Welcome to MilkyWay@home

All work Units giving "Computational Error"

Message boards : Number crunching : All work Units giving "Computational Error"
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · Next

AuthorMessage
Un4given

Send message
Joined: 14 Feb 09
Posts: 19
Credit: 62,373,513
RAC: 0
Message 53186 - Posted: 15 Feb 2012, 3:56:03 UTC - in response to Message 53154.  

Nope. Still doesn't work. Still get the same computational error. I'm done until this BS issue is fixed.
ID: 53186 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
spingadus[MM]

Send message
Joined: 26 Apr 11
Posts: 2
Credit: 2,571,411
RAC: 0
Message 53187 - Posted: 15 Feb 2012, 4:23:30 UTC

I have the same issue. All computational errors. Looks like I missed the double credit window due to this! Grrrrr!

Anyways, here's what I'm running if it helps.

Boinc 7.0.15
AMD drivers 12.1
HD 6970
Windows 7

This all started happening after I upgraded both BOINC and my card drivers.
ID: 53187 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53188 - Posted: 15 Feb 2012, 4:45:06 UTC - in response to Message 53186.  

Nope. Still doesn't work. Still get the same computational error. I'm done until this BS issue is fixed.
That wasn't for your error. Your error suggests the OpenCL library is broken or missing.
ID: 53188 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Grutte Pier [Wa Oars]~MAB The ...
Avatar

Send message
Joined: 30 Dec 11
Posts: 13
Credit: 2,788,359
RAC: 0
Message 53190 - Posted: 15 Feb 2012, 11:28:19 UTC
Last modified: 15 Feb 2012, 11:29:01 UTC

Atm it seems it's working fine.

Installed 6.10.60 again and afterwards http://www.arkayn.us/forum/index.php?PHPSESSID=f0483088d797862abe1bbb0a1b6bd4a2&action=downloads;sa=view;down=60 on my XP64

GTX 460 FTW 1GB (1.075V > 1.012V / 850MHz > 890MHz) / 6.10.60 / 275.33 XP32 OK
GTX 460 SC 768MB (763MHz > 820MHz) / 6.10.60 / 285.58 XP64 OK

Will change some things in nearby future such as drivers, voltages and speed and watch what happens.
ID: 53190 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Alyx

Send message
Joined: 29 Jul 08
Posts: 6
Credit: 10,991,883
RAC: 0
Message 53196 - Posted: 15 Feb 2012, 18:06:46 UTC

I downgrade drivers to 11.9 and ran the 1.02 app_info.xml from Arkayn. I'm still getting a gpu crash within about 10sec of task start. All tasks failing.

Moving to a different project, really makes me sad though, only like 3 days from 5M. :(
ID: 53196 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Ray_GTI-R
Avatar

Send message
Joined: 5 Nov 10
Posts: 69
Credit: 15,064,831
RAC: 0
Message 53203 - Posted: 16 Feb 2012, 2:11:19 UTC - in response to Message 53184.  

After approx 01.00 UTC 15/2/2012 all 0.82 (ati14) GPU tasks deadline dated 27/2/2012 02:03++ failed with computation error.
All remaining unstarted GPU tasks have been aborted.
The option for no new tasks is initiated.

FWIW all other GPU tasks completed succesfully today AFAIK.

Please advise.
Your errors suggests rebooting.

Thanks Matt. That worked.

Care to elaborate?

This error does not occur if I run other GPU projects. Put another way .

If I HADN'T checked, asked, rebooted, re-tested:-

I'd still be blindly* running MW@H GPU tasks 24/7 costing me electricity/wear & tear doing nothing with my very expensive, now very rare hardware ... which I would prefer not to do.

* headless server

Suggestion. Issue a pro-tem-for-this-project "stop processing & stop accepting new tasks for this project" command and an Event log message for me to check why processing stopped, after e.g., 5th etc failed WU with the same "Computation failed" error. Just a thought.

Ray
ID: 53203 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53204 - Posted: 16 Feb 2012, 2:31:37 UTC - in response to Message 53203.  

Care to elaborate?

