Seti@Home optimized science apps and information
Optimized Seti@Home apps => Windows => GPU crunching => Topic started by: Raistmer on 24 Feb 2009, 06:56:31 pm
-
"team" packs (V10 included) became obsolete now. To simplify life for users who can't read whole this thread to stay tuned with latest changes (not too latest already though, BOINC 6.6.20 exists as recommended version more than month already AFAIK) I lock this thread .
All my own support of "teamed" packs now ceased (until I get some example why "teamed" pack should be used instead of BOINC 6.6.20 native GPU scheduling at least)
"teamed" packs were temporary solution and well served their aim during lifespan. But now this period is over.
What should be used instead:
1) BOINC 6.6.20
2) latest CUDA MB build (can be found in this thread and will be posted in new thread devoted optimized CUDA MultiBeam app).
3) appropriate app_info.xml
some examples can be found in this thread: http://setiathome.berkeley.edu/forum_thread.php?id=52589
2) and 3) could be replaced by using Jason's Lunatics installer (currently in beta stage, can be found in beta area of this forum: http://lunatics.kwsn.net/installer-testing/index.0.html )
What should not be used
1) ncpus field in cc_config.xml
2) app_info.xml supplied with obsolete "team" packs.
3) "teamed" modification of AK_v8 (was part of "team" packs).
The key difference from V9 packs is :
The "team" mod now supports multi-GPU configs.
There will be number_of_GPUs file in SETI project directory. By default it contains number of 1.
If you have more GPUs just edit that file (enter number of GPUs installed in host instead of 1 ).
And don't forget to change your cc_config.xml
Now ncpus value required to be NUMBER_OF_LOGICAL_PROCESSORS+NUMBER_OF_GPUs for host.
For example, for Quad with 2 CUDA-enabled GPUs it should be 6
Here is example of minimal cc_config.xml file you need
<cc_config>
<options>
<ncpus>NUMBER_OF_LOGICAL_PROCESSORS+NUMBER_OF_GPUs</ncpus>
</options>
</cc_config>
File should be placed in boinc data directory (the one that contains projects subdirectory).
Currently V10 available only in SSSE3 version, other builds will follow.
When you post to this thread seeking for help, please, don't forget to provide link on your host and description of your config (OS, number of GPU cards, what pack you use, video driver version).
It will wastly decrease number of unneeded questions and save time both for you and anyone who will help you.
Please, don't forget to check ALL STUFF (including these packs) you downloaded from Internet with updated antivirus.
Fixed version posted, please, update your configs.
Thanks mr.kjellen from SETI main forums for bug report.
-
Thanks I downloaded this yesterday! So far no problems. I only have astropulse in my waiting WU's right now. So can't say anything of the GPU crunching.
Also will this optimized client work with any of the new Bonic beta's? I'm still running 6.4.5 waiting on word if I can upgrade it yet.
-
I just registered here (after freeloading on the optimized clients posted here before), and am currently running the V10 package on my Q6600/8800GTX machine, under WinVistax86_Ultimate.
Looks to run ok, 4 process on the Q6600, a fifth called 'MB_6.08_mod_CUDA...' is taking about 5% CPU, and I see one of the 5 units running progressing at about twice the rate of the others (1 is at ~31%, 4 at ~15%).
Is there a way to see from within BOINC manager which WU is running on the GPU? (Besides observing it progresses quicker?)
Regards, Patrick.
-
I checked my system with V10a X64 installed and I have finally received and processed several CUDA jobs now without errors and one did detect and kill a VLAR workunit.
I'd say your V10a x86 and x64 packages are both working as desired.
Thanks Raistmer once again for your excellent work!
-
I only have that in my cc_config
<cc_config>
<log_flags>
</log_flags>
<options>
<dont_contact_ref_site>1</dont_contact_ref_site>
</options>
</cc_config>
<!-- View http://boinc.berkeley.edu/trac/wiki/ClientMessages for full set of
options and some explanations -->
Help me :(
-
I only have that in my cc_config
<cc_config>
<log_flags>
</log_flags>
<options>
<dont_contact_ref_site>1</dont_contact_ref_site>
</options>
</cc_config>
<!-- View http://boinc.berkeley.edu/trac/wiki/ClientMessages for full set of
options and some explanations -->
Help me :(
If you don't understand cc_config structure just replace your with that from first post. And don't forget to replace yellow line with acual number.
-
When you post to this thread seeking for help, please, don't forget to provide link on your host and description of your config (OS, number of GPU cards, what pack you use, video driver version).
It will wastly decrease number of unneeded questions and save time both for you and anyone who will help you.
Hello, Raistmer!
My computer http://setiathome.berkeley.edu/show_host_detail.php?hostid=4632306 works with Win2003 32-bit, Core2Duo, 1 GPU 9600GT, drv 182.06, BM 6.6.11, ncpus=3
I'm doing micromanagement of task queue at Boinc Manager everyday as You supposed at http://lunatics.kwsn.net/gpu-crunching/ak-v8-cuda-mb-team-work-mod.msg13293.html#msg13293 (1 - Suspend all tasks; 2 - resume non-VLAR task; 3 - resume VLAR tasks)
For my 2-core system normal behaviour is 3 copies of AK_... (2 running + 1 idle) and 1 copy of MB_...
Previous team packs worked as described above. But situation changed with new V10a pack! Every suspending of one running task and resuming of other task leads to one more copy of remaining in memory process "AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe".
I.e. if I wants to reassign one CPU-task to VLAR, I'll do suspending all not-running tasks, then suspending one chosen CPU-task, then resuming one VLAR-task. After this I can see in memory already 4 copies of AK_... (2 running, 2 idle) and 1 copy of MB_... Next suspendig/resuming leads to 5 copies of AK_... (2 running + 3 idle) and 1 copy of MB_...
Suspending/resuming of whole SETI@Home project isn't helps to remove useless copies, only BM restarting helps. What am I doing wrong?
P.S. V8 had no such behaviour.
[edit]Such behaviour isn't easily repeatable - i.e. not each reassign leads to remaining copies of AK_... It is sporadically. So far I can't reproduce it[/edit]
-
My computer has been throwing a lot of computation errors since I started using V10a x64. I went from V8 to V10a to get the new AP units. It is a Quad core running Vista 64 bit with driver 181.22 with a single GeForce 8500 GT.
Some of the errors are the VLAR kill, but most of them are not. Here hs a link to a workunit that is throwing the computation error.
http://setiathome.berkeley.edu/result.php?resultid=1173667098
-
When you post to this thread seeking for help, please, don't forget to provide link on your host and des#biption of ur config (OS, number of GPU cards, what pack you use, video driver version).
It will wastly decrease number of unneeded questions and save time both for you and anyone who will help you.
Hello, Raistmer!
My computer http://setiathome.berkeley.edu/show_host_deTAil.php?hostid=4632306 works with Win2003 32-bit, Core2Duo, 1 GPU 9600GT, drv 182.06, BM 6.6.11, ncpus=3
I'm ›ing micromanagement of task queue at Boinc Manager everyday as You supposed at http://lunatics.kwsn.net/gpu-crunching/ak-v8-cuda-mb-team-work-mod.msg13293.html#msg13293 (1 - Suspend all tasks; 2 - resume non-VLAR task; 3 - resume VLAR tasks)
For my 2-core system normal behaviour is 3 copies of AK_... (2 running + 1 idle) and 1 copy of MB_...
Previous team packs worked as described above. But situation changed with new V10a pack! Every suspending of one running task and resuming of other task leads to one more copy of remaining in memory process "AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe".
I.e. if I wants to reassign one CPU-task to VLAR, I'll do suspending all not-running tasks, then suspending one chosen CPU-task, then resuming one VLAR-task. After this I can see in memory already 4 copies of AK_... (2 running, 2 idle) and 1 copy of MB_... Next suspendig/resuming leads to 5 copies of AK_... (2 running + 3 idle) and 1 copy of MB_...
Suspending/resuming of whole SETI@Home project isn't helps to remove useless copies, only BM restarting helps. What am I doing wrong?
P.S. V8 had no such behaviour.
[edit]Such behaviour isn't easily repeatable - i.e. not each reassign leads to remaining copies of AK_... It is sporadically. So far I can't reproduce it[/edit]
Only ones that hold CUDA MB process should behave so.
CUDA MB will reject to stop now reducing probability that BOINC (or user ;) ) making wrong decision and tries to leave GPU idle by running CPU-only apps.
So long as least single SETI MB task running (for single GPU host) SETI MB team can do its GPU scheduling w/o additional help from user.
-
My computer has been throwing a lot of computation errors since I started using V10a x64. I went from V8 to V10a to get the new AP units. It is a Quad core running Vista 64 bit with driver 181.22 with a single GeForce 8500 GT.
Some of the errors are the VLAR kill, but most of them are not. Here is a link to a workunit that is throwing the computation error.
http://setiathome.berkeley.edu/result.php?resultid=1173667098
try to revert to old DLL versions (from older packs or stock).
Lookd like driver/CUDA runtime problem... If with same DLL/driver set stock app doesn't show such errors, report again please.
-
Only ones that hold CUDA MB process should behave so.
CUDA MB will reject to stop now reducing probability that BOINC (or user ;) ) making wrong decision and tries to leave GPU idle by running CPU-only apps.
So long as least single SETI MB task running (for single GPU host) SETI MB team can do its GPU scheduling w/o additional help from user.
Thanks! I understood possible sources of task-remnants during my VLAR-reassign process.
So, V10 already includes ideas from V8 mod like "GPU_watch_update_for_SSSE3.rar" and "No_suspend_on_BOINC_demand.rar".
BTW, Your work here is greatly appreciated!
-
SSE3 x86 and SSE3 x86 AMD-specific packs added.
ADDON:
SSE3 x64 Intel-specific pack added
-
How many cores set in xml for i7 with hyper-threading and one GPU? 5 or 9?
-
Nine
-
My computer has been throwing a lot of computation errors since I started using V10a x64. I went from V8 to V10a to get the new AP units. It is a Quad core running Vista 64 bit with driver 181.22 with a single GeForce 8500 GT.
Some of the errors are the VLAR kill, but most of them are not. Here is a link to a workunit that is throwing the computation error.
http://setiathome.berkeley.edu/result.php?resultid=1173667098
try to revert to old DLL versions (from older packs or stock).
Lookd like driver/CUDA runtime problem... If with same DLL/driver set stock app doesn't show such errors, report again please.
Hi, i get the same error message when running Raistmer's_opt_pack_V10a_x86_SSSE3_MB_CPU_GPU_team on my Dell XPS 1530, Geforce 8600M GT, driver version 179.48 (newest laptop version from nvidia) under Vista Home Premium 32bit.
Example WU: http://setiathome.berkeley.edu/result.php?resultid=1174343986
Tried swapping cufft.dll, cudart.dll and libfftw3f-3-1-1a_upx.dll with included versions from V8 package, but had no luck, same error message.
But i had stock cuda running with no errors: http://setiathome.berkeley.edu/result.php?resultid=1162474169
-
I believe Raistmer's development system requires drivers 180.xx and above, but the stock apps work with 179.xx drivers
-
Bummer, nvidia only offers 179 for laptops. Ok, i will try to install the regular drivers (inf modding as necessary ;D) and test again this evening when my cache is empty.
Thanks for the tip Richard!
-
Am I understanding things correctly about the VLAR in that V10 throws them away?
If that is the case it seems a shame since my system can complete them in about 100 minutes, 4 times as long as non VLAR ones. Again if it is the case would it be possible to make killing them optional?
-
Driver for Notebooks > 179 see http://www.laptopvideo2go.com/
-
I did ssome more tests after i got nvidia drivers 182.06 installed (do not trust the premodded inf files from laptopvideo2go...do it yourself if you have to >:()
I set up a standalone test with the short WU's
Using V10: executing MB_6.08_mod_CUDA_V10.exe works as expected:
Can't open init data file - running in standalone mode
Can't open init data file - running in standalone mode
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : GeForce 8600M GT
totalGlobalMem = 268435456
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 0
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 4
setiathome_CUDA: No device specified, determined to use CUDA device 1: GeForce 8600M GT
SETI@home using CUDA accelerated device GeForce 8600M GT
V10 modification by Raistmer
Priority of worker thread rised successfully
Priority of process adjusted successfully
Affinity of worker thread adjusted successfully
Total GPU memory 268435456 free GPU memory 176422912
setiathome_enhanced 6.02 Visual Studio/Microsoft C++
Build features: CPU-GPU team mod FFTW x86 CPUID: Intel(R) Core(TM)2 Duo CPU T9300 @ 2.50GHz
Cache: L1=64K L2=6144K
CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3
libboinc: 6.1.8
Work Unit Info:
...............
WU true angle range is : 0.604884
Optimal function choices:
-----------------------------------------------------
name
-----------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.00022 0.00000
v_ChirpData 0.12565 0.00000
v_Transpose4 0.00442 0.00000
FPU opt folding 0.00304 0.00000
Flopcounter: 745980599434.345090
Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
Wall-clock time elapsed since last restart: 298.0 seconds
called boinc_finish
But starting the *GPU_CPU_team_V10.exe results in an application error popup from windows, no further output on the commandline, no stderr.txt. eventvwr is not helpful either: Fehlerhafte Anwendung AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe, Version 0.0.0.0, Zeitstempel 0x49a516a3, fehlerhaftes Modul AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe, Version 0.0.0.0, Zeitstempel 0x49a516a3, Ausnahmecode 0xc000000d, Fehleroffset 0x000b2d9e, Prozess-ID 0xbf8, Anwendungsstartzeit 01c998de0f35a5cf. (sorry, german locale...)
So errorcode 0xc000000d is invalid argument, that is all i can read without installing IDApro
Guess i'll try V9 for now, that seems to run without errors in standalone, hopefully it will run under BOINC as well.
Edit::
Driver for Notebooks > 179 see http://www.laptopvideo2go.com/
I could not download any driver: "We have recognized that you are attempting to directly link to our drivers." *BS* i did not filter the referer...i could download the premodded infs, but they did not work with nvidias stock drivers because they reference some files that are not contained in nvidias distribution.
-
Don't know where are the Problem is .. may be the Browser?!? (try to use IE6/7 - i know, IE is not the favorit...)
I'm using the drivers from laptopvideo2go sometimes without any problems, only when playback BlueRay (CopyProteced) WHQL-driver is needed.
-
I've got a problem with my V10a x64 Cuda app, I believe it did it with the V10a x86 app too. Here's an example WU. http://setiathome.berkeley.edu/result.php?resultid=1173510764.
The message I get is this.
<message>
too many exit(0)s
</message>
Any idea on this error? It's not like I'm doing much else on this PC.
-
But starting the *GPU_CPU_team_V10.exe results in an application error popup from windows, no further output on the commandline, no stderr.txt. eventvwr is not helpful either: Fehlerhafte with nvidias stock drivers because they reference some files that are not contained in nvidias distribution.
Did you start it from command line?
Team builds don't support standalone work. The should run only under BOINC and only in SETI@home main project (hard link to particular layout for CUDA MB relatively to working path required).
-
I've got a problem with my V10a x64 Cuda app, I believe it did it with the V10a x86 app too. Here's an example WU. http://setiathome.berkeley.edu/result.php?resultid=1173510764.
The message I get is this.
<message>
too many exit(0)s
</message>
Any idea on this error? It's not like I'm doing much else on this PC.
Build features: Non-graphics CPU-GPU team mod IPP USE_SSSE3 x86
It's x86 build, not x64 one.
Update your config to V10a. V10 had rescheduling bug that could lead to such situation. So update REQUIRED.
-
I've got a problem with my V10a x64 Cuda app, I believe it did it with the V10a x86 app too. Here's an example WU. http://setiathome.berkeley.edu/result.php?resultid=1173510764.
The message I get is this.
<message>
too many exit(0)s
</message>
Any idea on this error? It's not like I'm doing much else on this PC.
Build features: Non-graphics CPU-GPU team mod IPP USE_SSSE3 x86
It's x86 build, not x64 one.
Update your config to V10a. V10 had rescheduling bug that could lead to such situation. So update REQUIRED.
I started using the V10a app as soon as you posted them the other day. And last night I started with the V10a Intel x64 app.
After looking at my completed WU's it shows that for my CPU WU's its x64, and the GPU WU's it's x86.
CPU
http://setiathome.berkeley.edu/result.php?resultid=1173515610
GPU
http://setiathome.berkeley.edu/result.php?resultid=1173515613 (http://setiathome.berkeley.edu/result.php?resultid=1173515613)
Here are the tasks for my computer.
http://setiathome.berkeley.edu/results.php?hostid=4706608
-
Show me x64 result with too many exits.
Result you posted before from V10 pack.
-
SSE3 x64 Intel-specific pack added.
[attachment deleted by admin]
-
Raistmer Thank YOU MAN !!! all working fine :)
using x64 xp pro and q6600 8800gtx all working nice and clear :) thank you ones again for your help
Best Regards
D.Draganov
-
When doing a Q6600 (4 cores and two gpus) should my cconfig say for cpu 6.
Thank you
-
When doing a Q6600 (4 cores and two gpus) should my cconfig say for cpu 6.
Thank you
Since Raistmer's probably asleep I'll answer as best I can. My understanding is 5 (because a GPU doesn't require a whole core). So that 'extra pretend' core should accommodate many GPUs. I hope, before too long, that Boinc handling of this improves to the point that these cc_config workarounds become obsolete though. Personally, deopending on what Boinc version you're running, I'd try it without the entry first, to see what happens, then up it by 1 and observe the effect. My p4 seems to work with v9 out of the box, while my dual core doesn't... go figure!
Jason
-
See first post, it stated as clearly as I could formulate that.
Here I better describe why it should be so.
In team mod BOINC doesn't know at all that some of apps it controls using GPU/CUDA.
It manages all applications as CPU ones. That is, it will run only ncpus copies of AK_v8 for example. But you need to take all cores and all GPUs busy, that's why you need number of started by BOINC apps to be NUMBER_OF_CORES + NUMBER_OF_GPUs in V10 packs.
-
So.... not advised to run with current Astropulse only work climate then, lest you get NumGPUs over subscription... right?
-
I just tried to install V10a x64 build on my XP x64 but it did not work.
I alway get a computation error.
Here is what I did:
Installed Boinc 6.4.5
Let Boinc fetch standard app + WUs
stop Boinc Service
place the files from the V10 Package in the Project directory and setup the cc_config.xml for 5 (4CPU + 1 GPU) and placed it in the main Boinc "user" directory.
start Boinc service
Both APPs Astro+Seti produce only computation errors all the time but I don´t know why.
Any idea what might cause the error?
The stock version runs without errors.
My system specs:
Intel Q9550 CPU
1x Nvidia GTX280 with 182.06
8 GB DDR-2 Ecc Ram
Windows XP x64 SP2
Boinc 6.4.5 service installation
-
It might be easier if you told us what the error messages actually said.
The strong, silent type ;D There's a Kashra at SETI who runs host 4493623 (http://setiathome.berkeley.edu/show_host_detail.php?hostid=4493623) - Q9450 and GTX280.
The error message (consistently) is
"Es gibt keine untergeordneten Prozesse, auf die gewartet werden muss. (0x80) - exit code 128 (0x80)"
-
"Es gibt keine untergeordneten Prozesse, auf die gewartet werden muss. (0x80) - exit code 128 (0x80)"
awww, without knowing what that is saying, it still 'sounds' rather coarse. [Hopefully Urs or Crunch3r might rock up, and make more sense of it]
-
Google thinks "There are no child processes to wait to be".
-
How about "Could not start Child Process?" . Maybe there is some executable from the package that was not put in the project folder?
-
I finally figured it out now.
The problem seems to be the protected mode installation of Boinc (Boinc runs as service).
After reconfiguring Boinc not to run in protected mode the V10 App runs just fine. I know protected mode will not work with Vista, but xp 64 should do fine - but it does not at least with V10.
I wonder why it works with the stock version in protected mode but not with V10.
Thanks for getting back to me this fast. :) The error message on the stats site "Could not start Child Process" was the clue.
-
Ahhh, The Old "Cuda does not like Boinc as Service/Protected Application in Vista" trick eh?(Maybe applies to x64?) Will remember that for the next customer!. Thanks for checking in and persevering :D
-
Thank you for the new release, it is working great on my system.
I have one complaint thou. Throwing out the VLAR WU... It is a shame, I was just looking to the Boinc client and I saw 12 of them beeing rejected one after another. I don't think it is fair to the other wingman.
Is there a way that this can be solved without autokill? Like force them to the CPU instead of GPU? What happens if there are not killed - under V10 app?
-
Google was close on this one - should be :
"There are no child processes to wait for". ;)
-
LoL, Thanks Urs' I have no Children yet either :(
-
Just found this (possible/temporary) solution in this forum post (http://qah.uni-muenster.de/forum_thread.php?id=161&nowrap=true#1243).
Short : Try that GLtest (http://freewebs.com/mannymax/cpp/GLtest.html) does NOT run. If that is the case, add the file MSCorEE.dll into the (windows)\\system32 directory.
Anyone feels to try out this ? Seems that this is a pure BOINC problem.
edit: ooppsee : "There are no subprocesses to wait for". Does it make sense now.
-
...does NOT run. If that is the case, add the file MSCorEE.dll into the (windows)\\system32 directory.
...
This would make perfect sense to me if so (can't test it though, currently no active Vista or x64 install), It means that either nVidia or Boinc failed to distribute the correct dependencies within their respective installers (either or both, depending on how you look at it)
[Edit: Incidentally, GLTest.exe runs fine on my Windows XP w/SP3 + eVGA 9600GSO, nVidia Driver version 181.22 ]
-
My computer has been throwing a lot of computation errors since I started using V10a x64. I went from V8 to V10a to get the new AP units. It is a Quad core running Vista 64 bit with driver 181.22 with a single GeForce 8500 GT.
Some of the errors are the VLAR kill, but most of them are not. Here is a link to a workunit that is throwing the computation error.
http://setiathome.berkeley.edu/result.php?resultid=1173667098
try to revert to old DLL versions (from older packs or stock).
Lookd like driver/CUDA runtime problem... If with same DLL/driver set stock app doesn't show such errors, report again please.
Well, everything looked to run OK with the older dll files. Redownloaded the dlls for V10 and it looks like some go through ok while others fail. Here are links to the wu's.
http://setiathome.berkeley.edu/result.php?resultid=1174424840 completed successfully
http://setiathome.berkeley.edu/result.php?resultid=1174852750 computation error
I've just installed the latest drivers from Nvidia 182.06 and will see how that works out.
-
sorry for that i said but most of the people don't know how to install the applications that is why they don't work
PS: Thanks Raistmer for the mod :)
-
So.... not advised to run with current Astropulse only work climate then, lest you get NumGPUs over subscription... right?
Anything else than SETI MB could result in overloaded CPU and idle GPU if leaved w/o user intervention. Lack of BOINC ability for project pairing make it impossible to be sure at least one task allocated for SETI MB and CPU->GPU rescheduling is possible only inside teamed SETI MB programs.
-
So.... not advised to run with current Astropulse only work climate then, lest you get NumGPUs over subscription... right?
Anything else than SETI MB could result in overloaded CPU and idle GPU if leaved w/o user intervention. Lack of BOINC ability for project pairing make it impossible to be sure at least one task allocated for SETI MB and CPU->GPU rescheduling is possible only inside teamed SETI MB programs.
Cheers for confirming that for me.
-
Thank you for the new release, it is working great on my system.
I have one complaint thou. Throwing out the VLAR WU... It is a shame, I was just looking to the Boinc client and I saw 12 of them beeing rejected one after another. I don't think it is fair to the other wingman.
Is there a way that this can be solved without autokill? Like force them to the CPU instead of GPU? What happens if there are not killed - under V10 app?
It much more fair to send VLAR for CPU processing than leave it to CUDA processing cause CPU will do it faster while CUDA will spend exessive time. All should do its own work. Topic was discussed already.
CPU rescheduling maybe possible but seems complicated in current conditions (especially because VLARs come in packs - how will you keep GPU busy and CPU not overloaded too much in this situation?
IF someone wanna fiddle with it I can provide sources of my mods for start.
-
About "child processes" issue:
Most probably it means that modded AK_v8b was unable to start CUDA_MB app. So it can't wait finish of non-started process hence it exited with that message.
Why it can't run CUDA app - there are many possibilities - one of them - access rights issue.
-
My WU's are going very slllooowwww. They take days like this and I haven't seen any CUDA or AK WU's forever. Any ideas?
(http://img178.imageshack.us/img178/7070/boinc.png)
-
Will the GPU_CPU combo team work on Vista with mutliple profiles running? It seems that whenever I load up my profile and than while my profile is running with BOINC in the background I switch to another profile, the CUDA app freezes and stops running. I wasn't really sure what was happening, but with V8 of the mod, BOINC would just error out saying it couldn't detect the GPU anymore. Now with V10 every single WU crashes with a Compute error.
Here's a V10 error : which only happens when BOINC is running on a simultaneous account running in the background
http://setiathome.berkeley.edu/result.php?resultid=1174143079
<core_client_version>6.4.5</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
setiathome_CUDA: Found 1 CUDA device(s):
Cuda error 'cudaGetDeviceProperties( &cDevProp, i )' in file 'd:/BTR/SETI6/SETI_MB_CUDA/client/cuda/cudaAcceleration.cu' in line 135 : initialization error.
</stderr_txt>
]]>
Here's when I was running V8a
http://setiathome.berkeley.edu/result.php?resultid=1171300146
<core_client_version>6.4.5</core_client_version>
<![CDATA[
<stderr_txt>
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : Device Emulation (CPU)
totalGlobalMem = -1
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 1
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1350000
totalConstMem = 65536
major = 9999
minor = 9999
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 16
setiathome_CUDA: device 1 is emulation device and should not be used, supports 9999.9999
setiathome_CUDA: No SETI@home capabale CUDA GPU found...
SETI@home NOT using CUDA, falling back on host CPU processing
setiathome_enhanced 6.02 Visual Studio/Microsoft C++
libboinc: 6.1.8
I'm making an assumption that CUDA does not work when you have multiple profiles logged in to the computer? Has anyone else tried this.
I first started to notice my problem when and I posted here (http://lunatics.kwsn.net/gpu-crunching/ak-v8-cuda-mb-team-work-mod.msg13896.html#msg13896) . I just only realized now after installing V10 that the mutilple users may be the reason.
Thanks
Vager
-
Probably only active user profile can interact with GPU.
-
Probably only active user profile can interact with GPU.
How about if I install the program in Protected mode? Will this allow BOINC to run while there is no one logged in and still use the GPU with CUDA?
-V
-
Probably only active user profile can interact with GPU.
