Seti@Home optimized science apps and information
Optimized Seti@Home apps => Windows => GPU crunching => Topic started by: Raistmer on 21 Feb 2009, 05:25:07 pm
-
These combos supersede both V7 and V8 combos.
(look http://lunatics.kwsn.net/gpu-crunching/modified-seti-mb-cuda-opt-ap-package-for-full-gpu-utilize.msg14445.html;topicseen#msg14445 and http://lunatics.kwsn.net/gpu-crunching/ak-v8-cuda-mb-team-work-mod.msg14462.html;topicseen#msg14462 threads if you are new in this GPU mod).
Owners of multi-GPU hosts should use Raistmer's_opt_pack_V9_x86_Multi_GPU.rar variant while all others should use version that corresponds SSE-level of their host.
That is:
Core2 and Core (SSE4.1 & SSSE3) -> Raistmer's_opt_pack_V9_x86_SSSE3_MB_CPU_GPU_team.rar
AMD users -> Raistmer's_opt_pack_V9_x86_SSE3_AMD_MB_CPU_GPU_team.rar
P4 with SSE3 support, Pentium D and so on -> Raistmer's_opt_pack_V9_x86_SSE3_MB_CPU_GPU_team.rar
Please, don't forget to check ALL STUFF (including these packs) you downloaded from Internet with updated AntiVirus.
I checked with 3 best ( IMHO ) antiviruses and found no infection, download on your own discretion.
Don't forget, you still need cc_config.xml.
Here is example of minimal cc_config.xml file you need
<cc_config>
<options>
<ncpus>enter_number_of_cores+1_value_here</ncpus>
</options>
</cc_config>
File should be placed in boinc data directory (the one that contains projects subdirectory).
When you post to this thread seeking for help, please, don't forget to provide link on your host and description of your config (OS, number of GPU cards, what pack you use, video driver version).
It will wastly decrease number of unneeded questions and save time both for you and anyone who will help you.
[attachment deleted by admin]
[attachment deleted by admin]
-
You da man! Thanks much. ;D
-
Please Sir may I have some more? I've passed these on to my teammates and some are asking about the AP App without GPU crunching. Do you have anything for them?
-
McAffee is reporting that the file magent49.exe is infected with Generic.dx PUP
-
McAffee is reporting that the file magent49.exe is infected with Generic.dx PUP
Where you find magent49.exe in these packages ????
-
Please Sir may I have some more? I've passed these on to my teammates and some are asking about the AP App without GPU crunching. Do you have anything for them?
Nope. It's BOINC domain, kick BOINC devs for correct CUDA/CPU support... It's not possible to sue same trick for AP as I did for AK_v8 - AstroPulse is totally different algorithm with different input and output data. It can't be switched to CUDA MB.
-
Hi,
Kaspersky tells me that AK_v8b_win_SSE3_AMD_GPU_CPU_team_V9.exe is infected with Trojan.Win32.Obfuscated.gen
Regards Uli
-
I'm just passing on what McAfee is reporting. They issue a warning on the website: http://files.mail.ru/ZQ0RN9 when I selected it from your link.
Found: Generic.dx PUP
-
Hi,
Kaspersky tells me that AK_v8b_win_SSE3_AMD_GPU_CPU_team_V9.exe is infected with Trojan.Win32.Obfuscated.gen
Regards Uli
Ok, thanks, I will check with available antiviruses. Removing pack for now.
-
I'm just passing on what McAfee is reporting. They issue a warning on the website: http://files.mail.ru/ZQ0RN9 when I selected it from your link.
Found: Generic.dx PUP
So virus on mail.ru site? funny... Can't check their site but will thoroughly check my own host :)
-
ok, lets see:
NOD32: No viruses.
DRWeb CureIt!: No viruses
AVG Free 8: No viruses
Well, I think Kaspersky too paranoid, never liked that antivirus.
I returning pack online, download and check by your own antiviruses.
-
I downloaded from here on Lunatic's. I ran a scan with both AVG and Spybot S&D. Neither one hit on anything
-
I downloaded from here on Lunatic's. I ran a scan with both AVG and Spybot S&D. Neither one hit on anything
Same here...
