Error while computing 100% of WU

TobiasH
TobiasH
Joined: 17 Nov 11
Posts: 1
Credit: 127374
RAC: 0
Topic 197060

Can Xou have a look at my results here?:

http://einsteinathome.org/account/tasks

Something's wrong and i'm not able to compute anything for e@h.
Other projects are working fine.

Gundolf Jahn
Gundolf Jahn
Joined: 1 Mar 05
Posts: 1079
Credit: 341280
RAC: 0

Error while computing 100% of WU

The link you gave is private, only visible for you.

Here are your tasks visible to all of us.

Your GPU doesn't seem to have enough memory (available):

Quote:
[12:45:26][3489][ERROR] Error creating CUDA FFT plan (error code: 2)
[12:45:26][3489][ERROR] Demodulation failed (error: 1011)!
[12:45:26][3489][WARN ] Sorry, at the moment your system doesn't have enough free CPU/GPU memory to run this task!
------> Returning control to BOINC, delaying next attempt for at least 15 minutes...
------> If this problem persists you should consider aborting this task...
[13:00:33][4465][INFO ] Application startup - thank you for supporting Einstein@Home!
[13:00:33][4465][INFO ] Starting data processing...
[13:00:33][4465][ERROR] Failed to enable CUDA thread yielding for device #0 (error: 2)! Sorry, will try to occupy one CPU core...
[13:00:33][4465][ERROR] Couldn't acquire CUDA context of device #0 (error: 2)!
[13:00:33][4465][ERROR] Demodulation failed (error: 1002)!
13:00:33 (4465): called boinc_finish

Unfortunately, you are running a BOINC version (7.0.27) with a bug in showing the GPU memory, so I can't tell if you could free enough memory to run a task successfully.

Gruß,
Gundolf

Computer sind nicht alles im Leben. (Kleiner Scherz)

vladimir.divis
vladimir.divis
Joined: 7 Mar 13
Posts: 1
Credit: 7157698
RAC: 0

Hello, could you tell me, why

Hello, could you tell me, why almost all of my units end like ID 394327240

on the page http://einsteinathome.org/workunit/171380741 - Error while computing - ?

I can´t find the reason.

Thakn you

Maximilian Mieth
Maximilian Mieth
Joined: 4 Oct 12
Posts: 130
Credit: 10301582
RAC: 3258

In the output for the WU the

In the output for the WU the message

Quote:
Maximum elapsed time exceeded


occurs. This means the task ran longer than BOINC thinks is accaptable. Indeed the run time was 257,643.09 seconds or 71 hours. This is very long. I don't know if this is because of your GPU, since I never heard of it. Maybe it has something to do with your preferences.
I see that you are crunching other projects as well. Could it be that they interfere somehow with E@H?

mlongbow
mlongbow
Joined: 2 Jan 13
Posts: 3
Credit: 6139255
RAC: 0

Hi, I'm getting Computation

Hi,
I'm getting Computation Errors for all of my Einstein tasks. I've tried reinstalled BOINC and this doesn't help.

SETI and Einstein are my only projects and SETI runs fine.

Any help would be greatly appreciated as I'd like to continue to run Einstein.

Thank you in advance.

Claggy
Claggy
Joined: 29 Dec 06
Posts: 560
Credit: 2699403
RAC: 0

Please post your Boinc

Please post your Boinc startup from the Event Log, the first 30 lines will do.

Claggy

mlongbow
mlongbow
Joined: 2 Jan 13
Posts: 3
Credit: 6139255
RAC: 0

Sorry about the delay but I

Sorry about the delay but I got caught up at work. I decided to uninstall Einstein completely. For GPU computing, besides Seti, I'm running GPUGRID. So thank you very much Claggy, but I'm going to keep running GPUGRID for now. Your help and quick reply is greatly appreciated. Here's the log after the current restart, running GPUGRID; I've only changed the account name to XXXXXXXXXX for security purposes. I hope it helps.

