#2 for today!
#2 for today!
120 million points, 1,000,000+ points a day, team went up 8 places in less than 30 days, 15 members returning work, 4+ milestones a day.
Team XS has done over 1 MILLION daily for about a week now and we're at #10 RAC
wplachy runs me over in about 45 days ... not that it will really help me much but I added a 7850 this morning to see if I can stretch that out a little longer
I see SAM dropped another card on this project recently
Sorry about that! Nothing personal just seemed to be waste to have those cards sit idle. I'll be visiting out of town friends for a week in the middle of Oct and will have my equipment shutdown. So pour it onOriginally Posted by Snow Crash
Bill P
Last edited by wplachy; 09-28-2013 at 09:57 AM. Reason: spelling
^^^ Looking good ^^^
Got the 7850 dialed in w/ GPU @1000 (PCIE2x16) cranks out 2 Aricebo WUs in 2hr 45min - theoretical PPD = 58176 but this is also my daily driver rig so most likely around 55K. Not quite 50% of what my 7950 does w/ GPU@1225 (PCIE3x16) but not too shabby either
Anyone running a 7770 - what's your experience?
Running 3770K on MVG @3.9 with one card (7950) @1100 now and have 2 threads in use running Win7. The other 6 threads are running a VM also with Boinc but running WCG in linux. It is my daily rig and is not 24/7.and glad to have you ... water's warm and especially nice for AMD - my 7950 averages just under 100k ppd (1 card PCIE3x16, OC GPU to 1250) I'm running 2 WU at a time, I tried 3 but there was no PPD difference, the GPU utilization went up but apparently that was just the overhead of managing 3 WUs.
These WUs are bandwidth sensitive, multi-card system running PCIE2 are definitely constrained.
Aricebo WUs are looking at the inner galaxy and are more likely to discover a binary pulsar but get about 10% less point than Perseus WUs that are looking outwards at ... you guessed it the Perseus Arm.
I found that running both types at the same did not perform well on NVidia w/ PCIE2x16
wplachy's in the house and making some serious noise ...
I am not sure yet but runtimes seem to behave differently for me than for SC.
I am going back over some quick tests that I did while it was raining at the weekend. Running Perseus arm survey only The first batch is as follows:
1. running 2 wu's concurrently on 2 threads using app_config
<gpu_usage>0.5</gpu_usage>
<cpu_usage>1.0</cpu_usage>
Completion times: best to worst = 5714-5723 so ave 5719 per 2 wu's or 2859 (47m39s) per wu.
2. running 3 wu's concurrently on 2 threads using app_config
<gpu_usage>0.33</gpu_usage>
<cpu_usage>0.50</cpu_usage>
Completion times: best to worst = 7854-7922-7939 so ave 7905 per 3 wu's or 2635 (43m55s) per wu.
3. running 4 wu's concurrently on 2 threads using app_config
<gpu_usage>0.25</gpu_usage>
<cpu_usage>0.50</cpu_usage>
Completion times: best to worst = 10253-10291-10332-10371 so ave 10312 per 4 wu's or 2578 (42m58s) per wu.
4. running 5 wu's concurrently on 2 threads using app_config
<gpu_usage>0.20</gpu_usage>
<cpu_usage>0.40</cpu_usage>
Completion times: best to worst = 13114-13169-13278-13288-13526 so ave 13275 per 5 wu's or 2655 (44m15s) per wu.
It is not a lot but there is a slight advantage 4 vs 3 as there is running 3 rather than 2 whereas with 5 it is going the wrong way again. I do however wonder if running 5 or 6 wu's concurrently but on 3 threads would still support this trend.
Obviously this is a very small sample and the gains are not exactly huge but if anything at all the above may show that individuals should try similar testing on individual hardware setups if wanting to maximise any points scoring potential.
Last edited by OldChap; 10-01-2013 at 11:00 AM.