-
Just to put the SSSE3 one in the clear (didn't grab the others yet:
http://virusscan.jotti.org/
File: Raistmer's_opt_pack_V9_SSSE3_MB_CPU_GPU_team.rar
Status:
OK
MD5: 6ed4e6d5f848d5dd39f75fc94dc916e6
Packers detected:
PE_PATCH.UPX, UPX
Scanner results
Scan taken on 22 Feb 2009 00:20:44 (GMT)
A-Squared Found nothing
AntiVir Found nothing
ArcaVir Found nothing
Avast Found nothing
AVG Antivirus Found nothing
BitDefender Found nothing
ClamAV Found nothing
CPsecure Found nothing
Dr.Web Found nothing
F-Prot Antivirus Found nothing
F-Secure Anti-Virus Found nothing
Ikarus Found nothing
Kaspersky Anti-Virus Found nothing
NOD32 Found nothing
Norman Virus Control Found nothing
Panda Antivirus Found nothing
Sophos Antivirus Found nothing
VirusBuster Found nothing
VBA32 Found nothing
-
For AMD_SSE3:
Service load: 0% 100%
File: Raistmer's_opt_pack_V9_x86_SSE3_AMD_MB_CPU_GPU_team.rar
Status: INFECTED/MALWARE
MD5: a1b3a45aa5977bb1879b28f4629ebd47
Packers detected: PE_PATCH.UPX, UPX
Scanner results
Scan taken on 22 Feb 2009 00:33:06 (GMT)
A-Squared Found nothing
AntiVir Found nothing
ArcaVir Found nothing
Avast Found nothing
AVG Antivirus Found nothing
BitDefender Found nothing
ClamAV Found nothing
CPsecure Found nothing
Dr.Web Found nothing
F-Prot Antivirus Found nothing
F-Secure Anti-Virus Found Trojan.Win32.Obfuscated.gen
Ikarus Found nothing
Kaspersky Anti-Virus Found Trojan.Win32.Obfuscated.gen
NOD32 Found nothing
Norman Virus Control Found nothing
Panda Antivirus Found nothing
Sophos Antivirus Found nothing
VirusBuster Found nothing
VBA32 Found nothing
Download at your own discretion as I said before. I think there is no viruses there...
-
My Boinc freezes as soon I putted in the new multi GPU files.
Thank you
-
Any VLAR kill team version for SSSE3?
-
VERY cool - My two GTX280s are crunching away, and I have 1 AP unit running on the CPU - I assume the other 3 cores will fill with more AP units when I can actually get them (things seem very plugged up on their end ATM)...
Hope this isn't too far off topic, but is there a reason why Seti doesn't use optimized versions by default? I would think they would want the most computing bang for their buck they could get, and it isn't very difficult to detect processor capabilities...
-
Any VLAR kill team version for SSSE3?
It's VLAR kill one.
-
Hope this isn't too far off topic, but is there a reason why Seti doesn't use optimized versions by default? I would think they would want the most computing bang for their buck they could get, and it isn't very difficult to detect processor capabilities...
They need much wider compatibility and portability than we have with opt apps.
-
My Boinc freezes as soon I putted in the new multi GPU files.
Thank you
Try to reboot. And if you want some more productive advice, please, post more info next time.
-
I have three GTX280's with the V9 multi GPU version installed and it only uses two cards. Is there a setting I need to change or is this a limitation of CUDA/BOINC?
Thanks
-
I downloaded and installed the AMD version. Running under Windows 7 with a Geforce 9800 GT and I'm getting errors with the multibeam part.
I did back up the complete Boinc data folders and have restored and back running as before and I did reboot before starting the new version.
No doubt I've done something stupid but here is the error log for one failed workunit grabbed from client_state.xml:
<result>
<name>16ja09aa.27910.34725.6.8.199_1</name>
<final_cpu_time>290.224200</final_cpu_time>
<exit_status>-1073741819</exit_status>
<state>3</state>
<platform>windows_intelx86</platform>
<version_num>608</version_num>
<fpops_cumulative>58866180000000.000000</fpops_cumulative>
<stderr_out>
<![CDATA[
<message>
- exit code -1073741819 (0xc0000005)
</message>
<stderr_txt>
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : GeForce 9800 GT
totalGlobalMem = 536870912
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1500000
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 14
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9800 GT is okay
SETI@home using CUDA accelerated device GeForce 9800 GT
setiathome_enhanced 6.03 Visual Studio/Microsoft C++
libboinc: 6.3.22
Work Unit Info:
...............
WU true angle range is : 0.432681
Optimal function choices:
-----------------------------------------------------
name
-----------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.00081 0.00000
v_ChirpData 0.02663 0.00000
v_Transpose4 0.01660 0.00000
FPU opt folding 0.00658 0.00000
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : GeForce 9800 GT
totalGlobalMem = 536870912
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1500000
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 14
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9800 GT is okay
SETI@home using CUDA accelerated device GeForce 9800 GT
Restarted at 17.66 percent.
setiathome_CUDA: Found 1 CUDA device(s):
Cuda error 'cudaGetDeviceProperties( &cDevProp, i )' in file 'd:/BTR/SETI6/SETI_MB_CUDA/client/cuda/cudaAcceleration.cu' in line 135 : invalid argument.
