Welcome to MilkyWay@home

GPU Issues Mega Thread

Message boards : News : GPU Issues Mega Thread
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · Next

AuthorMessage
captainjack

Send message
Joined: 22 Jun 13
Posts: 44
Credit: 64,258,609
RAC: 0
Message 66053 - Posted: 29 Dec 2016, 20:47:07 UTC

wb8ili,

The first thing I noticed is that you are running an older version of BOINC. You might try updating to the latest version and see if that makes a difference. The second thing I noticed is that your event log shows that the driver version of your GPU is unknown. Here is my event log with similar lines.

Wed 28 Dec 2016 10:26:18 AM CST | | Starting BOINC client version 7.6.33 for x86_64-pc-linux-gnu
Wed 28 Dec 2016 10:26:18 AM CST | | log flags: file_xfer, sched_ops, task
Wed 28 Dec 2016 10:26:18 AM CST | | Libraries: libcurl/7.50.1 OpenSSL/1.0.2g zlib/1.2.8 libidn/1.33 librtmp/2.3
Wed 28 Dec 2016 10:26:18 AM CST | | Data directory: /var/lib/boinc-client
Wed 28 Dec 2016 10:26:19 AM CST | | CUDA: NVIDIA GPU 0: GeForce GTX 970 (driver version 367.57, CUDA version 8.0, compute capability 5.2, 4036MB, 3806MB available, 3919 GFLOPS peak)
Wed 28 Dec 2016 10:26:19 AM CST | | CUDA: NVIDIA GPU 1: GeForce GTX 970 (driver version 367.57, CUDA version 8.0, compute capability 5.2, 4037MB, 3973MB available, 3919 GFLOPS peak)
Wed 28 Dec 2016 10:26:19 AM CST | | OpenCL: NVIDIA GPU 0: GeForce GTX 970 (driver version 367.57, device version OpenCL 1.2 CUDA, 4036MB, 3806MB available, 3919 GFLOPS peak)
Wed 28 Dec 2016 10:26:19 AM CST | | OpenCL: NVIDIA GPU 1: GeForce GTX 970 (driver version 367.57, device version OpenCL 1.2 CUDA, 4037MB, 3973MB available, 3919 GFLOPS peak)
Wed 28 Dec 2016 10:26:19 AM CST | | Host name: Barracuda
Wed 28 Dec 2016 10:26:19 AM CST | | Processor: 8 GenuineIntel Intel(R) Core(TM) i7-4820K CPU @ 3.70GHz [Family 6 Model 62 Stepping 4]
Wed 28 Dec 2016 10:26:19 AM CST | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm epb tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts
Wed 28 Dec 2016 10:26:19 AM CST | | OS: Linux: 4.8.0-32-generic


Something might be amiss with your GPU driver installation. What flavor of Linux are you using? And how did you install your GPU drivers. I am using Ubuntu 16.10 and used the standard Ubuntu driver installer.
ID: 66053 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66054 - Posted: 29 Dec 2016, 21:36:09 UTC - in response to Message 66053.  

The first thing I noticed is that you are running an older version of BOINC. You might try updating to the latest version and see if that makes a difference. The second thing I noticed is that your event log shows that the driver version of your GPU is unknown. Here is my event log with similar lines.

@draco_seti
I agree with the fact that the non-decteted driver is strange. Try to install the driver from your distribution repository. Can you also enter the following command in milkyway directory :
ldd * | grep -i "not found"

ID: 66054 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66055 - Posted: 30 Dec 2016, 0:42:14 UTC
Last modified: 30 Dec 2016, 0:46:40 UTC

captainjack and AF>EDLS -

EDIT: Did you see the messages that look like compile errors in the stdtxt for the invalid tasks for computer "Desktop"?

I have three LINUX computers that were working fine with Milkyway until the bundling of tasks so I assumed my issue has something to do with that. But, we will stick to my "Desktop" computer for now. If I get the "Desktop" working I will assume I can get the other two working.

I will try to answer all of the questions asked. If I missed something or didn't give a complete answer, let me know.

1) BOINC version. I think the latest version shown on the BOINC website for LINUX 64 is 7.2.42. I see you are running a later version, so I am confused about that.

2) Linux version UBUNTU 16.04.1 LTS 44.0-57-gereric

3) Driver Install - I think I just went to the SYNAPTIC Package Manager and installed NVIDIA-367. But that was a long time ago (pre-bundling) so I am not 100% sure, In any case, whatever I did worked on all computes for all of my projects until bundling of Milkyway.

