirte DC history once again:
Try to also port SixTrack to the OpenCL-capable (i.e. more recent) ARM Mali GPUs. To the best of my knowledge, so far there is not a single DC project supporting these types of GPUs.

Michael.


Next 20


©2019 CERN