ERROR: Invalid parameter detected in function (null). File: (null) Line: 0
ERROR: Expression: (null)
</stderr_txt>
]]>
</stderr_out>
<ready_to_report/>
<completed_time>1235300353.341991</completed_time>
<wu_name>16ja09aa.27910.34725.6.8.199</wu_name>
<report_deadline>1237157056.000000</report_deadline>
<file_ref>
<file_name>16ja09aa.27910.34725.6.8.199_1_0</file_name>
<open_name>result.sah</open_name>
</file_ref>
</result>
-
COULD be a driver issue. What nVidia driver do you have installed?
-
COULD be a driver issue. What nVidia driver do you have installed?
The latest one from nVidia (Prerelease - WDDM 1.1) installed on 19 Feb by Windows Update.
-
Hmmm. I stick to the finalised release ones from nVidia - can't help with that one.
Probably best to suspend processing until Raistmer checks in and can advise further.
-
That's what I thought :-)
Prerelease is all I get for Windows 7 at the moment.
There was another thread about VLAR units but I can't find that now. Usually they complete in 20-25 mins but the VLAR ones took about an hour and a half which seemed to be a lot quicker than was expected on the other thread but they went through on the 18-19 Feb so no records of them now apart from whats in stdoutdae.txt they had an angle of 0.01 something. Two of them are still on the seti page WU 142908101 and 102 if anyone wants to look at them.
-
I have three GTX280's with the V9 multi GPU version installed and it only uses two cards. Is there a setting I need to change or is this a limitation of CUDA/BOINC?
Thanks
It is not a limitation of boinc/cuda. Others have gotten such a setup to work.
Have you installed the drivers for each card via device manager?
-
Yes, all three cards show up in device manager with the newest NV driver 182.06 installed. They are recognized by the SLI control panel and by GPU-Z.
-
Have you set the number of cpu's in the cc_config file as described in post http://lunatics.kwsn.net/gpu-crunching/modified-seti-mb-cuda-opt-ap-package-for-full-gpu-utilize.0.html ?
-
Yes, I have a Q9650 quad core so I've set the cores+1 variable to 5.
What is odd is that CUDA-Z only "sees" two of the cards. While other programs "see" all three of the cards.
-
Will there be a 64 bit version?
-
I have three GTX280's with the V9 multi GPU version installed and it only uses two cards. Is there a setting I need to change or is this a limitation of CUDA/BOINC?
Thanks
Link on your host?
-
I downloaded and installed the AMD version. Running under Windows 7 with a Geforce 9800 GT and I'm getting errors with the multibeam part.
I did back up the complete Boinc data folders and have restored and back running as before and I did reboot before starting the new version.
No doubt I've done something stupid but here is the error log for one failed workunit grabbed from client_state.xml:
Driver version ?
-
Hmmm. I stick to the finalised release ones from nVidia - can't help with that one.
Probably best to suspend processing until Raistmer checks in and can advise further.
I don't plan tou install Windows 7 in near future, sorry. What xxx.xx version corresponds to WDM1.1 - no idea.
Windows 7 is beta software, BTW.
-
Will there be a 64 bit version?
Yes. but current x64 builds don't give so much speedup to hurry with them.
-
I don't plan tou install Windows 7 in near future, sorry. What xxx.xx version corresponds to WDM1.1 - no idea.
Windows 7 is beta software, BTW.
The driver version is 7.15.11.7943, nothing like xxx.xx. I know Windows 7 is beta, I've seen it mentioned in here so thought I'd report the problem, especially since it came out with an error message that might mean something. Thanks for the ap apps, that's running well.
-
For ones who wanna test x64 SSSE3 version of V9 combo - it attached to this post.
But keep in mind that I haven't ability to test it still. My GPU host running x86 Vista.
[attachment deleted by admin]
-
was just wondering if i should delete all previous optimized packages before installing a new one
thanks
-
I have three GTX280's with the V9 multi GPU version installed and it only uses two cards. Is there a setting I need to change or is this a limitation of CUDA/BOINC?
Thanks
Link on your host?
Forgive my ignorance, but what info are you asking for??
-
I have three GTX280's with the V9 multi GPU version installed and it only uses two cards. Is there a setting I need to change or is this a limitation of CUDA/BOINC?
Thanks
Link on your host?