4) ldd command - go to the end to see exactly what I was asked to enter. If I didn't do this correctly, let me know.

bob@Desktop:~$ cd BOINC
bob@Desktop:~/BOINC$ cd projects
bob@Desktop:~/BOINC/projects$ ls
climateprediction.net milkyway.cs.rpi.edu_milkyway
einstein.phys.uwm.edu setiathome.berkeley.edu
bob@Desktop:~/BOINC/projects$ cd ^C
bob@Desktop:~/BOINC/projects$ cd milkyway.cs.rpi.edu_milkyway
bob@Desktop:~/BOINC/projects/milkyway.cs.rpi.edu_milkyway$ ldd *
80_Rev_8_3.stars:
not a dynamic executable
80_rev_8_5.prmtrs:
not a dynamic executable
app_config.xml:
not a dynamic executable
EMD_20k_isotropic_1_54_npa2.lua:
not a dynamic executable
EMD_20k_isotropic_1_54_npa.lua:
not a dynamic executable
gnulist:
not a dynamic executable
gnulist~:
not a dynamic executable
milkyway_1.40_x86_64-pc-linux-gnu:
not a dynamic executable
milkyway_1.40_x86_64-pc-linux-gnu__opencl_nvidia_101:
linux-vdso.so.1 => (0x00007ffed7a33000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007ff88e7f5000)
libOpenCL.so.1 => /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 (0x00007ff88e5ea000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007ff88e3e1000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007ff88e1c4000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007ff88ddfb000)
/lib64/ld-linux-x86-64.so.2 (0x0000556cb2228000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007ff88dbf6000)
milkyway_nbody_1.54_x86_64-pc-linux-gnu:
linux-vdso.so.1 => (0x00007ffd38b8d000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f0b14dcd000)
libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007f0b14a4a000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f0b14741000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f0b14524000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f0b1415b000)
/lib64/ld-linux-x86-64.so.2 (0x00005601dfd45000)
libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007f0b13f44000)
milkyway_nbody_1.54_x86_64-pc-linux-gnu__mt:
linux-vdso.so.1 => (0x00007ffffe3e2000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fc4af327000)
libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fc4aefa4000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fc4aec9b000)
libgomp.so.1 => /usr/lib/x86_64-linux-gnu/libgomp.so.1 (0x00007fc4aea79000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fc4ae85c000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fc4ae492000)
/lib64/ld-linux-x86-64.so.2 (0x00005619f80ec000)
libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fc4ae27c000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fc4ae078000)
milkyway_separation_1.02_x86_64-pc-linux-gnu__opencl_nvidia:
linux-vdso.so.1 => (0x00007ffc8f5e9000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fe100f8e000)
libOpenCL.so.1 => /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 (0x00007fe100d83000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fe100b7a000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fe10095d000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fe100594000)
/lib64/ld-linux-x86-64.so.2 (0x000055da4220b000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fe10038f000)
milkyway_separation__modified_fit_1.36_x86_64-pc-linux-gnu:
linux-vdso.so.1 => (0x00007ffd75be7000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fc7c0cbb000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fc7c0ab3000)
libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fc7c0730000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fc7c0513000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fc7c014a000)
/lib64/ld-linux-x86-64.so.2 (0x000056279da52000)
libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fc7bff33000)
milkyway_separation__modified_fit_1.36_x86_64-pc-linux-gnu__opencl_nvidia_101:
linux-vdso.so.1 => (0x00007ffe22892000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f4ff6af7000)
libOpenCL.so.1 => /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 (0x00007f4ff68eb000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f4ff66e3000)
libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007f4ff6361000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f4ff6143000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f4ff5d7a000)
/lib64/ld-linux-x86-64.so.2 (0x0000561818d40000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f4ff5b76000)
libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007f4ff595f000)
parameters-14-3s-ModfitConstraints1-fast.txt:
not a dynamic executable
parameters-15-2s-ModfitConstraints1-fast.txt:
not a dynamic executable
parameters-15-3s-FixedAngles2.txt:
not a dynamic executable
parameters-15-3s-FixedAngles3.txt:
not a dynamic executable
parameters-15-3s-ModfitConstraints1-fast.txt:
not a dynamic executable
parameters-15-3s-ModfitConstraints2-fast.txt:
not a dynamic executable
parameters-15-3s-ModfitConstraints3-fast.txt:
not a dynamic executable
parameters-15-3s-ModfitConstraints4-fast.txt:
not a dynamic executable
parameters-15-3s-ModfitConstraints5-fast.txt:
not a dynamic executable
parameters-15-3s-sim-fast2.txt:
not a dynamic executable
parameters-15-3s-sim-fast-fixedangles.txt:
not a dynamic executable
parameters-15-3s-sim-fast.txt:
not a dynamic executable
parameters-16-2s-ModfitConstraints1-fast.txt:
not a dynamic executable
parameters-16-3s-ModfitConstraints1-fast.txt:
not a dynamic executable
parameters-19-3s-ModfitConstraints1-fast.txt:
not a dynamic executable
parameters-19-3s-ModfitConstraints2-fast.txt:
not a dynamic executable
parameters-19-3s-ModfitConstraints3-fast.txt:
not a dynamic executable
stars-14.txt:
not a dynamic executable
stars-15-sim-29Nov1.txt:
not a dynamic executable
stars-15.txt:
not a dynamic executable
stars-16.txt:
not a dynamic executable
stars-19.txt:
not a dynamic executable
Stripe15BPLSimulated8Dec1.txt:
not a dynamic executable
tidal_histogram_EMD_20k_v154_ft3p945_rt0p9862_r0p2_rr0p25_ml12_mlmdr0p25_10_20_15.hist:
not a dynamic executable
tidal_histogram_EMD_20k_v154_ft3p945_rt0p9862_r0p2_rr0p25_ml12_mr0p2_10_20_15.hist:
bob@Desktop:~/BOINC/projects/milkyway.cs.rpi.edu_milkyway$ ldd * | grep -i 'not found'
bob@Desktop:~/BOINC/projects/milkyway.cs.rpi.edu_milkyway$
ID: 66055 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66056 - Posted: 30 Dec 2016, 1:55:41 UTC - in response to Message 66055.  