My Biggest Fear Is When I die, My Wife Sells All My Stuff For What I Told Her I Paid For It.79 SB threads and 32 IB Threads across 4 rigs 111 threads Crunching!!
Edit above completing short test series. It is possible that absolute maximum performance is dependent on number of free cpu cores in support.
If you test your own hardware please post results.
Last edited by OldChap; 10-01-2013 at 11:09 AM.
My Biggest Fear Is When I die, My Wife Sells All My Stuff For What I Told Her I Paid For It.79 SB threads and 32 IB Threads across 4 rigs 111 threads Crunching!!
I dunno....
I have 2 GTX460s. 1 running under Linux one Windows. Even though the one under Windows was on a machine used daily, GPU set to OFF when PC in use, it always had a higher RAC than the one under Linux which was seldom used. So I move the GTX460 from the Linux box to another Windows PC and doing same app, Perseus, times are down from 22k seconds to 15k.
Anyone seeing a difference between Linux and WIndows with the GPU apps?
Yes, I'm seeing the same thing. I switched a couple of devices from Linux to Windows yesterday and pulled this:
.............................Windows.............. ...............Linux
Device.........Appl.....Nbr....Avg CPU...Avg Elap.....Nbr......Avg CPU....Avg Elap
I72600K-3...BRP4G...15......332.67....,170.42......517.... ...577.57....2,719.49
I72600K-3...BRP5.......8......915.44..7,848.64......183... .1,958.20...10,223.12
I72600K-4...BRP4G...19......346.79..2,371.69......536..... ..578.78.....2,728.31
I72600K-4...BRP5.......6......932.88..7,828.46......181... .1,973.26...10,195.82
Bill P
The GTX260 that was in the Windows went to the Linux box the GTX460 had been in and the complete time increased 7k-8k seconds over what it had been under Windows.
Seems to be a problem with certain versions of Nvidia driver under linux. I've switched from 319 to 304. Will update after a few WUs have finished.
Last edited by PoppaGeek; 10-05-2013 at 02:43 AM.
Interesting, but all mine are ATI cards. It appears there is more to it than the driver version.
Bill P
Driver change made NO difference.
Last edited by PoppaGeek; 10-05-2013 at 02:08 PM.
Welcome Bobby Brix! Glad to have ya on board!
WOW 1,667,135
Highest daily so far2m is not far away
Last edited by stoneageman; 10-14-2013 at 08:54 AM.
New Nvidia 331 beta driver seems to be showing improved numbers for E&H. Message at Message 127575 - Posted 22 Oct 2013 17:17:59 UTC by Bikeman (Heinz-Bernd Eggenstein). I will try it later today and report.
EDIT:
Here is how I installed the drivers after using several other ways that failed for one reason or another:
Uninstall current Nvidia drivers.
This is for Ubuntu. And driver was 331.17.If you want the latest version of the Nvidia drivers, you will have to install the version provided by Nvidia on their official website. Download the one marked 313.30 and make sure you get the right version for your architecture, 32-bit or 64-bit.
Log out of the system and press Ctrl + Alt + F1. Log in into a command line interface, navigate to the folder where you have downloaded the driver, and kill the LightDM display manager:
sudo service lightdm stop
sudo chmod a+x NVIDIA-Linux-x86_64-313.30.run
sudo ./NVIDIA-Linux-x86_64-313.30.run
All you have to do now is wait and follow the on-screen instructions. You might need to perform this operation twice if the Nouveau driver is active.
When the installation is done, enter the sudo reboot command and enjoy the newest Nvidia drivers.
Last edited by PoppaGeek; 10-29-2013 at 06:48 AM.
No difference. At all.
From what I read and hopefully understand, there are separate problems with E@H and Nvidia drivers and CUDA 5.5. They think the latest drivers fix the driver issues and are hoping they can now use CUDA 5.5. Testing is beginning on Albert@home.
Posting Permissions
Reply With Quote
Bookmarks