Forgive my ignorance, but what info are you asking for??
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4090095
Joe
-
was just wondering if i should delete all previous optimized packages before installing a new one
thanks
No, it will done automatically after installation of new pack.
-
I have three GTX280's with the V9 multi GPU version installed and it only uses two cards. Is there a setting I need to change or is this a limitation of CUDA/BOINC?
Thanks
Link on your host?
Forgive my ignorance, but what info are you asking for??
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4090095
Joe
Owner K Rider
CPU type GenuineIntel
Intel(R) Core(TM)2 Quad CPU Q9650 @ 3.00GHz [Intel64 Family 6 Model 23 Stepping 10]
Number of processors 4
Coprocessors [2] NVIDIA GeForce GTX 280 (1024MB)
Operating System Microsoft Windows Vista
Home Premium x64 Editon, Service Pack 1, (06.00.6001.00)
SETI app will use amount of GPUs provided by BOINC and BOINC sees only 2 GPUs. Check if you use SLI mode for 2 of 3 GPUs.
-
For ones who wanna test x64 SSSE3 version of V9 combo - it attached to this post.
But keep in mind that I haven't ability to test it still. My GPU host running x86 Vista.
13 downloads at moment I write this.... And no single report if it runs or not :-\
-
For ones who wanna test x64 SSSE3 version of V9 combo - it attached to this post.
But keep in mind that I haven't ability to test it still. My GPU host running x86 Vista.
13 downloads at moment I write this.... And no single repost if it runs or not :-\
Come on lurkers! fess up!
-
@Rastimer
I have copy all in to the project, but CUDA does not work!
BIONC Manager 6.6.0 x64
Sorry, but it is monday .. and every one takes a phonecall .. and all work must be KNOW ..
-
thnx to everyone involved for all the effort on the optimised apps...love them.
I just want to check something out if I may. I only crunch seti, no other projects. I have boinc 6.6.9 running on two boxes with Raistmer's V9 package SSSE3. Both boxes only run 4 threads, 3 on the cpu cores and 1 on the Nvidia graphics card. Both boxes have cc_config at 5. 1 core in box is idle. It was the same for the V8 and V7 packages even when I was running 6.6.4, 6.6.3.
Is it supposed to run this way or should there be 5 threads running..
-
thnx to everyone involved for all the effort on the optimised apps...love them.
I just want to check something out if I may. I only crunch seti, no other projects. I have boinc 6.6.9 running on two boxes with Raistmer's V9 package SSSE3. Both boxes only run 4 threads, 3 on the cpu cores and 1 on the Nvidia graphics card. Both boxes have cc_config at 5. 1 core in box is idle. It was the same for the V8 and V7 packages even when I was running 6.6.4, 6.6.3.
Is it supposed to run this way or should there be 5 threads running..
There should be no idle cores.
Check place where you put cc_config. Look first post.
-
Ok, #1 lurker fessing up here. I up graded this morning to the x64 kit but with S@H wedged on I/O, I'm not sure when I'll get any WU to try out the 64 bit version. Once the I/O issues are cleared up and I get some S@H WUs, I'll let you know how it works.
Thanks for all the hard work you'all do for us lurkers'.
John
-
If this is not needed still in 6.5.0 (which I have) when installing V9, then the question below is redundent, however its still valid for its own sake as it appears strange since it looks correct.
When I try to use the following in an xml file (sourced from Word or IE or any xml editor, tried several) and saved as file type xml:
<cc_config>
<options>
<ncpus>5</ncpus>
</options>
</cc_config>
I get the following error message in BOINC Manager:
Missing start tag in cc_config.xml
They seem to be nested correctly etc - any clues?
-
If this is not needed still in 6.5.0 (which I have) when installing V9, then the question below is redundent, however its still valid for its own sake as it appears strange since it looks correct.
When I try to use the following in an xml file (sourced from Word or IE or any xml editor, tried several) and saved as file type xml:
<cc_config>
<options>
<ncpus>5</ncpus>
</options>
</cc_config>
I get the following error message in BOINC Manager:
Missing start tag in cc_config.xml
They seem to be nested correctly etc - any clues?
1)use notepad ONLY (or FAR embedded editor) IE too clever with XML to be good for it - it change format as it like, not as BOINC like.
2) cc_config is NEEDED look first page.
-
Notepad did the trick, many thanks ;D
And a note of greatful thanks for all that you do with these apps, I know its been said many times, but it always bares repeating - you do a wonderful job that makes so many peoples lives a lot easier - Thank You ;)
-
Notepad did the trick, many thanks ;D
And a note of greatful thanks for all that you do with these apps, I know its been said many times, but it always bares repeating - you do a wonderful job that makes so many peoples lives a lot easier - Thank You ;)
:D
-
What are the proper settings to make SETI CUDA run all the time, but the computer processors to run only when the machine is idle?
is that possible?
