Welcome to MilkyWay@home

Posts by Sutaru Tsureku

1) Message boards : News : New Runs for MilkyWay@home N-Body (5/30/2020) (Message 69891)
Posted 4 Jun 2020 by ProfileSutaru Tsureku
Post:
Hello :)

I don't know, is there something wrong - just 2 seconds calculation times?

- - - - -

de_nbody_05_30_2020_v176_40k__data__2_1588605902_203704_0
<core_client_version>7.16.5</core_client_version>
<![CDATA[
<stderr_txt>
<search_application> milkyway_nbody 1.76 Windows x86_64 double OpenMP, Crlibm </search_application>
Using OpenMP 4 max threads on a system with 4 processors
Number of particles in bins is very small compared to total. (0 << 1). Skipping distance calculation
Number of particles in bins is very small compared to total. (0 << 1). Skipping distance calculation
<search_likelihood>-9999999.900000000400000</search_likelihood>
<search_likelihood_EMD>-0.000000000000000</search_likelihood_EMD>
<search_likelihood_Mass>-0.000000000000000</search_likelihood_Mass>
<search_likelihood_Beta>-0.000000000000000</search_likelihood_Beta>
17:26:23 (2144): called boinc_finish(0)

</stderr_txt>
]]>

- - - - -

de_nbody_05_30_2020_v176_40k__data__2_1588605902_193201_1
<core_client_version>7.16.5</core_client_version>
<![CDATA[
<stderr_txt>
<search_application> milkyway_nbody 1.76 Windows x86_64 double OpenMP, Crlibm </search_application>
Using OpenMP 4 max threads on a system with 4 processors
Number of particles in bins is very small compared to total. (0 << 1). Skipping distance calculation
Number of particles in bins is very small compared to total. (0 << 1). Skipping distance calculation
<search_likelihood>-9999999.900000000400000</search_likelihood>
<search_likelihood_EMD>-0.000000000000000</search_likelihood_EMD>
<search_likelihood_Mass>-0.000000000000000</search_likelihood_Mass>
<search_likelihood_Beta>-0.000000000000000</search_likelihood_Beta>
17:50:12 (5320): called boinc_finish(0)

</stderr_txt>
]]>

- - - - -

Thanks :)
2) Message boards : Number crunching : N-Body Simulation - error, why? (Message 69760)
Posted 26 Apr 2020 by ProfileSutaru Tsureku
Post:
Hello :)

My PC crunched this N-Body Simulation WU and got an error.
Why, what happended?
What was the reason, the WU, the PC...?
What could I do, that this will not happen again?

Thanks :)


de_nbody_03_21_2020_v176_40k__sim__1_1580162702_862858_1

https://milkyway.cs.rpi.edu/milkyway/result.php?resultid=588461652

<core_client_version>7.16.5</core_client_version>
<![CDATA[
<message>
Das Handle ist ung´┐Żltig. (this should be: ung├╝ltig) ;)
(0x6) - exit code 6 (0x6)</message>
<stderr_txt>
<search_application> milkyway_nbody 1.76 Windows x86_64 double OpenMP, Crlibm </search_application>
Using OpenMP 4 max threads on a system with 4 processors
Using OpenMP 4 max threads on a system with 4 processors
Using OpenMP 4 max threads on a system with 4 processors
Using OpenMP 4 max threads on a system with 4 processors
Failed to commit move of 'nbody_checkpoint_tmp_2460' to 'nbody_checkpoint' (15100): (null)Failed to move file 'nbody_checkpoint_tmp_2460' to 'nbody_checkpoint' (15105): (null)Failed to move file 'nbody_checkpoint_tmp_2460' to 'nbody_checkpoint' (15105): (null)Failed to move file 'nbody_checkpoint_tmp_2460' to 'nbody_checkpoint' (15105): (null)Failed to move file 'nbody_checkpoint_tmp_2460' to 'nbody_checkpoint' (15105): (null)Failed to move file 'nbody_checkpoint_tmp_2460' to 'nbody_checkpoint' (15105): (null)Failed to update checkpoint 'nbody_checkpoint' with temporary (0): No error
Failed to write checkpoint
Error running system: NBODY_CHECKPOINT_ERROR (64)
08:28:40 (2460): called boinc_finish(6)

</stderr_txt>
]]>


(I have every 60 secs checkpoint in the preferences)
3) Message boards : Number crunching : Milkyway@home N-Body Simulation, limit to just 1 thread and slow CPUs ? (Message 69736)
Posted 18 Apr 2020 by ProfileSutaru Tsureku
Post:
Yes, an app_config.xml file could do this... ;)

But I'm unsure if the/my slow CPU can finish N-Body Simulation WUs (they vary a lot) during the 12 days, just with 1 thread. ;)

I would like to know experiences from others which have similar slow CPUs - if it's possible to finish N-Body Simulation WUs before deadline with just 1 thread...