This error does not occur if I run other GPU projects. Put another way .
The drivers aren't particularly unreliable. They sometimes get into a bad state where nothing works.
ID: 53204 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Black~Mystic

Send message
Joined: 13 Nov 10
Posts: 10
Credit: 212,710,651
RAC: 0
Message 53205 - Posted: 16 Feb 2012, 2:37:09 UTC - in response to Message 53203.  
Last modified: 16 Feb 2012, 2:38:30 UTC

I am having similar problems.

My 24/7 rig: q6600 + 5830 win xp x32
CCC: 10.12
"Message from server: Catalyst Driver Version is Not OK for OpenCL app with this GPU"

this is running on a 24/7 machine so i look back and this error started occuring on 2/9/12 at 3:15pm pst


my main rig: q9550 + 5850 win 7 x64
CCC: 8.85
work is done in 2 seconds with computational error

dont know why
ID: 53205 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53206 - Posted: 16 Feb 2012, 2:52:31 UTC - in response to Message 53205.  

CCC: 10.12
"Message from server: Catalyst Driver Version is Not OK for OpenCL app with this GPU"
10.12 is ancient; you'll need something more recent. The most recent 12.1 should be fine.
ID: 53206 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Blurf
Volunteer moderator
Project administrator

Send message
Joined: 13 Mar 08
Posts: 804
Credit: 26,380,161
RAC: 0
Message 53207 - Posted: 16 Feb 2012, 2:53:47 UTC
Last modified: 16 Feb 2012, 2:55:42 UTC

I updated to 12.1 and got 2 valid WU's turned in today-otherwise lots of failures.

http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=233052

ID: 53207 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53208 - Posted: 16 Feb 2012, 3:01:25 UTC - in response to Message 53207.  

I updated to 12.1 and got 2 valid WU's turned in today-otherwise lots of failures.

http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=233052
Apparently the unroll problem wasn't fixed until 1 driver later than I thought. You shouldn't get it anymore for anything newer than R700 with drivers older than 11.6
ID: 53208 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Black~Mystic

Send message
Joined: 13 Nov 10
Posts: 10
Credit: 212,710,651
RAC: 0
Message 53209 - Posted: 16 Feb 2012, 3:57:19 UTC - in response to Message 53206.  

CCC: 10.12
"Message from server: Catalyst Driver Version is Not OK for OpenCL app with this GPU"
10.12 is ancient; you'll need something more recent. The most recent 12.1 should be fine.

they are stable though. upgrading to each CCC creates problems for my other programs.
ID: 53209 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
weasel473

Send message
Joined: 9 Dec 11
Posts: 5
Credit: 1,121,906
RAC: 0
Message 53214 - Posted: 16 Feb 2012, 12:35:59 UTC

Ever since 1.00 update been getting comp errors.

AMD Phenom II x4 965
ATI 4890 x 2 crossfire - CCC driver 11.9
Win 7 64-bit
BOINC 6.12.34 9x64)
Was chugging along fine before then.
All 1.02 openCl_amd_ati are failing at the 1:07 ; 1:08 mark.

Tried that Arkyan file - it broke Milkyway.

2/16/2012 7:29:24 AM | Milkyway@Home | Message from server: Your app_info.xml file doesn't have a usable version of MilkyWay@Home N-Body Simulation.

Suspending project until fix to prevent masses of comp errors.
ID: 53214 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53222 - Posted: 16 Feb 2012, 15:41:08 UTC - in response to Message 53214.  

Ever since 1.00 update been getting comp errors.

AMD Phenom II x4 965
ATI 4890 x 2 crossfire - CCC driver 11.9
Win 7 64-bit
BOINC 6.12.34 9x64)
Was chugging along fine before then.
All 1.02 openCl_amd_ati are failing at the 1:07 ; 1:08 mark.

Tried that Arkyan file - it broke Milkyway.

2/16/2012 7:29:24 AM | Milkyway@Home | Message from server: Your app_info.xml file doesn't have a usable version of MilkyWay@Home N-Body Simulation.

Suspending project until fix to prevent masses of comp errors.
Is your BOINC data directory on some weird filesystem or a network share or something?
ID: 53222 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Len LE/GE

Send message
Joined: 8 Feb 08
Posts: 261
Credit: 104,050,322
RAC: 0
Message 53250 - Posted: 17 Feb 2012, 22:08:48 UTC

I think the app_info he used is for separation only; so he needs to add a part for nbody to run that too.
ID: 53250 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
weasel473

Send message
Joined: 9 Dec 11
Posts: 5
Credit: 1,121,906
RAC: 0
Message 53259 - Posted: 18 Feb 2012, 12:35:49 UTC - in response to Message 53222.  

