SETI MB CUDA for Linux

[riofl]

@letni
Please see my big post above, I'm talking about cuda with no X server. Are you sure you've set it up all correctly? Also make sure you use compatible nvidia drivers and cuda libraries.

Also see my post http://lunatics.kwsn.net/linux/seti-mb-cuda-for-linux.msg19014.html#msg19014 and follow it to the letter.

Your card with 256 MB is borderline. You might get some out of memory messages here and there.

i got them all the time with my 8600GT 256mb. cuda tried to use it when it was the only device but it turned every wu in with out of memory errors. that was when i added the tesla and then later replaced the gt with the gtx i now have.

for someone who uses a linux desktop seriously, i doubt 256mb vidram will work at all unless maybe you define only 1 or 2 desktops at most and keep all the bells and whistles disabled along with using a solid color background.., or it is a 2nd card not used for video at all then it can be used properly.

[letni]

2. I have modified my app_info.xml to allow both AK_V8_SSE3 (32bit) and the cuda to run simultaneously (included .xml file).. I have 3 active tasks being worked on, two (for my dual CPU) say setiathome_enhanced 6.03 and run just fine.  The third is the CUDA which setiathome_enhanced 6.08 (cuda), and the status NEVER goes past Ready to start. It will eventuall error out with Computation error.
Anyone have any thoughts or advice on how to debug this?

There is an option that is on by default to not run cuda tasks when pc is in use. Check global_prefs.xml for <run_gpu_if_user_active>0</run_gpu_if_user_active> and change that 0 to 1.

That was the issue the whole time.. I guess I figured just cause I am not uxing XWINDOWs on a headless machine that I technically wasn't using the video card.  Enabling that let it do its thing

Thanks everyone for all your help.



letni

[Kunin]

Thanks, but before I use it how does the VLAR kill work?  I rebrand all of my VLAR to the CPU as soon as I can, and prefer to work whatever units I get since I have the 8 cores just sitting there most of the time.

Well if you miss a VLAR from the rebranding and it gets to your GPU, it will get aborted almost instantly by the client.

Ok, so it kills it as soon as it actually starts processing and no sooner?

[sunu]

That was the issue the whole time.. I guess I figured just cause I am not uxing XWINDOWs on a headless machine that I technically wasn't using the video card.  Enabling that let it do its thing
Thanks everyone for all your help.
letni

letni the hosts that you've posted above are full of errors. Are you sure you've solved all your problems?

Ok, so it kills it as soon as it actually starts processing and no sooner?

Yes. When it starts to crunch a wu, it checks if this wu is a VLAR and if it is, it aborts.

[letni]

That was the issue the whole time.. I guess I figured just cause I am not uxing XWINDOWs on a headless machine that I technically wasn't using the video card.  Enabling that let it do its thing
Thanks everyone for all your help.
letni

letni the hosts that you've posted above are full of errors. Are you sure you've solved all your problems?

I have the client running currently.. 2 threads on AK_V8_64bit_SSE3 (Pentium D) and one thread on cuda novlar 2.2 build.. The CUDA is extremly slow and I have noticed that the cuda thread is taking up 100% of one (out of 2) of my CPUs, slowing down my SSE3 CPU threads.. Here are the versions:

Nvidia Driver: 185.18.31
CUDA Toolkit: 2.2 (ldd reports proper libs - added to ld.so.conf) -also copied libs to project.. directory
SETI Version: 6.6.36
Environment: FC10_64bit - Runlevel 3 - no xwindows
Video Card - 8600 GTS 256MB

I have copied the CUDA binary to a system directory in the path as mentioned. 

I even tried the new 190 driver and the 2.3 toolkit and same effect, just downgraded back to 2.2 toolkit and 185 driver.. Still same issue.. 100% cpu utilization.. This can't be efficient.. Any suggestions?

[attachment deleted by admin]

[sunu]

latni can you give us a link of a wu done by the gpu?

I'm suspecting that you get an out of memory error and the wu is then done in cpu, that's why you get 100% cpu utilization by the cuda app.

[letni]

latni can you give us a link of a wu done by the gpu?

I'm suspecting that you get an out of memory error and the wu is then done in cpu, that's why you get 100% cpu utilization by the cuda app.

That is absoutly the case.. my first WU was finally finished by "GPU" and the error messages say MALLOC out of memory errors.. Looks like time for a better video card!

[sunu]

That is absoutly the case.. my first WU was finally finished by "GPU" and the error messages say MALLOC out of memory errors.. Looks like time for a better video card!

letni, what cuda app do you use? The 2.2 one or the one from the first post of this thread? The 2.2 one is very memory hungry. Try using the one from the first post of this thread and see if it helps. Mind you that it has a different name so you'll have to edit your app_info.xml accordingly.

[letni]

That is absoutly the case.. my first WU was finally finished by "GPU" and the error messages say MALLOC out of memory errors.. Looks like time for a better video card!

letni, what cuda app do you use? The 2.2 one or the one from the first post of this thread? The 2.2 one is very memory hungry. Try using the one from the first post of this thread and see if it helps. Mind you that it has a different name so you'll have to edit your app_info.xml accordingly.

That did the trick.. No 100% CPU usage anymore with the older binary.. Chugging away very fast now!! Hopefully no more computation errors!

[sunu]

That did the trick.. No 100% CPU usage anymore with the older binary.. Chugging away very fast now!! Hopefully no more computation errors!

letni I see you've already completed a few WUs with your GPU. Happy crunching! 

[riofl]

if i were to build a machine with 4 GTX295 cards, will boinc see and use all 8 cuda processors properly and efficiently, or would i be better off using 4 GTX285 single gpu cards? i had originally thoguht of using 4 teslas but the GTX 285 outperforms it by a lot  just going by raw gflops (74 tesla vs 127 GTX) as measured by boinc.

[sunu]

if i were to build a machine with 4 GTX295 cards, will boinc see and use all 8 cuda processors properly and efficiently, or would i be better off using 4 GTX285 single gpu cards?

Well, that is your choice. Boinc won't have any problems at all.

[pp]

And if it doesn't work you can send that machine to me... 

[sunu]

And if it doesn't work you can send that machine to me... 

Well, probably, first, he's going to bring that machine down on my head hard for making him blow his money away, but I'll take it anyway. 

[riofl]

And if it doesn't work you can send that machine to me... 

Well, probably, first, he's going to bring that machine down on my head hard for making him blow his money away, but I'll take it anyway. 

LOL as long as boinc can use all 8 processors efficiently it will be fine.. this is a '1st quarter next year' project im planning out now. prob use either an i7 proc or a couple quad core xeons not sure yet which would process better. i heard the modern xeons were super fast in math, but then ive also heard that about the i7 so... dunno... about the only thing that is a given is the choice of vid cards and hard drives and ram hehe friggin vid cards will cost as much as the rest of the machine will!