I wouldn't like to let it run just for test, it would be waste of CPU time if it won't finish before deadline... ;)

Thanks :)
4) Message boards : Number crunching : Milkyway@home N-Body Simulation, limit to just 1 thread and slow CPUs ? (Message 69733)
Posted 18 Apr 2020 by ProfileSutaru Tsureku
Post:
Hello :)

I have just a slow CPU :
Intel(R) Celeron(R) CPU J1900 @ 1.99GHz [Family 6 Model 55 Stepping 8]
(4 real Cores)

I would like to limit the N-Body Simulation app to just 1 CPU thread (with app_config.xml file).
I'm unsure if the WUs will finish during the 12 days deadline.

A Milkyway@home Separation WU lasts around 6 hours - for to compare.
Just crunching, no other things at the same time.

I work and play games during crunching, so the calculations time of the WUs increase...

Maybe you have also a slow CPU and you limit the N-Body Simulation app just to 1 thread?
I could limit the app to just 1 thread - what you think?

Thanks :)
5) Message boards : News : Scheduled Maintenance Concluded (Message 65822)
Posted 15 Nov 2016 by ProfileSutaru Tsureku
Post:
BTW.

AFAIK, Milkyway WUs could be created/send out if results come back.

The results which come from the members PCs make it possible to create new WUs.

This is different to other BOINC projects.
6) Message boards : News : Scheduled Maintenance Concluded (Message 65820)
Posted 15 Nov 2016 by ProfileSutaru Tsureku
Post:
Jake Weiss wrote:
Hey Everyone,

I have been able to get a working 32 bit GPU application, but for some reason, the 64 bit has been giving me an impossible amount of trouble. For the time being I am planning to release the 32 bit application to run in both the 32 and 64 bit plan class so everyone can get crunching again and we can get some science done while I continue to work on the 64 bit application. This application will run on 64 bit platforms just fine and since we do not use a large amount of memory, there really isn't even a need for the application to be 64 bit.

Is there any objection to this plan? I'll give it an hour or so before I release to listen for opinions.

Thank you all for being great.

Jake


Thank you. :-)

I would love to let run a x64 app on my x64 OS/hardware... :-)


But I don't know if the last x64 app was a x64 app..., because:

MilkyWay@Home v1.39 (opencl_ati_101)
<stderr_txt>
<search_application> milkyway_separation 1.39 Windows x86 double OpenCL </search_application>

MilkyWay@Home v1.43 (opencl_ati_101)
<stderr_txt>
<search_application> milkyway_separation 1.43 Windows x86 double OpenCL </search_application>



With the 1.43 app (Win8.1 x64):

AMD R9 Fury X:
MSI Afterburner:
3 WUs/GPU: Memory Usage: 143 MB

NV GT 730:
GPU-Z:
2 WUs/GPU:
Memory Usage (Dedicated): 110 MB
Memory Usage (Dynamic): 73 MB



In past the project delay was 60 seconds.
Then it was changed to/now it's:
Project requested delay of 91 seconds
[sched_op] Deferring communication for 00:01:31


If it would be needed to change this settings, please think to the very fast PCs which are around (like mine with 4* R9 Fury X VGA cards ;-) - that they could be fed/saturated 24/7... :-)
7) Message boards : News : Scheduled Maintenance Concluded (Message 65771)
Posted 14 Nov 2016 by ProfileSutaru Tsureku
Post:
AFAIK, this is currently normal, because there are 5 WUs now in 1 WU (*_bundle5_* in the WU name).
Everytime 1 WU finish of this 5 WUs, it begin again from 0%.
This happens 4 times and with calculation of the 5th WU it will finish to 100%.
8) Message boards : News : Scheduled Maintenance Concluded (Message 65769)
Posted 14 Nov 2016 by ProfileSutaru Tsureku
Post:
Thanks for info. :-)


BTW.
http://milkyway.cs.rpi.edu/milkyway/apps.php

My both PCs have Win8.1 x64 and the CPU 1.42 x64 app is running fine.
The CPU 1.40 x64 app made errors.

