+- +-
Say hello if visiting :) by Gecko
11 Jan 2023, 07:43:05 pm

Seti is down again by Mike
09 Aug 2017, 10:02:44 am

Some considerations regarding OpenCL MultiBeam app tuning from algorithm view by Raistmer
11 Dec 2016, 06:30:56 am

Loading APU to the limit: performance considerations by Mike
05 Nov 2016, 06:49:26 am

Better sleep on Windows - new round by Raistmer
26 Aug 2016, 02:02:31 pm

Author Topic: SETI MB CUDA for Linux  (Read 387553 times)

Offline riofl

  • Knight o' The Round Table
  • ***
  • Posts: 240
Re: SETI MB CUDA for Linux
« Reply #375 on: 22 Aug 2009, 12:06:34 pm »
riofl, what is happening?

I've checked again your host today and I've seen this: http://setiathome.berkeley.edu/results.php?hostid=4166601&offset=40&show_names=0&state=2

All 2 hundred and 3 hundred sec tasks were done by your 285. All two-digit sec tasks were done by your tesla. This is completely abnormal.

well i just went back to 2.6.25, recompiled everything to do with cuda/boinc, made sure there were no cuda 2.3 libs laying around so now we wait and see if that changes anything. looks like im still gonna get 30 min workunits but time will tell.

booted off my windows "nvidia checking" disk and checked both cards with rivatuner and also evga precision and it all looks right. everything set to factory except fans which i keep at 100%. did not use them to set anything simply cancelled out of whatever i looked at. i only use nvclock to set fans on boot of linux after X has reset them both.



Offline riofl

  • Knight o' The Round Table
  • ***
  • Posts: 240
Re: SETI MB CUDA for Linux
« Reply #376 on: 22 Aug 2009, 02:37:08 pm »
12 workunits done and still around 26min. a little faster average than before at 30 min but...

this is odd


Offline riofl

  • Knight o' The Round Table
  • ***
  • Posts: 240
Re: SETI MB CUDA for Linux
« Reply #377 on: 22 Aug 2009, 10:45:36 pm »
also the 3 digit time workunits are still the 285 and 2 digit the tesla.  i wonder if it has something to do with how busy my desktops are? i have quite a lot going on 24/7 with 18 gkrellm server monitors running in one desktop, usually 4 or 5 browser windows in different desktops with maybe 28 or so tabs open, average 8 or 10 ssh konqueror tabs open into our servers, email, virtualbox running xp which also runs boinc, kopete, 8 or 9 postit notes in the various desktops, a few kedit windows open plus momentary things like adobe reader, smplayer or whatever.. im in totally new territory here. my experience in graphics cards is plug it in and make sure it works with a stable and peppy screen :)

however the 'busyness' of the desktops is not new and was basically the same when i had 10-13min workunits out of both cards.

Offline riofl

  • Knight o' The Round Table
  • ***
  • Posts: 240
Re: SETI MB CUDA for Linux
« Reply #378 on: 22 Aug 2009, 11:04:28 pm »
i am trying to help someone in the boinc cuda forum. his workunits are giving strange things. he runs windows, the vlarkill cuda app and the ak cpu app, a 9400gt 1gb ram and the 190 driver with 2.3 toolkit. this is one of his workunits.. they are all similar..

his cuda app is specifically CUDA - MB_6.08_CUDA_V12_VLARKill_FPLim248.exe.

Work Unit Info:
...............
WU true angle range is : 1.479648
After app init: total GPU memory 1073741824 free GPU memory 963768320

Flopcounter: 11519105207831.588000

Spike count: 0
Pulse count: 0
Triplet count: 2
Gaussian count: 0

Wall-clock time elapsed since last restart: 3348.9 seconds
class T_FFT<0>: total=2.67e+006, N=98124, <>=27 (2.70e+001), min=0 (0.00e+000)
class T_FFT<8>: total=9.30e+001, N=3, <>=31 (3.10e+001), min=31 (3.10e+001)
class T_FFT<16>: total=1.25e+002, N=7, <>=17 (1.70e+001), min=15 (1.50e+001)
class T_FFT<64>: total=2.65e+002, N=29, <>=9 (9.00e+000), min=0 (0.00e+000)
class T_FFT<256>: total=0.00e+000, N=115, <>=0 (0.00e+000), min=0 (0.00e+000)
class T_FFT<512>: total=2.65e+003, N=229, <>=11 (1.10e+001), min=0 (0.00e+000)
class T_FFT<1024>: total=4.30e+003, N=457, <>=9 (9.00e+000), min=0 (0.00e+000)
class T_FFT<2048>: total=1.50e+004, N=915, <>=16 (1.60e+001), min=0 (0.00e+000)
class T_FFT<4096>: total=3.94e+003, N=211, <>=18 (1.80e+001), min=15 (1.50e+001)
class T_FFT<8192>: total=1.72e+004, N=845, <>=20 (2.00e+001), min=15 (1.50e+001)
called boinc_finish