I can't see the names of your computers. Do you have a link to a faulty work unit, please ?

About the answered questions, everything seems correct.
ID: 66056 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
captainjack

Send message
Joined: 22 Jun 13
Posts: 44
Credit: 64,258,609
RAC: 0
Message 66057 - Posted: 30 Dec 2016, 2:48:40 UTC

wb8ili,

1) The Linux version on the BOINC Berkeley website isn't kept up to date very well since the BOINC team lost their funding. If you use the Ubuntu Software installer to install BOINC, it will install 7.6.33. From what I understand, it has some improvements at recognizing GPU versions. The Ubuntu installer will install boinc in a different set of folders and run it under the user-id of "boinc".

3) IIRC, I installed the NVIDIA drivers by opening the "System Settings" (icon looks like a gear with a wrench laid over top of it), then open "Software and Updates", then click on "Additional Drivers" folder. There are options to "Use X.Org X server" or "Use NVIDIA binary driver 367.57". I chose NVIDIA binary driver.

Maybe those changes will help.

Keep us posted on your progress.
ID: 66057 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66058 - Posted: 30 Dec 2016, 8:07:09 UTC - in response to Message 66057.  


1) The Linux version on the BOINC Berkeley website isn't kept up to date very well since the BOINC team lost their funding. If you use the Ubuntu Software installer to install BOINC, it will install 7.6.33. From what I understand, it has some improvements at recognizing GPU versions. The Ubuntu installer will install boinc in a different set of folders and run it under the user-id of

I don't know on ubuntu but on fedora or centos, new versions are sometimes a regression : on centos I reverted to 7.2.42 due to partial display problems ; on fedora it's not detecting idle state
ID: 66058 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
draco_seti

Send message
Joined: 23 Jan 14
Posts: 8
Credit: 36,283
RAC: 0
Message 66059 - Posted: 30 Dec 2016, 8:28:03 UTC