Just curious...
The CPU 1.40 x86 app is still online, this app is running fine?
9) Message boards : News : Scheduled Maintenance Concluded (Message 65701)
Posted 12 Nov 2016 by ProfileSutaru Tsureku
Post:
BTW.
The 1.39 CPU app was slower on the above mentioned PC.

de_modfit_fast_19_3s_136_ModfitConstraints2_3_1478718902_2595000_2
Run Time - CPU Time - gr.Cr. - app
809.55 - 668.44 - 26.73 - MilkyWay@Home v1.39
10) Message boards : News : Scheduled Maintenance Concluded (Message 65700)
Posted 12 Nov 2016 by ProfileSutaru Tsureku
Post:
At least on my dual Xeon CPU PC with Win8.1 x64 Pro the 1.42 CPU app run like it should - I guess:

de_modfit_fast_19_3s_136_ModfitConstraints3_3_1478718902_2055111_2
Run Time - CPU Time - gr.Cr. - app
796.49 - 633.84 - 26.73 - MilkyWay@Home v1.42 (1 WU)

de_modfit_fast_19_3s_136_bundle5_ModfitConstraints3_4_1478900148_40245_0
Run Time - CPU Time - gr.Cr. - app
4,331.97 - 3,166.94 - 133.66 - MilkyWay@Home v1.42 (5 WUs in 1 WU)

CPU Time and granted Credits are *5.

Run Time is higher than CPU Time because of currently SETI GPU app support. Because the currently Milkyway 1.42 ATI OpenCL GPU app don't work... ;-) - like I read here in this thread.
Milkyway 1.40 ATI OpenCL GPU app made computation errors (I sent Jake a PM because of the OS error message which appeared in my Win8.1 x64 Pro).
11) Message boards : News : Scheduled Maintenance Concluded (Message 65696)
Posted 12 Nov 2016 by ProfileSutaru Tsureku
Post:
Jake Weiss wrote:
Peciak,

That's weird. The version info doesn't say its an OpenCL app. Let me see if I forgot to set the flag when I recompiled it.

Sorry about this, I haven't slept much over the last couple days trying to get this update done.

Jake

Jake Weiss wrote:
Hey Everyone,

I'm still working on a fix. Having issues with other the Windows OpenCL version but not Linux OpenCL. Need to see if my drivers are back on the machine I'm testing with or if there is actually an issue with the client.

Might take a couple hours for a fix.


Sorry,

Jake


Jake, what you think about to cancel the release of the new (Windows) >1.42 apps?

Just go back to former 1.39 and let it over the weekend like before.

You could relax and 'recharge your batteries' over the weekend - and at Monday a new working day begin.

:-)
12) Message boards : Number crunching : AMD Radeon R9 Fury X - app_info.xml and apps - optimizations (Message 65390)
Posted 5 Oct 2016 by ProfileSutaru Tsureku
Post:
I don't know if this ratios are correct...

If I look online the 1.39 app say in the <stderr_txt>:
(...)
Estimated AMD GPU GFLOP/s: 672 SP GFLOP/s, 134 DP FLOP/s
(...)

This would be a 5:1 ratio for the R9 Fury X.
13) Message boards : Number crunching : Run Multiple WU's on Your GPU (Message 65387)
Posted 5 Oct 2016 by ProfileSutaru Tsureku
Post:
Maybe it would be helpful to make an overview (new/other sticky thread) how much WUs/GPU simultaneously give the highest output referred to the VGA cards?


I start with...

After a few fast tests - more will follow - the current result:

On my AMD Radeon R9 Fury X's I let run 3 WUs/GPU with:

<app_config>
<app_version>
<app_name>milkyway</app_name>
<plan_class>opencl_ati_101</plan_class>
<avg_ncpus>0.01</avg_ncpus>
<ngpus>0.33</ngpus>
<cmdline>--non-responsive --gpu-target-frequency 1 --gpu-polling-mode -1 --gpu-wait-factor 0 --process-priority 4 --gpu-disable-checkpointing</cmdline>
</app_version>
<app_version>
<app_name>milkyway_separation_modified__fit</app_name>
<plan_class>opencl_ati_101</plan_class>
<avg_ncpus>0.01</avg_ncpus>
<ngpus>0.33</ngpus>
<cmdline>--non-responsive --gpu-target-frequency 1 --gpu-polling-mode -1 --gpu-wait-factor 0 --process-priority 4 --gpu-disable-checkpointing</cmdline>
</app_version>
</app_config>


On my NVIDIA GeForce GT 730 I let run 2 WUs/GPU with:

<app_config>
<app_version>
<app_name>milkyway</app_name>
<plan_class>opencl_nvidia_101</plan_class>
<avg_ncpus>0.01</avg_ncpus>
<ngpus>0.5</ngpus>
<cmdline>--non-responsive --gpu-target-frequency 1 --gpu-polling-mode 0 --gpu-wait-factor 0 --process-priority 4</cmdline>
</app_version>
<app_version>
<app_name>milkyway_separation_modified__fit</app_name>
<plan_class>opencl_nvidia_101</plan_class>
<avg_ncpus>0.01</avg_ncpus>
<ngpus>0.5</ngpus>
<cmdline>--non-responsive --gpu-target-frequency 1 --gpu-polling-mode 0 --gpu-wait-factor 0 --process-priority 4</cmdline>
</app_version>
</app_config>


(strange, (pre) and (code) don't work properly - is the website broken?)