How about if I install the program in Protected mode? Will this allow BOINC to run while there is no one logged in and still use the GPU with CUDA?
-V
No.
-
They take days like this and I haven't seen any CUDA or AK WU's forever. Any ideas?
Dude, how are you doing that? I have in average one AP 5.00 every couple of days and I still have to see one AP5.03. Maybe because I do not run the beta and you do?
-
Intell the multiple gpu+cpu SSE3 Intel V10. My system Q6600+8800+9800 Nvidia. Really suffering barely gets any work done. Everytime I click on the Boinc takes a while connecting to Boinc.
Thank you
-
i'm running boinc 6.6.11 and V10a and can't get any of the AP units to run on the gpu. right now all i have is AP work units and am running 9 AP app simultaneously. this has been reproduced on my other four computers with gpu's.
The GPU temp is low and task manager says everything is running on the cpu as i do not see any cuda executable running in task manager.
all i see is nine occurrences of "ap_5.03r112_sse3.exe*32" running in task manager.
-
i'm running boinc 6.6.11 and V10a and can't get any of the AP units to run on the gpu. right now all i have is AP work units and am running 9 MB app simultaneously. this has been reproduced on my other four computers with gpu's.
The GPU temp is low and task manager says everything is running on the cpu as i do not see any cuda executable running in task manager.
all i see is six occurrences of "ap_5.03r112_sse3.exe*32"
No AP Gpu app yet.
There are other factors that may be stopping MB work download if you're using a development version of Boinc:
http://lunatics.kwsn.net/5-windows/problem-downloading-seti-enhanced-astropulse-ok.msg15030.html#msg15030
http://lunatics.kwsn.net/gpu-crunching/v10-of-modified-seti-mb-cuda-opt-ap-package-for-full-multi-gpucpu-use.msg15002.html#msg15002
[Edit: As mentioned on main "Work fetch for app_info type installations seems not too happy at the moment either. (reverting to 6.5.0 fixed it for me)"]
-
My Boinc keeps on getting stuck on communicating with client.
Thank you
-
My Boinc keeps on getting stuck on communicating with client.
Thank you
Hmm, not sure what would cause that. That might be a better question for on NumberCrunching forum. (Unless anyone else around here has some better ideas? )
-
About all work get problems.
It's BOINC issues. Science apps don't request work at all, they just process tasks BOINC give to them.
So these problems are not the topic of this thread. Much better to report them on BOINC own forum.
But doing this don't forget that if there is no work for particular app (AP or MB) at this moment then no BOINC version could get work in that case.
-
Version of CUDA MB w/o affinity lock mod attached here.
[attachment deleted by admin]
-
Version of CUDA MB w/o affinity lock mod attached here.
Call me dumb but what does this do?
-
Version of CUDA MB w/o affinity lock mod attached here.
Call me dumb but what does this do?
It's replacement for CUDA MB part of V10a packs. Intended to improve performance on multy-GPU hosts. As was shown on main site current builds stops (all) when one of CUDA apps loads its new task. If you have only single GPU board you don't need this upgrade at all.
-
Sweet thanks again for the prompt response.
Guess I'll start using that file then!
-
On my AMD 3400+ 8800GT is there any way to get only the gpu to do work, the is useless. This seems really slow for cuda.
Thank you
-
Theres a file inside the seti.at.home folder where all the files go that says number of gpus, that the purpose of this file. Do I put two in it, or do I just change my cc file.
Thank you
-
Theres a file inside the seti.at.home folder where all the files go that says number of gpus, that the purpose of this file. Do I put two in it, or do I just change my cc file.
Thank you
May I ask one question in return? ;)
Do anyone ever read first page where all instructions listed ? ;D
if file says number of GPUs I would guess that the number in this file should be consistent with number of GPUs installed (if first page with instructions doesn't clearly say something else).
Sorry for sarcasm but.... ;D
this file needed for team to work correctly in multi-GPU config.
cc_config.xml needed by BOINC to cheat it. Pretty different purposes.
-
May I ask one question in return? ;)
Do anyone ever read first page where all instructions listed ? ;D
Gecko_R7 and I recently had a PM discussion about this. The answer is no.
-
On my AMD 3400+ 8800GT is there any way to get only the gpu to do work, the is useless. This seems really slow for cuda.
Thank you
Dont's say that AMD 3400+ is useless. I can die from heart explode thinking about 2 my Athlons XP and two AMD 64 3200+ :P :P :P :P
-
May I ask one question in return? ;)
Do anyone ever read first page where all instructions listed ? ;D
Gecko_R7 and I recently had a PM discussion about this. The answer is no.
I see ;D ;D ;D
-
Only issue I'm having is I'm only getting AP work. Not sure why, could be due to version of Boinc. I do see this in Boinc's Seti properties.
[attachment deleted by admin]
-
Please see thread at:
http://lunatics.kwsn.net/5-windows/problem-downloading-seti-enhanced-astropulse-ok.msg15043.html;topicseen#msg15043
and on Number crunching the is some similar thread. It's a Boinc problem.
Jason
-
The topic or board you are looking for appears to be either missing or off limits to you.
-
Sorry, my mistake, that's development area... here's a link on main:
http://setiathome.berkeley.edu/forum_thread.php?id=52306
, Long story short, development version may not work as expected, going back to 6.5.0 (even though still a development version) worked for me.
Jason
-
I am using the multi gpu package, and it seems on my Q6600 and 9800+8800 the seti does work only the cpu works mostly. Or really slow cuda. My results are really bad. On the Amd 3400+ + 8800 results are bad too.
Thank you
-
6.5.0 still only nabs AP for me, I guess tomorrow I'll try 6.4.5. Only way I can pick up a MB unit is to remove AP from app_info.xml. I removed AP, got a bunch of MB units. I then put AP back in, and it would only picked up AP units after that. (Q9550 + 8800GTS, so I go through MB very fast).
-
Yeah, it's still fiddly. Website prefs set to MB only, and 6.5.0 works for me without messing with the app_info. With the wacky behaviour I'm not surprised if it doesn't work right, or the same, for others though.
-
i use 6.5.0 too no problem at all
-
Just installed V10a X64 SSE3. I get a "can't load library cudart.dll" message and no GPU processing. Also, after inserting the cc_config file, bionc tries to run 3 threads off my 2 cores instead of using the GPU.
Using vista X64, GTX260/216 with driver 182.06 and BIONC 6.4.5X64.
If I use the BIONC 6.4.5 X86 version, cuda loads properly, but with this new V10a, I seem to only pull down .wu's so I have no idea if the GPU is going to run right.
computer link: http://setiathome.berkeley.edu/hosts_user.php?userid=9033226
-
Just installed V10a X64 SSE3. I get a "can't load library cudart.dll" message and no GPU processing. Also, after inserting the cc_config file, bionc tries to run 3 threads off my 2 cores instead of using the GPU.
Using vista X64, GTX260/216 with driver 182.06 and BIONC 6.4.5X64.
If I use the BIONC 6.4.5 X86 version, cuda loads properly, but with this new V10a, I seem to only pull down .wu's so I have no idea if the GPU is going to run right.
computer link: http://setiathome.berkeley.edu/hosts_user.php?userid=9033226
checjk if you have cudart.dll in seti project directory.
-
My 3400+ + 8800GT is barely getting 2000 per day. My Q6600+9800+8800 Barely gets 4000 a day. Seems like only cpu is working. I set the cc on 3400 to 2, and the Q6600 to 6. Running the amd and intel version of V10, GPU+CPU team work. I think the cpu is slowling down the GPU. Or am i doing something wrong. My other Q6600 with no GPU at all gets me 6000+ results per day.
Thank you
-
My 3400+ + 8800GT is barely getting 2000 per day. My Q6600+9800+8800 Barely gets 4000 a day. Seems like only cpu is working. I set the cc on 3400 to 2, and the Q6600 to 6. Running the amd and intel version of V10, GPU+CPU team work. I think the cpu is slowling down the GPU. Or am i doing something wrong. My other Q6600 with no GPU at all gets me 6000+ results per day.
Thank you
renew links on hosts under question, I wanna look if they do CUDA MB tasks or not.
-
Will the GPU_CPU combo team work on Vista with mutliple profiles running? It seems that whenever I load up my profile and than while my profile is running with BOINC in the background I switch to another profile, the CUDA app freezes and stops running. I wasn't really sure what was happening, but with V8 of the mod, BOINC would just error out saying it couldn't detect the GPU anymore. Now with V10 every single WU crashes with a Compute error.
Here's a V10 error : which only happens when BOINC is running on a simultaneous account running in the background
http://setiathome.berkeley.edu/result.php?resultid=1174143079
...
Here's when I was running V8a
http://setiathome.berkeley.edu/result.php?resultid=1171300146
...
I'm making an assumption that CUDA does not work when you have multiple profiles logged in to the computer? Has anyone else tried this.
I first started to notice my problem when and I posted here (http://lunatics.kwsn.net/gpu-crunching/ak-v8-cuda-mb-team-work-mod.msg13896.html#msg13896) . I just only realized now after installing V10 that the mutilple users may be the reason.
Thanks
Vager
Hi Vager and Raistmer,
Unfortunately I can confirm this... I am using remote desktop sessions at work and home to access differnt clients and saw the same "initialization errors" like this:
XP 64, English: http://setiathome.berkeley.edu/result.php?resultid=1176701007
XP 32, German: http://setiathome.berkeley.edu/result.php?resultid=1176884903
So on different machines running Windows XP 32 and 64bit. Same with protected and non protected install... Same with V9 and V10... Same with Nvidia driver 180.xx, 181.xx and 182.xx... Same with English and German localized OS + drivers... So I decided downgrading to V8 and everthing ran as it should.
Reading your post made me login via remote desktop again, installing V10, generating some errors and... moving after this to the machine *uff*, I logged in without using the remote desktop session after restarting the OS and guess what... No errors till now.
XP 32, German: http://setiathome.berkeley.edu/result.php?resultid=1176899513
However, will try to use the stock apps for testing and report back as I am lazy and like the remote desktop thingy. ::)
Thanks for your post Vager, helped a lot, thought I am to stupid to install V10. :-\ And of cause Raistmer for your work and interest. :)
Cheers,
yodi
edit: Added some results.
-
ok I closed out of boinc copied the files in the Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team.rar file into the seti boinc folder and created the cc_config.xml file when i restarted boinc every WU failed except the ap WU then when boinc connected it didnt download any enhanced seti WU but it downloaded ap Wu's now i am crunching 3 Ap Wu's. what do i need to do to get crunching seti enhanced wu's again?
-
Just installed V10a X64 SSE3. I get a "can't load library cudart.dll" message and no GPU processing. Also, after inserting the cc_config file, bionc tries to run 3 threads off my 2 cores instead of using the GPU.
Using vista X64, GTX260/216 with driver 182.06 and BIONC 6.4.5X64.
If I use the BIONC 6.4.5 X86 version, cuda loads properly, but with this new V10a, I seem to only pull down .wu's so I have no idea if the GPU is going to run right.
computer link: http://setiathome.berkeley.edu/hosts_user.php?userid=9033226
checjk if you have cudart.dll in seti project directory.
cudart.dll installs to the priogramfilesx86\bionc folder. do you mean the data directory projects folder?
-
It seems to me my GPU is doing some work, really fast to complete aprox 2-10mins. CPU takes alot longer 45mins-130mins. It then seems the gpu waits for the cpu to complete its work in order to go on with more work. Is there any way to get only the GPU to work on V10.
Thank you
-
Here are some stats. You can see my Q6600 with no GPU (seti ssse3 optimized) is doing alot better then my V10 Q6600 with 9800 + 8800 GPU.
Thank you
[attachment deleted by admin]
-
I've made a crude sum from the charts you've posted from 2009-2-11 and onwards and they are about the same (~85000).
-
On the day where the graph is the allway up, its because seti was down it added all my credit from the past few days.
Thank you
-
You can see my Q6600 with no GPU (seti ssse3 optimized) is doing alot better then my V10 Q6600 with 9800 + 8800 GPU.
Check your pending credit. I currently have 38,229.95 pending credit, and that's with me not really crunching for the last week. Most likely your past couple weeks haven't been fully credited yet, so you can't compare them.
-
Unfortunately I can confirm this... I am using remote desktop sessions at work and home to access differnt clients and saw the same "initialization errors" like this:
It's known limitation of CUDA - see CUDA FAQ. It will not with remote desktop, but will work with VNC though.
-
ok I closed out of boinc copied the files in the Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team.rar file into the seti boinc folder and created the cc_config.xml file when i restarted boinc every WU failed except the ap WU then when boinc connected it didnt download any enhanced seti WU but it downloaded ap Wu's now i am crunching 3 Ap Wu's. what do i need to do to get crunching seti enhanced wu's again?
Maybe to read first post and follow its recommendations ? ;)
-
Just installed V10a X64 SSE3. I get a "can't load library cudart.dll" message and no GPU processing. Also, after inserting the cc_config file, bionc tries to run 3 threads off my 2 cores instead of using the GPU.
Using vista X64, GTX260/216 with driver 182.06 and BIONC 6.4.5X64.
If I use the BIONC 6.4.5 X86 version, cuda loads properly, but with this new V10a, I seem to only pull down .wu's so I have no idea if the GPU is going to run right.
computer link: http://setiathome.berkeley.edu/hosts_user.php?userid=9033226
checjk if you have cudart.dll in seti project directory.
cudart.dll installs to the priogramfilesx86\bionc folder. do you mean the data directory projects folder?
I mean that ALL files inside pack archive should be placed together in seti@home project folder.
Any other experimentation up to you :)
-
ok I closed out of boinc copied the files in the Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team.rar file into the seti boinc folder and created the cc_config.xml file when i restarted boinc every WU failed except the ap WU then when boinc connected it didnt download any enhanced seti WU but it downloaded ap Wu's now i am crunching 3 Ap Wu's. what do i need to do to get crunching seti enhanced wu's again?
Maybe to read first post and follow its recommendations ? ;)
well i assumed that if you read my post that you would know i had 2 cores plus 1 gpu hence the "crunching 3 Ap Wu's" stated in the original post but your right i did forget the link to my host so here it is ... http://setiathome.berkeley.edu/show_host_detail.php?hostid=4773686
-
Well this would help (from the first page of this thread):
When you post to this thread seeking for help, please, don't forget to provide link on your host and description of your config (OS, number of GPU cards, what pack you use, video driver version).
It will wastly decrease number of unneeded questions and save time both for you and anyone who will help you.
Well, the link gives us your OS & GPU Card, and the pack should be V10 of modified SETI MB CUDA + opt AP package?, just leaves the most important item: the Driver Version?
Claggy
-
I just registered here (after freeloading on the optimized clients posted here before), and am currently running the V10 package on my Q6600/8800GTX machine, under WinVistax86_Ultimate.
Looks to run ok, 4 process on the Q6600, a fifth called 'MB_6.08_mod_CUDA...' is taking about 5% CPU, and I see one of the 5 units running progressing at about twice the rate of the others (1 is at ~31%, 4 at ~15%).
Is there a way to see from within BOINC manager which WU is running on the GPU? (Besides observing it progresses quicker?)
Regards, Patrick.
I'd still be interested in an answer to the question I posed above; I have the idea the whole V10a package is running fine on my Vistax64 config, but I would appreciate a somewhat more detailed insight into what WUs are, at what moment, running on one of the main CPU cores, and which WU is running on the GPU...
Regards, Patrick.
-
ok I closed out of boinc copied the files in the Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team.rar file into the seti boinc folder and created the cc_config.xml file when i restarted boinc every WU failed except the ap WU then when boinc connected it didnt download any enhanced seti WU but it downloaded ap Wu's now i am crunching 3 Ap Wu's. what do i need to do to get crunching seti enhanced wu's again?
Maybe to read first post and follow its recommendations ? ;)
well i assumed that if you read my post that you would know i had 2 cores plus 1 gpu hence the "crunching 3 Ap Wu's" stated in the original post but your right i did forget the link to my host so here it is ... http://setiathome.berkeley.edu/show_host_detail.php?hostid=4773686
Ok, but time lost, now we have "under maintenance state" will take a look after.
-
I just registered here (after freeloading on the optimized clients posted here before), and am currently running the V10 package on my Q6600/8800GTX machine, under WinVistax86_Ultimate.
Looks to run ok, 4 process on the Q6600, a fifth called 'MB_6.08_mod_CUDA...' is taking about 5% CPU, and I see one of the 5 units running progressing at about twice the rate of the others (1 is at ~31%, 4 at ~15%).
Is there a way to see from within BOINC manager which WU is running on the GPU? (Besides observing it progresses quicker?)
Regards, Patrick.
I'd still be interested in an answer to the question I posed above; I have the idea the whole V10a package is running fine on my Vistax64 config, but I would appreciate a somewhat more detailed insight into what WUs are, at what moment, running on one of the main CPU cores, and which WU is running on the GPU...
Regards, Patrick.
Well, explore your BOINC ;)
Especially - look into slots folders. There you will find what task crunched by whom, what current task progress state and so on if you curious in that.
-
Well, explore your BOINC ;)
Especially - look into slots folders. There you will find what task crunched by whom, what current task progress state and so on if you curious in that.
OK, that works, although a lot more cryptic than I'd hoped. ;)
I don't know BOINC very well, so forgive me asking on a bit: there is no way for a BOINC client process (i.e. the regular setiboinc ... and the Seti-MB-CUDA variant) to influence what is displayed in the BOINC Manager 'Tasks'-overview list (and I mean the fields Application or Status?)
Regards, Patrick.
-
Well, explore your BOINC ;)
Especially - look into slots folders. There you will find what task crunched by whom, what current task progress state and so on if you curious in that.
OK, that works, although a lot more cryptic than I'd hoped. ;)
I don't know BOINC very well, so forgive me asking on a bit: there is no way for a BOINC client process (i.e. the regular setiboinc ... and the Seti-MB-CUDA variant) to influence what is displayed in the BOINC Manager 'Tasks'-overview list (and I mean the fields Application or Status?)
Regards, Patrick.
No way.
If you search easier ways - use stock or kick BOINC devs to fix BOINC itself ;)
-
ok I closed out of boinc copied the files in the Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team.rar file into the seti boinc folder and created the cc_config.xml file when i restarted boinc every WU failed except the ap WU then when boinc connected it didnt download any enhanced seti WU but it downloaded ap Wu's now i am crunching 3 Ap Wu's. what do i need to do to get crunching seti enhanced wu's again?
Maybe to read first post and follow its recommendations ? ;)
well i assumed that if you read my post that you would know i had 2 cores plus 1 gpu hence the "crunching 3 Ap Wu's" stated in the original post but your right i did forget the link to my host so here it is ... http://setiathome.berkeley.edu/show_host_detail.php?hostid=4773686
Ok, but time lost, now we have "under maintenance state" will take a look after.
setiathome_CUDA: Found 1 CUDA device(s):
Cuda error 'cudaGetDeviceProperties( &cDevProp, i )' in file 'd:/BTR/SETI6/SETI_MB_CUDA/client/cuda/cudaAcceleration.cu' in line 135 : invalid argument.
SO CUDA can't even detect what GPUs your host has. Check if all required DLLs installed, check driver version (at least 180.20 required) and be sure you don't use service (protected) BOINC installation.
-
Unfortunately I can confirm this... I am using remote desktop sessions at work and home to access differnt clients and saw the same "initialization errors" like this:
It's known limitation of CUDA - see CUDA FAQ. It will not with remote desktop, but will work with VNC though.
Hello Raistmer,
Thanks for your hint, hard to find the CUDA 2.1 FAQ at http://forums.nvidia.com/index.php?showtopic=84440. ;)
I do not want to start a dispute here wasting your time, in case you're interested - just some thoughts:
1. The Nvidia FAQ states CUDA is not working with remote desktop - in fact it worked with v8.
2. The Seti CUDA FAQ (http://setiathome.berkeley.edu/cuda_faq.php) states it will not run with the protected install, in fact it does - at least under XP.
So I guess not all the information in those FAQ's are up to date.
If you're interested I can test the stock apps if it's working in general or not. ;) Already installed the stock apps on one system today to see if it's running without a remote desktop connection and would test it with remote desktop tomorrow.
Will have a look on TightVNC for sure, used that before switching to remote desktop sessions some years ago - so it's not a big thing and should work as VNC does not login as 'second' user on the PC (looks like that may be the real root cause as mentioned by Vager before).
Thanks again + cheers,
yodi
-
Hello
Here is a link of my Q6600 with no CUDA only 4 cores, running optimized sss3 clients.
http://stats.free-dc.org/stats.php?page=hostbycpid&cpid=ff50ecddd761032e2f58f60bfe3ba7cb
Look how well it does.
Here is a link to my Q6600 with 9800+8800 V10 Multi GPU + CPU SSSE3 team
http://stats.free-dc.org/stats.php?page=hostbycpid&cpid=c4231145f02b77aa55256fbefc80b63a
And Finally my Amd3400+ 8800 V9 GPU+CPU AMD SSE3 Team
http://stats.free-dc.org/stats.php?page=hostbycpid&cpid=e786f5ec1dfe91bb54beddb9dfc27893
The CUDA systems barely do any work. Seems like only the cpus is working and the GPU lacks behind. Does 2-3 or three results then the rest is done by the cpu. In other order words I dont think seti is sending much cuda work.
Thank you
-
ok I closed out of boinc copied the files in the Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team.rar file into the seti boinc folder and created the cc_config.xml file when i restarted boinc every WU failed except the ap WU then when boinc connected it didnt download any enhanced seti WU but it downloaded ap Wu's now i am crunching 3 Ap Wu's. what do i need to do to get crunching seti enhanced wu's again?
Maybe to read first post and follow its recommendations ? ;)
well i assumed that if you read my post that you would know i had 2 cores plus 1 gpu hence the "crunching 3 Ap Wu's" stated in the original post but your right i did forget the link to my host so here it is ... http://setiathome.berkeley.edu/show_host_detail.php?hostid=4773686
Ok, but time lost, now we have "under maintenance state" will take a look after.
setiathome_CUDA: Found 1 CUDA device(s):
Cuda error 'cudaGetDeviceProperties( &cDevProp, i )' in file 'd:/BTR/SETI6/SETI_MB_CUDA/client/cuda/cudaAcceleration.cu' in line 135 : invalid argument.
SO CUDA can't even detect what GPUs your host has. Check if all required DLLs installed, check driver version (at least 180.20 required) and be sure you don't use service (protected) BOINC installation.
as for the service protected install dont remember if i did or didnt but i know i was processing seti using cuda before the install of the optimized app. will check to make sure of the video driver version i think its the latest one out there dated feb 09 but i'll look again.
ok i had 179.xx installed. now i have 180.20 installed. now how do i go about getting wu's other then astropulse running. here is what my cc_config.xml file contains in case something there is a problem.
<cc_config>
<options>
<ncpus>3</ncpus>
</options>
</cc_config>
-
1) http://setiathome.berkeley.edu/show_host_detail.php?hostid=4820762
V9 pack used, all work.
2) http://setiathome.berkeley.edu/results.php?hostid=4737399&offset=1160&show_names=0
Too big cache, tired to find completed results :P
V9 pack used, all work.
3) http://setiathome.berkeley.edu/results.php?hostid=4675326&offset=20&show_names=0
Host config broken.
<core_client_version>6.6.11</core_client_version>
<![CDATA[
<message>
CreateProcess() failed - Access is denied. (0x5)
</message>
]]>
Why do you use DEVELOPMENT BOINC version? Do you member of BOINC beta tester group or BOINC developer to use it?
Or do you one of guys who like to create problems on plain place?
If you going to use advanced stuff be prepared to handle consequencies, otherwise even don't touch it!
It like shoot yourself in the leg. I write it here in forum and not in PM couse it touches ALL users who do the same things with their hosts.
BOINC development versions have many already known problems with scheduling and work fetch and probably some of still unknown ones. And when you (all of you!) try to use them for production work you doing something not good definitely. And then you come to seti app devs with BOINC problems :-X
For this particular host error is clearly designated: CreateProcess() failed - Access is denied. (0x5)
Check why one app can't access to another app on your host. Begin with security rights assignment policy.
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
-
If you're interested I can test the stock apps if it's working in general or not. ;) Already installed the stock apps on one system today to see if it's running without a remote desktop connection and would test it with remote desktop tomorrow.
jFYI, the stock apps are working fine logged in via remote desktop. :-\
http://setiathome.berkeley.edu/result.php?resultid=1177433675
-
My GTX 260 is been sitting there for three days now. I complety removed Boinc and reinstalled it.
Thank you
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
-
If you're interested I can test the stock apps if it's working in general or not. ;) Already installed the stock apps on one system today to see if it's running without a remote desktop connection and would test it with remote desktop tomorrow.
jFYI, the stock apps are working fine logged in via remote desktop. :-\
http://setiathome.berkeley.edu/result.php?resultid=1177433675
The single difference between my build and stock one that can influence of CUDA app startup is CUDA version used at compile time. I use CUDA 2.1, stock version - probably 2.0.
So, different driver versions are required to run. Check if you have 180.20 and up installed. There should be no difference in remote desktop related behavior.
Try to describe your test case in details so I could reproduce it on my hosts.
-
My GTX 260 is been sitting there for three days now. I complety removed Boinc and reinstalled it.
Thank you
1) Install BOINC 6.4.5 as proven to work. I will not even try to explore situations with higher BOINC versions - they are KNOWN to have bugs (maybe 6.5.0 is OK, I don't know, I personally know that 6.4.5 is OK for V10 configs).
2) Install V10a pack. Check that number_of_gpus and cc_config.xml are edited to reflect your number of CUDA-enabled GPUs and number of cores + number of GPUs respectively.
3) Start BOINC.
If it will not work, then probably screenshots will be required.
-
My nvidia GTX 295 seems to run only on 1 core. Sometimes even this core stops. :(
System: Q9450 @ 3,4 (water), geforce GTX 295.
HSchmirPo
-
If you're interested I can test the stock apps if it's working in general or not. ;) Already installed the stock apps on one system today to see if it's running without a remote desktop connection and would test it with remote desktop tomorrow.
jFYI, the stock apps are working fine logged in via remote desktop. :-\
http://setiathome.berkeley.edu/result.php?resultid=1177433675
The single difference between my build and stock one that can influence of CUDA app startup is CUDA version used at compile time. I use CUDA 2.1, stock version - probably 2.0.
So, different driver versions are required to run. Check if you have 180.20 and up installed. There should be no difference in remote desktop related behavior.
Try to describe your test case in details so I could reproduce it on my hosts.