Is your BOINC data directory on some weird filesystem or a network share or something?


It's on an external HD FAT32 format.
ID: 53259 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Len LE/GE

Send message
Joined: 8 Feb 08
Posts: 261
Credit: 104,050,322
RAC: 0
Message 53264 - Posted: 18 Feb 2012, 14:15:35 UTC

Looking at the list of your WUs with errors.
2* simulation v1.02
1* nbody v0.84 (mt)

All 3 are showing the same error:
Failed to update checkpoint file ('separation_checkpoint_tmp' to 'separation_checkpoint') (2): No such file or directory

You could switch off checkpointing for separation because of the short runtimes on your gpu, but your problem isn't for separation alone.
It 'smells' like the external disk is the problem.
Can you try and move your BOINC dir to an internal drive?
ID: 53264 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53309 - Posted: 19 Feb 2012, 18:33:22 UTC - in response to Message 53264.  

The checkpoint file update is done using transactions if it's available on the system so that you don't lose a checkpoint in the event of a power failure at the wrong moment or anything like taht.

I remember checking and adding a fallback if the FS didn't support transactions but it looks like it's not there now. I'll readd that I guess but moving it to an NTFS partition would avoid the problem.
ID: 53309 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
[TA]Assimilator1
Avatar

Send message
Joined: 22 Jan 11
Posts: 375
Credit: 64,707,164
RAC: 24
Message 53419 - Posted: 25 Feb 2012, 13:19:23 UTC - in response to Message 53309.  

After a 9mth hiatus I thought I'd give MW a shot again but I'm am also getting every single WU erroring out :(.

Had to update drivers so it's now on Cat 12.1, updated BOINC to 6.12.34 (btw I also tried 7.0.18 but it couldn't detect my GPU!, so went back to v6).

Specs:-
Win XP 32, HD4830, C2Q Q6600, 4GB RAM(3.25 useable), P45 chipset.