bash-4.4$ ./boinc
./boinc: /lib64/libssl.so.1.0.0: no version information available (required by ./boinc)
./boinc: /usr/lib64/libcurl.so.4: no version information available (required by ./boinc)
./boinc: /lib64/libcrypto.so.1.0.0: no version information available (required by ./boinc)
30-Dec-2016 10:25:00 [---] cc_config.xml not found - using defaults
30-Dec-2016 10:25:00 [---] Starting BOINC client version 7.2.42 for x86_64-pc-linux-gnu
30-Dec-2016 10:25:00 [---] log flags: file_xfer, sched_ops, task
30-Dec-2016 10:25:00 [---] Libraries: libcurl/7.51.0 OpenSSL/1.0.2j zlib/1.2.8 libssh2/1.7.0
30-Dec-2016 10:25:00 [---] Data directory: /ADISKS/BOINC-drago_seti-acctmgr
boinc: /lib64/libssl.so.1.0.0: no version information available (required by boinc)
boinc: /usr/lib64/libcurl.so.4: no version information available (required by boinc)
boinc: /lib64/libcrypto.so.1.0.0: no version information available (required by boinc)
30-Dec-2016 10:25:00 [---] CUDA: NVIDIA GPU 0: GeForce GTX 750 Ti (driver version unknown, CUDA version 8.0, compute capability 5.0, 2000MB, 1793MB available, 2082 GFLOPS peak)
30-Dec-2016 10:25:00 [---] OpenCL: NVIDIA GPU 0: GeForce GTX 750 Ti (driver version 375.26, device version OpenCL 1.2 CUDA, 2000MB, 1793MB available, 2082 GFLOPS peak)
30-Dec-2016 10:25:00 [---] Host name: draco
30-Dec-2016 10:25:00 [---] Processor: 8 GenuineIntel Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz [Family 6 Model 60 Stepping 3]
30-Dec-2016 10:25:00 [---] Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm ida arat pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm xsaveopt
30-Dec-2016 10:25:00 [---] OS: Linux: 4.4.38
30-Dec-2016 10:25:00 [---] Memory: 15.59 GB physical, 18.57 GB virtual
30-Dec-2016 10:25:00 [---] Disk: 201.66 GB total, 176.62 GB free
30-Dec-2016 10:25:00 [---] Local time is UTC +2 hours
30-Dec-2016 10:25:00 [climateprediction.net] URL http://climateprediction.net/; Computer ID 1386000; resource share 20
30-Dec-2016 10:25:00 [WUProp@Home] URL http://wuprop.boinc-af.org/; Computer ID 66461; resource share 20
30-Dec-2016 10:25:00 [Poem@Home] URL http://boinc.fzk.de/poem/; Computer ID 229220; resource share 60
30-Dec-2016 10:25:00 [Poem@Home] Project has ended - OK to detach
30-Dec-2016 10:25:00 [rosetta@home] URL http://boinc.bakerlab.org/rosetta/; Computer ID 1726969; resource share 60
30-Dec-2016 10:25:00 [Milkyway@Home] URL http://milkyway.cs.rpi.edu/milkyway/; Computer ID 564505; resource share 80
30-Dec-2016 10:25:00 [SETI@home] URL http://setiathome.berkeley.edu/; Computer ID 7225057; resource share 100
30-Dec-2016 10:25:00 [---] General prefs: from http://bam.boincstats.com/ (last modified 28-Feb-2014 08:40:36)
30-Dec-2016 10:25:00 [---] Host location: none
30-Dec-2016 10:25:00 [---] General prefs: using your defaults
30-Dec-2016 10:25:00 [---] Reading preferences override file
30-Dec-2016 10:25:00 [---] Preferences:
30-Dec-2016 10:25:00 [---] max memory usage when active: 6385.12MB
30-Dec-2016 10:25:00 [---] max memory usage when idle: 8779.55MB
30-Dec-2016 10:25:00 [---] max disk usage: 15.00GB
30-Dec-2016 10:25:00 [---] max CPUs used: 4
30-Dec-2016 10:25:00 [---] suspend work if non-BOINC CPU load exceeds 50%
30-Dec-2016 10:25:00 [---] (to change preferences, visit a project web site or select Preferences in the Manager)
30-Dec-2016 10:25:00 [---] Not using a proxy
30-Dec-2016 10:25:00 Initialization completed
30-Dec-2016 10:25:00 [rosetta@home] Sending scheduler request: To report completed tasks.
30-Dec-2016 10:25:00 [rosetta@home] Reporting 2 completed tasks
30-Dec-2016 10:25:00 [rosetta@home] Not requesting tasks: don't need
30-Dec-2016 10:25:03 [rosetta@home] Scheduler request completed
30-Dec-2016 10:25:08 [climateprediction.net] Sending scheduler request: To fetch work.
30-Dec-2016 10:25:08 [climateprediction.net] Requesting new tasks for CPU
30-Dec-2016 10:25:14 [climateprediction.net] Scheduler request completed: got 0 new tasks
30-Dec-2016 10:25:14 [climateprediction.net] Project has no tasks available
30-Dec-2016 10:25:19 [Poem@Home] Sending scheduler request: To fetch work.
30-Dec-2016 10:25:19 [Poem@Home] Requesting new tasks for CPU and NVIDIA
30-Dec-2016 10:25:22 [Poem@Home] Scheduler request completed: got 0 new tasks
30-Dec-2016 10:25:22 [Poem@Home] Project has no tasks available

here is mine output from boinc start....