</stderr_txt>
]]>

i dont know what the fft lines mean but i have a feeling they should not be there. my first thought was to drop back to the 185 series drivers and the 2.2 toolkit. im not sure 2.3 and a 9400 can work together.

any ideas?
« Last Edit: 22 Aug 2009, 11:09:47 pm by riofl »

Offline Josef W. Segur

  • Janitor o' the Board
  • Knight who says 'Ni!'
  • *****
  • Posts: 3112
Re: SETI MB CUDA for Linux
« Reply #379 on: 23 Aug 2009, 01:38:25 am »
i am trying to help someone in the boinc cuda forum. his workunits are giving strange things. he runs windows, the vlarkill cuda app and the ak cpu app, a 9400gt 1gb ram and the 190 driver with 2.3 toolkit. this is one of his workunits.. they are all similar..

his cuda app is specifically CUDA - MB_6.08_CUDA_V12_VLARKill_FPLim248.exe.
...
i dont know what the fft lines mean but i have a feeling they should not be there. my first thought was to drop back to the 185 series drivers and the 2.2 toolkit. im not sure 2.3 and a 9400 can work together.

any ideas?

The FFT lines are normal for those builds, just keeping some statistics on those which may give clues for future improvements. The FPLim2048 in the file name is also related to the same effort.
                                                                         Joe

Offline Jason G

  • Construction Fraggle
  • Knight who says 'Ni!'
  • *****
  • Posts: 8980
Re: SETI MB CUDA for Linux
« Reply #380 on: 23 Aug 2009, 04:33:45 am »
...
The FFT lines are normal for those builds, ...

Aww yeah, forgot about those  :-\ . Well in case anyone's wondering why the <256> size measures 0, it mutated into a test piece toward future coding efforts, so the 'standard' code inside the timer is never run for that one.
« Last Edit: 23 Aug 2009, 04:36:42 am by Jason G »

Offline riofl

  • Knight o' The Round Table
  • ***
  • Posts: 240
Re: SETI MB CUDA for Linux
« Reply #381 on: 23 Aug 2009, 06:54:15 am »
thanks guys. ok then his processing is probably normal. a 9400 is not the fastest card and he was concerned something was wrong since his cuda processing times just about match his cpu times. his cpu is a Q9300 so it is very probable since i believe a 9400 would weigh in around 4gflops or so going by boinc's measurement standards.

thanks again.


Kunin

  • Guest
Re: SETI MB CUDA for Linux
« Reply #382 on: 24 Aug 2009, 04:16:26 pm »
Two linux hosts in the top 20 now!

Offline riofl

  • Knight o' The Round Table
  • ***
  • Posts: 240
Re: SETI MB CUDA for Linux
« Reply #383 on: 24 Aug 2009, 05:57:10 pm »
cool!

vejpuste

  • Guest
Re: SETI MB CUDA for Linux
« Reply #384 on: 25 Aug 2009, 07:55:46 am »
Hello,
I try Crunch3rs CUDA seti application and search google and this forum too but result is not OK.
I tried to CUDA 2.1 and aplication setiathome-CUDA-6.08.x86_64-pc-linux-gnu. This compute OK but take 100% of CPU.
http://setiathome.berkeley.edu/result.php?resultid=1340190227