Also, I have set the # of ncpus to 3 (dual core + 9800 GT), but in the TASKS it shows THREE "enhanced" tasks running at the same time. Is that correct??
-
What are the proper settings to make SETI CUDA run all the time, but the computer processors to run only when the machine is idle?
is that possible?
Also, I have set the # of ncpus to 3 (dual core + 9800 GT), but in the TASKS it shows THREE "enhanced" tasks running at the same time. Is that correct??
1)it's BOINC defualt behavior - CPU app running only when CPU idle from another tasks, casue app priority is only 1 point higher than idle process. All another ready to run process will force science app to free CPU (Win OS will do that actually of course).
2) If one of them shows CPU time close to zero - yes, it's OK.
-
Is there any need to update this one (it works w.o. any problems. I'm running other projects as well and the new op. AP version.
MB_6.08_mod_VLAR_kill_CUDA.exe
-
Is there any need to update this one (it works w.o. any problems. I'm running other projects as well and the new op. AP version.
MB_6.08_mod_VLAR_kill_CUDA.exe
No need to update - never break working system ;)
If you added AP 5.03 - all fine. Only AMD team app speeded up a littlein new release, all other enhancements should decrease amount of cases when GPU stays idle.
-
Just got first WUs for the Projekt. Tested V9 64bit directly, works fine for me, with Windows 7 64 bit. 182.06 is my W7 Graphics Driver version and i'm using Boinc Manager 6.4.5
But i can't say anything on the speed so far.
-
No need to update - never break working system ;)
If you added AP 5.03 - all fine. Only AMD team app speeded up a littlein new release, all other enhancements should decrease amount of cases when GPU stays idle.
The Ap is running now there is enough work. If your are interested I noticed a definite correlation between the cuda.exe and the GPU temperature and run time. The faster the cuda.exe runs (the more time it gets to run or the CPU is faster e.g. overclock) the GPU does more work in less time. So maybe optimizing the cuda.exe run time is not a bad idea afterall.
-
No need to update - never break working system ;)
If you added AP 5.03 - all fine. Only AMD team app speeded up a littlein new release, all other enhancements should decrease amount of cases when GPU stays idle.
The Ap is running now there is enough work. If your are interested I noticed a definite correlation between the cuda.exe and the GPU temperature and run time. The faster the cuda.exe runs (the more time it gets to run or the CPU is faster e.g. overclock) the GPU does more work in less time. So maybe optimizing the cuda.exe run time is not a bad idea afterall.
What is cuda.exe ??
-
No need to update - never break working system ;)
If you added AP 5.03 - all fine. Only AMD team app speeded up a littlein new release, all other enhancements should decrease amount of cases when GPU stays idle.
The Ap is running now there is enough work. If your are interested I noticed a definite correlation between the cuda.exe and the GPU temperature and run time. The faster the cuda.exe runs (the more time it gets to run or the CPU is faster e.g. overclock) the GPU does more work in less time. So maybe optimizing the cuda.exe run time is not a bad idea afterall.
What is cuda.exe ??
A process like MB_6.08_mod_VLAR_kill_CUDA.exe
-
I don't know if it was asked before: Can I use this mod to crunch on the GPU even with BOINC installed in protected (= service) mode?
-
I don't know if it was asked before: Can I use this mod to crunch on the GPU even with BOINC installed in protected (= service) mode?
If you don't use Vista yes.
-
Hi Raistmer,
I've had some feedback by PM that the v9 Cuda app locked up (In the installer package I'm making)
Is it sufficient for me to replace the DLL's with the old ones from v8a? Does this mean the v9 ones need recalling / rebuilding or just the packages updated & replaced?
Jason
-
I now believe the cuda app is still running but in Boinc Manager it says it is not running. The GPU temp is up and after a while the work unit completes and it goes on to the next one. Boinc manager may display working again but after a while it again says it's not working.
Strange.
-
Hi Raistmer,
I've had some feedback by PM that the v9 Cuda app locked up (In the installer package I'm making)
Is it sufficient for me to replace the DLL's with the old ones from v8a? Does this mean the v9 ones need recalling / rebuilding or just the packages updated & replaced?
Jason
Replacing the libs should work fine. V8 and V7 were build with CUDA 2.1 too but I took DLLs from stock app then... And now I decided to do "all correct" and took CUDA 2.1 RTL that came with used CUDA Tools... seems was wrong move.