On both PCs no idle CPU-Cores, CPUs fully loaded with CPU WUs.
14) Message boards : Number crunching : MilkyWay@Home N-Body Sim. - Exit status 196 (0xc4) EXIT_DISK_LIMIT_EXCEEDED (Message 65386)
Posted 5 Oct 2016 by ProfileSutaru Tsureku
Post:
Hm, it's not so nice to let run still the 1.62 N-body app (send out WUs) - and a very high percentage of the results finish with an error...

When will be released a new app, so it's again meaningful to let run N-body WUs?

Thanks.
15) Message boards : Number crunching : ESA's Gaia satellite - most detailed 3D map ever made of our Milky Way galaxy (Message 65297)
Posted 26 Sep 2016 by ProfileSutaru Tsureku
Post:
ESA's Gaia satellite: http://sci.esa.int/gaia

Gaia's billion-star map hints at treasures to come: http://sci.esa.int/jump.cfm?oid=58272


...hmm - and now?

That's the 'unofficially' end, or the imminent end of MilkyWay@Home?

Or do we here something different than Gaia of ESA?


Thanks.
16) Message boards : Number crunching : MilkyWay@Home N-Body Sim. - Exit status 196 (0xc4) EXIT_DISK_LIMIT_EXCEEDED (Message 65296)
Posted 26 Sep 2016 by ProfileSutaru Tsureku
Post:
I liked to let run the N-body WUs on the CPUs, but with an error rate of ~ 50 % it's... ahh... not so 'nice'... - so I stopped crunching N-body WUs...
17) Message boards : Number crunching : MilkyWay N-Body Sim., 1.62(mt) vs. 1.62(st) app - speed difference? (Message 65133)
Posted 11 Sep 2016 by ProfileSutaru Tsureku
Post:
For MilkyWay N-Body Sim. we could choose 2 apps and different settings...

Currently, the...

1.62 (multi thread) app - all available CPU-Threads allowed
1.62 (multi thread) app - limit to 'all -1' CPU-Threads (e.g. Quad-Core CPU, 4 CPU-Threads -1 = use 3 CPU-Threads)
1.62 (multi thread) app - limit to 1 CPU-Thread
1.62 (single thread) app - use just 1 CPU-Thread


I tested the
1.62 (mt) app (limited to 1 CPU-Thread)
and the
1.62 (st) app
...on my Celeron J1900 Quad-Core CPU, and it looks like the 1.62 (mt) app is much slower with this config.


If you have VGA cards installed, or you use the iGPU, you shouldn't run the (mt) app on all available CPU-Threads, if yes the GPU WUs stop (from my experiences).
This is still like this?


E.g. on a Quad-Core CPU, the (mt) app allowed to use 3 CPU-Threads is faster/slower than the (st) app?
...at the end of the day, which app crunch more WUs?

E.g. on 12 CPU-Threads CPUs (2 * 6 = 12 real CPU-Cores (my dual Xeon PC, HT off ;-) )...
the (mt) app allowed to use 11 CPU-Threads
vs.
(st) app?
...at the end of the day, which app crunch more WUs?


Speed differences: (mt) app all CPU-Threads allowed vs. (mt) app 'all -1' CPU-Threads allowed?


Or with the (mt) app it must be always straight numbers, like 2, 4, 6, 8 CPU-Threads for max. speed?


Maybe someone made already all this tests?


Thanks.
18) Message boards : Number crunching : MilkyWay@Home N-Body Sim. - Exit status 196 (0xc4) EXIT_DISK_LIMIT_EXCEEDED (Message 65132)
Posted 11 Sep 2016 by ProfileSutaru Tsureku
Post:
MilkyWay@Home N-Body Sim. - Exit status 196 (0xc4) EXIT_DISK_LIMIT_EXCEEDED

de_nbody_8_22_16_v162_2k_1_1472577603_750574
http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=1300435691

de_nbody_8_22_16_v162_2k_1_1472577603_1010655
http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=1304727954


[EDIT:
de_nbody_8_22_16_v162_2k_1_1472577603_1004517
http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=1304616435

de_nbody_8_1_16_v162_2k_3_1472577603_1016213
http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=1304838530]



In the BOINC/Messages are:
Aborting task xxxxxx: exceeded disk limit: xx.xxMB > 50.00MB


Is this something an admin need to look?

