V10/11 of modified SETI MB CUDA + opt AP package for full multi-GPU+CPU use

[Archangel999]

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

[Raistmer]

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.

[Jason G]

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.

[Raistmer]

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.

[Raistmer]

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.

[YukonTrooper]

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?

[Vager]

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 . I just only realized now after installing V10 that the mutilple users may be the reason. 

Thanks
Vager

[Raistmer]

Probably only active user profile can interact with GPU.

[Vager]

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

[Raistmer]

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.

[SoNic]

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?

[elec999]

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

[RottenMutt]

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.

[Jason G]

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)"]

[elec999]

My Boinc keeps on getting stuck on communicating with client.
Thank you