Hello Raistmer,
Please excuse the wrong information posted from my side. Guess I've checked some wrong workunits yesterday. They were ok, but must be processed without a remote desktop session. I used the PC today via remote desktop only, checked again some workunits and they were listed with the outcome "Success". Having a closer look on those tasks, all were showing the same error like optimized apps - "initialization error". The differnce is that stock apps are falling back from GPU to CPU processing. So they will be computed with the CPU and a result send to the server. As it's does not make sense/is not possible for optimized apps to fall back from GPU to CPU (already used) the workunit will not be continued and reported with a "Client error"...
Stock app result:
---
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : Device Emulation (CPU)
totalGlobalMem = -1
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 1
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1350000
totalConstMem = 65536
major = 9999
minor = 9999
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 16
setiathome_CUDA: device 1 is emulation device and should not be used, supports 9999.9999
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: Device Emulation (CPU) is okay
SETI@home using CUDA accelerated device Device Emulation (CPU)
Cuda error 'cufftPlan1d(&fft_analysis_plans[FftNum], FftLen, CUFFT_C2C, NumDataPoints / FftLen)' in file 'c:/sw/gpgpu/seti/seti_boinc/client/cuda/cudaAcc_fft.cu' in line 49 : initialization error.
Cuda error 'cufftPlan1d(&fft_analysis_plans[FftNum], FftLen, CUFFT_C2C, NumDataPoints / FftLen)' in file 'c:/sw/gpgpu/seti/seti_boinc/client/cuda/cudaAcc_fft.cu' in line 49 : initialization error.
setiathome_CUDA: CUDA runtime ERROR in plan FFT. Falling back to HOST CPU processing...
setiathome_enhanced 6.03 Visual Studio/Microsoft C++
libboinc: 6.3.22
---
So nothing to waste additional time on from your side. :D
I am sorry for any circumstances and thanks a lot for your great work! :)
Cheers,
yodi - with already installed TightVNC - that might work fine
-
Raistmer,
i've checked everything my video driver was 179.xx now i have 185.20 and for some reason iit doesnt download anything but ap wu's
-
Raistmer,
i've checked everything my video driver was 179.xx now i have 185.20 and for some reason iit doesnt download anything but ap wu's
All loading/work fetches up to BOINC, see prev posts.
-
My nvidia GTX 295 seems to run only on 1 core. Sometimes even this core stops. :(
System: Q9450 @ 3,4 (water), geforce GTX 295.
HSchmirPo
Ask on main forums - I seen some messages with similar troubles - you need to enable second core some way. Maybe turn off SLI mode if it applies here?
-
yodi - with already installed TightVNC - that might work fine
I still use remote desktop on my server host, but just don't touch local login session. That is, BOINC runs under user session logged locally and I connect to another session remotely. It works fine for me.
Think it's possible on WinXP too, you just need 2 different user accounts in this case (not sure though - didn't try this).
-
My nvidia GTX 295 seems to run only on 1 core. Sometimes even this core stops. :(
System: Q9450 @ 3,4 (water), geforce GTX 295.
HSchmirPo
Ask on main forums - I seen some messages with similar troubles - you need to enable second core some way. Maybe turn off SLI mode if it applies here?
... and activate the psychX computing on seconnd core or exted desktop on it ....
-
I plan to switch my Machine to XP 64bit, am I making a good choice.
Thank you
-
If you will not meet CUDA app freeze, then yes, Win x64 slightly faster then Win x86 regarding SETI apps.
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
-
Any plans for an SSE3 64bit version for AMD? I found the Intel only one a couple pages in, my poor Quad FX could really use the help!
Thanks
-
Do you think if ran multiple instances on a GPU it would give us better results.
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
Its motherboard has PCI-E slots?
-
Any plans for an SSE3 64bit version for AMD? I found the Intel only one a couple pages in, my poor Quad FX could really use the help!
Thanks
AMD CPUs should use x86 SSE3_AMD build. It's fastest build for such calss of CPUs.
-
Do you think if ran multiple instances on a GPU it would give us better results.
?
What do you mean? What multiple instances?
-
Do you think if ran multiple instances on a GPU it would give us better results.
?
What do you mean? What multiple instances?
He means MIMD operation I think ... Sorry, I think GPUs are a SIMD device? so one active instance per Compute device, though I'm sure multiple apps would run by switching one another out of device context (taking turns).
-
Running 2 apps on single GPU seems to decrease performance.
So for now it is better one CUDA app per GPU.
-
Sorry, to make such a big deal. But it seems to me this GPU+CPU team, really slows things down. I mean it seems the GPU is really slowing down the cpu, and on a older computer the cpu is slowing down the GPU. Is there any way to make run on their own.
Thank you
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
My 270's do sse3
-
All I can say, is that I got my two "cuda monster", running. Install Boinc 6.4.5, install cuda 2.1.
Q6600@3.6ghz, GTX 260 Core 216, 8800 GT G92 <- First Monster (6 instances running, 2 Cudas + 4 Cpu) -> Happy to say this guy doesnt make that much noise, loudest thing is my hard drive.
Q6600@Stock, 9800GT, 8800GTS <- Second Monster (6 instances running, 2 Cudas + 4 Cpu) -> This guy is like a jet due to the older GPUs, and XFX motherboard Loud fans.
All running V10 + SSE3.
Running XP 32, hoping to go to XP 64.
Thank you for all of your hard work
-
Since installing V10 i am getting nothing but AP wu's, ideas ???
-
Since installing V10 i am getting nothing but AP wu's, ideas ???
Untick AP in your SETI preferences.
-
Sorry, to make such a big deal. But it seems to me this GPU+CPU team, really slows things down. I mean it seems the GPU is really slowing down the cpu, and on a older computer the cpu is slowing down the GPU. Is there any way to make run on their own.
Thank you
No on both things.
But it wise to pair relative slow GPU with relative slow CPU if you have choice. Or, maybe, put all GPUs in one host. Feel free to try different variants, but reduce your work queue first. Trashing whole quad cache is not best way to go.
-
Here are updates to V10b for CPU part of team mods for x86 versions.
Now CPU app will not do attempts to re-schedule VLAR on GPU even if GPU is idle.
In multi-core systems it will allow another instance of CPU app that running non-VLAR task do re-schedule slightly later. So, total host performance should increase.
Thanks to Bob Mahoney who inspired this mod update.
ADDON: Be careful, it's UPDATE, not full pack. So don't delete anything from project directory, just update single exe file (or you will end with smth like posted below).
[attachment deleted by admin]
-
Here are updates to V10b for CPU part of team mods for x86 versions.
Now CPU app will not do attempts to re-schedule VLAR on GPU even if GPU is idle.
In multi-core systems it will allow another instance of CPU app that running non-VLAR task do re-schedule slightly later. So, total host performance should increase.
Thanks to Bob Mahoney who inspired this mod update.
Are the update I get
3/7/2009 08:46:31||Starting BOINC client version 6.4.7 for windows_intelx86
3/7/2009 08:46:31||log flags: task, file_xfer, sched_ops
3/7/2009 08:46:31||Libraries: libcurl/7.19.4 OpenSSL/0.9.8j zlib/1.2.3
3/7/2009 08:46:31||Running as a daemon
3/7/2009 08:46:31||Data directory: C:\Documents and Settings\All Users\Application Data\BOINC
3/7/2009 08:46:31||Running under account boinc_master
3/7/2009 08:46:31|SETI@home|[error] State file error: result 12ja09af.2025.890.14.8.226_1 is in wrong state
3/7/2009 08:46:31|SETI@home|[error] State file error: result 13ja09aa.24294.1299.4.8.242_0 is in wrong state
3/7/2009 08:46:31|SETI@home|[error] State file error: result 12ja09af.2025.890.14.8.228_0 is in wrong state
3/7/2009 08:46:31|SETI@home|[error] State file error: result 12ja09af.2025.26115.14.8.86_0 is in wrong state
3/7/2009 08:46:31|SETI@home|[error] State file error: result 12ja09af.2025.26524.14.8.135_0 is in wrong state
3/7/2009 08:46:31|SETI@home|[error] State file error: result 12ja09af.2025.26524.14.8.236_0 is in wrong state
3/7/2009 08:46:31||Processor: 4 GenuineIntel Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz [x86 Family 6 Model 15 Stepping 11]
3/7/2009 08:46:31||Processor features: fpu tsc sse sse2 mmx
3/7/2009 08:46:31||OS: Microsoft Windows XP: Professional x86 Editon, Service Pack 3, (05.01.2600.00)
3/7/2009 08:46:31||Memory: 2.00 GB physical, 3.85 GB virtual
3/7/2009 08:46:31||Disk: 69.23 GB total, 4.44 GB free
3/7/2009 08:46:31||Local time is UTC -5 hours
3/7/2009 08:46:31||Not using a proxy
3/7/2009 08:46:31||CUDA devices found
3/7/2009 08:46:31|SETI@home|URL: http://setiathome.berkeley.edu/; Computer ID: 4675326; location: home; project prefs: default
3/7/2009 08:46:31||General prefs: from SETI@home (last modified 06-Mar-2009 14:33:59)
3/7/2009 08:46:31||Computer location: home
3/7/2009 08:46:31||General prefs: no separate prefs for home; using your defaults
3/7/2009 08:46:31||Preferences limit memory usage when active to 1023.49MB
3/7/2009 08:46:31||Preferences limit memory usage when idle to 1637.58MB
3/7/2009 08:46:31||Preferences limit disk usage to 4.40GB
3/7/2009 08:46:31||Preferences limit # CPUs to 6
3/7/2009 08:46:31|SETI@home|Started upload of 12ja09af.27454.4980.13.8.105_1_0
3/7/2009 08:46:31|SETI@home|Started upload of 12ja09af.27454.26115.13.8.138_0_0
3/7/2009 08:46:31|SETI@home|Starting 12ja09af.2025.26524.14.8.232_1
3/7/2009 08:46:31|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:32|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:32|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:33|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:34|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:35|SETI@home|[error] Application file AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe missing signature
3/7/2009 08:46:35|SETI@home|[error] BOINC cannot accept this file
3/7/2009 08:46:35|SETI@home|Starting 12ja09af.2025.26524.14.8.225_0
3/7/2009 08:46:35|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:35|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:36|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:36|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:38|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:38|SETI@home|Starting 12ja09af.2025.26524.14.8.238_0
3/7/2009 08:46:38|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:39|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:39|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:39|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:40|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:40|SETI@home|Starting 13ja09aa.24294.5389.4.8.111_1
3/7/2009 08:46:40|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:40|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:40|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:41|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:41|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:41|SETI@home|Starting 13ja09aa.24294.5389.4.8.107_0
3/7/2009 08:46:41|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:42|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:42|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:43|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:44|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:44|SETI@home|Starting 13ja09aa.24294.5389.4.8.99_0
3/7/2009 08:46:44|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:44|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:44|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:44|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:44|SETI@home|[error] Process creation failed: Access is denied. (0x5)
3/7/2009 08:46:45|SETI@home|Computation for task 12ja09af.2025.26524.14.8.232_1 finished
3/7/2009 08:46:45|SETI@home|Output file 12ja09af.2025.26524.14.8.232_1_0 for task 12ja09af.2025.26524.14.8.232_1 absent
3/7/2009 08:46:45|SETI@home|Computation for task 12ja09af.2025.26524.14.8.225_0 finished
3/7/2009 08:46:45|SETI@home|Output file 12ja09af.2025.26524.14.8.225_0_0 for task 12ja09af.2025.26524.14.8.225_0 absent
3/7/2009 08:46:45|SETI@home|Computation for task 12ja09af.2025.26524.14.8.238_0 finished
3/7/2009 08:46:45|SETI@home|Output file 12ja09af.2025.26524.14.8.238_0_0 for task 12ja09af.2025.26524.14.8.238_0 absent
3/7/2009 08:46:45|SETI@home|Computation for task 13ja09aa.24294.5389.4.8.111_1 finished
3/7/2009 08:46:45|SETI@home|Output file 13ja09aa.24294.5389.4.8.111_1_0 for task 13ja09aa.24294.5389.4.8.111_1 absent
3/7/2009 08:46:45|SETI@home|Computation for task 13ja09aa.24294.5389.4.8.107_0 finished
3/7/2009 08:46:45|SETI@home|Output file 13ja09aa.24294.5389.4.8.107_0_0 for task 13ja09aa.24294.5389.4.8.107_0 absent
3/7/2009 08:46:45|SETI@home|Computation for task 13ja09aa.24294.5389.4.8.99_0 finished
3/7/2009 08:46:45|SETI@home|Output file 13ja09aa.24294.5389.4.8.99_0_0 for task 13ja09aa.24294.5389.4.8.99_0 absent
3/7/2009 08:46:51|SETI@home|Finished upload of 12ja09af.27454.26115.13.8.138_0_0
3/7/2009 08:46:51|SETI@home|Started upload of 12ja09af.27454.26115.13.8.152_0_0
3/7/2009 08:46:54|SETI@home|Finished upload of 12ja09af.27454.4980.13.8.105_1_0
3/7/2009 08:46:54|SETI@home|Started upload of 12ja09af.27454.26115.13.8.121_1_0
3/7/2009 08:46:55|SETI@home|Finished upload of 12ja09af.27454.26115.13.8.152_0_0
3/7/2009 08:46:55|SETI@home|Started upload of 12ja09af.27454.26115.13.8.166_0_0
3/7/2009 08:46:58|SETI@home|Finished upload of 12ja09af.27454.26115.13.8.121_1_0
3/7/2009 08:46:58|SETI@home|Started upload of 12ja09af.27454.26115.13.8.144_1_0
3/7/2009 08:46:59|SETI@home|Finished upload of 12ja09af.27454.26115.13.8.166_0_0
3/7/2009 08:47:01|SETI@home|Finished upload of 12ja09af.27454.26115.13.8.144_1_0
3/7/2009 08:47:56|SETI@home|Fetching scheduler list
3/7/2009 08:48:01|SETI@home|Master file download succeeded
3/7/2009 08:48:07|SETI@home|Sending scheduler request: Requested by user. Requesting 1036805 seconds of work, reporting 109 completed tasks
3/7/2009 08:48:12|SETI@home|Scheduler request completed: got 0 new tasks
3/7/2009 08:48:12|SETI@home|Message from server: No work sent
3/7/2009 08:48:12|SETI@home|Message from server: No work is available for SETI@home Enhanced
3/7/2009 08:48:12|SETI@home|Message from server: (reached daily quota of 14 results)
3/7/2009 08:48:12|SETI@home|Message from server: (Project has no jobs available)
Thank you
-
Here are updates to V10b for CPU part of team mods for x86 versions.
Now CPU app will not do attempts to re-schedule VLAR on GPU even if GPU is idle.
In multi-core systems it will allow another instance of CPU app that running non-VLAR task do re-schedule slightly later. So, total host performance should increase.
Thanks to Bob Mahoney who inspired this mod update.
Are the update I get
3/7/2009 08:48:12|SETI@home|Message from server: No work sent
3/7/2009 08:48:12|SETI@home|Message from server: No work is available for SETI@home Enhanced
3/7/2009 08:48:12|SETI@home|Message from server: (reached daily quota of 14 results)
Thank you
It's good that only 14 tasks can be trashed now ;)
What you did to recive such result? Probably deleted old app_info.xml ?
Or even tried to install update on host w/o V10 pack installed before ?
-
I got the same errors. Looking at it now, i forgot that i was still using v9. I upgraded to v10, using the update, and everything is working fine now.
-
I got the same errors. Looking at it now, i forgot that i was still using v9. I upgraded to v10, using the update, and everything is working fine now.
OMG, guys, please, think twice before trashing 10 days chaches, SETI servers already overloaded even w/o such actions.
The recommended way to do any (not only this one) update of opt apps:
1) DISABLE network access in BOINC
2) STOP BOINC
3) Copy BOINC whole data directory in another place as backup.
4) install update
5) start BOINC.
6) if all work fine - resume network access, else - stop BOINC and restore BOINC data folder from backup.
In other case you risk to trash whole your cache and be blamed by all few hundreds of your wingmans for that unfriendly action!
As failed result stated:
<file_name>setiathome_6.08_windows_intelx86__cuda.exe</file_name>
It means, your BOINC installation want to get this file but can't. You should already have it in project directory _before_ downloading work.
Either edit your app_info to point on another CUDA MB app you really try to install or download this stock version first.
-
I know, i hate losing the work. I only keep 2 days of work, didn't lose too much.
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
My 270's do sse3
Maybe his point is that sse2 runs faster. i've lost 25% rac on my opteron rigs since switching.
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
My 270's do sse3
Maybe his point is that sse2 runs faster. i've lost 25% rac on my opteron rigs since switching.
SSE3_AMD runs faster than SSE2 on AMD.
-
Here are updates to V10b for CPU part of team mods for x86 versions.
Now CPU app will not do attempts to re-schedule VLAR on GPU even if GPU is idle.
In multi-core systems it will allow another instance of CPU app that running non-VLAR task do re-schedule slightly later. So, total host performance should increase.
Thanks to Bob Mahoney who inspired this mod update.
ADDON: Be careful, it's UPDATE, not full pack. So don't delete anything from project directory, just update single exe file (or you will end with smth like posted below).
Any chances of x64 binaries?
Regards, Patrick.
-
Since installing V10 i am getting nothing but AP wu's, ideas ???
Untick AP in your SETI preferences.
Thanks didn't even think to look there :(
Have another question.
Can i run V10 opt apps along side an MW opt app ?
-
x64 SSSE3 & SSE3_Intel V10b updates added.
AMD users with x64 Windows should use SSE3_AMD x86 binary.
[attachment deleted by admin]
-
Is there a AMD x64 V10.
Thank you
-
I guess GPU applications are still in early development stage and are not much optimized yet, since the GPU temps are still much lower (5-10C lower) then during some (GPU bound) games, and much, much lower (10-15C lower) then when running FurMark... GTX295 is in question.
Does anyone know for sure is there any work being done on SETI CUDA code optimization?
P.S. Big thanks to Raistmer, V10a(b) apps are working well and stable on my machine (WinXP 32bit, GTX295+Q9650, 6 apps running, 2GPUs and 4CPUs).
-
Probably it can be optimized more, but don't forget that CUDA doesn't use all hardware parts of GPU as GPU-intensive games do.
Any texture-related hardware hardly used here for example.
-
Thank you for the hard work guys.
-
Is there a V10 for AMD 64.
Thank you
-
Is there a V10 for AMD 64.
Thank you
x86 SSE3_AMD variant.
-
Run the 32bit for AMD 64 on a 64bit os? Sorry I forgot to add this.
Thank you
-
I'm wondering what to do next. Before I energized the GPU application with Raistmers V9 my PC was running 4,000-4,200 average work done. Now, with the GPU, I'm running 3,800. Five WU are in progress at all times but it hasn't seemed to make a difference over the past 2 months.
Maybe I should just change to V10, see what happens. But that is usually poor troubleshooting. Can someone suggest diagnostics?
Thanks Art
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4296770
http://setiathome.berkeley.edu/result.php?resultid=1180991315 (CPU WU I think)
http://setiathome.berkeley.edu/result.php?resultid=1180494106 (GPU WU I think)
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
Its motherboard has PCI-E slots?
Yes running a 9600XT on it now and standard seticuda under XP.
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
Its motherboard has PCI-E slots?
Yes running a 9600XT on it now and standard seticuda under XP.
Ok, CPU-Z output (in html form or as text file) would be nice for this host.
-
I'm wondering what to do next. Before I energized the GPU application with Raistmers V9 my PC was running 4,000-4,200 average work done. Now, with the GPU, I'm running 3,800. Five WU are in progress at all times but it hasn't seemed to make a difference over the past 2 months.
Maybe I should just change to V10, see what happens. But that is usually poor troubleshooting. Can someone suggest diagnostics?
Thanks Art
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4296770
http://setiathome.berkeley.edu/result.php?resultid=1180991315 (CPU WU I think)
http://setiathome.berkeley.edu/result.php?resultid=1180494106 (GPU WU I think)
Make screenshot of windows task manager and post it here.
-
I'm wondering what to do next. Before I energized the GPU application with Raistmers V9 my PC was running 4,000-4,200 average work done. Now, with the GPU, I'm running 3,800. Five WU are in progress at all times but it hasn't seemed to make a difference over the past 2 months.
Maybe I should just change to V10, see what happens. But that is usually poor troubleshooting. Can someone suggest diagnostics?
Thanks Art
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4296770
http://setiathome.berkeley.edu/result.php?resultid=1180991315 (CPU WU I think)
http://setiathome.berkeley.edu/result.php?resultid=1180494106 (GPU WU I think)
Make screenshot of windows task manager and post it here.
This is enough, right? You didn't need the entire TM window?
[attachment deleted by admin]
-
I'm about to build another PC. The general plan is a Q9400, MSI P45 Neo3-FR mobo, Crucial Ballistix DDR2-800 memory (that I have in my junkbox from warranty replacement). I'm open to suggestion about these components and also a video card. I was thinking one of Nvidia 9000 series on CUDA list in the $100 range - their newer ones are too expensive. Be good if I can get 4,500-5,000 average out of it. What say you pro's?
Thanks
Art
-
This is enough, right? You didn't need the entire TM window?
Yes, thanks.
It seems all work as it should on this screenshot. Your RAC drop could be explaned by big pending credit perhaps....
ADDON: another possibility - you did run AP tasks before and switched off AP tsks now. In general opt AP gives better credit per hour than MB (it can be considered as small compensation for many AP troubles :) )
-
This is enough, right? You didn't need the entire TM window?
Yes, thanks.
It seems all work as it should on this screenshot. Your RAC drop could be explaned by big pending credit perhaps....
OK I'll check on that. There was that period when SETI wasn't sending WU a couple weeks ago. Could be I haven't fully got back up to speed. With the video added in (8500GT) I was expecting 4,500 or so. The 8500 appears to be running at about half the rate of a single CPU in the Q6600.
Thanks Art
-
My own Q9450 did ~4400 with MB tasks before CUDA start. Now it ~5200 with 9600GSO addition. But it still not stabilized (I expect it to be higher).
-
ADDON: another possibility - you did run AP tasks before and switched off AP tsks now. In general opt AP gives better credit per hour than MB (it can be considered as small compensation for many AP troubles :) )
I don't have AP turned off on purpose that I know of. True, I don't see any running. Checking my SETI prefs I see another line item for AP V5 has been added in seti@home prefs since last I looked. Now enabled.
Thanks for the hint!
Art
-
ADDON: another possibility - you did run AP tasks before and switched off AP tsks now. In general opt AP gives better credit per hour than MB (it can be considered as small compensation for many AP troubles :) )
I don't have AP turned off on purpose that I know of. True, I don't see any running. Checking my SETI prefs I see another line item for AP V5 has been added in seti@home prefs since last I looked. Now enabled.
Thanks for the hint!
Art
But keep in mind that "team" combos intended for MB tasks mostly. With AP tasks in queue BOINC still can do dumb things leaving GPU idle.
-
My own Q9450 did ~4400 with MB tasks before CUDA start. Now it ~5200 with 9600GSO addition. But it still not stabilized (I expect it to be higher).
Am I correct to thinik the important GPU spec is core clock?
You hinted in earlier post that stream processors are not involved in GPU crunching. How important is memory clock?
Thanks Art
-
My own Q9450 did ~4400 with MB tasks before CUDA start. Now it ~5200 with 9600GSO addition. But it still not stabilized (I expect it to be higher).
Am I correct to thinik the important GPU spec is core clock?
You hinted in earlier post that stream processors are not involved in GPU crunching. How important is memory clock?
Thanks Art
Not correct to think stream processors not included. I said "texture-related hardware", not stream processors. There is dedicated hardware that will do linear approximation between 2 dots in texture for example. This particular part can be used inside CUDA BTW, but I don't think this app use it. But there are another parts of GPU that can't be accessed via CUDA at all.
Will try to find relevant info in CUDA FAQ or forums (I seen that there).
-
Ok, here:
"
What texture features does CUDA support?
CUDA supports 1D and 2D textures, which can be accessed with normalized (0..1) or integer coordinates. Textures can also be bound to linear memory and accessed with the "tex1Dfetch" function.
The hardware only supports 1, 2 and 4-component textures, not 3-component textures.
3D textures, cube maps, texture arrays, compressed textures and mip-maps are not currently supported.
"
and
"
Are graphics operations such as z-buffering and alpha blending supported in CUDA?
No. Access to video memory in CUDA is done via the load/store mechanism, and doesn't go through the normal graphics raster operations like blending. We don't have any plans to expose blending or any other raster ops in CUDA.
"
AND AFAIK any game will do blending a lot :)
-
Am I correct to thinik the important GPU spec is core clock?
Think no.
look beta forum for GPU OCing questions. It was showed that shader clock most important and engine clock least important.
My own GPU can support high memory freqs (for now it works on 2x1140 and 2x1120 known to be stable already). With shader freqs it still awaiting evaluation...
-
Ok, here:
"
What texture features does CUDA support?
CUDA supports 1D and 2D textures, which can be accessed with normalized (0..1) or integer coordinates. Textures can also be bound to linear memory and accessed with the "tex1Dfetch" function.
The hardware only supports 1, 2 and 4-component textures, not 3-component textures.
3D textures, cube maps, texture arrays, compressed textures and mip-maps are not currently supported.
"
and
"
Are graphics operations such as z-buffering and alpha blending supported in CUDA?
No. Access to video memory in CUDA is done via the load/store mechanism, and doesn't go through the normal graphics raster operations like blending. We don't have any plans to expose blending or any other raster ops in CUDA.
"
AND AFAIK any game will do blending a lot :)
From this maybe I can infer CUDA uses some but not all capabilities. Just considering SETI or Einstein processing, then, there must be a point beyond which it is wasted money to buy more performance. Would it be true that increased core clock is always valuable, memory less so? And, is it possible to decide how many stream processors is enough, or is the case "more is better"?
I am trying to decide how best to implement the new PC with regard to SETI processing. Given I don't understand much about video processing, guessing which specs will yield the most result per dollar is a task. The spec sheets that I've read for example don't talk about texture so it is hard to relate to specs.
Regards Art
-
Look Richard's thread on SETI main about CUDA completion times for this.
You can see there if high end card give adequate performance boost or not comparing to their prices....
Maybe 2 midrange cards could work better than one more costly high-end card... Performance-related info still not so big to give easy answers on such questions...
BTW, if GPU supportd computation capability 1.3 - the SETI CUDA MB app can make use of it.
In my understandig it's a rough analogue to CPU SSE level (that is, new instructions added). And CUDA MB can use them.
In other aspects - the more processors GPU have and the higher its freqs - the more faster it will be (also memory bus bandwith should matter).