Maybe there is a workaround via cc_config.xml file (or an other way) possible?


Thanks.
19) Message boards : Number crunching : app_info.xml Help (Message 64954)
Posted 29 Jul 2016 by ProfileSutaru Tsureku
Post:
I didn't know that the Milkyway server send tasks to outdated version numbers in app_info.xml file.


If you use an app_info.xml file, you MUST observe what your PC do.
If you use an outdated app you will 'destroy' all tasks
(maybe also the science?).


(Currently it's the only way for members with newer AMD hardware to participate here.)



You could use the first entries in my thread without GPU cmdline settings:


<app_info>
<app>
<name>milkyway_nbody</name>
<user_friendly_name>Milkyway N-Body Sim.</user_friendly_name>
</app>
<file_info>
<name>milkyway_nbody_1.62_windows_x86_64.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway_nbody</app_name>
<version_num>162</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>milkyway_nbody_1.62_windows_x86_64.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>milkyway</name>
<user_friendly_name>Milkyway</user_friendly_name>
</app>
<file_info>
<name>milkyway_1.36_windows_x86_64.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway</app_name>
<version_num>136</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>milkyway_1.36_windows_x86_64.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>milkyway</name>
</app>
<file_info>
<name>milkyway_1.36_windows_x86_64__opencl_ati_101.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway</app_name>
<version_num>136</version_num>
<platform>windows_x86_64</platform>
<avg_ncpus>1</avg_ncpus>
<max_ncpus>1</max_ncpus>

<plan_class>opencl_ati_101</plan_class>
<cmdline></cmdline>
<coproc>
<type>ATI</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>milkyway_1.36_windows_x86_64__opencl_ati_101.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>milkyway_separation__modified_fit</name>
<user_friendly_name>Milkyway Sep. (Mod. Fit)</user_friendly_name>
</app>
<file_info>
<name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway_separation__modified_fit</app_name>
<version_num>136</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>milkyway_separation__modified_fit_1.36_windows_x86_64.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>milkyway_separation__modified_fit</name>
</app>
<file_info>
<name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway_separation__modified_fit</app_name>
<version_num>136</version_num>
<platform>windows_x86_64</platform>
<avg_ncpus>1</avg_ncpus>
<max_ncpus>1</max_ncpus>

<plan_class>opencl_ati_101</plan_class>
<cmdline></cmdline>
<coproc>
<type>ATI</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe</file_name>
<main_program/>
</file_ref>
</app_version>
</app_info>


http://milkyway.cs.rpi.edu/milkyway/download/milkyway_nbody_1.62_windows_x86_64.exe
http://milkyway.cs.rpi.edu/milkyway/download/milkyway_1.36_windows_x86_64.exe
http://milkyway.cs.rpi.edu/milkyway/download/milkyway_1.36_windows_x86_64__opencl_ati_101.exe
http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64.exe
http://milkyway.cs.rpi.edu/milkyway/download/milkyway_separation__modified_fit_1.36_windows_x86_64__opencl_ati_101.exe


This should work.

After you could decide how much % CPU the GPU app get (this don't set really the CPU usage of the GPU app, it help to let free/idle a few % CPU):
<avg_ncpus>1</avg_ncpus>
<max_ncpus>1</max_ncpus>


1 CPU-thread for 1 app/task
0.5 for 1/2 CPU-thread for 1 app/task (2 apps use 1 CPU-thread)
0.34 for 1/3 CPU-thread for 1 app/task (3 apps use 1 CPU-thread)
...

From my experiences, the CPU should a few % idle. (If not the GPU app calculation could stand still (not feeded from the CPU) and this result in a task error.)


And how much tasks simultaneously on the GPU:
<count>1</count>

1 = 1 app
0.5 = 2 apps simultaneously
0.33 = 3 apps simultaneously
...



And after you could test the cmdline settings (until now I found these, I don't know if there are more):

  • --non-responsive
  • --gpu-target-frequency N
  • --gpu-polling-mode N
  • --gpu-wait-factor N
  • --process-priority N
  • --gpu-disable-checkpointing



Until now I saw no 'officially' statement about these settings/what they do.
If you like, then use them carefully (after testing).

20) Message boards : Number crunching : app_info.xml Help (Message 64953)
Posted 29 Jul 2016 by ProfileSutaru Tsureku
Post:
double post


Next 20

©2023 Astroinformatics Group