Now I test CUDA 2.3 with same apliaction and result is SIGSEGV: segmentation violation
http://setiathome.berkeley.edu/result.php?resultid=1344497914
CentOS5 64bit
CUDA driver 190.18
CUDA Toolkit and SDK 2.3
ldd setiathome-CUDA-6.08.x86_64-pc-linux-gnu
libcufft.so.2 => /usr/local/cuda/lib64/libcufft.so.2 (0x00002b7786226000)
libcudart.so.2 => /usr/local/cuda/lib64/libcudart.so.2 (0x00002b7786c7a000)
libcuda.so.1 => /usr/lib64/libcuda.so.1 (0x00002b7786eba000)
libstdc++.so.6 => /usr/lib64/libstdc++.so.6 (0x0000003ca0200000)
libm.so.6 => /lib64/libm.so.6 (0x0000003c9a200000)
libpthread.so.0 => /lib64/libpthread.so.0 (0x0000003c9aa00000)
libc.so.6 => /lib64/libc.so.6 (0x0000003c99e00000)
libdl.so.2 => /lib64/libdl.so.2 (0x0000003c9a600000)
libgcc_s.so.1 => /lib64/libgcc_s.so.1 (0x0000003c9f600000)
librt.so.1 => /lib64/librt.so.1 (0x0000003c9e600000)
libz.so.1 => /usr/lib64/libz.so.1 (0x0000003c9ae00000)
/lib64/ld-linux-x86-64.so.2 (0x0000003c99a00000)

I try add setiathome-CUDA-6.08.x86_64-pc-linux-gnu to /usr/local/bin but still not working.
CUDA 2.2 take segmentation violation too.
Thanks for any ideas
Libor

pp

  • Guest
Re: SETI MB CUDA for Linux
« Reply #385 on: 25 Aug 2009, 08:45:02 am »

vejpuste

  • Guest
Re: SETI MB CUDA for Linux
« Reply #386 on: 25 Aug 2009, 08:59:23 am »
You need the 2.2 CUDA binary: http://calbe.dw70.de/mb/viewtopic.php?p=868#p868
I try this application too but here is another problem
ldd setiathome-6.08.CUDA_2.2_x86_64-pc-linux-gnu
./setiathome-6.08.CUDA_2.2_x86_64-pc-linux-gnu: /usr/lib64/libstdc++.so.6: version `GLIBCXX_3.4.9' not found (required by ./setiathome-6.08.CUDA_2.2_x86_64-pc-linux-gnu)
CentOS5 have no GLIBCXX_3.4.9 in updates now.
Libor

Offline Urs Echternacht

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 4121
  • ++
Re: SETI MB CUDA for Linux
« Reply #387 on: 25 Aug 2009, 09:01:59 am »
You need the 2.2 CUDA binary: http://calbe.dw70.de/mb/viewtopic.php?p=868#p868
I try this application too but here is another problem
ldd setiathome-6.08.CUDA_2.2_x86_64-pc-linux-gnu
./setiathome-6.08.CUDA_2.2_x86_64-pc-linux-gnu: /usr/lib64/libstdc++.so.6: version `GLIBCXX_3.4.9' not found (required by ./setiathome-6.08.CUDA_2.2_x86_64-pc-linux-gnu)
CentOS5 have no GLIBCXX_3.4.9 in updates now.
Libor
Search for a newer version of "libstdc++", GLIBCXX_3.4.9 is the version number of that library.
_\|/_
U r s

lordvader

  • Guest
Re: SETI MB CUDA for Linux
« Reply #388 on: 25 Aug 2009, 11:32:50 am »
... currently trying the 2.6.27 kernel, and CUDA seems fine (and hoping that AP is stable).

Quick question though. I had about 70 WUs uploaded, but not reported. I then tinkered with my app_info.xml, and lost all the WUs, so can't report them ! Is there a way to report with the boinc client ? Otherwise, there's 70 units sitting there, and no one will ever know !!!

Offline Urs Echternacht

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 4121
  • ++
Re: SETI MB CUDA for Linux
« Reply #389 on: 25 Aug 2009, 11:38:01 am »
... currently trying the 2.6.27 kernel, and CUDA seems fine (and hoping that AP is stable).

Quick question though. I had about 70 WUs uploaded, but not reported. I then tinkered with my app_info.xml, and lost all the WUs, so can't report them ! Is there a way to report with the boinc client ? Otherwise, there's 70 units sitting there, and no one will ever know !!!
On main the only way is currently to run your cache dry, detach from project and immediately after reattach to project. That way the "lost" wus will be marked "detached" and send out again.
_\|/_
U r s

 

Welcome, Guest.
Please login or register.
 
 
 
Forgot your password?
Members
Total Members: 97
Latest: ToeBee
New This Month: 0
New This Week: 0
New Today: 0
Stats
Total Posts: 59559
Total Topics: 1672
Most Online Today: 24
Most Online Ever: 983
(20 Jan 2020, 03:17:55 pm)
Users Online
Members: 0
Guests: 21
Total: 21
Powered by EzPortal