AK V8 + CUDA MB team work mod

[SoNic]

Maybe you have cc_config in the wrong folder? It resides in BOINC, two levels up from the work folder.

That was it, silly me Thanks a lot, now my PC is slughish too 
Wold be nice that those tickets will be solved quickly, especially the one about suspending only the CUDA at will...

[k6xt]

I don't know then, I have a GeForce 8600GTS with 256MB ram and the only problems I have now are during task switches.

I don't think its card memory. My 8500 has 512MB. Its GPU scheduling or something and reading thru prior posts on this thread it seems some of the experts and code wizards are working on it.

[ceciltseng]

is passable AK V8 + CUDA MB team work with 2 or 3 GPU at same time ?

[Raistmer]

I think I'm seeing some of the symptoms you're describing Raistmer. I tried your moded app in your previous post, and I thought that the problem was solved as I don't think I made it past 24 hours without my GPU going idle. I applied the app last night and this morning my GPU temp was high telling me that it was being used. When I got home today I noticed that the temp was back to normal indicating that nothing was being used.
 So after reading your post about Vista (I'm using the 64bit version) which app do I change the affinty for? I'm not sure which one is used soley for the GPU. I have 4 processes running. (I only have a dual core)

AK_v8b_win_SSSE3x_GPU_CPU_team.exe is running at 3 instances 2 of them running around 22% and the 3rd one running at 00 CPU usage. The MB_6.08_mod_CPU_team_CUDA.exe file is running at 50% CPU. Which process would I change as all for of them have both CPU's checked off for the affinity.

Thanks
Vager

for BOINC only you should not change affinity. Only if some non- BOINC CPU consuming task working....
GPU temp will fall dow time to time - when it starts new task. It's notmal.
It's not normal only if this fall takes more than ~min

[Raistmer]

Agreed
Well, attached app little more "smart" in this sense and will leave worker thread on single (first) core. It could give some performance degradation indeed in general case (it can't fill idle window of another core) but it really helped in my situation. And achieved GPU temp is highest (the same was when no non-BOINC app runs).

OK, I have read almost all the thread, I have DL the SSE3 package (I have a Core2Duo) and this version of CUDA app. Mt task manager now shows one AK_V8 app at 50%, one AK_V8 at 00% and one MB_9.08 CUDA at 2%.
In Boinc manager I have 2 working units, one normal and another one that doesn't increase the CPU time field (but it is working).
Is this normal? I did make an config file with 3 CPU's and placed it on the work folder.
The CUDA app will run at 50% just for a while at the begining...
PC is very responsive.

For core2 duo you should use SSSE3 version - it will faster. Moreover you probably forgot about cc_config.xml file. Ont core still idle in your config

[Raistmer]

Maybe you have cc_config in the wrong folder? It resides in BOINC, two levels up from the work folder.

That was it, silly me Thanks a lot, now my PC is slughish too 
Wold be nice that those tickets will be solved quickly, especially the one about suspending only the CUDA at will...

So you have responsive system w/o cc_config ? Then remove it. On good GPU it's better to have GPU working even if one core idle than to have all cores loaded but turning off GPU.

[Jason G]

So you have responsive system w/o cc_config ? Then remove it. On good GPU it's better to have GPU working even if one core idle than to have all cores loaded but turning off GPU.

And Lucky for me it's working best that way (1 core mostly idle), because it's another hot day here 

[SoNic]

So you have responsive system w/o cc_config ? Then remove it. On good GPU it's better to have GPU working even if one core idle than to have all cores loaded but turning off GPU.

It is a noticeable difference with 3 units compared to only 2, but hey, at night, who cares And it is not THAT bad, I won't be able to play games and IE it is kinda slow (I am using more Safari and that is faster anyway). And it is a cold day here, I need the heat
I have a C2D E4300 and a GeForce 9500GT w/512M. Running only seti. Maybe I can make a batch file to switch between 2 and 3 CPU (bad part is that BOINC did run the benchmarks after the "read config file").
I am using the file with SSE3 in description for non-AMD - it's the right one I guess?
I have now 3seti  units running in Boinc and in traskman it shows 2 AK at 46-48%, one AK at 0% linked with the CUDA that takes 2-4%...
Too bad that it is aborting (nicelly) the VLAR units - I guess it is a work in progress, you will figure those too?
Thank you a lot!