10/5/2013 11:52:19 AM | | Starting BOINC client version 7.0.64 for windows_x86_64
10/5/2013 11:52:19 AM | | log flags: file_xfer, sched_ops, task
10/5/2013 11:52:19 AM | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
10/5/2013 11:52:19 AM | | Data directory: C:\ProgramData\BOINC
10/5/2013 11:52:19 AM | | Running under account XXXXXXXXXX
10/5/2013 11:52:19 AM | | Processor: 8 GenuineIntel Intel(R) Core(TM) i7 CPU 950 @ 3.07GHz [Family 6 Model 26 Stepping 5]
10/5/2013 11:52:19 AM | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 cx16 sse4_1 sse4_2 popcnt syscall nx lm vmx tm2 pbe
10/5/2013 11:52:19 AM | | OS: Microsoft Windows 7: Ultimate x64 Edition, Service Pack 1, (06.01.7601.00)
10/5/2013 11:52:19 AM | | Memory: 24.00 GB physical, 40.00 GB virtual
10/5/2013 11:52:19 AM | | Disk: 167.58 GB total, 99.50 GB free
10/5/2013 11:52:19 AM | | Local time is UTC -4 hours
10/5/2013 11:52:19 AM | | CUDA: NVIDIA GPU 0: GeForce GTX 470 (driver version 327.23, CUDA version 5.50, compute capability 2.0, 1280MB, 1182MB available, 1089 GFLOPS peak)
10/5/2013 11:52:19 AM | | CUDA: NVIDIA GPU 1: GeForce GTX 660 Ti (driver version 327.23, CUDA version 5.50, compute capability 3.0, 2048MB, 1947MB available, 2985 GFLOPS peak)
10/5/2013 11:52:19 AM | | OpenCL: NVIDIA GPU 0: GeForce GTX 470 (driver version 327.23, device version OpenCL 1.1 CUDA, 1280MB, 1182MB available, 1089 GFLOPS peak)
10/5/2013 11:52:19 AM | | OpenCL: NVIDIA GPU 1: GeForce GTX 660 Ti (driver version 327.23, device version OpenCL 1.1 CUDA, 2048MB, 1947MB available, 2985 GFLOPS peak)
10/5/2013 11:52:19 AM | SETI@home | Found app_info.xml; using anonymous platform
10/5/2013 11:52:19 AM | | Config: use all coprocessors
10/5/2013 11:52:19 AM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 6649806; resource share 1000
10/5/2013 11:52:19 AM | GPUGRID | URL http://www.gpugrid.net/; Computer ID 159191; resource share 100
10/5/2013 11:52:19 AM | SETI@home | General prefs: from SETI@home (last modified 27-Sep-2013 02:24:33)
10/5/2013 11:52:19 AM | SETI@home | Computer location: home
10/5/2013 11:52:19 AM | SETI@home | General prefs: no separate prefs for home; using your defaults
10/5/2013 11:52:19 AM | | Reading preferences override file
10/5/2013 11:52:19 AM | | Preferences:
10/5/2013 11:52:19 AM | | max memory usage when active: 12287.07MB
10/5/2013 11:52:19 AM | | max memory usage when idle: 22116.73MB
10/5/2013 11:52:19 AM | | max disk usage: 16.76GB
10/5/2013 11:52:19 AM | | max CPUs used: 6
10/5/2013 11:52:19 AM | | suspend work if non-BOINC CPU load exceeds 50 %
10/5/2013 11:52:19 AM | | max download rate: 10240000 bytes/sec
10/5/2013 11:52:19 AM | | max upload rate: 4096000 bytes/sec
10/5/2013 11:52:19 AM | | (to change preferences, visit a project web site or select Preferences in the Manager)
10/5/2013 11:52:19 AM | | Not using a proxy

Claggy
Claggy
Joined: 29 Dec 06
Posts: 560
Credit: 2699403
RAC: 0

First i'd try a different

First i'd try a different driver (looking at your other projects I can see you're already done that), they try Einstein again,
Second i'd try a project reset and fresh files.

Claggy

mlongbow
mlongbow
Joined: 2 Jan 13
Posts: 3
Credit: 6139255
RAC: 0

Hi Claggy, Tried the

Hi Claggy,

Tried the program reset. That didn't work, although Seti@Home was running without a hitch, with the new drivers.

Then I let Seti finish off the files it had and uninstalled and reinstalled BOINC. Then I set up personal parameters (run 2x GPU, CPU max threads, etc.). Again, Seti worked fine but every time I ran any Einstein files, they finished up in a few seconds with the output as "Computation Error."

So, I've switched over to GPUGRID, to hold me over, in case something at Seti breaks down and I need GPU tasks. I run a several GPUGRID tasks per week, but that's about it.

Anyway, thanks again for helping me out. I just couldn't understand why the Einstein tasks worked one minute and stopped working the next.

Claggy
Claggy
Joined: 29 Dec 06
Posts: 560
Credit: 2699403
RAC: 0

RE: Hi Claggy, Tried the

Quote:

Hi Claggy,

Tried the program reset. That didn't work, although Seti@Home was running without a hitch, with the new drivers.


Program Reset?, No, I said Project Reset.

You haven't contacted the project since the 23 Sep 2013 0:39:01 UTC when you had 320.49 drivers installed, and you haven't got any uncompleted tasks,
so how do you know that it still doesn't work with newer drivers?

Computers belonging to mlongbow

Claggy

mountkidd
mountkidd
Joined: 14 Jun 12
Posts: 176
Credit: 12621402555
RAC: 8038985

The stderr logs are showing

The stderr logs are showing an access violation in nvcuda.dll. The developers should be looking at this. Its possible that it might be a driver problem - WHQL drivers in the 31xxx series have been very stable...

Gord

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.