Latest drivers (NVidia and ATI)

[Purple Rabbit]

I didn't see any speed up after my update to 190 and 2.3 dll  (sample size of 3). I'm still getting about 45 minutes (wall clock time) for the GPU and 1:20 hours for the CPU (Q6600). I suspect my 8600GTS is doing all it can. It may have changed a minute or so, but I don't watch it that closely so I can't tell.

Where can I download the nanobots to upgrade my 8600GTS to infinite speed? 

Rick

[popandbob]

On a GTX260 I just did a shorty in 1minute 20 seconds wall time... an improvement of... 2.1x faster!!
Now the question is... are they valid??
It seems almost too good to be true

-Bob

[sunu]

On a GTX260 I just did a shorty in 1minute 20 seconds wall time... an improvement of... 2.1x faster!!
Now the question is... are they valid??
It seems almost too good to be true
-Bob

Yes, unfortunately berkeley has switched off the tasks pages and we can't check.

[MarkJ]

I didn't see any speed up after my update to 190 and 2.3 dll  (sample size of 3). I'm still getting about 45 minutes (wall clock time) for the GPU and 1:20 hours for the CPU (Q6600). I suspect my 8600GTS is doing all it can. It may have changed a minute or so, but I don't watch it that closely so I can't tell.

Where can I download the nanobots to upgrade my 8600GTS to infinite speed? 

Rick

Did you update the cufft and cudart.dll's in the projects\setiathome folder? If not then you'd still be running the older cuda version (whichever one you had previously).

[Firehawk]

Sorry, I miss that for sure but...Where can I get the needed files?

[sunu]

Get them from http://lunatics.kwsn.net/index.php?module=Downloads;sa=dlview;id=208

You'll also need the latest nvidia drivers.

[Pappa]

On a GTX260 I just did a shorty in 1minute 20 seconds wall time... an improvement of... 2.1x faster!!
Now the question is... are they valid??
It seems almost too good to be true

-Bob

What I have running in "Seti Beta" is having "no" issues with stock or other unnoted users that were still running Optimized after the release. That is including the 2.3 DLL's introduced yesterday after it was released into Seti Main.

[popandbob]

Well if the results are valid I'm seeing a HUGE improvement.
I am seeing wall times of 10.5 minutes for a long task (increased sensitivity), 5.5 minutes for an non increased sensitivity long task, and 1.3 for a short non increased sensitivity shorty and 3 min for a increased one.

Previously with 2.2 it was 8 min for a long task and 3 for a shorty.

Improvement for shorty's = 2x faster
Improvement for longer task = 1.5x faster

Bob

P.S. I estimate the final DCF at below 0.0085 since right now it takes 10 min for a task which estimates 2.5hrs @ DCF 0.17

[Sutaru Tsureku]

Get only the needed 2.3 dlls in beta downloads here, and get 190.38 driver from nVidia.  Some small speedup at high angle ranges is observed with V12, will be experimenting to see if new compiler makes a better build, or not, for a while.

I took the CUDA_V2.3 (.dll's) from the 'public DL area' here.
They are the same like in the 'beta release area'?

Or how I could understand your post?
You would like to optimize the '.dll's' or the 'CUDA_app'?


@ opt. crew
I have an other question because of the 'new Enhanced WUs' from SETI@home.
Could you look to this thread in the SETI@home-NC forum?
http://setiathome.berkeley.edu/forum_thread.php?id=54764
Because of new longer MB WUs..
The VLARkill option of the CUDA_V12_app will identify VLARs like before?

Or maybe.. no longer VLARkill needed, because the VLARs will be faster calculated with CUDA_V2.3 ?
Or this is only possible with a new CUDA_app?


O.K., one more question to the opt. crew.. 
For only CUDA crunching and best performance, PhysX ON/OFF ?

Over the system tray icon from nVIDIA.. right click -> performance and quality setting / system performance -> I can choose:

* high performance
* performance
* quality
* high quality

Stock is 'quality'.
How should be the setting for best CUDA performance?


Thanks! 

[popandbob]

VLAR's are just as slow as before... or well maybe a little slower even?
I ran one as a test in stand alone mode and well after 20 min it was only 0.35% complete.

As to my previous speed claims I've now had a couple tasks take 18 min... I tried to see how to tell the difference in the work unit header but I couldn't see anything that made sense.
I did also have an issue before when a task didn't end right the next tasks would take 20 min but I'm not sure that's the case this time because one finished in between that was a shorty at 2 minutes. Its also a possibility that there is a lot more speed variation depending on AR now than before.

Bob

[Raistmer]

As I already answered on SETI main, no changes  in VLAR (kill) situation.
You will process all other tasks just faster.

[popandbob]

O.K., one more question to the opt. crew.. 
For only CUDA crunching and best performance, PhysX ON/OFF ?

Over the system tray icon from nVIDIA.. right click -> performance and quality setting / system performance -> I can choose:

* high performance
* performance
* quality
* high quality

Stock is 'quality'.
How should be the setting for best CUDA performance?

I'm not one of the team but...

PhysX doesn't affect crunching... leave it on or off it doesn't matter for performance however with it on you shouldn't need to put a load (monitor or dummy plug) on a video card to use it (in theory)

High performance may give a very small boost but the best bet is to not have the screen displaying anything at all (in other words use the blank screen saver and not using the PC)

Bob

[popandbob]

Now that the task list is turned on again...
They are valid!
So looking at the improvements I'm seeing about 10 credits a minute. (8.8 for a 92 credit task and 12.46 for a 29.08 credit task)
So 14000 RAC possible with a single GTX260core216
 
Bob

[Zeus Fab3r]

Now that the task list is turned on again...
They are valid!
Bob

I hope they are, but should I be voried about this Result?
Strange is that they are in Completed, waiting for validation state, not invalid ?!¿¡

[Purple Rabbit]

Did you update the cufft and cudart.dll's in the projects\setiathome folder? If not then you'd still be running the older cuda version (whichever one you had previously).

Drat! I put them in the BOINC folder. It's fixed now. I wasn't paying attention again