-
Hello I'm wondering if my computer is really crunching as fast as it should
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4686284&ipprivate=1 Link to my desktop /w 2 EVGA GTX260 gpu's and a quadcore Q6600 intel running on Windows XP sp3
I have downloaded your new V10a x86 sse3x from your first post (the top one i downloaded is this correct for 32 bit windows?)
I am running the 6.4.7 version of boinc
I have the cc_config.xml set to 6 processes
just seems awfully slow to be running 6 processes at once and only have a 8K RAC which is excactly the same as when i had 1 gpu.. i have gotten absolutely no gain from running 2 gpu's thus far..
thanks
-
Did you ever build on for older SSE2 AMD CPUs + a GPU?
What config do you have? For what CPU you need SSE2 app ?
Opteron 170/270/280 AMD
Its motherboard has PCI-E slots?
Yes running a 9600XT on it now and standard seticuda under XP.
Ok, CPU-Z output (in html form or as text file) would be nice for this host.
Sorry it does SSE3 My Duh!
-
Hello I'm wondering if my computer is really crunching as fast as it should
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4686284&ipprivate=1 Link to my desktop /w 2 EVGA GTX260 gpu's and a quadcore Q6600 intel running on Windows XP sp3
I have downloaded your new V10a x86 sse3x from your first post (the top one i downloaded is this correct for 32 bit windows?)
I am running the 6.4.7 version of boinc
I have the cc_config.xml set to 6 processes
just seems awfully slow to be running 6 processes at once and only have a 8K RAC which is excactly the same as when i had 1 gpu.. i have gotten absolutely no gain from running 2 gpu's thus far..
thanks
Same here. So far I've not seen any action from the GPU.
Have you had any trouble with the EVGA card? I saw a post suggesting EVGA was having some issues.
Thanks Art
-
Off subject a bit..............
I remember there existed a NON TEAM build somewhere but can't find it. Can anyone help me out?
Looking for NON TEAM cuda app
-
Hello I'm wondering if my computer is really crunching as fast as it should
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4686284&ipprivate=1 Link to my desktop /w 2 EVGA GTX260 gpu's and a quadcore Q6600 intel running on Windows XP sp3
I have downloaded your new V10a x86 sse3x from your first post (the top one i downloaded is this correct for 32 bit windows?)
I am running the 6.4.7 version of boinc
I have the cc_config.xml set to 6 processes
just seems awfully slow to be running 6 processes at once and only have a 8K RAC which is excactly the same as when i had 1 gpu.. i have gotten absolutely no gain from running 2 gpu's thus far..
thanks
Same here. So far I've not seen any action from the GPU.
Have you had any trouble with the EVGA card? I saw a post suggesting EVGA was having some issues.
Thanks Art
so far no issues but my gpu's arent crunching wu's in 2-4 mins like they where when i just had a single gpu.. after adding second it is taking like 20-30 mins to crunch them now.. and 1hr 30 mins for cpu to complete a wu, where before it would do it in 45mins to 58 mins tops..
i dont see the purpose of running 2 gpu processes if it slows everything else down it isnt worth the expense of extra card and extra electricity to run the damn thing
-
Hello I'm wondering if my computer is really crunching as fast as it should
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4686284&ipprivate=1 Link to my desktop /w 2 EVGA GTX260 gpu's and a quadcore Q6600 intel running on Windows XP sp3
I have downloaded your new V10a x86 sse3x from your first post (the top one i downloaded is this correct for 32 bit windows?)
I am running the 6.4.7 version of boinc
I have the cc_config.xml set to 6 processes
just seems awfully slow to be running 6 processes at once and only have a 8K RAC which is excactly the same as when i had 1 gpu.. i have gotten absolutely no gain from running 2 gpu's thus far..
thanks
"
setiathome_CUDA: No device specified, determined to use CUDA device 1: GeForce GTX 260
SETI@home using CUDA accelerated device GeForce GTX 260
CPU-GPU team mod by Raistmer
"
It's not V10 output. Update to V10b version.
ADDON: just for example, true V10 output:
"
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9600 GSO is okay
SETI@home using CUDA accelerated device GeForce 9600 GSO
V10 modification by Raistmer
"
-
Off subject a bit..............
I remember there existed a NON TEAM build somewhere but can't find it. Can anyone help me out?
Looking for NON TEAM cuda app
The same CUDA app can be used w/o its team CPU counterpart. But CPU teamed app can not be used separately.
-
Hello I'm wondering if my computer is really crunching as fast as it should
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4686284&ipprivate=1 Link to my desktop /w 2 EVGA GTX260 gpu's and a quadcore Q6600 intel running on Windows XP sp3
I have downloaded your new V10a x86 sse3x from your first post (the top one i downloaded is this correct for 32 bit windows?)
I am running the 6.4.7 version of boinc
I have the cc_config.xml set to 6 processes
just seems awfully slow to be running 6 processes at once and only have a 8K RAC which is excactly the same as when i had 1 gpu.. i have gotten absolutely no gain from running 2 gpu's thus far..
thanks
Same here. So far I've not seen any action from the GPU.
Have you had any trouble with the EVGA card? I saw a post suggesting EVGA was having some issues.
Thanks Art
so far no issues but my gpu's arent crunching wu's in 2-4 mins like they where when i just had a single gpu.. after adding second it is taking like 20-30 mins to crunch them now.. and 1hr 30 mins for cpu to complete a wu, where before it would do it in 45mins to 58 mins tops..
i dont see the purpose of running 2 gpu processes if it slows everything else down it isnt worth the expense of extra card and extra electricity to run the damn thing
Is it your result?
http://setiathome.berkeley.edu/result.php?resultid=1180810147
it takes ~500seconds to complete, 500 realtime seconds, and 120.2188 CPU seconds.
What you talk about?
-
"
setiathome_CUDA: No device specified, determined to use CUDA device 1: GeForce GTX 260
SETI@home using CUDA accelerated device GeForce GTX 260
CPU-GPU team mod by Raistmer
"
It's not V10 output. Update to V10b version.
ADDON: just for example, true V10 output:
"
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9600 GSO is okay
SETI@home using CUDA accelerated device GeForce 9600 GSO
V10 modification by Raistmer
"
i dont understand what you are asking me to do?? where is version 10b?
-
There's different versions of V10b in different posts on Page 10.
Claggy
-
Off subject a bit..............
I remember there existed a NON TEAM build somewhere but can't find it. Can anyone help me out?
Looking for NON TEAM cuda app
The same CUDA app can be used w/o its team CPU counterpart. But CPU teamed app can not be used separately.
Thanks for that, I just switched over from your V7a VLAR_fix app to V10a (without the team counterpart),
(I wanted to see the wall time, but didn't want to ask if you'd update the v7a app.)
First wu completed satis, 972.4secs.
Claggy
-
Lurker checking in, x64 V10b apps working well for me and doing an incredible amount of work the past few days.
Raistmer, it took me 6 years to break 1 million work units but my second million will be completed in early July at this rate.
Sir, you clearly rock in my book.
john
-
"
setiathome_CUDA: No device specified, determined to use CUDA device 1: GeForce GTX 260
SETI@home using CUDA accelerated device GeForce GTX 260
CPU-GPU team mod by Raistmer
"
It's not V10 output. Update to V10b version.
ADDON: just for example, true V10 output:
"
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9600 GSO is okay
SETI@home using CUDA accelerated device GeForce 9600 GSO
V10 modification by Raistmer
"
i dont understand what you are asking me to do?? where is version 10b?
First page of this thread - V10a.
You can stop on it or look further to find V10b update.
Result I linked NOT V10 one at all. Not V10, nor V10a, nor V10b. So you should update to V10 pack.
-
Lurker checking in, x64 V10b apps working well for me and doing an incredible amount of work the past few days.
Raistmer, it took me 6 years to break 1 million work units but my second million will be completed in early July at this rate.
Sir, you clearly rock in my book.
john
Glad to hear that :) If project leaders will not change cobblestone credit value too much your next million could be even faster provided you will do upgrade to new hardware again ;).
-
"
setiathome_CUDA: No device specified, determined to use CUDA device 1: GeForce GTX 260
SETI@home using CUDA accelerated device GeForce GTX 260
CPU-GPU team mod by Raistmer
"
It's not V10 output. Update to V10b version.
ADDON: just for example, true V10 output:
"
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9600 GSO is okay
SETI@home using CUDA accelerated device GeForce 9600 GSO
V10 modification by Raistmer
"
i dont understand what you are asking me to do?? where is version 10b?
First page of this thread - V10a.
You can stop on it or look further to find V10b update.
Result I linked NOT V10 one at all. Not V10, nor V10a, nor V10b. So you should update to V10 pack.
im already using V10a
is V10b better for dual video cards??
sorry for the dumb questions im new to this tinkering with BOINC
-
Lurker checking in, x64 V10b apps working well for me and doing an incredible amount of work the past few days.
Raistmer, it took me 6 years to break 1 million work units but my second million will be completed in early July at this rate.
Sir, you clearly rock in my book.
john
What am I doing wrong, I have so much GPU and CPU power, and getting terribly low results.
Thank you
-
"
setiathome_CUDA: No device specified, determined to use CUDA device 1: GeForce GTX 260
SETI@home using CUDA accelerated device GeForce GTX 260
CPU-GPU team mod by Raistmer
"
It's not V10 output. Update to V10b version.
ADDON: just for example, true V10 output:
"
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9600 GSO is okay
SETI@home using CUDA accelerated device GeForce 9600 GSO
V10 modification by Raistmer
"
i dont understand what you are asking me to do?? where is version 10b?
First page of this thread - V10a.
You can stop on it or look further to find V10b update.
Result I linked NOT V10 one at all. Not V10, nor V10a, nor V10b. So you should update to V10 pack.
im already using V10a
is V10b better for dual video cards??
sorry for the dumb questions im new to this tinkering with BOINC
record in results you send claims you don't use V10a. So re-check your installation. And post screenshot of your windows task manager.
-
maybe im putting the stuff in the wrong folder where excactly in which folder is this V10b supposed to go?? i have been placing all of it into the boinc/seti/ application folder that has about 500 WU's in it.. if this is the wqrong folder let me know where to put it..
i downloaded and started using v10B last night as well
the cc_config.xml is placed in a diffrent folder but im pretty sure that is in the right spot..
3/10/2009 10:34:12 AM||Starting BOINC client version 6.4.7 for windows_intelx86
3/10/2009 10:34:12 AM||log flags: task, file_xfer, sched_ops
3/10/2009 10:34:12 AM||Libraries: libcurl/7.19.4 OpenSSL/0.9.8j zlib/1.2.3
3/10/2009 10:34:12 AM||Data directory: C:\Documents and Settings\All Users\Application Data\BOINC
3/10/2009 10:34:12 AM||Running under account Chris
3/10/2009 10:34:12 AM|SETI@home|Found app_info.xml; using anonymous platform
3/10/2009 10:34:12 AM||Processor: 4 GenuineIntel Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz [x86 Family 6 Model 15 Stepping 11]
3/10/2009 10:34:12 AM||Processor features: fpu tsc pae nx sse sse2 mmx
3/10/2009 10:34:12 AM||OS: Microsoft Windows XP: Professional x86 Editon, Service Pack 3, (05.01.2600.00)
3/10/2009 10:34:12 AM||Memory: 2.50 GB physical, 4.34 GB virtual
3/10/2009 10:34:12 AM||Disk: 34.46 GB total, 7.49 GB free
3/10/2009 10:34:12 AM||Local time is UTC -6 hours
3/10/2009 10:34:12 AM||Not using a proxy
3/10/2009 10:34:12 AM||CUDA devices found
3/10/2009 10:34:12 AM|SETI@home|URL: http://setiathome.berkeley.edu/; Computer ID: 4686284; location: home; project prefs: default
3/10/2009 10:34:12 AM||General prefs: from SETI@home (last modified 08-Jan-2009 02:22:47)
3/10/2009 10:34:12 AM||Computer location: home
3/10/2009 10:34:12 AM||General prefs: using separate prefs for home
3/10/2009 10:34:12 AM||Reading preferences override file
3/10/2009 10:34:12 AM||Preferences limit memory usage when active to 1279.23MB
3/10/2009 10:34:12 AM||Preferences limit memory usage when idle to 2302.62MB
3/10/2009 10:34:12 AM||Preferences limit disk usage to 7.59GB
3/10/2009 10:34:12 AM||Preferences limit # CPUs to 6
3/10/2009 10:34:12 AM|SETI@home|Restarting task 13ja09aa.14911.72.8.8.88_1 using setiathome_enhanced version 608
3/10/2009 10:34:12 AM|SETI@home|Restarting task 13ja09aa.14911.72.8.8.102_0 using setiathome_enhanced version 608
3/10/2009 10:34:12 AM|SETI@home|Restarting task 13ja09aa.14911.481.8.8.232_1 using setiathome_enhanced version 608
3/10/2009 10:34:12 AM|SETI@home|Restarting task 13ja09ab.6382.890.6.8.121_1 using setiathome_enhanced version 608
3/10/2009 10:34:12 AM|SETI@home|Restarting task 13ja09ab.6382.890.6.8.160_1 using setiathome_enhanced version 608
3/10/2009 10:34:12 AM|SETI@home|Restarting task 13ja09ab.6382.890.6.8.157_1 using setiathome_enhanced version 608
[attachment deleted by admin]
-
This morning I'm almost out of WU. About 20 SETI WU and 10 AP. Is it me or is it the servers? Usually I have SETI in the hundreds waiting to start.
Also wanted to be sure I'm not missing any speed enhancements. My work directory has:
ap_5.03r112_SSE3
ap_5.00r103_SSE3
AK_v8b_win_SSSE3x_GPU_CPU_team_V9
I believe Raistmer posted that going to V10 will not decrease processing time. Is there any other reason to change to V10?
Can I get rid of ap_5.00r103_SSE3?
Thanks
Art
-
dunno how to take a screenshot of task manager how do u do that?
Yesterday I found that cut and paste here will not work with screen shot. Here's what worked for me:
Open Task Manager. Click twice on the CPU column, so that the SETI processors are showing at top.
Shrink the window so its showing only what you need.
Press ALT-PRTSC which takes a snapshot of the active (Task Manager - TM) window.
Open MSPaint or some other graphics editor.
Paste (CTRL-V) the TM screenshot into the editor.
Save the screenshot as a jpg file.
Go to this thread, Reply to Raistmer's post.
Press Additional Options.
Attach your jpg file.
Post.
The screenshot should show up when you Post your post. Worked for me.
Regards
Art
-
Can I get rid of ap_5.00r103_SSE3?
The work is still around - just got a v5.00 I needed for testing at only the second deliberate "work fetch" attempt I made looking for one.
Up to you whether you want to help clean it up, though.
[One sweetener - you're almost guaranteed instant credits when you finish one, because there are only resends available. And I'm about to make myself very popular with Firefly, who has been waiting since 12 January (and two deadline expiries) for a wingmate for his 749.30 pending credits]
-
Can I get rid of ap_5.00r103_SSE3?
The work is still around - just got a v5.00 I needed for testing at only the second deliberate "work fetch" attempt I made looking for one.
Up to you whether you want to help clean it up, though.
[One sweetener - you're almost guaranteed instant credits when you finish one, because there are only resends available. And I'm about to make myself very popular with Firefly, who has been waiting since 12 January (and two deadline expiries) for a wingmate for his 749.30 pending credits]
THanks..I'll leave it there for now.
-
The work is still around - just got a v5.00 I needed for testing at only the second deliberate "work fetch" attempt I made looking for one.
Up to you whether you want to help clean it up, though.
[One sweetener - you're almost guaranteed instant credits when you finish one, because there are only resends available. And I'm about to make myself very popular with Firefly, who has been waiting since 12 January (and two deadline expiries) for a wingmate for his 749.30 pending credits]
Speaking of pending credit. I've stayed away from worrying about it - but. I have pending credit going back >1,000 completed wu. I'm using a small network with 4 PCs and my brother crunches with another 4 PCs all on one seti account. Is this backlog normal?
-
maybe im putting the stuff in the wrong folder where excactly in which folder is this V10b supposed to go?? i have been placing all of it into the boinc/seti/ application folder that has about 500 WU's in it.. if this is the wqrong folder let me know where to put it..
i downloaded and started using v10B last night as well
the cc_config.xml is placed in a diffrent folder but im pretty sure that is in the right spot..
Ok, lets look at your screenshot together now... How many AK_v8 do you see active? I see 5 active one and one waiting. And one CUDA_MB app active.
What does it mean for quad with 2 GPUs? It means that one GPU WILL be idle with such config.
And why this happened? My bet is because someone doesn't read first page completely and ignored any stuff regarding to number_of_GPUs file value.
Of course I can highlight that string too in first post, but don't think it will increase readability....
Citation
"
There will be number_of_GPUs file in SETI project directory. By default it contains number of 1.
If you have more GPUs just edit that file (enter number of GPUs installed in host instead of 1 ).
"
So? Am I right or I right? ;) Edit that file.
-
Speaking of pending credit. I've stayed away from worrying about it - but. I have pending credit going back >1,000 completed wu. I'm using a small network with 4 PCs and my brother crunches with another 4 PCs all on one seti account. Is this backlog normal?
Check few of that pending tasks . If they have "initial" validation state - yes, all OK. But if many of them have checked but no consensus status... well, it's time to check your host stability and correctness then.
-
i've tried to locate this file where you put 2 gpu's and i don't see it..
ok trying something little diffrent tried putting processes to 7 in the cc_config.xml file since i figured i had 1 idle process in last task manager ( 1 core not doing anything)
and here is what it is doing now.. all 6 cores busy with 1 extra process doing nuthing.. seems like this might work what u think raistmer??
[attachment deleted by admin]
-
ok i will post a screen shot of what is in my c:/programfiles/Boinc file folder thier is nothing here i can edit...
[attachment deleted by admin]
-
i've tried to locate this file where you put 2 gpu's and i don't see it..
ok trying something little diffrent tried putting processes to 7 in the cc_config.xml file since i figured i had 1 idle process in last task manager ( 1 core not doing anything)
and here is what it is doing now.. all 6 cores busy with 1 extra process doing nuthing.. seems like this might work what u think raistmer??
I think it still runs SINGLE CUDA_MB app. But your little experiment just overloaded your CPU even more - it will decrease performance, not increase it.
Check your seti project forlder once more. Then check archive from that you performad V10 pack installation. And if you doesn't see that file even there - well, attach that archive, will look on it.
-
ok i will post a screen shot of what is in my c:/programfiles/Boinc file folder thier is nothing here i can edit...
OMG, and why BOINC folder? why not something else?
Where ALL files from V10 pack archive should go?
-
do you see the file to mod in here?
[attachment deleted by admin]
-
yes, I see it. number_of_....
And better try to use another view mode in explorer. It seems you can't see full file names.
-
i see the one file named number_of_gpus_
and when i click to edit it it just has a number (1) written on the page and nothing else..
i changed the number to 2 then saved and still same results... is thier supposed to be something else written on that page or not?
-
i see the one file named number_of_gpus_
and when i click to edit it it just has a number (1) written on the page and nothing else..
i changed the number to 2 then saved and still same results... is thier supposed to be something else written on that page or not?
Restart BOINC after editing that file. And post new windows task manager screenshot.
-
i'm at work right now for the next 5 hrs will do this soon as i get off of work.. was this in the right folder though?? it was placed in the folder that boinc/seti places all the work units..
-
Everything seems to be fully running V10, for me. But my results seems to be getting worst. I dropped to 12,000 points from 22,000. And now got more computers up. I even added two more P4 3.2HT.
Thank you
-
Heres my two GPU system. I get good completion, but bad overall results. Not enough work. Every 7 hours it stops and waits.
Thank you
[attachment deleted by admin]
-
good news and bad news... lol
got both gpu's crunching now, but now have 6 instances of regualar work units being tasked.. i dunno what is going on..
what do you think?? cc_config.xml still says 6 processors should i maybe reduce it to 4 or 5 so i dont have 2 extra processes doing 0% work??
[attachment deleted by admin]
-
now all OK. Re-read description of how this mod work in first posts of this and other threads about "team" mod.
-
Yesterday I reported running out of work. Still the same thing today. I have a dozen or so AP units in progress. But in BOINC manager Projects tab pressing SETI update returns a msg:
.....Requesting 0 seconds of work. ......
With no SETI WU in the queue that does not seem like the right choice :-( Anyone help me understand what is going on? The only recent change I made is on the SETI site to enable AP WU.
All 3 choices for work are enabled (SAH Preferences):
SAH Enhanced
AP
AP V5
Thanks
Art
-
Yesterday I reported running out of work. Still the same thing today. I have a dozen or so AP units in progress. But in BOINC manager Projects tab pressing SETI update returns a msg:
.....Requesting 0 seconds of work. ......
With no SETI WU in the queue that does not seem like the right choice :-( Anyone help me understand what is going on? The only recent change I made is on the SETI site to enable AP WU.
All 3 choices for work are enabled (SAH Preferences):
SAH Enhanced
AP
AP V5
Thanks
Art
So if you enabled AP you got AP. And you got so many AP tasks that BOINC doesn't count you need any more work in near few days.
So, action=>consequencies.
Wait until some of AP tasks will be done, then if you will lucky you could get more MB work.
-
now all OK. Re-read description of how this mod work in first posts of this and other threads about "team" mod.
<cc_config>
<options>
<ncpus>6</ncpus>
</options>
</cc_config> is placed excactly where you say to and i still had 2 idle processes in task manager..
-
now all OK. Re-read description of how this mod work in first posts of this and other threads about "team" mod.
<cc_config>
<options>
<ncpus>6</ncpus>
</options>
</cc_config> is placed excactly where you say to and i still had 2 idle processes in task manager..
ALL OK. It SHOULD be so, they waiting CUDA_MB. You have 4 cores - 4 CPU apps running. You have 2 GPUs - 2 GPU apps running. What else you want ??
-
This update ONLY for those who use BOINC only for SETI MB crunching. No other projects, not even AstroPulse, ONLY SETI Enhanced (MultiBeam).
In this build CPU-GPU re-scheduling is disabled (it's not needed for only SETI MB configuration).
It should increase total performance for such configs.
Again, use it ONLY if you crunch SETI MB solely.
And don't forget RULEs for opt apps updating:
1) DISABLE network access in BOINC
2) STOP BOINC
3) Copy BOINC whole data directory in another place as backup.
4) install update
5) start BOINC.
6) if all work fine - resume network access, else - stop BOINC and restore BOINC data folder from backup.
[attachment deleted by admin]
-
Yesterday I reported running out of work. Still the same thing today. I have a dozen or so AP units in progress. But in BOINC manager Projects tab pressing SETI update returns a msg:
.....Requesting 0 seconds of work. ......
With no SETI WU in the queue that does not seem like the right choice :-( Anyone help me understand what is going on? The only recent change I made is on the SETI site to enable AP WU.
All 3 choices for work are enabled (SAH Preferences):
SAH Enhanced
AP
AP V5
Thanks
Art
So if you enabled AP you got AP. And you got so many AP tasks that BOINC doesn't count you need any more work in near few days.
So, action=>consequencies.
Wait until some of AP tasks will be done, then if you will lucky you could get more MB work.
Maybe so. However I've also got only 8 AP. 4 in progress, 4 waiting. I specify 10 days of work in queue. This is not 10 days on the particular PC. So will wait out the AP WU see if I get more when the last 4 start.
-
This update ONLY for those who use BOINC only for SETI MB crunching. No other projects, not even AstroPulse, ONLY SETI Enhanced (MultiBeam).
In this build CPU-GPU re-scheduling is disabled (it's not needed for only SETI MB configuration).
It should increase total performance for such configs.
Again, use it ONLY if you crunch SETI MB solely.
And don't forget RULEs for opt apps updating:
1) DISABLE network access in BOINC
2) STOP BOINC
3) Copy BOINC whole data directory in another place as backup.
4) install update
5) start BOINC.
6) if all work fine - resume network access, else - stop BOINC and restore BOINC data folder from backup.
Just a suggestion it would be helpful to take the + opt AP part out of the name. This thread is confusing enough already for us non-code wizards.
Regards
Art
-
This update ONLY for those who use BOINC only for SETI MB crunching. No other projects, not even AstroPulse, ONLY SETI Enhanced (MultiBeam).
Thank You very much!
It's right my case!
[edit] Only one thing remains - don't launch GPU-part in case of VLAR workunit (do CPU, even with sharing core with already launched), so no more losses of workunits ;)
Every WU will be crunched (maybe slightly longer but no errored). Show must go on :)
[/edit]
-
yodi - with already installed TightVNC - that might work fine
I still use remote desktop on my server host, but just don't touch local login session. That is, BOINC runs under user session logged locally and I connect to another session remotely. It works fine for me.
Think it's possible on WinXP too, you just need 2 different user accounts in this case (not sure though - didn't try this).
Hi Raistmer,
b@ck from some wired testing regarding remote desktop sessions on Windows XP. Here is the result, jFYI.
You mentioned it's possible to keep the first (local) session running on the machine when logging in as a different user via remote desktop using Vista. Tried this with XP32 and XP64 as well but unfortunately this is not possible (or I am to unexperienced to manage it), when logging in as a different user via remote desktop, the first (local) session will be terminated and I ran in the same issues (CUDA device not detected).
The describes issues seams to be related to CUDA device detection in general (rpd is using it's own video driver). Starting BOINC after logging in via remote desktop will show a no CUDA device found message within the BOINC manager.
Here is a workaround to get and keep crunching running (more or less):
1. Stop BOINC.
1.1. In case no service installation done before - uninstall BOINC and install it in protected mode (as a service).
2. Install modified V10 apps.
3. Overwrite the libfftw3f-3-1-1a_upx.dll, cufft.dll and cudart.dll with those from V8 apps. (Otherwise you'll see the same behavior mentioned earlier (http://lunatics.kwsn.net/12-gpu-crunching/v10-of-modified-seti-mb-cuda-opt-ap-package-for-full-multi-gpucpu-use.msg15321.html#msg15321) with the V10 stock apps: BOINC will never detect the CUDA device when logging in later via remote desktop... So the modified apps will flush all cached WUs with computation errors as it will not fall back to CPU processing.)
4. Set the BOINC service startup type to automatic (to have it running before any login).
4.1. Same for the terminal service, if not done before (this enables a remote desktop login without logging in a user locally).
5. Reboot the computer.
What will happen now is the following. The computer starts, our BOINC service as well. No user is logged in via remote desktop and BOINC will detect the CUDA device, starts computation, everything is fine.
Option 1: You login directly on the machine, nothing will change, BOINC is up and running.