This is part of BOINCs log:-

25/02/2012 12:27:18 | | Starting BOINC client version 6.12.34 for windows_intelx86
25/02/2012 12:27:18 | | log flags: file_xfer, sched_ops, task
25/02/2012 12:27:18 | | Libraries: libcurl/7.21.6 OpenSSL/1.0.0d zlib/1.2.5
25/02/2012 12:27:18 | | Data directory: D:\DC\BOINC\Data
25/02/2012 12:27:18 | | Running under account Mark
25/02/2012 12:27:18 | | Processor: 4 GenuineIntel Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz [Family 6 Model 15 Stepping 11]
25/02/2012 12:27:18 | | Processor: 4.00 MB cache
25/02/2012 12:27:18 | | 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 nx lm vmx tm2 pbe
25/02/2012 12:27:18 | | OS: Microsoft Windows XP: Professional x86 Edition, Service Pack 3, (05.01.2600.00)
25/02/2012 12:27:18 | | Memory: 3.25 GB physical, 5.09 GB virtual
25/02/2012 12:27:18 | | Disk: 269.22 GB total, 176.15 GB free
25/02/2012 12:27:18 | | Local time is UTC +0 hours
25/02/2012 12:27:18 | | ATI GPU 0: ATI Radeon HD 4700/4800 (RV740/RV770) (CAL version 1.4.1664, 512MB, 762 GFLOPS peak)
25/02/2012 12:27:18 | | Version change (7.0.18 -> 6.12.34)
25/02/2012 12:27:18 | Milkyway@Home | URL http://milkyway.cs.rpi.edu/milkyway/; Computer ID 405798; resource share 100
25/02/2012 12:27:18 | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID not assigned yet; resource share 100
25/02/2012 12:27:18 | | No general preferences found - using BOINC defaults
25/02/2012 12:27:18 | | Reading preferences override file
25/02/2012 12:27:18 | | Preferences:
25/02/2012 12:27:18 | | max memory usage when active: 1663.49MB
25/02/2012 12:27:18 | | max memory usage when idle: 2994.28MB
25/02/2012 12:27:18 | | max disk usage: 10.00GB
25/02/2012 12:27:18 | | (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
25/02/2012 12:27:18 | | Not using a proxy
25/02/2012 12:27:18 | | Running CPU benchmarks
25/02/2012 12:27:18 | | Suspending computation - CPU benchmarks in progress
25/02/2012 12:27:49 | | Benchmark results:
25/02/2012 12:27:49 | | Number of CPUs: 4
25/02/2012 12:27:49 | | 3044 floating point MIPS (Whetstone) per CPU
25/02/2012 12:27:49 | | 6495 integer MIPS (Dhrystone) per CPU
25/02/2012 12:27:53 | Milkyway@Home | Sending scheduler request: To fetch work.
25/02/2012 12:27:53 | Milkyway@Home | Requesting new tasks for ATI GPU
25/02/2012 12:27:55 | Milkyway@Home | Scheduler request completed: got 0 new tasks
25/02/2012 12:27:55 | Milkyway@Home | No tasks sent
25/02/2012 12:27:55 | Milkyway@Home | Tasks for CPU are available, but your preferences are set to not accept them
25/02/2012 12:28:36 | Milkyway@Home | update requested by user
25/02/2012 12:28:40 | Milkyway@Home | Sending scheduler request: Requested by user.
25/02/2012 12:28:40 | Milkyway@Home | Requesting new tasks for ATI GPU
25/02/2012 12:28:41 | Milkyway@Home | Scheduler request completed: got 0 new tasks
25/02/2012 12:28:41 | Milkyway@Home | Not sending work - last request too recent: 46 sec
25/02/2012 12:35:46 | Milkyway@Home | Sending scheduler request: To fetch work.
25/02/2012 12:35:46 | Milkyway@Home | Requesting new tasks for ATI GPU
25/02/2012 12:35:52 | Milkyway@Home | Scheduler request completed: got 20 new tasks
25/02/2012 12:35:55 | Milkyway@Home | Started download of milkyway_separation_1.02_windows_intelx86__opencl_amd_ati.exe
25/02/2012 12:35:55 | Milkyway@Home | Started download of parameters-82-2s.txt
25/02/2012 12:35:56 | Milkyway@Home | Finished download of parameters-82-2s.txt
25/02/2012 12:35:56 | Milkyway@Home | Started download of single_t82_3_3.txt
25/02/2012 12:35:59 | Milkyway@Home | Finished download of milkyway_separation_1.02_windows_intelx86__opencl_amd_ati.exe
25/02/2012 12:36:00 | Milkyway@Home | Finished download of single_t82_3_3.txt
25/02/2012 12:36:00 | Milkyway@Home | Starting task ps_separation_82_2s_mix3_3_6322195_0 using milkyway version 102
25/02/2012 12:36:02 | Milkyway@Home | Computation for task ps_separation_82_2s_mix3_3_6322195_0 finished
25/02/2012 12:36:02 | Milkyway@Home | Starting task ps_separation_82_2s_mix3_3_6322189_0 using milkyway version 102
25/02/2012 12:36:03 | Milkyway@Home | Computation for task ps_separation_82_2s_mix3_3_6322189_0 finished

**********************************************************************

Any ideas?
ID: 53419 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Matt Arsenault
Volunteer moderator
Project developer
Project tester
Project scientist

Send message
Joined: 8 May 10
Posts: 576
Credit: 15,979,383
RAC: 0
Message 53424 - Posted: 25 Feb 2012, 21:24:37 UTC - in response to Message 53419.  

After a 9mth hiatus I thought I'd give MW a shot again but I'm am also getting every single WU erroring out :(.

Had to update drivers so it's now on Cat 12.1, updated BOINC to 6.12.34 (btw I also tried 7.0.18 but it couldn't detect my GPU!, so went back to v6).
Your driver installation is missing the OpenCL dll. The catalyst installer apparently offers an option to not install it (why I have no idea), but reinstall your drivers without unchecking the install APP SDK option in the custom install part.
ID: 53424 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Previous · 1 · 2 · 3 · Next

Message boards : Number crunching : All work Units giving "Computational Error"

©2024 Astroinformatics Group