-
I now believe the cuda app is still running but in Boinc Manager it says it is not running. The GPU temp is up and after a while the work unit completes and it goes on to the next one. Boinc manager may display working again but after a while it again says it's not working.
Strange.
I have read somewhere that BOINC works better if no one looking on it ;) Maybe it's the same case ;) ;D
-
Replacing the libs should work fine. V8 and V7 were build with CUDA 2.1 too but I took DLLs from stock app then... And now I decided to do "all correct" and took CUDA 2.1 RTL that came with used CUDA Tools... seems was wrong move.
Bummer! ... Oh well .. better remove that installer then from the testing thread :'( Are you updating the packages? Perhaps we should test them in testing area first?
-
Replacing the libs should work fine. V8 and V7 were build with CUDA 2.1 too but I took DLLs from stock app then... And now I decided to do "all correct" and took CUDA 2.1 RTL that came with used CUDA Tools... seems was wrong move.
Bummer! ... Oh well .. better remove that installer then from the testing thread :'( Are you updating the packages? Perhaps we should test them in testing area first?
It worked just fine on my host while there were work.... They disabled servers even before my host uploaded all work done :-\ :-\ :-\
Didn't see any work for CUDA more 24 hours already :-X
-
Just for info:
there is
//limit to 8 GPU's for now
comment in CUDA MB source.
That is, current CUDA MB build can't support more than 8 GPUs per host.
-
Just for info:
there is
//limit to 8 GPU's for now
comment in CUDA MB source.
That is, current CUDA MB build can't support more than 8 GPUs per host.
Given Nvidia's issues @ 40nm process....might be a while yet before Quad-GPU on dual PCB.....so luckily not much need for a while.
However, bet we see this from AMD/ATI sooner than we think. ;)
-
My four computers have been running fine the last 2 hours. Perhaps the electrons just needed to be trained, I don't know. I did download the 3 dll's directly from Seti (fanout) and will try replacing them if I have further problems. Will advise here.
[edit] Just after this post one hung up. Copied in the stock dll's and rebooted. It's running again. Will advise.
[edit again] And another cuda app hung up. Now installed stock app into all 4 machines, rebooted and running again. Will adivse.
-
No Good. :'( :'(
Still looks like the MB_6.08_mod_CUDA_V9.exe is hung up in Boinc Manager. It shows "Waiting to run, .04 cpu's, 1 CUDA". But the GPU temp is still up indicating that it is still running.
I have seen many times in the last hours that the work does complete and starts a new work unit. But it can show as described above at any time.
Don
-
is that with the older DLL's now?
-
Yes.......now using the older dll's. Also on two of my machines I have had to restart Boinc in order to get the CUDA app going again. Looks like a hard lock up can also occur.
-
No Good. :'( :'(
Still looks like the MB_6.08_mod_CUDA_V9.exe is hung up in Boinc Manager. It shows "Waiting to run, .04 cpu's, 1 CUDA". But the GPU temp is still up indicating that it is still running.
I have seen many times in the last hours that the work does complete and starts a new work unit. But it can show as described above at any time.
Don
IT STILL RUNNING. Key phrase. So what you worry about ?
-
But it's NOT running. It has hung up solid 2 times on this work unit. And I may be able to supply more.
[attachment deleted by admin]
-
But it's NOT running. It has hung up solid 2 times on this work unit. And I may be able to supply more.
I don' need result file, but would like to see stderr output for this task and logs from BOINC.
-
Here is another real work unit. Sorry I sent the wrong file earlier. I will try to get the other info.
[attachment deleted by admin]
-
Hopefully these are what you are looking for. If not tell me the actual file names you wish to see.
[attachment deleted by admin]
-
Hopefully these are what you are looking for. If not tell me the actual file names you wish to see.
Your logs show BOINC crash.
Unhandled Exception Detected...
- Unhandled Exception Record -
Reason: Access Violation (0xc0000005) at address 0x7C421FA1 read attempt to address 0x00000034
Engaging BOINC Windows Runtime Debugger...
********************
BOINC Windows Runtime Debugger Version 6.6.5
Dump Timestamp : 02/24/09 03:43:21
No info about science app there. stderr of current task located in slot subdir.
-
This from the slot running the CUDA app. That work unit is currently showing "Waiting to run, (0.04 CPU's, 1CUDA" and the progress is stuck at 0.00% . I have seen progress stuck at many different values. The GPU temp is still up indicating possible working.