Option 2: You're using remote desktop to login. As BOINC is already running, it detected the CUDA device before this login. Once you logged in via remote desktop the machine will be more than busy with the WU calculated using our CUDA device at this moment (in my case the CPU or GPU fan is more than noticeable). It will continue calculating up to 100%, throw a computation error BUT crunches all following CUDA WUs without any error, even if the rpd video driver is in use at this time.
Maybe this information is some kind of interesting. :)
Cheers,
yodi
-
Presumably this will be different on a server-class OS, where a second user can log in using Remote Desktop without terminating any existing user's sessions.
-
Personally I am using UltraVNC to remote connect to another PC. It doesn't log off the user, it is more secure and... it works even on Vista x64.
-
Anybody tried Teamviewer? Easy to use software an its free. I'm very satisfied with the software.
-
And don't forget RULEs for opt apps updating:
1) DISABLE network access in BOINC
2) STOP BOINC
3) Copy BOINC whole data directory in another place as backup.
4) install update
5) start BOINC.
6) if all work fine - resume network access, else - stop BOINC and restore BOINC data folder from backup.
I want to reinstall BOINC as a service - now its an app - so I don't have to be logged on. Do these instructions apply, if I delete and reinstall BOINC? Or, will I lose my WU cache? (WinXP SP3)
I'm now using V9. Am also thinking this would be an opportunity to upgrade to the V10 that allows AP and other apps. Advice appreciated.
Thanks Art
-
Presumably this will be different on a server-class OS, where a second user can log in using Remote Desktop without terminating any existing user's sessions.
Hi Richard, you are right. Had a quick look on wiki. (http://en.wikipedia.org/wiki/Terminal_Services) It explains very well that concurrent remote sessions are allowed for server operating systems only. And in addition why Raistmer's local session will not be terminated using Vista: "...can host the remote session in the context of the currently logged in user without creating a new session, and make the Desktop, or a subset of it, available over Remote Desktop Protocol...". :)
Personally I am using UltraVNC to remote connect to another PC. It doesn't log off the user, it is more secure and... it works even on Vista x64.
Anybody tried Teamviewer? Easy to use software an its free. I'm very satisfied with the software.
Hi SoNic and Saprovor, thanks a lot for your valuable hints here. Personally I already tried a VNC client (TightVNC) and TeamViewer, both are working fine.
Please see my post above just as a kind of MS remote desktop proof, playing around a bit, not more or less. To be honest I just like this service, my experience is that remote desktop is much more 'performant' than all other solutions around. :-X
I want to reinstall BOINC as a service - now its an app - so I don't have to be logged on. Do these instructions apply, if I delete and reinstall BOINC? Or, will I lose my WU cache? (WinXP SP3)
Hi Art, yes - it will work fine, you will not loose the cache or current V9 app. The BOINC data folder will not be deleted when uninstalling BOINC. Even better, when installing BOINC again (e.g. as a service), it will 'remember' the old data folder. Would perform the following (and did it this way a lot of times before):
1. Stop BOINC.
2. Uninstall BOINC.
3. Install BOINC, choose the protected mode install (as a service).
4. Start BOINC, should run now as a service.
4.1. Please keep in mind to set the BOINC service startup type to automatic (will then run when you're not logged in).
Here is no real need to disable network access or backup the data folder (just my point of view) but feel free to do so, it's the secure way. When performing later an update to V10, it's for sure an excellent idea as Raistmer explained. :)
Cheers,
yodi
-
The key difference from V9 packs is :
The "team" mod now supports multi-GPU configs.
There will be number_of_GPUs file in SETI project directory. By default it contains number of 1.
If you have more GPUs just edit that file (enter number of GPUs installed in host instead of 1 ).
And don't forget to change your cc_config.xml
{Snip}
Fixed version posted, please, update your configs.
Thanks mr.kjellen from SETI main forums for bug report.
The quote above is from the first page on this thread. Re: the reference to "Fixed version posted......" Does this mean somewhere in those 15 pages there is a fix to V10 that I need to install?
Second item, this for Yodi: You said:
Hi Art, yes - it will work fine, you will not loose the cache or current V9 app. The BOINC data folder will not be deleted when uninstalling BOINC. Even better, when installing BOINC again (e.g. as a service), it will 'remember' the old data folder. Would perform the following (and did it this way a lot of times before):
1. Stop BOINC.
2. Uninstall BOINC.
3. Install BOINC, choose the protected mode install (as a service).
4. Start BOINC, should run now as a service.
4.1. Please keep in mind to set the BOINC service startup type to automatic (will then run when you're not logged in).
Here is no real need to disable network access or backup the data folder (just my point of view) but feel free to do so, it's the secure way. When performing later an update to V10, it's for sure an excellent idea as Raistmer explained. Smiley
Cheers,
yodi
Unfortunately this did not occur on my PC. Uninstalling BOINC also emptied out the BOINC work directory in my "My Documents" including SETI and Einstein folders. I saved work before uninstalling so now I'll see if the BOINC service installation will begin working from my last, saved and restored, work directory.
Is there something I can to to ensure the new BOINC service uses the saved work?
I was using BOINC 6.4.5 and that is the install I will repeat for the service configuration.
Thanks
Art
-
Second item, this for Yodi: You said:
Hi Art, yes - it will work fine, you will not loose the cache or current V9 app. The BOINC data folder will not be deleted when uninstalling BOINC. Even better, when installing BOINC again (e.g. as a service), it will 'remember' the old data folder. Would perform the following (and did it this way a lot of times before):
1. Stop BOINC.
2. Uninstall BOINC.
3. Install BOINC, choose the protected mode install (as a service).
4. Start BOINC, should run now as a service.
4.1. Please keep in mind to set the BOINC service startup type to automatic (will then run when you're not logged in).
Here is no real need to disable network access or backup the data folder (just my point of view) but feel free to do so, it's the secure way. When performing later an update to V10, it's for sure an excellent idea as Raistmer explained. Smiley
Cheers,
yodi
Unfortunately this did not occur on my PC. Uninstalling BOINC also emptied out the BOINC work directory in my "My Documents" including SETI and Einstein folders. I saved work before uninstalling so now I'll see if the BOINC service installation will begin working from my last, saved and restored, work directory.
Thanks
Art
This is wrong. My work directory was restored with reinstalling Boinc. But, my graphics card is now idle. Five AP WU are running, two at half speed.
Did I miss an update somewhere in these 15 pages of posts?
Conditions:
XP SP3
Q6600 processor
<cc_config>
<options>
<save_stats_days>120</save_stats_days>
<ncpus>5</ncpus>
</options>
</cc_config>
number_of_gpu = 1
NX8500GT GPU
V10 installed.
-
{Snip}
But, my graphics card is now idle. Five AP WU are running, two at half speed.
Did I miss an update somewhere in these 15 pages of posts?
Conditions:
XP SP3
Q6600 processor
<cc_config>
<options>
<save_stats_days>120</save_stats_days>
<ncpus>5</ncpus>
</options>
</cc_config>
number_of_gpu = 1
NX8500GT GPU
V10 installed.
I found V10b executable update on page 6 of this thread, installed and restarted the service. There was no change...my GPU remains idle. What do I need to do?
Thanks
Art
http://setiathome.berkeley.edu/show_host_detail.php?hostid=3885559
[attachment deleted by admin]
-
...My work directory was restored with reinstalling Boinc. But, my graphics card is now idle. Five AP WU are running, two at half speed.
Hi Art, good to know finally it worked. :) For the idle graphic card: this is usual as AP WUs will not be calculated using the graphic card. Do you have any setiathome enhanced WUs in your cache? Guess the right host is this one, (http://setiathome.berkeley.edu/show_host_detail.php?hostid=4296770) with AP WUs only downloaded for any reason.
In case you have no setiathome enhanced WUs cached, please check in your preferences, (http://setiathome.berkeley.edu/prefs.php?subset=project) if setiathome enhanced is enabled or not. Once there, check as well, if the graphic card is allowed to be used.
Your cc_config and number_of_gpu files are looking fine.
Cheers,
yodi
-
...My work directory was restored with reinstalling Boinc. But, my graphics card is now idle. Five AP WU are running, two at half speed.
Hi Art, good to know finally it worked. :) For the idle graphic card: this is usual as AP WUs will not be calculated using the graphic card. Do you have any setiathome enhanced WUs in your cache? Guess the right host is this one, (http://setiathome.berkeley.edu/show_host_detail.php?hostid=4296770) with AP WUs only downloaded for any reason.
In case you have no setiathome enhanced WUs cached, please check in your preferences, (http://setiathome.berkeley.edu/prefs.php?subset=project) if setiathome enhanced is enabled or not. Once there, check as well, if the graphic card is allowed to be used.
Your cc_config and number_of_gpu files are looking fine.
Cheers,
yodi
All SETI work sources are checked and GPU enabled in prefs. But still no SETI WU downloaded. Raistmer suggested it is because I have AP checked, that SETI would then prefer to download only AP WU. I also asked why only 4 or 5 AP WU in queue, when I have 10 days in preferences. Four or 5 WU in queue is only enough for a half day.
At any rate this PC has nothing but AP in SETI queue. It is good to know that I cannot expect GPU activity with only AP WU, so now I can go back to sleep :-)
Thanks
Art
-
...My work directory was restored with reinstalling Boinc. But, my graphics card is now idle. Five AP WU are running, two at half speed.
Hi Art, good to know finally it worked. :) For the idle graphic card: this is usual as AP WUs will not be calculated using the graphic card. Do you have any setiathome enhanced WUs in your cache? Guess the right host is this one, (http://setiathome.berkeley.edu/show_host_detail.php?hostid=4296770) with AP WUs only downloaded for any reason.
In case you have no setiathome enhanced WUs cached, please check in your preferences, (http://setiathome.berkeley.edu/prefs.php?subset=project) if setiathome enhanced is enabled or not. Once there, check as well, if the graphic card is allowed to be used.
Your cc_config and number_of_gpu files are looking fine.
Cheers,
yodi
All SETI work sources are checked and GPU enabled in prefs. But still no SETI WU downloaded. Raistmer suggested it is because I have AP checked, that SETI would then prefer to download only AP WU. I also asked why only 4 or 5 AP WU in queue, when I have 10 days in preferences. Four or 5 WU in queue is only enough for a half day.
At any rate this PC has nothing but AP in SETI queue. It is good to know that I cannot expect GPU activity with only AP WU, so now I can go back to sleep :-)
Thanks
Art
It has been mentioned on the Seti Boards that quite a few people are only getting Astropulse_v5, myself being one of them,
My Laptop not having any multibeam since sometime in February, to overcome it you could try deselecting astropulse and astropulse_v5 in your preferences,
and select 'If no work for selected applications is available, accept work from other applications?' to yes,
It'll mean you'll ask for Multibeam work and if there's none, then you'll get Astropulse, and if you still get too much Astropulse,
then deselect it untill you do need it again.
Claggy
-
Inside the number of gpus file you have to put your gpu type also other then the number of gpus.
Thank you
-
Just a Quick Question. In one of my system I have the GTX260 and 8800GT, boinc is seeing it as two 8800. Doest it matter.
3/13/2009 21:25:31||CUDA devices found
3/13/2009 21:25:31||Coprocessor: GeForce 8800 GT (2)
Thank you
-
Inside the number of gpus file you have to put your gpu type also other then the number of gpus.
Thank you
OK. My file only has the character 1 in it. How do I identify a NX8500? And, just today I received a NX9800GTX for a new PC. How do I identify that?
In other words, what text does the GPU file expect to see other than the number of GPU's?
Or looking at it another way, where's a help page on how to identify a GPU?
BOINC knows about the GPU. I see it in Messages tab when BOINC starts up.
Thanks
Art
-
My number of GPU file just says 2 for 2 GPUs.
Thank you
-
Inside the number of gpus file you have to put your gpu type also other then the number of gpus.
Thank you
Did you forget question sign after end of sentence?
If yes - answer is no.
If it was your suggestion to other members - please, stop making incorrect assumptions about way pack is working. There should be NOTHING except single number.
It described in first post, plese, read already available info before start to invent something. This can lead only to more caches trashing...
-
Perhaps I just don't understand what is supposed to happen. I allowed AP and SETI WU in SETI preferences. I ask for 10 days of work in my cache.
Since then I have no SETI work at all, only AP. And I have only a maximum of 8 AP WU in cache, about one day of work (~12 hr/APWU). My GPU is continuously idle whereas before AP it was always at 100%.
What I expected to happen is some cores would do AP, some SETI, my GPU would be busy with SETI WU, and I'd maintain enough work for 10 days.
My operating conditions are as stated just 4 or 5 posts down:
Conditions:
XP SP3
Q6600 processor
<cc_config>
<options>
<save_stats_days>120</save_stats_days>
<ncpus>5</ncpus>
</options>
</cc_config>
number_of_gpu = 1
NX8500GT GPU
V10 installed.
From my perspective enabling AP is not a good thing. Not only have I taken a huge hit in RAC until if and when credit grants catch up but my GPU hasn't done a tick of work. It seems for many of my AP WU my wingman errors out, opts out before finishing, or is working with a P2-200 that can't possibly finish before the deadline. The RAC is nice at 1,250 per WU but not if its never credited.
I don't mind so much, waiting for credit grants to start flowing. But I do mind an idle GPU.
Is it accurate to say, if I want a hardworking GPU I need to disable AP?
Or, do I need an entry in app_info.xml or cc_config, that will permit CPU crunching of AP and SETI, and also SETI crunching on GPU - as the name of this discussion implies?
Thanks
Art
-
It described in first post, plese, read already available info before start to invent something. This can lead only to more caches trashing...
This is getting painful... At the beginning of this forums it is stated that those apps are for advanced users only.
And here are the questions that show disinterest at least to read the thread from the beginning. That's not "advanced". Trashing WU not fair to the other wingman and not for the science itself.
-
This is getting painful... At the beginning of this forums it is stated that those apps are for advanced users only.
And here are the questions that show disinterest at least to read the thread from the beginning. That's not "advanced". Trashing WU not fair to the other wingman and not for the science itself.
I dont understand you remark with "advanced" in combination with the recents messages here (could be my english), mayby you can explain a bit more? If its only the AP problem in combination with slow wingmans then just disable AP and delete the queued AP's.
Personally my credits went up from 2500 to a fantastic 5400 (cpu q6600@2400 + 9800gt running V10) so a little reading and experimenting wont hurt i guess.
-
This is getting painful... At the beginning of this forums it is stated that those apps are for advanced users only.
And here are the questions that show disinterest at least to read the thread from the beginning. That's not "advanced". Trashing WU not fair to the other wingman and not for the science itself.
I dont understand you remark with "advanced" in combination with the recents messages here (could be my english), mayby you can explain a bit more? If its only the AP problem in combination with slow wingmans then just disable AP and delete the queued AP's.
Personally my credits went up from 2500 to a fantastic 5400 (cpu q6600@2400 + 9800gt running V10) so a little reading and experimenting wont hurt i guess.
What SoNic is refering to is that some don't know what they're doing/are to lazy to read the initial post and that's why this thread gets bloated with postings from people that got no clue.
'Advanced' users should be able to get it working without spaming this thread.
-
What SoNic is referring to is that some don't know what they're doing/are to lazy to read the initial post and that's why this thread gets bloated with postings from people that got no clue.
'Advanced' users should be able to get it working without spamming this thread.
(http://img.photobucket.com/albums/v330/setiweb/READSTICKIES.png)
-
This is getting painful... At the beginning of this forums it is stated that those apps are for advanced users only.
And here are the questions that show disinterest at least to read the thread from the beginning. That's not "advanced". Trashing WU not fair to the other wingman and not for the science itself.
I dont understand you remark with "advanced" in combination with the recents messages here (could be my english), mayby you can explain a bit more? If its only the AP problem in combination with slow wingmans then just disable AP and delete the queued AP's.
Personally my credits went up from 2500 to a fantastic 5400 (cpu q6600@2400 + 9800gt running V10) so a little reading and experimenting wont hurt i guess.
What SoNic is refering to is that some don't know what they're doing/are to lazy to read the initial post and that's why this thread gets bloated with postings from people that got no clue.
'Advanced' users should be able to get it working without spaming this thread.
http://www.grokdotcom.com/topics/errormessages.htm
-
@ Raistmer
I got a 9800GTX+ today for experimenting purposes and found this topic.
Installed the V10 with the update and it looks like everything is working great.
Will let you know in a few days (or earlier) if I encounter any problems.
Great work!
-
I am a few computition errors once in a while, but overall is going strong.
Thank you
-
I came to grips, internally, with AP vs SETI vs MB work. After reading in the SETI boards that someone had success manually managing the division of work I stopped AP WU downloads temporarily . Sorry I don't recall where, was reading a lot. Its working for me.
Why I post is for this interesting factoid which I have not seen elsewhere. Temporarily I halted inprogress AP until one core switched to SETI and began processing. It seems it was a CUDA unit. After a time I restarted AP processing..lo and behold! The CUDA unit continued processing, albeit very slowly such that for a time the BOINC tasks tab timer was increasing rather than decreasing.
This is probably not a good thing and I won't do it again. My result does not match wingman, and a second wingman is now processing. I'm sure I will lose credit. I believe this is the result:
http://setiathome.berkeley.edu/workunit.php?wuid=424562219
The good news viz AP is patience is a virtue. I've completed about 30 AP WU which have finally begun to verify. V10 is calculating these at ~12 hr per WU. After shutting off further AP download I finally got some SETI which will begin to process tomorrow as the AP cache empties.
If the gurus have a better way to manage work I am all ears. It could be, if I was patient enough, the work would manage itself as the SETI WU return deadline gets near such that BOINC would prioritize them. The trick seems, if some SETI WU are desired, to occasionally manually disable AP downloads, let the cache empty. OTOH I read a blog by Matt Lebofsky implying the reason we got lots of AP recently has to do with differences in AP vs SETI server queue distribution, such that it will eventually manage itself. I wish I'd recorded where I read that on the SETI boards.
Finally, rummaging through the several xml files I noticed that both SETI and BOINC have "Maintain this minimum work" and "Maintain that extra days work" with min set to 0.1 days (or maybe 0.01 I forget) and of course the max of 10 days. I have now set these both to 5 days, i.e. maintain 5 days min and 5 days additional is how the xml states it. I know not, TBA, if this is useful - just did it this AM. Could not find enlightenment on the boards. Some posters have expressed dismay at 10 days cached work. Out here in southwest Colorado USA flyover country we lose power, internet access, and both such that 10 days can be a minimum during stormy season which is fast approaching.
Searching the boards is one time consuming, albeit productive, activity for those of us who are not in the guru category, although fully capable of adding 2 and 2. Occasionally a succinct summary of current events, functionality, expectations etc would be very useful troubleshooting to compare what we SHOULD see vs. what we DO see.
V10 is working for me! Profuse thanks to those who built it.
Art
-
Hi guys....
I read page one and just installed V10 (the third one) for a P4 + one 8500GT (driver 182.08) to see the effect....
My BOINCMGR version is 6.6.11, OS XP SP3 x86.
The CPU is not crunching at all, the process AK_v8b_win_SSE3_GPU_CPU_team_V10 is idle.
BOINCMGR shows "No work available for the applications you have selected. Please check your settings on the web site."
This is my cc_config.xml:
<cc_config>
<options>
<ncpus>2</ncpus>
</options>
</cc_config>
How may I correct this problem? :P
This is a test (taste) for this new app I came across, I am so willing to use this app for all my computers with GTX295 ;D to get higher RAC!!
So many thanks!! ::)
Peter.
-
it seems that team mod is not needed for SETI main - if u install 6.6.15 and above it will use CPU for SETIMB too
-
Is it worth running my AMD 3400+ and Intel P4 HT. Or are they just slowing down my other systems. Right now those two got work, and my other systems get no work.
Thank you
-
A strange problem which occurs here from time to time is that sometimes when boinc 6.4.7 want to do some high priority tasks it starts a few new tasks but it seems to ignore the max amount of cpu's mentioned in the cc_config.xml (or is counting them wrongly). At such moments my q6600 and nvidia 9800gt are then running 5 cpu tasks + a gpu task (so 6 tasks in total).
Is this problem a boinc related problem or has it todo with a changed cc_config.xml or optimized client?
Any ideas?
Greetings,
Marius
Processor: Intel(R) Core(TM)2 Quad CPU Q6600
GPU processor: GeForce 9800 GT (driver 185.20)
cc_config.xml
<cc_config>
<options>
<ncpus>5</ncpus>
</options>
</cc_config>
-
Another problem i noticed; Sometimes the MB_6.08_mod_CUDA_V10.exe stops while its at 1 second of cpu (MB shows no activity in task manager and its using only 32.412kb of memory). It stays this way until i restart boinc. Is this a known problem/bug or can i solve/finetune boinc or nvidia software to avoid this?
It could be related to high priority boinc units which seem to overrule running threads (but i just as well be plain wrong)
Greetings,
Marius
Processor: Intel(R) Core(TM)2 Quad CPU Q6600
GPU processor: GeForce 9800 GT (driver 185.20)
cc_config.xml
<cc_config>
<options>
<ncpus>5</ncpus>
</options>
</cc_config>
-
Another problem i noticed; Sometimes the MB_6.08_mod_CUDA_V10.exe stops while its at 1 second of cpu (MB shows no activity in task manager and its using only 32.412kb of memory). It stays this way until i restart boinc. Is this a known problem/bug or can i solve/finetune boinc or nvidia software to avoid this?
It could be related to high priority boinc units which seem to overrule running threads (but i just as well be plain wrong)
Greetings,
Marius
Processor: Intel(R) Core(TM)2 Quad CPU Q6600
GPU processor: GeForce 9800 GT (driver 185.20)
cc_config.xml
<cc_config>
<options>
<ncpus>5</ncpus>
</options>
</cc_config>
Look this thread about CUDA app freezings: http://lunatics.kwsn.net/12-gpu-crunching/vbscript-fights-cuda.0.html
-
I'm running "stock" Boinc 6.6.17-64bit on my lappy, no optimized application installed yet. I immediately noticed that it will keep the GPU fed with work units, it also labels the Enhanced 6.08 work units as "(cuda)". It appears to me the latest Boinc runs cuda applications and fetches cuda applications as you would expect, woot!
I noticed in the c:/program data/.../setiathome.berkeley.edu folder there is not an app_info.xml file. If a install Raistmer's Opt V10a Pack along with a appropriate cc_config.xml file (or none) I end up running one more AP work unit then the number logical CPU's, rather then placing a 6.08 cuda work unit on the GPU.
So how can one use Raistmer's Opt V10a Pack and get it to behave the same as stock??? I think what is in the app_info file needs to be updated for the latest boinc.
what would keep me from renaming Raistmer's executables the same a the stock executable and copy the dll files? i really don't want to do that, they could easily be over written by Bionc.
edit: also posted http://setiathome.berkeley.edu/forum_thread.php?id=52628&nowrap=true#878280
-
I'm running "stock" Boinc 6.6.17-64bit on my lappy, no optimized application installed yet. I immediately noticed that it will keep the GPU fed with work units, it also labels the Enhanced 6.08 work units as "(cuda)". It appears to me the latest Boinc runs cuda applications and fetches cuda applications as you would expect, woot!
I noticed in the c:/program data/.../setiathome.berkeley.edu folder there is not an app_info.xml file. If a install Raistmer's Opt V10a Pack along with a appropriate cc_config.xml file (or none) I end up running one more AP work unit then the number logical CPU's, rather then placing a 6.08 cuda work unit on the GPU.
So how can one use Raistmer's Opt V10a Pack and get it to behave the same as stock??? I think what is in the app_info file needs to be updated for the latest boinc.
what would keep me from renaming Raistmer's executables the same a the stock executable and copy the dll files? i really don't want to do that, they could easily be over written by Bionc.
AFAIK you need app_info in all cases when you want to use opt apps. No mater what BOINC version do you use or do you use CPU only or CPU+GPU.
Working w/o app_info will enable only stock apps on your host.
-
what is the benefit of your optimized cuda over stock cuda???
I'm going to try MarkJ's app_info, just wondering if it is worth while to insert your cuda app over the stock.
this should finally get my gpu loaded.
-
what is the benefit of your optimized cuda over stock cuda???
1) VLAR-kill mod
2) correct priority settings
3) elapsed time information availability
[4) affinity binding and ignoring of BOINC suspend order]
Last position is relative advantage, not in all cases it's good.
In coming V11 (at least CUDA app if not team pack) will be reduction of initial CPU time.
But I spoke not only about CUDA app itself. If you will not use app_info.xml you will not be able to use opt AP (~5x performnce loss) and opt AK_v8 (~1,5-2 performance loss).
All opt apps need appropriate app_info to be used.
-
ok, i plugged in your cuda app. i'm running all your apps on Boinc 6.6.17 using MarkJ's app_info.xml, i replaced the stock executables with yours in the app_info file and everything works. i have not had a chance to see if the gpu count option works yet at the bottom of the app_info file.
see the following thread for MarkJ's app_info instructions.
http://setiathome.berkeley.edu/forum_thread.php?id=52589
edit: i have not had to modify the gpu count at the bottom of MarkJ's app_info file on machines with more then one video card.
-
I wonder if could be 2 quenies , one for ap , sec for gpu - all mb go for gpu , and we could set cpu cores for quenie ap , and units gpu with quenie mb , and if ap quenie would be empty they could fetch from sec quenie mb - that could solve problems with gpu idle - and cpu idle , and for cpu - eliminate situation when work at 3 wu on 2 cores
-
Is it possible to have a grid displaying all the versions, with, at least, a brief explanation and the platform involved and a link to a specific forum ?? (and whatever else usefull for a better comprehension of all the optimized Seti applications)
Something like http://www.zslip.com/ for milkyway !!
-
i think you mean queues
I wonder if could be 2 queues, one for ap , sec for gpu - all mb go for gpu , and we could set cpu cores for queues ap , and units gpu with queues mb , and if ap queues would be empty they could fetch from sec queues mb - that could solve problems with gpu idle - and cpu idle , and for cpu - eliminate situation when work at 3 wu on 2 cores
this is what boinc 6.6.17 (beta) does. you need to use MarkJ's app_info file and edit it to use all of Raistmer's apps.
-
Look this thread about CUDA app freezings: http://lunatics.kwsn.net/12-gpu-crunching/vbscript-fights-cuda.0.html
Thanks Raistmer, hadn't realized that thread was the solution. Works perfectly sofar:
22-03-2009 15:33:23 > 03ja09ab.14408.24323.15.8.250_1 runtime 41s -> compute error?
22-03-2009 17:13:52 > 03ja09aa.9115.25021.15.8.235_1 runtime 123s -> stuck ?