as all can see - it is the latest boinc version, and latest nvidia driver.
ID: 66059 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
draco_seti

Send message
Joined: 23 Jan 14
Posts: 8
Credit: 36,283
RAC: 0
Message 66060 - Posted: 30 Dec 2016, 8:33:45 UTC - in response to Message 66054.  

ldd *
EMD_v162.lua:
not a dynamic executable
hist_v162_ft3p945_rt0p98_rl0p2_rr0p2_ml12_mrp2__6_20_16.hist:
not a dynamic executable
milkyway_1.40_x86_64-pc-linux-gnu:
not a dynamic executable
milkyway_1.40_x86_64-pc-linux-gnu__opencl_nvidia_101:
linux-vdso.so.1 (0x00007ffd1a5b2000)
libm.so.6 => /lib64/libm.so.6 (0x00007f3a13a1f000)
libOpenCL.so.1 => /usr/lib64/libOpenCL.so.1 (0x00007f3a13819000)
librt.so.1 => /lib64/librt.so.1 (0x00007f3a13611000)
libpthread.so.0 => /lib64/libpthread.so.0 (0x00007f3a133f3000)
libc.so.6 => /lib64/libc.so.6 (0x00007f3a1302d000)
/lib64/ld-linux-x86-64.so.2 (0x00005633cf124000)
libdl.so.2 => /lib64/libdl.so.2 (0x00007f3a12e27000)
milkyway_nbody_1.62_x86_64-pc-linux-gnu__mt:
not a dynamic executable
parameters-19-3s-ModfitConstraints3-fast.txt:
not a dynamic executable
stars-19.txt:
not a dynamic executable
ID: 66060 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66061 - Posted: 30 Dec 2016, 12:57:09 UTC

captianjack and [AF>EDLS]GuL -


[AF>EDLS]GuL -

If you click on my name (wb8ili) on the left of this message -
then under the Badges row there is a row Computers - click on "here" -
then you should see a list of computers - column 2 is the names -
scroll to "Desktop" and then click on "Tasks" in column 1 -
then go to Invalid.

Here is a link - Sorry I haven't figured out how to make it a real link

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=1924604416


captianjack -

In Other Software, Additional Drivers, 367.57 is already checked. So nothing happens there.

I will install the latest BOINC. I see it in the Synaptic Package Manager.[/url]
ID: 66061 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66062 - Posted: 30 Dec 2016, 15:31:16 UTC

I have reverted back to BOINC 7.2.42. I will try 7.6.33 sometime in the future when I have more time to figure out where everything is stored and I complete all of the tasks I have already downloaded. It looks like you basically have to "start over" when upgrading from the Berkeley installer to the UBUNTU installer (add the projects back in, etc.)


Here is the first part of a stdtxt file from one of my invalid tasks from yesterday. When it gets to "CL_BUILD_PROGRAM_FAILURE", it just doesn't look good to me.



<core_client_version>7.2.42</core_client_version>
<![CDATA[
<stderr_txt>
<search_application> milkyway_separation 1.40 Linux x86_64 double OpenCL </search_application>
Reading preferences ended prematurely
BOINC GPU type suggests using OpenCL vendor 'NVIDIA Corporation'
Setting process priority to 0 (13): Permission denied
Error loading Lua script 'astronomy_parameters.txt': [string "number_parameters: 4..."]:1: '<name>' expected near '4'
Switching to Parameter File 'astronomy_parameters.txt'
<number_WUs> 5 </number_WUs>
<number_params_per_WU> 20 </number_params_per_WU>
Using SSE3 path
Found 1 platform
Platform 0 information:
Name: NVIDIA CUDA
Version: OpenCL 1.2 CUDA 8.0.46
Vendor: NVIDIA Corporation
Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts
Profile: FULL_PROFILE
Using device 0 on platform 0
Found 1 CL device
Device 'GeForce GTX 650 Ti BOOST' (NVIDIA Corporation:0x10de) (CL_DEVICE_TYPE_GPU)
Board:
Driver version: 367.57
Version: OpenCL 1.2 CUDA
Compute capability: 3.0
Max compute units: 4
Clock frequency: 1032 Mhz
Global mem size: 2090401792
Local mem size: 49152
Max const buf size: 65536
Double extension: cl_khr_fp64
Build log:
--------------------------------------------------------------------------------
<kernel>:176:72: warning: unknown attribute 'max_constant_size' ignored
__constant real* _ap_consts __attribute__((max_constant_size(18 * sizeof(real)))),
^
<kernel>:178:62: warning: unknown attribute 'max_constant_size' ignored
__constant SC* sc __attribute__((max_constant_size(NSTREAM * sizeof(SC)))),
^
<kernel>:179:67: warning: unknown attribute 'max_constant_size' ignored
__constant real* sg_dx __attribute__((max_constant_size(256 * sizeof(real)))),
^
<kernel>:227:26: error: use of undeclared identifier 'inf'
tmp = mad((real) Q_INV_SQR, z * z, tmp); /* (q_invsqr * z^2) + (x^2 + y^2) */
^
<built-in>:33:19: note: expanded from here
#define Q_INV_SQR inf
^