[Raistmer]

I am using the file with SSE3 in description for non-AMD - it's the right one I guess?

Hm, as I wrote on your first question it's NOT correct.
Correct version for Core2 Duo will be SSSE3 one. (Here it posted w/o any SSE reference as it was first available release).
SSE3 will give decreased performance.

[k6xt]

So you have responsive system w/o cc_config ? Then remove it. On good GPU it's better to have GPU working even if one core idle than to have all cores loaded but turning off GPU.

I tried removing cc_config and restarting BOINC. BOINC ran with one core more or less idle but the GPU, according to its temperature, is crunching. Removing cc_config did not affect the sluggish video performance - which is so poor it makes the PC unusable. I have to stop BOINC to do anything with it.

[chelski]

I notice some "wrong" behaviour: if a task goes to urgent state and the client starts it "pushing out" the current CUDA task, the new task don't transit to CUDA but stays on the CPU, so there are 3 tasks on my 2-core CPU and the GPU is idle until one of the tasks is finished.

Look 1-2 pages before for update that cures this situation.

Have been running the new affinity worker with the "Team" package.  Worked wonderfully and cured the "transition" error previously when new CUDA task gets stuck at 0:00:01.  Also noticed work transitions seamlessly from GPU to CPU a(When the CPU finishes a unit it tend to take over the ongoing CUDA WU.  Kind of surprised me at first until I realised that was how my CPU tasks seems to run faster.  CUDA worker then starts a new WU)

Thanks again Raistmer for all the effort in helping us run the various CUDA clients without having to pull all our hair off   I would say it looks like the latest Team package with the new worker it is stable and fast enough to consider making it to the main lunatics optimised client page!

[k6xt]

Agreed
Well, attached app little more "smart" in this sense and will leave worker thread on single (first) core. It could give some performance degradation indeed in general case (it can't fill idle window of another core) but it really helped in my situation. And achieved GPU temp is highest (the same was when no non-BOINC app runs).

It's can't be considered as upgrade cause it will help in some cases (when CUDA app appers freezing w/o reason) and can decrease performance (slightly if will do it) in other cases.

ADDON:
And some suggestion: If you experience some delays (PC behave sluggish) when running CUDA app and browsing Inet, playing game or watching video on multicore system, try exclude first CPU (By setting affinity for process in task manager) for non-BOINC app that experience delays (i.e. browser, game, media player). You could get better experience that way. Don't forget to upgrade to attached build of course in this case.

The new CUDA app attached to the above Raismer post has fixed my sluggish behavior problem. While I can still see the effects of maximum GPU work load the GUI is usable for other things now. All 4 cores are active at 25% each, the CUDA application shows the occasional 1% CPU usage, GPU temperature indicates full load, all cores are at 100%, and I can use the GUI.

One effect I will turn off is the Nvidia window-transparency-while-dragging feature. This is slow to activate when the GPU is at 100%.

I note there are now seven AK_V8b* instances plus the CUDA app running.  Seven seems like a lot. Boinc Tasks shows five running, two "waiting to run". I assume one of the five running is the CUDA app.

Very satisfied user! :-))

[ofp1]

Hi,
Can anyone post detaliled instructions on how to optimize a system with CUDA.

I have a Intel Quad Core 9500 4 GB Ram and a Nvidia evga GTX 260 Graphics Card on Windows Vista Ultimate 32 bits optimized only with  Win32_AK_AP_SSE41

Thanks

[Archangel999]

Raistmer thanks for all you have done i have use your app all the time from the start with gpu and all working fine. Thank's for your great support !!!

PS :i will post the results but i'm waiting the new watercooling kit for my system and push it to te limit now my Q6600 is OC to 3.4Ghz i think i will reach 3.8 with the watercooling will see

Best Regard's
D.Draganov

[k6xt]

Raistmer thanks for all you have done i have use your app all the time from the start with gpu and all working fine. Thank's for your great support !!!

PS :i will post the results but i'm waiting the new watercooling kit for my system and push it to te limit now my Q6600 is OC to 3.4Ghz i think i will reach 3.8 with the watercooling will see

Best Regard's
D.Draganov

Mr. Dragonov what mobo are you using? My MSI P35 Neo Combo/Q6600 starts errors at 3.2GHz with memory not overclocked.

I second your thanks to Raistmer. Great software.
Thanks