22-03-2009 17:16:35 > 03ja09aa.9115.25021.15.8.250_1 runtime 285s -> stuck ?
22-03-2009 17:24:42 > 03ja09aa.9115.25021.15.8.248_1 runtime 773s -> stuck ?
22-03-2009 17:27:25 > 03ja09aa.9115.25021.15.8.254_1 runtime 935s -> stuck ?
22-03-2009 17:30:07 > 03ja09aa.9115.25021.15.8.249_1 runtime 1098s -> stuck ?
22-03-2009 18:58:02 > 30dc08aa.20531.4571.15.8.224_1 runtime 83s -> compute error?
22-03-2009 19:37:22 > 03ja09ad.9820.481.10.8.171_1 runtime 62s -> compute error?
22-03-2009 20:18:32 > 10ja09ac.28248.3340.3.8.96_1 runtime 128s -> stuck ?
23-03-2009 02:00:26 > 03ja09ad.9820.13160.10.8.120_1 runtime 82s -> compute error?
23-03-2009 08:56:39 > 11ja09aa.20812.20931.7.8.2_0 runtime 44s -> compute error?
23-03-2009 10:15:18 > 10ja09ac.24743.77435.8.8.0_1 runtime 43s -> compute error?
23-03-2009 17:05:30 > 10ja09ac.24743.89296.8.8.3_1 runtime 43s -> compute error?
-
where can I find Mark app_info.xml ? , should I use Raistmer apps or use standalone optimized ap and mb ak v8 ?
-
where can I find Mark app_info.xml ? , should I use Raistmer apps or use standalone optimized ap and mb ak v8 ?
with BOINC 6.6.17 you should be able to use "standalone" opt apps.
-
I have all errors on cuda mb :( , even if i edited platform to windows_x86_64 , but what i need change it uses setiathome_6.08_windows_intelx86__cuda.exe , where can i download 64bit version?
-
I have all errors on cuda mb :( , even if i edited platform to windows_x86_64 , but what i need change it uses setiathome_6.08_windows_intelx86__cuda.exe , where can i download 64bit version?
There is no x64 CUDA MB released cause preliminary builds still doesn't show any speed increase.
-
Here V10/11 CUDA MB update (old filename used to simplify updating).
Just replace your current CUDA MB executable with this one.
It has some performance gain due to decreased CPU consumption during startup.
ADDON: Also, it should do more smooth %done increase indication.
[attachment deleted by admin]
-
Here V10/11 CUDA MB update (old filename used to simplify updating).
Just replace your current CUDA MB executable with this one.
It has some performance gain due to decreased CPU consumption during startup.
ADDON: Also, it should do more smooth %done increase indication.
Seems to work great :)
-
Just switched to the optimized apps and things seem to be running quite well. I don't have any AP workunits yet, I disabled them to make sure I got some MB for CUDA. Hopefully AP work units will go faster as well. I've only had two notable issues so far.
1. Trying to track down the latest release + update + get it all together is rather confusing
2. I'm on a laptop and had to update my graphics drivers via laptopvideotogo.com
Given the fairly small numbers of downloads I see right now I may be able to host your apps on my server if your interested Raistmer. Possibly could have a centralized status page as well for latest version information.
Have you considered releasing optimized apps for platforms other than windows? I'm crunching MB units in about 3 hours on a Core2 6320 (1.86GHz) on FreeBSD and it would be nice if I could crunch a bit faster.
-
Just switched to the optimized apps and things seem to be running quite well. I don't have any AP workunits yet, I disabled them to make sure I got some MB for CUDA. Hopefully AP work units will go faster as well. I've only had two notable issues so far.
1. Trying to track down the latest release + update + get it all together is rather confusing
2. I'm on a laptop and had to update my graphics drivers via laptopvideotogo.com
Given the fairly small numbers of downloads I see right now I may be able to host your apps on my server if your interested Raistmer. Possibly could have a centralized status page as well for latest version information.
Have you considered releasing optimized apps for platforms other than windows? I'm crunching MB units in about 3 hours on a Core2 6320 (1.86GHz) on FreeBSD and it would be nice if I could crunch a bit faster.
As all conservation laws say, for reducing someone efforts someone else should do work.
For now I have no time to collect updates, do nice web pages and so on... I hope you understand. If someone wonna do this work, it would be very appreciated.
About FreeBSD - never worked with this OS. There is some porter to FreeBSD in boinc_opt mail list, but he wants to work only with stock app codebase. Maybe when part of optimizations will be carried into stock code another platforms will get performance boost too (in first place it concerns AP app).
-
Here V10/11 CUDA MB update (old filename used to simplify updating).
Just replace your current CUDA MB executable with this one.
It has some performance gain due to decreased CPU consumption during startup.
ADDON: Also, it should do more smooth %done increase indication.
Does this have VLAR kill?
-
Does this have VLAR kill?
sure
-
OK. Thanks.
Will try it out on my "old" rig.
-
:-) i use 6.6.17 boinc 64bit, and small changed mark's app_info , and ak v8 64bit , ap 32bit , and mb cuda 32bit too , yeah , i updated nvidia notebook driver to vista64 181.22 , and now working without error :-) thanks , with Raistmer opts i couldnt get any cuda work , now i have many wu waiting , and ap working too
-
3/25/2009 12:36:25|SETI@home|Message from server: (Project has no jobs available)
Seems dried up. I need some cuda work.
Thank you
-
Raistmer do you recommend moving from Boinc 6.4.5
Thank you
-
Raistmer do you recommend moving from Boinc 6.4.5
Thank you
To recommend smth I wanna try it first. I still use 6.4.5, but it doesn't mean that this is the best way to go. Simple I didn't try 6.6.17 still.
-
Sorry if this has been asked before.
I am running V10a with the latest FFTW update. All was running well but then as the MB work has dried up on my machine, it has started to run 3 astropulse units on my dual cpu. Is this normal? I guess this is a side effect of the cc file stating 3 cpus?
http://setiathome.berkeley.edu/show_host_detail.php?hostid=3366055
-
Sorry if this has been asked before.
I am running V10a with the latest FFTW update. All was running well but then as the MB work has dried up on my machine, it has started to run 3 astropulse units on my dual cpu. Is this normal? I guess this is a side effect of the cc file stating 3 cpus?
http://setiathome.berkeley.edu/show_host_detail.php?hostid=3366055
Yes it is normal, in fact that's the official purpose of that setting; to emulate more CPUs than the host actually has. Running 3 APs on a dual CPU system is somewhat less efficient than two, so you could temporarily change the cc_config. However, the project does have one mb_splitter running now, so you may get at least some GPU work.
Joe
-
ok thamnks for clarifying that.
didn't bother changing the cc again.
however did managed to get a few MB units, however bonic didn't start them, carried on doing the three AP jobs.
i tried suspening one of the AP units, thinking it would go onto the next MB unit, but it didn't, it just tried to start the next AP unit??
ended up having to suspend 10 AP units before it got to the MB work unit and started that, which it did pass to GPU for processing.
-
Just out of curiosity, sorry if it's a stupid question. I'm kinda new to this.
I'm using BOINC v6.6.18 and NVIDIA driver v182.08 on WIndows XP x64. I have QX6700 and 3 GPUs (GTX295+8600GTS). I've set the <ncpus> option to 7 (4+3). and so far it run it seems to run ok but rather on a slow side.
I'm crunching on SETI@Home Beta and none of these tasks run on CUDA. All my SETI WUs are setiathome_enchanced 6.08, aren't these WUs supposed to be run by optimized CUDA app according to the app_info.xml? If so, then I might have a problem? I concurrently run GPUGRID project and it used all 3 CUDA tasks while SETI Beta taking 3 running slots but none show it it's utilizing CUDA GPU.
-
Just out of curiosity, sorry if it's a stupid question. I'm kinda new to this.
I'm using BOINC v6.6.18 and NVIDIA driver v182.08 on WIndows XP x64. I have QX6700 and 3 GPUs (GTX295+8600GTS). I've set the <ncpus> option to 7 (4+3). and so far it run it seems to run ok but rather on a slow side.
I'm crunching on SETI@Home Beta and none of these tasks run on CUDA. All my SETI WUs are setiathome_enchanced 6.08, aren't these WUs supposed to be run by optimized CUDA app according to the app_info.xml? If so, then I might have a problem? I concurrently run GPUGRID project and it used all 3 CUDA tasks while SETI Beta taking 3 running slots but none show it it's utilizing CUDA GPU.
With Boinc 6.6.x you don't need an <ncpus> entry in a cc_config file, just remove the entry, it was for Boinc 6.4.x to fool it it into thinking it had an extra CPU, Boinc 6.6.x knows about GPU's and doesn't need the work around.
setiathome _enhanced_6.08 is the Cuda app, and please don't run optimised apps on Beta unless they are for special testing of new unrealeased apps,
I 've recently been matched up with this user's computer (http://setiweb.ssl.berkeley.edu/beta/show_host_detail.php?hostid=38837) on Beta, he's running optimised Astropulse 5.00 r103 and trying to Validate against astropulse 5.04 (ie astropulse_v5) , Which isn't very helpful there, and a PM hasn't helped.
Run the optimised apps on the Main project, and visit this thread (http://setiathome.berkeley.edu/forum_thread.php?id=52589) to get the special app_info for Boinc 6.6.1x.
Claggy
-
Hi,
i need ask.. what the best build now ? ( for X2 Athlon and GTX 260 ) ? ( Cuda computing priorytet )
?
-
Hi,
What is the setting for using both cores in a GTX 295?
I have one GTX 295 and using the default setting of 1 in number_of_gpus does not seem to utilize more than one core, as the computations equals a GTX 285. A setting of 2 will spawn 2 GPU executables, but one of those will have a full CPU utilized continously, so it's not working..
I have seen references to various tweaks and also references to both cores running, but not become any wiser as to what is the correct combo of settings to utilize both cores on the GTX 295.
Regards
Morten Ross
-
Sum core numbers (each CPU core and each GPU core) and enter it as ncpus in cc_config.
Main rule - each core should run its own app instance.
@Slawek
V10/11 CUDA MB build from this thread fastest one for CUDA for the moment.
-
Hi,
That's also what I did, which results in the second cuda-executable with constant 100% on one CPU.
4 CPU cores + 2 GPU cores (one GTX 295 card) => ncpus=6 .
I would expect the two cuda-apps to utilize an equal share on no less than 4% CPU each.
To me there seems to be a problem in the second cuda app's ability of feeding the second core, as it instead is using CPU.
Nvidia driver 182.08, Windows 7 x64..
Morten
-
Hi,
That's also what I did, which results in the second cuda-executable with constant 100% on one CPU.
4 CPU cores + 2 GPU cores (one GTX 295 card) => ncpus=6 .
I would expect the two cuda-apps to utilize an equal share on no less than 4% CPU each.
To me there seems to be a problem in the second cuda app's ability of feeding the second core, as it instead is using CPU.
Nvidia driver 182.08, Windows 7 x64..
Morten
Check how many GPUs your BOINC sees.
What app do you use? If you use V10 pack - edit number_of_GPUs file and set 2 instead 1 there.
And make sure you don't use any kind of SLI mode.
-
Hi,
This is what Boinc sees:
"31.03.2009 21:18:16 CUDA device: GeForce GTX 295 (driver version 18208, CUDA version 1.3, 896MB, est. 106GFLOPS)", which is correct, as there is only one physical card in system - with two GPU cores.
I use Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team, as as said earlier - I've set the value to 2 in "number_of_GPUs" file.
Morten
-
Hi,
This is what Boinc sees:
"31.03.2009 21:18:16 CUDA device: GeForce GTX 295 (driver version 18208, CUDA version 1.3, 896MB, est. 106GFLOPS)", which is correct, as there is only one physical card in system - with two GPU cores.
I use Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team, as as said earlier - I've set the value to 2 in "number_of_GPUs" file.
Morten
Search SETI main forum when it will return from outage. There was thread about multicore GPUs and how to enable both cores.
-
Okay, the problem is this: I only want to use the optimized apps at my GPU. On the CPU should run Einstein@home. I am using BOINC-Manager 6.6.20. Down loaded and installed the latest package. But if I get an WU for SETI the Manager isn´t run it on the GPU, I have only 2 active tasks. Is there something that I can do?
-
Hi,
This is what Boinc sees:
"31.03.2009 21:18:16 CUDA device: GeForce GTX 295 (driver version 18208, CUDA version 1.3, 896MB, est. 106GFLOPS)", which is correct, as there is only one physical card in system - with two GPU cores.
I use Raistmer's_opt_pack_V10a_x64_SSSE3_MB_CPU_GPU_team, as as said earlier - I've set the value to 2 in "number_of_GPUs" file.
Morten
you have to disable SLI for CUDA to see both GPUs as "independent" GPU's...
-
I think, I said wrong. I have a C2D and 1 GPU for crunching. The GPU should do SETI with the optimized app and the 2 CPUs Einstein.
-
I think, I said wrong. I have a C2D and 1 GPU for crunching. The GPU should do SETI with the optimized app and the 2 CPUs Einstein.
I don't think boinc is smart enough for this... if it sees a unused core (cpu or gpu) and is has a seti task, it can give it to CPU as well. And then your einstain comes, and there is no free cpu core, and it waits for it....
Have you tried latest development 6.6.20? Maybe this one is smart enough?
-
Okay, the problem is this: I only want to use the optimized apps at my GPU. On the CPU should run Einstein@home. I am using BOINC-Manager 6.6.20. Down loaded and installed the latest package. But if I get an WU for SETI the Manager isn´t run it on the GPU, I have only 2 active tasks. Is there something that I can do?
You just need a Cuda only app_info, Raistmer's V10/V11 app can be run standalone without the team part.
Here's a Cuda only app info using Raistmer's V11 app (http://lunatics.kwsn.net/12-gpu-crunching/v10-of-modified-seti-mb-cuda-opt-ap-package-for-full-multi-gpucpu-use.msg16231.html#msg16231), you'll need to put in your own GPU flops figure, but Multiply it by 0.2 first, get it from the Boinc messages log and Don't forget all the extra zeroes seeing as its in gigaflops.
Claggy
<app_info>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>MB_6.08_mod_CUDA_V10.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft.dll</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<platform>windows_intelx86</platform>
<avg_ncpus>0.127970</avg_ncpus>
<max_ncpus>0.127970</max_ncpus>
<flops>12000000000</flops>
<plan_class>cuda</plan_class>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
</app_version>
</app_info>
-
Thanks a lot. Looks like it works. If BOINC mangaer says CUDA has 85GFlops, I have only to change "<flops>12000000000</flops>" to "<flops>85000000000</flops>"?
-
Thanks a lot. Looks like it works. If BOINC mangaer says CUDA has 85GFlops, I have only to change "<flops>12000000000</flops>" to "<flops>85000000000</flops>"?
Sorry, you've got to Multiply that figure by 0.2
My 9800GTX+ was 87 Est.Gflops, ie 87 000 000 000 * 0.2 = 17 400 000 000
see MarkJ's app_info thread (http://setiathome.berkeley.edu/forum_thread.php?id=52589)
Claggy
-
Tahnks a lot again. Now I think, I have it. ;)
-
Sorry for beeing a noob first :)
im using Bonic Client 6.4.7
Intel Core2Duo 8400 45nm with support ut to SSE4.1
3Gb Ram PC1023
XP 32bit Pro SP3
Gainward 260 55nm version 216 shaders
i see 2 versions one called x86_SSSE3 and x86_SSE3 and im not shure whitch version i sould use.
Second Question is where is this cc_config.xml you are talking about, i dont have this file on my pc (checkt manuell and via search funktion includet hidden/system ... files.
-
You can use the SSSE3 one.
You say that you use boinc 6.4.7. I suggest you download the latest beta 6.6.20 from berkeley. It's beta but it hasn't any big problems and it has much much better handling of cuda.
The cc_config.xml file is found in the boinc directory together with the boinc executables, client_state.xml etc. I think it doesn't exist by default, you have to write one by yourself.
-
thx sunu have found the place and createt the file :D
-
Ok Torix. Forgot to tell you, here (http://boinc.berkeley.edu/wiki/Client_configuration) you can find everything you can put in cc_config.xml.
-
thx Raistmer for your aps.
with the original astropulse_v5_503 my computer needet 54h to complete the unit with your moddet ap_5.03r112_SSE3.exe it went down to 7h 25min now. Also changed the Bonic client now to the Beta 6.6.20 Version (computet first all downloadet WU´s and update it without any active WU´s) seems running fine on my pc.
-
Hi everyone. I have a quick question. If I try the package with 6.6.20 will I need to edit app_info to include flops (or edit it in any other way for that matter), or will it just be enough to do what's said in the first post?
thanks
--
Orin
my PC (http://setiathome.berkeley.edu/hosts_user.php?userid=251328)
-
thx Raistmer for your aps.
with the original astropulse_v5_503 my computer needet 54h to complete the unit with your moddet ap_5.03r112_SSE3.exe it went down to 7h 25min now. Also changed the Bonic client now to the Beta 6.6.20 Version (computet first all downloadet WU´s and update it without any active WU´s) seems running fine on my pc.
Yes, opt AP is a LOT faster than 5.03 stock app but, please, don't forget that current state of opt AP is a result of whole Lunatics team work. All entered some speeding up mods or gave some speeding up ideas.
BTW, some of these modifications already merged in stock too so we can hope new 5.05 and up AP will be much faster than its precursors.
-
Hi everyone. I have a quick question. If I try the package with 6.6.20 will I need to edit app_info to include flops (or edit it in any other way for that matter), or will it just be enough to do what's said in the first post?
thanks
--
Orin
my PC (http://setiathome.berkeley.edu/hosts_user.php?userid=251328)
There is two ways to achieve the same goal (use all 3 opt apps for crunching).
Either by using my V10 pack or by using BOINC 6.6.14 and up with corresponding app info file.
If you have no problems with BOINC 6.6.20 itself the second way is better that is, with BOINC 6.6.20 you need ONLY CUDA MB part of V10 pack (or even better, V10/11 update, I will post it to first page too soon. For now search this thread). Correct app_info you can take from this thread on SETI main forum:
http://setiathome.berkeley.edu/forum_thread.php?id=52589
And don't forget to remove cc_config.xml file when you end using "team" pack. It was only temporary solution until BOINC can't do CUDA scheduling correctly. Now BOINC repaired so - no need to use team pack anymore. Only CUDA opt app could be used still cause it gives some performance increase over stock one.
-
There is two ways to achieve the same goal (use all 3 opt apps for crunching).
Either by using my V10 pack or by using BOINC 6.6.14 and up with corresponding app info file.
If you have no problems with BOINC 6.6.20 itself the second way is better that is, with BOINC 6.6.20 you need ONLY CUDA MB part of V10 pack (or even better, V10/11 update, I will post it to first page too soon. For now search this thread).
This (http://lunatics.kwsn.net/12-gpu-crunching/v10-of-modified-seti-mb-cuda-opt-ap-package-for-full-multi-gpucpu-use.msg16231.html#msg16231) one, right? What about AK_v8b_win_SSE3_AMD_GPU_CPU_team_V10.exe and AP apps? Do i take them from v10 package, or do I just skip them?
Correct app_info you can take from this thread on SETI main forum:
http://setiathome.berkeley.edu/forum_thread.php?id=52589
Allright, I'll give it a go.
Thanks Raistmer
--
Orin
-
I've tried to use this mod version on S@H CUDA WU but always get computation error within 30 secs. Not sure what I have done wrong. Is there any place I can retrieve the log of this error WU?
-
I've tried to use this mod version on S@H CUDA WU but always get computation error within 30 secs. Not sure what I have done wrong. Is there any place I can retrieve the log of this error WU?
Read Raistmer's post two before yours since you are also using Boinc 6.6.20,
I assume this is the host you're talking about:
hostid=4852276 (http://setiathome.berkeley.edu/results.php?hostid=4852276&offset=20&show_names=0&state=0)
And Please Stop using Optimised Astropulse 5.00 r103 on Seti Beta, It' doesn't validate with 5.03 on Seti Main, and it sure Won't Validate with AP 5.04 or 5.05
hostid=39303 (http://setiathome.berkeley.edu/beta/results.php?hostid=39303)
Claggy
-
I've tried to use this mod version on S@H CUDA WU but always get computation error within 30 secs. Not sure what I have done wrong. Is there any place I can retrieve the log of this error WU?
Read Raistmer's post two before yours since you are also using Boinc 6.6.20,
I assume this is the host you're talking about:
hostid=4852276 (http://setiathome.berkeley.edu/results.php?hostid=4852276&offset=20&show_names=0&state=0)
And Please Stop using Optimised Astropulse 5.00 r103 on Seti Beta, It' doesn't validate with 5.03 on Seti Main, and it sure Won't Validate with AP 5.04 or 5.05
hostid=39303 (http://setiathome.berkeley.edu/beta/results.php?hostid=39303)
Claggy
Is that mean I should delete any reference line that link to the CPU app in my app_info? I've attcahed my current app_info as below.
<name>astropulse_v5</name>
</app>
<file_info>
<name>ap_5.03r112_SSE3.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>astropulse_v5</app_name>
<version_num>503</version_num>
<platform>windows_intelx86</platform>
<flops>7285841676</flops>
<file_ref>
<file_name>ap_5.03r112_SSE3.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</name>
<executable/>
</file_info>
<file_info>
<name>MB_6.08_mod_CPU_team_CUDA.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft.dll</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_intelx86</platform>
<flops>4903931897</flops>
<file_ref>
<file_name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<platform>windows_intelx86</platform>
<avg_ncpus>0.127970</avg_ncpus>
<max_ncpus>0.127970</max_ncpus>
<flops>21200000000</flops>
<plan_class>cuda</plan_class>
<file_ref>
<file_name>MB_6.08_mod_CPU_team_CUDA.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
</app_version>
</app_info>
The second Computer ID isn't mine, I've not crunch SETI beta for a while although part of my rig hasn't been updated to reflect this. I'll try to do that soon. So is there any optimized app that can be used with Beta?
Thanks
frigens
-
AK_v8b_win_SSE3_AMD_GPU_CPU_team_V10.exe and AP apps? Do i take them from v10 package, or do I just skip them?
You can take AP app from V10 pack (V503 rev112) it's identical to standalone Lunatics build but should not use AK_v8 "teamed" apps with 6.6.20 and new app_info.
You should replace them with usual AK_v8 apps from Lunatics Download section.
-
I've tried to use this mod version on S@H CUDA WU but always get computation error within 30 secs. Not sure what I have done wrong. Is there any place I can retrieve the log of this error WU?
Read Raistmer's post two before yours since you are also using Boinc 6.6.20,
I assume this is the host you're talking about:
hostid=4852276 (http://setiathome.berkeley.edu/results.php?hostid=4852276&offset=20&show_names=0&state=0)
And Please Stop using Optimised Astropulse 5.00 r103 on Seti Beta, It' doesn't validate with 5.03 on Seti Main, and it sure Won't Validate with AP 5.04 or 5.05
hostid=39303 (http://setiathome.berkeley.edu/beta/results.php?hostid=39303)
Claggy
Is that mean I should delete any reference line that link to the CPU app in my app_info? I've attcahed my current app_info as below.
snip
The second Computer ID isn't mine, I've not crunch SETI beta for a while although part of my rig hasn't been updated to reflect this. I'll try to do that soon. So is there any optimized app that can be used with Beta?
Thanks
frigens
Your app_info seems to be missing the first few lines
<app_info>
<app>
You should replace AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe with the normal SSSE3 app.
Are sure that isn't your host on Beta?, Because it links through to the other hosts on Main.
Claggy
-
Well, everything seems to be working fine now ;D
Thanks again Raistmer
Out of curiosity though, what kind of temperatures are you guys seeing on your GPU and CPU(s)?
--
Orin
-
Out of curiosity though, what kind of temperatures are you guys seeing on your GPU and CPU(s)?
Still in process of OCing, but when I rised shader freq to 1920 and got temp of 62-65C GPU started produce many computation errors and invalid results.
With 1910 and temp around 62C it works OK it seems. Memory on 1110x2 for now, engine freq still untouched on 600MHz.
-
With all my CPU and GPU power. I am still getting really bad results.
Thank you
-
elec999 is this (http://setiathome.berkeley.edu/hosts_user.php?userid=65052) you?
This (http://setiathome.berkeley.edu/show_host_detail.php?hostid=4830774) machine runs stock apps. You should switch it to optimized apps.
Checking your most powerful machines, you don't seem to have such a high workunit output. Do you use all of their cores? Do you use them all day, every day (24/7)? If you want good RAC and overall credit, you need to run your machines 24/7.
Edit: If you don't have already, upgrade your boinc to 6.6.20, especially those machines with CUDA GPU.
-
Hey guys, need some help.
I have a i7 920 running with 3x GTX285s (don't worry 1 is on loan ;)). Vista X64. BOINC 6.6.20
I was running the "base" client and getting MB wu's completed in about 10 mins real time per GPU. I've now enabled astropulse and installed this V10 app.
The "number_of_GPUs" file is set to: 3
CC_config is set to:
<cc_config>
<options>
<ncpus>11</ncpus>
</options>
</cc_config>
Now when I restarted BOINC, all of my CUDA MB units switched over to standard CPU WU's (8 running) and I do not see any CUDA apps running. Now whats weird is my GPUs are still seeing a load (not full load) and getting warm.
So...what did I screw up? ;)
Thanks guys
BTW. here is a link to the host details if that helps:
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4864280
-
So...what did I screw up? ;)
I stand corrected. It does look like I'm using 3 GPUs and 5 logical CPUs...The application column dropped the "(cuda)" designation so that threw me off.
I'm not getting AP units, but I guess as long as the CPUs are also crunching MBs...that's not a problem?
What is odd though is that I was getting to claim ~50 points per MB cuda WU before installing this apt. Now it looks like I'm only getting ~15points per wu.
That sound right?
client is 6.6.20 btw.
-
I'm not getting AP units, but I guess as long as the CPUs are also crunching MBs...that's not a problem?
Have you got an optimized AP app? You've also got to edit accordingly your app_info.xml.
What is odd though is that I was getting to claim ~50 points per CUDA WU before installing this apt. Now it looks like I'm only getting ~15points per wu.
That sound right?
It's just a matter of workunit angle range.
Update your boinc to 6.6.20.
-
Hi Sunu,
Thanks for the help.
I am running 6.6.20, sorry left that out before.
Sounds good, I was thinking it was something to get with the angle, but since it happened at the exact same time I switched over. I wasn't sure.