[attachment deleted by admin]
-
This from the slot running the CUDA app. That work unit is currently showing "Waiting to run, (0.04 CPU's, 1CUDA" and the progress is stuck at 0.00% . I have seen progress stuck at many different values. The GPU temp is still up indicating possible working.
try to look into state.sah from that slot each 10-15 min look for value of <prog> tag.
If i increase task is making progress irragarding what BOINC manager writes.
-
Work is being finished, uploaded, etc. New work started. Confirming messages in Boinc message area. Boinc Manager continues to show work as stated earlier. "Waiting to run, 0.04 cpu's, 1 CUDA". Still using the dll's downloaded from Seti fanout earlier today. Three more error files included here.
[attachment deleted by admin]
-
Work is being finished, uploaded, etc. New work started. Confirming messages in Boinc message area. Boinc Manager continues to show work as stated earlier. "Waiting to run, 0.04 cpu's, 1 CUDA". Still using the dll's downloaded from Seti fanout earlier today. Three more error files included here.
There is no errors in these stderrs.
Can you specify what problem you have? Waiting to run is not an error too, it's just message that this task awaiting its turn.
-
Problem is that sometimes work is actually stopped or appears to be stopped. Perhaps it's not but I don't know if it is stopped or not because of the "Waiting to run, 0.04 cpu's, 1 CUDA" message in Boinc Manager. I have proven that the work is being done while showing that message in Boinc Manager. It is impossible to know the true state of the work with this message. That is the big problem. I just cannot tell the state of the work with that message in Boinc Manager even though it is being crunched.
This state cannot be overlooked. You will be flooded with complaints if this is released.
-
Problem is that sometimes work is actually stopped or appears to be stopped. Perhaps it's not but I don't know if it is stopped or not because of the "Waiting to run, 0.04 cpu's, 1 CUDA" message in Boinc Manager. I have proven that the work is being done while showing that message in Boinc Manager. It is impossible to know the true state of the work with this message. That is the big problem. I just cannot tell the state of the work with that message in Boinc Manager even though it is being crunched.
This state cannot be overlooked. You will be flooded with complaints if this is released.
It released already. V9 includes (among others) mod that rejects to stop CUDA app when BOINC wants to stop it.
This should decrease probability of having 5 CPU apps running on quad but idle GPU.
Probably you see effect of this mod.
As I already said you can see if app actually runs and making progress by looking into state.sah file.
My main concern to ensure full utilization of both CPU and GPU. What BOINC thinks or writes about situation and how it interprets situation - not my concern.
This mods actually hack BOINC and cheat it. When BOINC will be able to run both CUDA MB and opt AK_v8 simultaneously on the same host the need in these team mods will disappear.
-
I installed using "AstroPulse & CudaMB, 1+ GPUs, no Team (req SSE3)". I do NOT have the <ncpus> in the cc_config file. I am therefore running 4 AP work units on the CPU's and 1 CUDA on the video card. This is exactly the configuration I want on my quads.
To be unable to monitor the progress of the CUDA-MB work in Boinc Manager is unsatisfactory. You seem to feel that it's ok since it is crunching the data. I with respect, humbly dissagree.
-
For ones who wanna test x64 SSSE3 version of V9 combo - it attached to this post.
But keep in mind that I haven't ability to test it still. My GPU host running x86 Vista.
13 downloads at moment I write this.... And no single repost if it runs or not :-\
Come on lurkers! fess up!
Been running this 64bit package for a few days now on my i7, and everything seems to go just fine. Seeing a nice speedup on the x64 AK also.
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4496384
-
Only been able to run the new V9 app for 24 hours or so (after the upload issue have been cleared off and no completed unit put at risk). So far so good. With V8 there will be some intervention from Maik script to stop the app hang (where it got stuck at 0:00:00 CPU time) but experience with V9 seems very positive.
Thanks and great work.
CPU type GenuineIntel
Intel(R) Core(TM)2 Duo CPU E6550 @ 2.33GHz [x86 Family 6 Model 15 Stepping 11]
Number of processors 2
Coprocessors NVIDIA GeForce 9600 GSO (383MB)
Operating System Microsoft Windows XP
Professional x86 Editon, Service Pack 3, (05.01.2600.00)
-
I installed using "AstroPulse & CudaMB, 1+ GPUs, no Team (req SSE3)". I do NOT have the <ncpus> in the cc_config file. I am therefore running 4 AP work units on the CPU's and 1 CUDA on the video card. This is exactly the configuration I want on my quads.
To be unable to monitor the progress of the CUDA-MB work in Boinc Manager is unsatisfactory. You seem to feel that it's ok since it is crunching the data. I with respect, humbly dissagree.