I did resets the project to see if that would make a difference...I now have 11 WU's running at once rather than 8.
here is my AP info
- <app_info>
- <app>
<name>astropulse</name>
</app>
- <file_info>
<name>ap_5.00r103_SSE3.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>astropulse</app_name>
<version_num>500</version_num>
- <file_ref>
<file_name>ap_5.00r103_SSE3.exe</file_name>
<main_program />
</file_ref>
</app_version>
- <app>
<name>astropulse_v5</name>
</app>
- <file_info>
<name>ap_5.03r112_SSE3.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>astropulse_v5</app_name>
<version_num>503</version_num>
- <file_ref>
<file_name>ap_5.03r112_SSE3.exe</file_name>
<main_program />
</file_ref>
</app_version>
- <app>
<name>setiathome_enhanced</name>
</app>
- <file_info>
<name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</name>
<executable />
</file_info>
- <file_info>
<name>cudart.dll</name>
<executable />
</file_info>
- <file_info>
<name>cufft.dll</name>
<executable />
</file_info>
- <file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable />
</file_info>
- <file_info>
<name>MB_6.08_mod_CUDA_V10.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>528</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>607</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
</app_info>
-
I did resets the project to see if that would make a difference...I now have 11 WU's running at once rather than 8.
You're ok, that's how it should be, 8 CPU + 3 GPU.
-
I did resets the project to see if that would make a difference...I now have 11 WU's running at once rather than 8.
You're ok, that's how it should be, 8 CPU + 3 GPU.
Thanks Sunu.
BOINC just started telling me that there aren't any AP wu's available, so I guess thats why I'm only getting MBs right now.
The MB's are flying though. About 7 mins RT for each GPU's and ~22min for each CPU core.
-
BOINC just started telling me that there aren't any AP wu's available, so I guess thats why I'm only getting MBs right now.
The MB's are flying though. About 7 mins RT for each GPU's and ~22min for each CPU core.
Happy crunching then. Watch boinc to see when you get AP workunits.
-
Hi Sunu,
Thanks for the help.
I am running 6.6.20, sorry left that out before.
Sounds good, I was thinking it was something to get with the angle, but since it happened at the exact same time I switched over. I wasn't sure.
I did resets the project to see if that would make a difference...I now have 11 WU's running at once rather than 8.
here is my AP info
- <app_info>
- <app>
<name>astropulse</name>
</app>
- <file_info>
<name>ap_5.00r103_SSE3.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>astropulse</app_name>
<version_num>500</version_num>
- <file_ref>
<file_name>ap_5.00r103_SSE3.exe</file_name>
<main_program />
</file_ref>
</app_version>
- <app>
<name>astropulse_v5</name>
</app>
- <file_info>
<name>ap_5.03r112_SSE3.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>astropulse_v5</app_name>
<version_num>503</version_num>
- <file_ref>
<file_name>ap_5.03r112_SSE3.exe</file_name>
<main_program />
</file_ref>
</app_version>
- <app>
<name>setiathome_enhanced</name>
</app>
- <file_info>
<name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</name>
<executable />
</file_info>
- <file_info>
<name>cudart.dll</name>
<executable />
</file_info>
- <file_info>
<name>cufft.dll</name>
<executable />
</file_info>
- <file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable />
</file_info>
- <file_info>
<name>MB_6.08_mod_CUDA_V10.exe</name>
<executable />
</file_info>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>528</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>607</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
- <app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
- <file_ref>
<file_name>AK_v8b_win_x64_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program />
</file_ref>
- <file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
- <file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
- <file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
- <file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
</app_info>
A couple of things:
1: Boinc 6.6.x no longer needs the <ncpus> workaround, that was just for Boinc 6.4.x, Boinc 6.6.x now knows about the GPU's fitted, and so doesn't need this entry.
2: Your app_info has been opened and saved in Internet Explorer, you should only use notepad to edit it, it now has an extra space (known as Claggy's Space)
every time there is a <main_program /> or <executable /> entry, should be <main_program/> and <executable/>, also has lots of - entries that shouldn't be there.
3: The Team mode was get round problems with Boinc 6.4.x, you should now use V10 app stand alone, i.e. without the team part, and use a normal AK_V8 app for the CPU,
See this thread for a Proper app_info for Boinc 6.6.x: app_info for AP500, AP503, MB603 and MB608 (http://setiathome.berkeley.edu/forum_thread.php?id=52589)
Claggy
-
So basically to sum up, delete the CC_Config file since I no longer need the ncpu's flag. Install the V10 stand-alone app, and create a new app_info file using the link you provided.
In regards to the third item on your list, where can I find the V10 stand-alone app? Did a search but did not get any results back.
Thanks for the help Claggy, I'll give this a shot tonight!
-
So basically to sum up, delete the CC_Config file since I no longer need the ncpu's flag. Install the V10 stand-alone app, and create a new app_info file using the link you provided.
In regards to the third item on your list, where can I find the V10 stand-alone app? Did a search but did not get any results back.
Thanks Claggy, I'll give this a shot tonight!
If you've been running the V10 team package, you already have it, you just need to re-use the .dll's and the 'MB_6.08_mod_CUDA_V10.exe' file,
or you could use the V11 app from this post: MB_6.08_mod_CUDA_V11_def_func_FFTW_ESTIMATE_update (http://lunatics.kwsn.net/12-gpu-crunching/v10-of-modified-seti-mb-cuda-opt-ap-package-for-full-multi-gpucpu-use.msg16231.html#msg16231) which has the same file name for easy upgrading!
Claggy
-
Hey guys,
I think I got everything finally running correctly...atleast initially.
Did a fresh reinstall of 6.6.20. Installed the V10 packages in post one of this thread, then copying in the V11 CUDA package. Using the stock app_info that came with the V10 pkg.
Now when I started up the project after all of this, I got 3 CUDA MB wu's and 8 AP units. My 3 GPU's knocked out the MB's in about 10 mins each. So great, CPU's and GPU's running 100%...greatness!
However once the MB units were finished, I was unable to get more.
I just have all 8 AP's running.
This is what I see in the BOINC log:
4/8/2009 8:43:29 PM SETI@home [sched_op_debug] Starting scheduler request
4/8/2009 8:43:29 PM SETI@home Sending scheduler request: To fetch work.
4/8/2009 8:43:29 PM SETI@home Requesting new tasks
4/8/2009 8:43:29 PM SETI@home [sched_op_debug] CPU work request: 0.00 seconds; 0 idle CPUs
4/8/2009 8:43:29 PM SETI@home [sched_op_debug] CUDA work request: 864000.86 seconds; 3 idle GPUs
4/8/2009 8:43:34 PM SETI@home Scheduler request completed: got 0 new tasks
4/8/2009 8:43:34 PM SETI@home [sched_op_debug] Server version 607
4/8/2009 8:43:34 PM SETI@home Message from server: No work sent
4/8/2009 8:43:34 PM SETI@home Message from server: No work is available for Astropulse
4/8/2009 8:43:34 PM SETI@home Project requested delay of 11 seconds
4/8/2009 8:43:34 PM SETI@home [sched_op_debug] Deferring communication for 11 sec
4/8/2009 8:43:34 PM SETI@home [sched_op_debug] Reason: requested by project
4/8/2009 8:45:50 PM SETI@home [sched_op_debug] Starting scheduler request
4/8/2009 8:45:50 PM SETI@home Sending scheduler request: To fetch work.
4/8/2009 8:45:50 PM SETI@home Requesting new tasks
4/8/2009 8:45:50 PM SETI@home [sched_op_debug] CPU work request: 0.00 seconds; 0 idle CPUs
4/8/2009 8:45:50 PM SETI@home [sched_op_debug] CUDA work request: 864000.86 seconds; 3 idle GPUs
4/8/2009 8:45:55 PM SETI@home Scheduler request completed: got 0 new tasks
4/8/2009 8:45:55 PM SETI@home [sched_op_debug] Server version 607
4/8/2009 8:45:55 PM SETI@home Message from server: No work sent
4/8/2009 8:45:55 PM SETI@home Message from server: No work is available for Astropulse
Do I just need to give it more time, or could I have something off in the install?
AP wu's also look to be going at a 13hr-16 hour pace. I think it was about 40 hours before, so that's a nice improvment.
-
non-teamed AK_v8b for AMD SSE3-level CPUs (for both x86 and x64 usage).
[attachment deleted by admin]
-
non-teamed AK_v8b for AMD SSE3-level CPUs (for both x86 and x64 usage).
I have been trying to find info earlier in thread, but found nothing.
What are the advantages of this build?
From the name I gather its normal MB, not CUDA? Is it faster than previously released ak_v8b?
-
non-teamed AK_v8b for AMD SSE3-level CPUs (for both x86 and x64 usage).
I have been trying to find info earlier in thread, but found nothing.
What are the advantages of this build?
From the name I gather its normal MB, not CUDA? Is it faster than previously released ak_v8b?
As I can remember there was no v8b for AMD available in non-teamed flavor. Only pre-release ones in closed section. This one should have same performance as pre-release (but it's fresh rebuild - small speed deviation in both sides possible). It can be used as "standalone" CPU MB opt app for AMD CPUs. Posted in this thread as replacement to "teamed" version for those who will do V10 "team" ->BOINC 6.6.20 transition.
-
OK.
So if I'm allready running 6.6.20 with the official ak_v8b SSE3_AMD (which I believe is publicly available somewhere), there should be no difference?
I'll stick to that then :-)
-
So if I'm allready running 6.6.20 with the official ak_v8b SSE3_AMD (which I believe is publicly available somewhere), there should be no difference?
Fine if available. There should be no difference in speed. Only CPUID features were changed recently.
-
I seem to have a problem. I am running 6.6.20 and the v10 applications. I only see 2 tasks running in BOINC and when I check the Task Manager, I see 1 MB task running at 50%, 1 CUDA task running 0-1%, and 1 MB task with nothing loaded at 0%. (I am not running AP.)
What have I done wrong?
Thanks,
Here is my app_info.xml:
<app_info>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AK_v8b_win_SSE3_GPU_CPU_team_V10.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft.dll</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable/>
</file_info>
<file_info>
<name>MB_6.08_mod_CUDA_V10.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>528</version_num>
<file_ref>
<file_name>AK_v8b_win_SSE3_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<file_ref>
<file_name>AK_v8b_win_SSE3_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>607</version_num>
<file_ref>
<file_name>AK_v8b_win_SSE3_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<file_ref>
<file_name>AK_v8b_win_SSE3_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
</app_info>
Here is my local_prefs_override.xml:
<global_preferences>
<run_on_batteries>1</run_on_batteries>
<run_if_user_active>1</run_if_user_active>
<run_gpu_if_user_active>1</run_gpu_if_user_active>
<start_hour>0.000000</start_hour>
<end_hour>0.000000</end_hour>
<net_start_hour>0.000000</net_start_hour>
<net_end_hour>0.000000</net_end_hour>
<leave_apps_in_memory>0</leave_apps_in_memory>
<confirm_before_connecting>0</confirm_before_connecting>
<hangup_if_dialed>0</hangup_if_dialed>
<dont_verify_images>0</dont_verify_images>
<work_buf_min_days>0.100000</work_buf_min_days>
<work_buf_additional_days>0.500000</work_buf_additional_days>
<max_ncpus_pct>100.000000</max_ncpus_pct>
<cpu_scheduling_period_minutes>60.000000</cpu_scheduling_period_minutes>
<disk_interval>60.000000</disk_interval>
<disk_max_used_gb>100.000000</disk_max_used_gb>
<disk_max_used_pct>50.000000</disk_max_used_pct>
<disk_min_free_gb>0.100000</disk_min_free_gb>
<vm_max_used_pct>75.000000</vm_max_used_pct>
<ram_max_used_busy_pct>50.000000</ram_max_used_busy_pct>
<ram_max_used_idle_pct>90.000000</ram_max_used_idle_pct>
<max_bytes_sec_up>0.000000</max_bytes_sec_up>
<max_bytes_sec_down>0.000000</max_bytes_sec_down>
<cpu_usage_limit>100.000000</cpu_usage_limit>
</global_preferences>
and here is my cc_config.xml:
<cc_config>
<log_flags>
<task>1</task>
<file_xfer>1</file_xfer>
<sched_ops>1</sched_ops>
<cpu_sched_debug>0</cpu_sched_debug>
<work_fetch_debug>0</work_fetch_debug>
</log_flags>
<options>
<save_stats_days>30</save_stats_days>
<report_results_immediately>1</report_results_immediately>
</options>
</cc_config>
-
I seem to have a problem. I am running 6.6.20 and the v10 applications. I only see 2 tasks running in BOINC and when I check the Task Manager, I see 1 MB task running at 50%, 1 CUDA task running 0-1%, and 1 MB task with nothing loaded at 0%. (I am not running AP.)
What have I done wrong?
Your app_info is from the team mod, it doesn't work with 6.6.* There are other posts in this thread about which files you need. As well as this thread on the seti forums http://setiathome.berkeley.edu/forum_thread.php?id=52589 for the correct app_info.
-
Your app_info is from the team mod, it doesn't work with 6.6.*
V10 pack does work with any 6.6.x BOINC including 6.6.20. Actually I running it exactly with BOINC 6.6.20 right now.
But starting from BOINC 6.6.14 as was mentioned many times in this thread already there is possibility to use BOINC own scheduling mechanism for CUDA applications to run both CPU and GPU SETI MB versions simultaneously. That's why team pack can be disabled now.
But to do this you need replace app_info.xml _and_ SETI CPU MB "teamed" app ("teamed" AK_v8). Only SETI CUDA MB and SETI AP should be leaved untouched while upgrading from V10 pack to BOINC 6.6.20.
You need to delete cc_config.xml also (or just edit it to remove ncpus section if you use cc_config for some other purposes too).
-
Your app_info is from the team mod, it doesn't work with 6.6.*
V10 pack does work with any 6.6.x BOINC including 6.6.20. Actually I running it exactly with BOINC 6.6.20 right now.
But starting from BOINC 6.6.14 as was mentioned many times in this thread already there is possibility to use BOINC own scheduling mechanism for CUDA applications to run both CPU and GPU SETI MB versions simultaneously. That's why team pack can be disabled now.
But to do this you need replace app_info.xml _and_ SETI CPU MB "teamed" app ("teamed" AK_v8). Only SETI CUDA MB and SETI AP should be leaved untouched while upgrading from V10 pack to BOINC 6.6.20.
You need to delete cc_config.xml also (or just edit it to remove ncpus section if you use cc_config for some other purposes too).
What with 23 pages of app_info.xml postings, corrections, BOINC version x.y.z and a.b.c, it is more then just a bit confusing.
I wasn't running CUDA before. I just replaced a GPU that was failing and upgraded to a CUDA GPU. So there were no changes to be made to the cc_config.xml file.
In anticipation of the CUDA work, I upgraded from a 5.x BOINC to the latest version 6.6.20.
I used the ap_info.xml from the v10a package and basically only removed the AP information. After that, I just copied everything into the projects folder and started BOINC back up.
Exactly what other changes do I need to make to the app_info.xml?
If need be, I am willing to downgrade BOINC to 6.4.7.
-
Downgrade not needed.
You can use first posted app_info from corresponding SETI forum thread (and more or less safely ignore all later 23 pages ;) ) but check if app names corresponding names of your executables.
That way you need unmodded AK_v8 (from download section of this site), my V10/11 CUDA MB build (from this thread) (I assume you don't want to run AP so not listed it).
Another way is install V10 pack as it is. Add cc_config file with ncpus field (look first page). For doing ONLY SETI MB on both CPU and GPU, w/o AP or other projects V10 pack seems to me as more preferable way (still) cause it can balance workload between CPU and GPU while BOINC has separate work fetch (you can have plenty of "CPU" MB tasks while your GPU will sit idle cause it can't fetch new work fot itself).
If you participate in some another project too then BOINC 6.6.20 preferable.
-
I have tried a few time to get this to work......
Each time I error out and loose some WU's.......
Could I get some help please????
This is the machine:
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4293313
It's running Vista Ultimate 32bit, it has 2 8800GTS's 320mb, 182.50, Raistmer's_opt_pack_V10a_x86_SSE3_AMD_MB_CPU_GPU_team.rar, BOINC 6.6.20
Also, I am trying to just get Cuda to run on there, what I am looking for is a way to kill off VLAR WU's....
Thanks for your time...
-
If you lose tasks it means you don't follow the rules for upgrading.
"
The recommended way to do any (not only this one) update of opt apps:
1) DISABLE network access in BOINC
2) STOP BOINC
3) Copy BOINC whole data directory in another place as backup.
4) install update
5) start BOINC.
6) if all work fine - resume network access, else - stop BOINC and restore BOINC data folder from backup.
In other case you risk to trash whole your cache and be blamed by all few hundreds of your wingmans for that unfriendly action!
"
<core_client_version>6.6.20</core_client_version>
<![CDATA[
<message>
app_version download error: couldn't get input files:
<file_xfer_error>
<file_name>setiathome_6.08_windows_intelx86__cuda.exe</file_name>
<error_code>-200</error_code>
</file_xfer_error>
That means you don't have this file but you need it before downloading any work with app_info file installed.
Either edit app_info to point on CUDA MB app you really try to install or download this stock version first.
-
I did the data folder back up, but even when I put it back it was gone, but anywase.
I got rid of the stock app, prolly shouldn't have, and I just copied the whole rar to the work folder.
The error you posted happined a bit ago, before I said ta hell with it and used the stock app again.
But, like before, like I said, I copied the contents of the rar to the work folder, I didnt change anything in the xml, and everything errors, even with an empty cache, then it downloads a couple WU's and them error out also....
-
I did the data folder back up, but even when I put it back it was gone, but anywase.
I got rid of the stock app, prolly shouldn't have, and I just copied the whole rar to the work folder.
The error you posted happined a bit ago, before I said ta hell with it and used the stock app again.
But, like before, like I said, I copied the contents of the rar to the work folder, I didnt change anything in the xml, and everything errors, even with an empty cache, then it downloads a couple WU's and them error out also....
1)List content of project folder
2) Give link on fresh errored result.
-
I did the data folder back up, but even when I put it back it was gone, but anywase.
I got rid of the stock app, prolly shouldn't have, and I just copied the whole rar to the work folder.
The error you posted happined a bit ago, before I said ta hell with it and used the stock app again.
But, like before, like I said, I copied the contents of the rar to the work folder, I didnt change anything in the xml, and everything errors, even with an empty cache, then it downloads a couple WU's and them error out also....
1)List content of project folder
2) Give link on fresh errored result.
1) right now it's all stock.
2) I am pretty sure this is the last errored one I got with the Raistmer's_opt_pack_V10a: http://setiathome.berkeley.edu/result.php?resultid=1203461771
Thats why I am a bit confused....
I am sorry if I am being a pain, thanks again for the help
-
[1) right now it's all stock.
2) I am pretty sure this is the last errored one I got with the Raistmer's_opt_pack_V10a: http://setiathome.berkeley.edu/result.php?resultid=1203461771
Thats why I am a bit confused....
I am sorry if I am being a pain, thanks again for the help
the same error
<core_client_version>6.6.20</core_client_version>
<![CDATA[
<message>
app_version download error: couldn't get input files:
<file_xfer_error>
<file_name>setiathome_6.08_windows_intelx86__cuda.exe</file_name>
<error_code>-200</error_code>
</file_xfer_error>
</message>
]]>
Possibly you tried to use V10 CUDA MB, but you had stock app filename in app_info.
That's why they all errored.
-
On my LL I reinstalled the os. And Install V10 again. But keep on getting compusion error. And have to wait 20hours each time for more work.
Thanks
-
On my LL I reinstalled the os. And Install V10 again. But keep on getting compusion error. And have to wait 20hours each time for more work.
Thanks
It seems it's better to upgrade to BOINC 6.6.20 for you and use provided app_info (on SETI main) for it.
You have bad luck with this pack definitely and by refusing to follow update rules you trash tasks instead of process them... not very good tactic. Why you ignore backup stage in your experiments?
-
Where can I find the app_info on seti.
Thanks
-
http://setiathome.berkeley.edu/forum_thread.php?id=52589
-
Fresh V11 SETI CUDA build for standalone/team use with single GPU-multi core systems (try to restrict boinc.exe from using first core to achieve better GPU performance )
I found no speed difference between stock CUDA runtime (2.0 probably) and 2.1 CUDA runtime I used for building this app so use that version wich gives better stability on your host (no GPU freezing).
ADDON: added build w/o affinity lock. Maybe it best suited for high performance multi-GPU systems while build with affinity lock on first core could achieve better performance on single-GPU systems (with boinc.exe excluded from first core).
ADDON2: Build with VLAR kill mod disable added.
[attachment deleted by admin]
-
I plan to install three more video cards today. a 9800GTX+, two 8800GTS. Do you think this is a good idea. I will install to my B5. It can handle four video cards. And when my XFX board returns from RMA, I will install another 8800GT.
Thanks
-
Hey guys, with much help from Claggy, I have the optimizations working correctly on my rig.
However, after comparing my CUDA results with a couple other guys on the SETI forum, it seems like my performance may be a little off.
Rig Specs:
i7 920 @ 4.0GHz w/ Vista x64
3x GTX285 GPU's
BOINC 6.6.20
My average CUDA WU completion time is anywhere from 7 minutes to 15 minutes...usually around 15 minutes lately.
I am crunching AP at the same time and BOINC is running 8 AP's concurrently...for a total of 11 processes.
I've been reading reports of guys doing 3-5 minute CUDA wu's with virtually the exact same setup (both proc and gpu's). Do I just have some really "bad angle" WU's...or is this a tradeoff of running both CUDA and AP...or is this unusual?
The GPU's don't really seem to be fully utilized. I know this is a crappy way of measuring, but my GPU temps seem to be about 10-15 degree's cooler when crunching than before...again a bad example, but seems to indicate less load than before the optimizers.
Thanks for the assistance, and all of your hard work on these appss.
-
Hey,
have you tried to run one project solo? You can turn off AP in your Boinc main account settings in setiathome.de
perhaps the AP code is messing around with the Seti apps especially since you have a i7 920 cpu with the "hyperthreading" feature. Could really be a bottleneck caused by I/O from AP or seti running together. Just try to run seti alone and recheck your times, if they are fine you got your solution - use the cc_config file to limit Seti+AP e.g. to 9 or 10 procs including the GPUs to have 1 or 2 CPU cores left for system and kernel stuff.
-
I was thinking it could be a I/O issue as well.
How exactly do I limit the number of active CPU's in the cc_config.
Is it still the: <ncpus>6</ncpus> for example?
UPDATE:
I just dropped the Processor Utilization in the BOINC pref's to 50%, so now I have 4 AP's running and 3 CUDAs......CUDA WU time dropped from 17min to 10 mins...
I think you were right.
I guess the real question then is, is the "loss" of 4 AP units worth the 25-50% decrease in CUDA WU times.
-
I just dropped the Processor Utilization in the BOINC pref's to 50%, so now I have 4 AP's running and 3 CUDAs......CUDA WU time dropped from 17min to 10 mins...
Very interesting.
I did some standalone benchmarking of CUDA MB while CPU running 4 another BOINC tasks (not AP though, einstein@home ones) and didn't see any degradation in CUDA MB elapsed times and speed.
But it was quad w/o HT.
Do you use V10 or V11 CUDA MB build from this thread or stock one?
-
I guess the real question then is, is the "loss" of 4 AP units worth the 25-50% decrease in CUDA WU times.
Well, if forget about fact that 1 sec of AP work gives better credit than 1 sec of SETI MB work it seems you didn't change total host performance.
There were reports that with HT on 8 AP took twice the time 4 AP take with HT off on the same host. You leaved HT on but affectively disable some on CPU cores.
Try to compute overall host work done in both your configs (unfortunately, credits not very suitable for that cause AP and MB credit rates different).
-
New VLAR limit value used (0.12 instead of 0.14). For details see this thread:
http://lunatics.kwsn.net/12-gpu-crunching/gpu-cpu-pefrmance-dependence-from-ar-value.msg16800.html#msg16800
[attachment deleted by admin]
-
I just dropped the Processor Utilization in the BOINC pref's to 50%, so now I have 4 AP's running and 3 CUDAs......CUDA WU time dropped from 17min to 10 mins...
Very interesting.
I did some standalone benchmarking of CUDA MB while CPU running 4 another BOINC tasks (not AP though, einstein@home ones) and didn't see any degradation in CUDA MB elapsed times and speed.
But it was quad w/o HT.
Do you use V10 or V11 CUDA MB build from this thread or stock one?
I'm using the V11 that was referenced a few pages back. I'm now had a full 24 hours of crunching with HT more or less disabled (thru BOINC anyway). AP processing time dropped from about 17-20 hours down to 10-11 hours consistant. CUDA WU's are still pumping out in 10 minutes solid compared with 15-20 mins prior.
This seems to confirm what you were saying about HT rigs crunching slower, which makes since since the four HT "cores" are not true physical CPUs.
So far it would seem that my overall production has increased. Due to the decrease in time to process AP units, I'm not that much slower on AP than before, and cuda is running close to twice as fast....not bad.
-
I wonder if someone could help.
I've got a quad 6600 with a 9600gt cuda gpu running Win XP pro with bionc 6.6.20.
I'm wanting to run AP wu's using an optimised app on all 4 cpu cores and stock (or opt i'm not bothered) app for MB608 wu's on my GPU.
I've tried "Raistmer's_opt_pack_V10a_x86_SSSE3_MB_CPU_GPU_team" pack but when I restart bionc it drops all my cuda wu's but processes my AP wu's great. This is what I've been doing:
- Stop network activity in bionc
- Close bionc and check processes have stopped
- Back up my bionc dir
- Drop opt V10 apps in to seti data directory - incuding packaged app_info file
- "number_of_GPUs" file is '1'
- cc_config = <ncpus>5</ncpus> (4 cores and 1 gpu)
- Restart bionc
But its annoying how I cant get it to run cuda especially as everything works great, all be it slow, with just the stock apps from seti.
cheers Rich
-
I wonder if someone could help.
I've got a quad 6600 with a 9600gt cuda gpu running Win XP pro with bionc 6.6.20.
I'm wanting to run AP wu's using an optimised app on all 4 cpu cores and stock (or opt i'm not bothered) app for MB608 wu's on my GPU.
I've tried "Raistmer's_opt_pack_V10a_x86_SSSE3_MB_CPU_GPU_team" pack but when I restart bionc it drops all my cuda wu's but processes my AP wu's great. This is what I've been doing:
- Stop network activity in bionc
- Close bionc and check processes have stopped
- Back up my bionc dir
- Drop opt V10 apps in to seti data directory - incuding packaged app_info file
- "number_of_GPUs" file is '1'
- cc_config = <ncpus>5</ncpus> (4 cores and 1 gpu)
- Restart bionc
But its annoying how I cant get it to run cuda especially as everything works great, all be it slow, with just the stock apps from seti.
cheers Rich
In addition this is my host: http://setiathome.berkeley.edu/show_host_detail.php?hostid=4819034
I have just tried again with the V10 and updated my nvidia drivers to 182.50 and haverecorded the error message in bionc as:
19/04/2009 17:27:29 SETI@home [error] No app version for result: windows_intelx86 608 cuda
This message occurs for each cuda I have in the cache. all AP restarted fine
Rich
-
check your app_info file. It should contain corret app name (the same you have in project folder)
-
check your app_info file. It should contain corret app name (the same you have in project folder)
Everything seems to be in order with the app_info as far as I can tell, here is the text from the file:
<app_info>
<app>
<name>astropulse</name>
</app>
<file_info>
<name>ap_5.00r103_SSE3.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>astropulse</app_name>
<version_num>500</version_num>
<file_ref>
<file_name>ap_5.00r103_SSE3.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>astropulse_v5</name>
</app>
<file_info>
<name>ap_5.03r112_SSE3.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>astropulse_v5</app_name>
<version_num>503</version_num>
<file_ref>
<file_name>ap_5.03r112_SSE3.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft.dll</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable/>
</file_info>
<file_info>
<name>MB_6.08_mod_CUDA_V10.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>528</version_num>
<file_ref>
<file_name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<file_ref>
<file_name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>607</version_num>
<file_ref>
<file_name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<file_ref>
<file_name>AK_v8b_win_SSSE3x_GPU_CPU_team_V10.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<file_ref>
<file_name>MB_6.08_mod_CUDA_V10.exe</file_name>
</file_ref>
</app_version>
</app_info>
-
<core_client_version>6.6.20</core_client_version>
<![CDATA[
<message>
CreateProcess() failed - </message>
]]>
"teamed" AK_v8 app can't spawn CUDA MB app possibly. Check value in Number_of_GPUs file.
Also, check if you use BOINC service install. Maybe BOINC "protected" install short of spawn child process access right? ...
-
Got it working finally thanks to Claggy, but I do have a question.
It isnt a really big deal, but just curious why the wu times would increase?? They went up about 5 minutes from the stock one.
From 17-18 minutes to 22-23 minutes per.
-
Got it working finally thanks to Claggy, but I do have a question.
It isnt a really big deal, but just curious why the wu times would increase?? They went up about 5 minutes from the stock one.
From 17-18 minutes to 22-23 minutes per.
Is that while doing Astropulse at the same time?, I Know the version of Boinc (6.6.23) i'm running shows Elapsed time as apposed to CPU time now,
I can't say I've seen Cuda WU's generally taking longer, unless you've now got WU's with a High AR instead of a Mid Range AR,
Astropulse WU's are a different matter, Boinc shows elapsed time, but reports CPU time,
and while I'm doing Cuda WU's there can be an hour's differerence between the two.
Claggy
-
Got it working finally thanks to Claggy, but I do have a question.
It isnt a really big deal, but just curious why the wu times would increase?? They went up about 5 minutes from the stock one.
From 17-18 minutes to 22-23 minutes per.
Is that while doing Astropulse at the same time?, I Know the version of Boinc (6.6.23) i'm running shows Elapsed time as apposed to CPU time now,
I can't say I've seen Cuda WU's generally taking longer, unless you've now got WU's with a High AR instead of a Mid Range AR,
Astropulse WU's are a different matter, Boinc shows elapsed time, but reports CPU time,
and while I'm doing Cuda WU's there can be an hour's differerence between the two.
Claggy
All that rig does it crunch CUDA's, no AP's on that one, it is using 6.6.20.
-
Please, before asking "why my crunch time increased/decreased" check if you compare times for results with THE SAME Angle Range (AR) value.
Time for crunching tasks with different ARs differ strongly both for CPU and GPU apps. It's meaningless to compare results with different ARs to conclude that your host become suddenly faster or slower.
-
I could have sworn I replied to this......heh
Anywase, If I came off as sounding like a prick I am sorry, thats not what I meant to do.
I was just saying, all the WU's so far are taking a bit longer, it's not a problem, I was just curious.
-
Raistmer.........or anyone..........
Is the file MB_6.08_mod_CUDA_V11_VLARKill_refined.exe suitable for use in a standard, non teamed setup? Oh....on a single GPU also.
Thanks
-
Raistmer.........or anyone..........
Is the file MB_6.08_mod_CUDA_V11_VLARKill_refined.exe suitable for use in a standard, non teamed setup? Oh....on a single GPU also.
Thanks
All CUDA MB builds can be used in standart setup, this one included.
-
Is there is a possibility to suspend only GPU computation while use computer with moded CUDA ? With stock client I uncheck "Use GPU while computer is in use" in preferences of client but with moded aplications it is not work :( and only possiblity seems to uncheck "While computer is in use" with small idle, say 0.10 ;)
Thanks in advance,
Andrey
-
Were there any performance enhancements with this mod compared to stock Cuda client other than to consolidate the WUs to both CPUs and GPUs...? It seems my GPU didn't get any performance boost at all.
Not that I'm underestimating Raistmer's work, I do appreciate it.
Anyhow, my daily quota has been reduced from 1200 to 500... Any remedy to this..?
-
I'm successfully processing only AP and CUDA WU on a pair of Q6600 with CUDA cards using the optimized apps. Over the past few weeks my RAC has doubled to about 16,000 mostly due to these two PCs. All seems to be working fine except:
The stderr files shows CUDA's are taking on the order 100 seconds. But the calendar time seems to be a few hours. The CUDA cards run about as hot as usually stated on this site. I'm hoping an expert can spot why the CUDA's seem to take up excessive calendar time. Appreciate any help!
Here is the stderr for a typical work unit:
http://setiathome.berkeley.edu/result.php?resultid=1208947940
and for the same WU this is the BOINC Message showing almost 2 hours to complete:
2009-04-27 05:00:25 SETI@home Starting task 01fe09aa.6562.18886.6.8.69_0 using setiathome_enhanced version 608
2009-04-27 06:56:12 SETI@home Computation for task 01fe09aa.6562.18886.6.8.69_0 finished
At these times the PC was idle and, in any case, I permit CUDA computation while the PC is in use.
The SAH portion of app_info is:
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AK_v8_win_SSSE3x.exe</name>
<executable/>
</file_info>
<file_info>
<name>setiathome_6.08_windows_intelx86__cuda.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft.dll</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3-1-1a_upx.dll</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_intelx86</platform>
<flops>5160439018.79946125</flops>
<file_ref>
<file_name>AK_v8_win_SSSE3x.exe</file_name>
<main_program/>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<platform>windows_intelx86</platform>
<avg_ncpus>0.127970</avg_ncpus>
<max_ncpus>0.127970</max_ncpus>
<flops>1000000000</flops>
<plan_class>cuda</plan_class>
<file_ref>
<file_name>setiathome_6.08_windows_intelx86__cuda.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft.dll</file_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-1-1a_upx.dll</file_name>
</file_ref>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
</app_version>
</app_info>
-
I'm successfully processing only AP and CUDA WU on a pair of Q6600 with CUDA cards using the optimized apps. Over the past few weeks my RAC has doubled to about 16,000 mostly due to these two PCs. All seems to be working fine except:
The stderr files shows CUDA's are taking on the order 100 seconds. But the calendar time seems to be a few hours. The CUDA cards run about as hot as usually stated on this site. I'm hoping an expert can spot why the CUDA's seem to take up excessive calendar time. Appreciate any help!
Here is the stderr for a typical work unit:
http://setiathome.berkeley.edu/result.php?resultid=1208947940
and for the same WU this is the BOINC Message showing almost 2 hours to complete:
2009-04-27 05:00:25 SETI@home Starting task 01fe09aa.6562.18886.6.8.69_0 using setiathome_enhanced version 608
2009-04-27 06:56:12 SETI@home Computation for task 01fe09aa.6562.18886.6.8.69_0 finished
At these times the PC was idle and, in any case, I permit CUDA computation while the PC is in use.
The line in stderr says "CPU time 139.5781"
That's how long the Q6600 spent on them. Your 8500 GT (unfortunately, one of the slowest CUDA cards available) may indeed have taken almost two hours to complete the task. But during that time, all but a minute fraction of the power of one core of the Q6600 was available for AP, browsing the web, or whatever. So the CUDA contribution, comparatively small as it is, is all a net gain to your productivity.
-
Is there is a possibility to suspend only GPU computation while use computer with moded CUDA ? With stock client I uncheck "Use GPU while computer is in use" in preferences of client but with moded aplications it is not work :( and only possiblity seems to uncheck "While computer is in use" with small idle, say 0.10 ;)
Thanks in advance,
Try to switch to BOINC 6.6.20 + corresponding app_info. Now it's recommended method of using modded SETI CUDA MB. "team" mod considered as deprecated :)
Andrey
По русски читать можешь?
-
Were there any performance enhancements with this mod compared to stock Cuda client other than to consolidate the WUs to both CPUs and GPUs...? It seems my GPU didn't get any performance boost at all.
Not that I'm underestimating Raistmer's work, I do appreciate it.
Anyhow, my daily quota has been reduced from 1200 to 500... Any remedy to this..?
Yes, current CUDA MB build has advantages in speed versus stock one. Not so big as our other opt apps have though.
Dayly quota can be reduced due pack of VLARs rejected by CUDA MB for example. IF this is a reason you could try to use rebranding script to move VLAR tasks from GPU to CPU queue.
-
I'm successfully processing only AP and CUDA WU on a pair of Q6600 with CUDA cards using the optimized apps. Over the past few weeks my RAC has doubled to about 16,000 mostly due to these two PCs. All seems to be working fine except:
The stderr files shows CUDA's are taking on the order 100 seconds. But the calendar time seems to be a few hours. The CUDA cards run about as hot as usually stated on this site. I'm hoping an expert can spot why the CUDA's seem to take up excessive calendar time. Appreciate any help!
Here is the stderr for a typical work unit:
http://setiathome.berkeley.edu/result.php?resultid=1208947940
and for the same WU this is the BOINC Message showing almost 2 hours to complete:
2009-04-27 05:00:25 SETI@home Starting task 01fe09aa.6562.18886.6.8.69_0 using setiathome_enhanced version 608
2009-04-27 06:56:12 SETI@home Computation for task 01fe09aa.6562.18886.6.8.69_0 finished
At these times the PC was idle and, in any case, I permit CUDA computation while the PC is in use.
The line in stderr says "CPU time 139.5781"
That's how long the Q6600 spent on them. Your 8500 GT (unfortunately, one of the slowest CUDA cards available) may indeed have taken almost two hours to complete the task. But during that time, all but a minute fraction of the power of one core of the Q6600 was available for AP, browsing the web, or whatever. So the CUDA contribution, comparatively small as it is, is all a net gain to your productivity.
Re CUDA processing time on 8500: Understood. Its GFLOPS rating is <10, my 9600GTX+ is 100. Plus the 8500 is the very first - oldest - on the NVIDIA CUDA list. It was my impression that time is in seconds, so the card processed for 139 seconds over a 2 hour period. Correct?
Thanks - Art
-
Re CUDA processing time on 8500: Understood. Its GFLOPS rating is <10, my 9600GTX+ is 100. Plus the 8500 is the very first - oldest - on the NVIDIA CUDA list. It was my impression that time is in seconds, so the card processed for 139 seconds over a 2 hour period. Correct?
Thanks - Art
No. The host CPU (one core of the Q6600) ran for 139 seconds - pre-processing the data, managing transfers to and from main memory, storing checkpoint files to disk - general housekeeping.
The GPU (CUDA) card will have been running pretty much flat out for the full two hours, with only the briefest of pauses while new data was transferred to/from disk or main memory.
-
Is there is a possibility to suspend only GPU computation while use computer with moded CUDA ? With stock client I uncheck "Use GPU while computer is in use" in preferences of client but with moded aplications it is not work :( and only possiblity seems to uncheck "While computer is in use" with small idle, say 0.10 ;)
Thanks in advance,
Try to switch to BOINC 6.6.20 + corresponding app_info. Now it's recommended method of using modded SETI CUDA MB. "team" mod considered as deprecated :)
Andrey
По русски читать можешь?
Thanks ! As I finally understand, one have to read http://setiathome.berkeley.edu/forum_thread.php?id=52589 then find most optimized programs(for AP and GPU), change app_info.xml and that`s all !
Читать могу ;) Еще раз спасибо
-
I still feel stupid. I have 6 GPUS and really bad results.
What happened to the auto installer.
Thanks
-
Andrey
What version of Boinc are you using?
Is there is a possibility to suspend only GPU computation while use computer with moded CUDA ? With stock client I uncheck "Use GPU while computer is in use" in preferences of client but with moded aplications it is not work :( and only possiblity seems to uncheck "While computer is in use" with small idle, say 0.10 ;)
Thanks in advance,
Andrey
This may be a Bug in the Boinc Core. As I have noticed it on the one machine that I has set to suspend when in use.
Regards
-
elec999
You Sig shows 6 machines with various GPU's
Quad Core E5410 2.33mhz 12mb cache x 2 Seti SSSE4.1 Optimized
E6720 Palit 9800 Super +1GB V10
Q6600 Asus 8800 GTS Stock
Q6600 EVGA GTX260 Core 216 Asus 8800TOP (G92) V10
IBM P4 3GHZ (HT) Seti Optimized
Boinc 6.4.5
Could you verify that all machines have the same version of Boinc and identify which machines work or do not work.
I still feel stupid. I have 6 GPUS and really bad results.
What happened to the auto installer.
Thanks
Regards
-
...
What happened to the auto installer.
...
Over in the beta development thread,
http://lunatics.kwsn.net/public-release-beta-forum/windows-32-bit-only-installer-nt-xp-vista-win7.msg17174.html#msg17174
we need more information from you to be of help.
Jason
-
How should I edit the app_info so that I can crunch optimised AP via CPU and stock AP via CUDA...? No MB units involved. I'm not good at XML editing.
Thank you.
-
How should I edit the app_info so that I can crunch optimised AP via CPU and stock AP via CUDA...? No MB units involved. I'm not good at XML editing.
Thank you.
There is no CUDA AP available.
-
There is no CUDA AP available.
Then why is ap_graphics_5.03_windows_intelx86.exe being downloaded on my other instance of BOINC...?
I was wondering if this said AP client can be integrated into the existing V10 package. If so, how would I edit the app_info.xml to identify and utilise the client...?
Thanks
-
There is no CUDA AP available.
Then why is ap_graphics_5.03_windows_intelx86.exe being downloaded on my other instance of BOINC...?
I was wondering if this said AP client can be integrated into the existing V10 package. If so, how would I edit the app_info.xml to identify and utilise the client...?
Thanks
ap_graphics_5.03_windows_intelx86.exe does not crunch WUs, it's the executable launched by the screensaver or BOINC Manager to display graphics. It is separate from the crunching app due to the way BOINC 6.x deals with Vista (and presumably Win 7) requirements.
Joe
-
ap_graphics_5.03_windows_intelx86.exe does not crunch WUs, it's the executable launched by the screensaver or BOINC Manager to display graphics. It is separate from the crunching app due to the way BOINC 6.x deals with Vista (and presumably Win 7) requirements.
Joe
oops...! my bad... thanks for knocking some sense out of me... ;D
-
Hi @ll
How's the best way to run MB and AP CPU opt app and MB CUDA opt app?
I mean, where do i download the opti applications and the corresponding app_info file? Should I do my own app_info file? Do u recommend version 6.6.20?
Thanks in advance.
-
Hi @ll
How's the best way to run MB and AP CPU opt app and MB CUDA opt app?
I mean, where do i download the opti applications and the corresponding app_info file? Should I do my own app_info file? Do u recommend version 6.6.20?
Thanks in advance.
See this thread:
app_info for AP500, AP503, MB603 and MB608 (http://setiathome.berkeley.edu/forum_thread.php?id=52589)
Raistmer's app's can be found spread out in this thread,
the easiest way to get all the other optimised apps is to get the right combined package from Arkayn's Site:
Multibeam and Astropulse Combined Packages (http://www.arkayn.us/seti/)
Claggy
-
Hi @ll
How's the best way to run MB and AP CPU opt app and MB CUDA opt app?
I mean, where do i download the opti applications and the corresponding app_info file? Should I do my own app_info file? Do u recommend version 6.6.20?
Thanks in advance.
See this thread:
app_info for AP500, AP503, MB603 and MB608 (http://setiathome.berkeley.edu/forum_thread.php?id=52589)
Raistmer's app's can be found spread out in this thread,
the easiest way to get all the other optimised apps is to get the right combined package from Arkayn's Site:
Multibeam and Astropulse Combined Packages (http://www.arkayn.us/seti/)
Claggy
Thx for the info Claggy.
-
Hmpf...
I've downloaded the Package : Raistmer's_opt_pack_V10a_x86_SSE3_AMD_MB_CPU_GPU_team.rar
For WinXP, AMD Phenom 9550 und a GTX285 should be the right combination.
However, since I relaunched BOINC 6.6.20, the only Message I receive is :
Message from server: No work sent
Message from server : No work is available for Astropulse
At this time, however, there are 24592 AP WorkUnits and 120065 MB WorkUnits ready to send.
Setting the cc_config.xml to 5 CPUs (QuadCore + 1GPU) only resulted in the CPU attempting to crunch 5 AP WorkUnits (were already in Cache) at once...
The above Server Messages were the same with ncpus set to 5.
My Preferences allow for all Applications and GPU is set to be used even when Computer is in use.
The app_info.xml is unmodified right from the Package.
Any Ideas ?
-- edit --
For my single GPU config, I downloaded the stock CUDA application and manually added it into my old app_info.xml.
BOINC immediately downloaded MB WorkUnits and appears to work just fine.
Do I understand correctly that the stock CUDA Application does not support Multi-GPU configs (plan to build 2xGTX295 with 4 GPUs in a system) ?
-
...
Message from server: No work sent
Message from server : No work is available for Astropulse
At this time, however, there are 24592 AP WorkUnits and 120065 MB WorkUnits ready to send.
...
Astropulse is the old application, it is quite likely there is no work available for that. Astropulse v5 is the new one, those 24592 tasks should be all or almost all for that application. Those server messages are exact, they'll say "Astropulse v5" if that is what isn't available.
However, the "no work is available" message refers to the 100 slots in the shared memory between the Feeder and Scheduler. At any moment, there may well be no work of a particular kind there, and the Scheduler can't send what it doesn't know about.
If the server message only reports about "Astropulse", that may mean your project preferences (http://setiathome.berkeley.edu/prefs.php?subset=project) have somehow been set to only accept that kind of work.
Joe
-
CUDA 2.2 benchmarking results:
1) New CUFFT can't run with 182.50 driver
2) new (2.2) CUDA runtime+ current CUDA MB can operate with 182.50 driver
3) there is small speedup from using CUDA_RT of 2.2 and there is no speedup from rebuilding current CUDA MB sources with CUDA 2.2
4) there is significant speedup (it even offsets lack of OCing on my GPU) from using current drivers (185.85) + CUDA RT 2.2 + CUFFT 2.2 (again, all builds show that speedup, not only freshly rebuilt one).
Summary: for those who can go with new drivers it's worth to upgrade to CUDA 2.2 runtime w/o upgrading current CUDA MB app.
For all others it's worth to try to use new cudart.dll + old cufft.dll.
(new CUDA 2.2 runtime attached (cudart.dll + cufft.dll )
Don't forget to update video driver to 185.85 version.
[attachment deleted by admin]
-
Thanks for the heads up Raistmer.
I´m trying the newest drivers (185.85), with CUDA 2.2 supplied by you, on my 9500.
Looking forward to see the results.
-
Astropulse is the old application, it is quite likely there is no work available for that. Astropulse v5 is the new one, those 24592 tasks should be all or almost all for that application. Those server messages are exact, they'll say "Astropulse v5" if that is what isn't available.
However, the "no work is available" message refers to the 100 slots in the shared memory between the Feeder and Scheduler. At any moment, there may well be no work of a particular kind there, and the Scheduler can't send what it doesn't know about.
If the server message only reports about "Astropulse", that may mean your project preferences (http://setiathome.berkeley.edu/prefs.php?subset=project) have somehow been set to only accept that kind of work.
Joe
Alright, so I will give it another shot and add more patience ;)
I've read that BOINC 6.6.20 does not work with the V10, so which BOINC version is suitable ?
(Note - I'm using the Windows 7 RC 64bit, not sure if that affects the whole thing)
-
CUDA 2.2 benchmarking results:
1) New CUFFT can't run with 182.50 driver
2) new (2.2) CUDA runtime+ current CUDA MB can operate with 182.50 driver
3) there is small speedup from using CUDA_RT of 2.2 and there is no speedup from rebuilding current CUDA MB sources with CUDA 2.2
4) there is significant speedup (it even offsets lack of OCing on my GPU) from using current drivers (185.85) + CUDA RT 2.2 + CUFFT 2.2 (again, all builds show that speedup, not only freshly rebuilt one).
Summary: for those who can go with new drivers it's worth to upgrade to CUDA 2.2 runtime w/o upgrading current CUDA MB app.
For all others it's worth to try to use new cudart.dll + old cufft.dll.
(new CUDA 2.2 runtime attached (cudart.dll + cufft.dll )
Don't forget to update video driver to 185.85 version.
I've applied the full 'triple treatment' (driver, runtime and fft) to my rigs (2 x 9800GT and a 9800GTX+), which run the stock v6.08 from Berkeley. Good impression all round: display seems smoother, app runs faster, and I'm even seeing signs of lower CPU loading (though maybe that's just BOINC's way of telling me the boxes were due a reboot ;D ). I'm still not going to risk throwing a VLAR into the mix, but apart from that we seem to have a winner.
-
I have one nagging question concerning the V10 mod :
Does the CUDA application read the proxy settings from the BOINC Manager preferences?
If not, that would explain why it persistently fails to download and process any Workunits for me.
(after a fresh install, I have (again) 6 AP WorkUnits running on the quad due to the recommended cc_config.xml and 0 CUDA WorkUnits on the idle GPUs, still receive the bogus server messages, Message from Server : No Astropulse WorkUnits available)
-- edit --
Changed Proxy to direct Internet connection but so far nothing changed.
-
I have one nagging question concerning the V10 mod :
Does the CUDA application read the proxy settings from the BOINC Manager preferences?
...
The app does not have anything to do with work fetch, that's BOINC's job. You'll have to figure out why the server thinks you've disabled the other kinds of work. One thing I forgot when I suggested checking your project preferences (http://setiathome.berkeley.edu/prefs.php?subset=project) is that there are 4 venues, the host might be using any one of those so you have to also confirm that setting on the host page or by looking at the BOINC messages on the host at startup.
Joe
-
The Host is under venue "Home" as all my Systems.
Good news is : Partial success !
After completely uninstalling and deleting the entire Directories of the former installation, I went for a brand new install with BOINC 6.4.5 Win64, set run mode to "Suspended", then attached SETI as new Project.
After allowing it to download one AP WorkUnit, I quit the BOINC manager.
Then I installed the appropriate V10 Package, edited the Number_of_GPUs to 2 and inserted the cc_config.xml reflecting 6 CPUs (4 CPU + 2 GPU).
However, when I restarted BOINC with all in place, the CPU got fed with 5 AP WorkUnits, while the GPU only runs 1 WorkUnit.
Now I'd have to wait some 20 hours for a CPU to finish its AP job and hope that the 2nd GPU gets a workunit instead.
Worst case, once the non-existent 6th core is free, the CPU may get assigned Job #5 while the GPU remains only half loaded.
Is that normal and unavoidable ?
-
*arg*
My fears were correct, after 1 GPU quickly finishing its job, I now (again) have the Quad CPU running 6 Tasks while the GPU didn't get any work :(
The GPUs next chance to get assigned work is in.... approx 30 hours, as the QuadCore is now running extremely inefficient on 6 AP jobs.
This stuff is really killing me. I organized some 3000$ worth of GPUs to do some serious crunching but this is just costing me tons of time with no visible success.
I already wish I had build 4-5 Octa Core CPU systems or with max. 1 GPU added instead, at least those would be long crunching at full speed...
I don't get it how this works easy for others, for me this has been the biggest single pain in the arse I ever had with BOINC so far...
(http://www.falconfly.de/img/wallbash.gif)
-----------------------------------------------------------------
Another attempt :
I created a Work venue, so I can experiment without affecting the already smooth running Hosts.
- set Preferences to run Mainbeam WorkUnits only
The Result for now looks good as far as I can tell, for the first time ever I got both GPUs running it seems :
(http://www.falconfly.de/temp/cuda.jpg)
The question remains, however, will it happen again that the CPU gets 6 applications loaded or will that modified cuda recognize the situation and keep both GPUs busy instead ?
-
Hi FalconFly,
I'm just curious if there's a particular reason you're preferring Boinc 6.4.5 over 6.6.20 (Sorry if you mentioned it already, but I haven't fully read the thread ;) ) Further, you mention changing the number of GPUs to 2 ? I'm not aware of such a setting! :o
I would recommend the following configuration (after backing up your current config) :
- Boinc 6.6.20
- No cc_config n_cpus entry at all
- Install applications using hanfy dandy installer from the Beta Installer thread (Or manually if preferred, Worth a try since you have Tester access? )
- edit/insert flops values in app_info (If desired)
- [EDIT: I notice your installation is Win64, so Installer may or may not work, and you'd want to switch out the CPU AKv8 app with the 64 bit variety.... But still should get you going]
-
"team" packs (V10 included) became obsolete now. To simplify life for users who can't read whole this thread to stay tuned with latest changes (not too latest already though, BOINC 6.6.20 exists as recommended version more than month already AFAIK) I lock this thread.
All my own support of "teamed" packs now ceased (until I get some example why "teamed" pack should be used instead of BOINC 6.6.20 native GPU scheduling at least)
Will remove V10 archives from first post also.
"teamed" packs were temporary solution and well served their aim during lifespan. But now this period is over.
What should be used instead:
1) BOINC 6.6.20
2) latest CUDA MB build (can be found in this thread and will be posted in new thread devoted optimized CUDA MultiBeam app).
3) appropriate app_info.xml
some examples can be found in this thread: http://setiathome.berkeley.edu/forum_thread.php?id=52589
2) and 3) could be replaced by using Jason's Lunatics installer (currently in beta stage, can be found in beta area of this forum: http://lunatics.kwsn.net/installer-testing/index.0.html )
What should not be used
1) ncpus field in cc_config.xml
2) app_info.xml supplied with obsolete "team" packs.
3) "teamed" modification of AK_v8 (was part of "team" packs).