Your config differs from recommended for these packs. So you will see all "nice" side effects of incorrect BOINC scheduling for CUDA tasks. W/o cc_config time to time you will get idle GPU and idle core - it's worse than to have overloaded core time to time IMHO.
-
Been running this 64bit package for a few days now on my i7, and everything seems to go just fine. Seeing a nice speedup on the x64 AK also.
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4496384
Fine. Will do x64 V10 then.
-
thnx to everyone involved for all the effort on the optimised apps...love them.
I just want to check something out if I may. I only crunch seti, no other projects. I have boinc 6.6.9 running on two boxes with Raistmer's V9 package SSSE3. Both boxes only run 4 threads, 3 on the cpu cores and 1 on the Nvidia graphics card. Both boxes have cc_config at 5. 1 core in box is idle. It was the same for the V8 and V7 packages even when I was running 6.6.4, 6.6.3.
Is it supposed to run this way or should there be 5 threads running..
There should be no idle cores.
Check place where you put cc_config. Look first post.
thankyou...i should have it more carefully...again thnx for all the great work...
will try V10 soon...
-
I don't know if it was asked before: Can I use this mod to crunch on the GPU even with BOINC installed in protected (= service) mode?
If you don't use Vista yes.
thank you for your reply - I'm using Vista64 and BOINC as a service install... so that explains it :-[
-
Hi, my computer is only receiving Astropulse workunits, upgraded from V8a to v9 ssse3 package, it is crunching 5 AP v5.03 units simultaneous but the GPU is at 52°C, it used to be at 72°C when crunching Seti at Home Ehanced 6.03 Wu's, is this normal not to receive SAH units only extra Large AP that takes 11 Hrs to complete and claiming 1213 Credits? maybe it would be problems from SETI servers, is anyone having the same problem?
Here is a link of my Host
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4711443
Thanks
-
Hi, my computer is only receiving Astropulse workunits, upgraded from V8a to v9 ssse3 package, it is crunching 5 AP v5.03 units simultaneous but the GPU is at 52°C, it used to be at 72°C when crunching Seti at Home Ehanced 6.03 Wu's, is this normal not to receive SAH units only extra Large AP that takes 11 Hrs to complete and claiming 1213 Credits? maybe it would be problems from SETI servers, is anyone having the same problem?
Here is a link of my Host
http://setiathome.berkeley.edu/show_host_detail.php?hostid=4711443
Thanks
Reciving tasks has no common with how app works. When you will get some work for CUDA MB try to suspend one of AP tasks to give CUDA MB chance to run (if BOINC will not do it by itself)
-
Hi - continuing from the topic from Seti NC forums:
Is it too much work for you to help compile a "Non-TEAM" package that does this: Run AP on CPU cores and leaving the MBs to the CUDA client?
I run the V9 team version (SSSE3) but due to the shorter reporting deadline of the MB WUs, it defaults to run 3 MB WUs instead of 2AP + 1MU(onCUDA). Tried suspending the MBs as you suggested but this starve the CUDA and run 3 APs instead.
Since the MB seems to be more efficient on CUDA and AP can only be run on CPU, my reasoning is that it should be the preferred configuration esp to clear off old R103 AP (Atropulse 5.00) WUs (unless when we have a situation where no AP WUs are available-then should run the TEAM config)
-
Hi - continuing from the topic from Seti NC forums:
Is it too much work for you to help compile a "Non-TEAM" package that does this: Run AP on CPU cores and leaving the MBs to the CUDA client?
I run the V9 team version (SSSE3) but due to the shorter reporting deadline of the MB WUs, it defaults to run 3 MB WUs instead of 2AP + 1MU(onCUDA). Tried suspending the MBs as you suggested but this starve the CUDA and run 3 APs instead.
Since the MB seems to be more efficient on CUDA and AP can only be run on CPU, my reasoning is that it should be the preferred configuration esp to clear off old R103 AP (Atropulse 5.00) WUs (unless when we have a situation where no AP WUs are available-then should run the TEAM config)
Use V9 multi-GPU pack.
-
I'm completrly new to all of this. Just stumbled across this page as the default BIONC app didnt seem to be using my GPU (the temp didnt go up anyway). Could anyone tell me if i've done this right.. I have an E8500 + 9800GTX, i set the number of cores in cc_config to 3 and now BIONC is running 3 tasks. My GPU temp has risen to 70c so I can tell its using it. But instead of using Astropulse its now using setiathome_enhanced_6.0.8
(http://www.bassbin.co.uk/pictures/setiathome.jpg)