--------------------------------------------------------------------------------
clBuildProgram: Build failure (-11): CL_BUILD_PROGRAM_FAILURE
Error building program from source (-11): CL_BUILD_PROGRAM_FAILURE
Error creating integral program from source
Failed to calculate likelihood
Using SSE3 path
Found 1 platform
Platform 0 information:
Name: NVIDIA CUDA
Version: OpenCL 1.2 CUDA 8.0.46
Vendor: NVIDIA Corporation
Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts
Profile: FULL_PROFILE
Using device 0 on platform 0
Found 1 CL device
Device 'GeForce GTX 650 Ti BOOST' (NVIDIA Corporation:0x10de) (CL_DEVICE_TYPE_GPU)
Board:
Driver version: 367.57
Version: OpenCL 1.2 CUDA
Compute capability: 3.0
Max compute units: 4
Clock frequency: 1032 Mhz
Global mem size: 2090401792
Local mem size: 49152
Max const buf size: 65536
Double extension: cl_khr_fp64
Build log:
--------------------------------------------------------------------------------
ID: 66062 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66063 - Posted: 30 Dec 2016, 16:10:20 UTC - in response to Message 66061.  


If you click on my name (wb8ili) on the left of this message -
then under the Badges row there is a row Computers - click on "here" -
then you should see a list of computers - column 2 is the names -
scroll to "Desktop" and then click on "Tasks" in column 1 -
then go to Invalid.


That's the way I checked but I can only see your hostids but not their names.

You're right, it seems to be a computation error. I have no more ideas, sorry.
ID: 66063 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66064 - Posted: 30 Dec 2016, 16:29:14 UTC

[AF>EDLS]GuL

I never noticed that before. If you click on your own computers the names are shown. But, the names are not shown for anyone else.

The ID is 636700 but it doesn't matter now that I posted the stdtxt.
ID: 66064 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
mmonnin

Send message
Joined: 2 Oct 16
Posts: 162
Credit: 1,004,380,968
RAC: 17,412
Message 66076 - Posted: 3 Jan 2017, 15:47:22 UTC

My GTX 570 is working in Ubuntu, 2x at once.
http://milkyway.cs.rpi.edu/milkyway/results.php?hostid=710005
ID: 66076 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66077 - Posted: 3 Jan 2017, 16:57:31 UTC

Not an expert by any means - It looks like, for whatever reason, I have a problem compiling a CL program (whatever that is).

Maybe some missing library or out-of-date library.

As I stated in a previous post, this "issue" is not limited just one of my computers.
ID: 66077 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66078 - Posted: 3 Jan 2017, 17:06:27 UTC

As I stated before, I thought it is a UBUNTU (64bit?) and NVIDIA card issue. But that was proven incorrect.

Now I will propose a another factor -

If I looked correctly, both captianjack and [AF>EDLS]GuL have all Intel CPU's. mmonninn has the computers hidden. So, I can't tell.

The 3 computers that I can't run Milkyway GPU on all have AMD processors.

Could the manufacturer of the CPU make a difference whether a CL program compiles or not?
ID: 66078 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66082 - Posted: 3 Jan 2017, 22:02:38 UTC - in response to Message 66078.  

Could the manufacturer of the CPU make a difference whether a CL program compiles or not?


I am not sure but it may be a possibility. I have read somewhere, maybe on seti, that the difficulty of opencl is that it can work everywhere, but it is not automatic.

In particular, you have no amd opencl line when boinc is starting. Try to install opencl amd sdk http://developer.amd.com/tools-and-sdks/opencl-zone/amd-accelerated-parallel-processing-app-sdk/.

Some further interesting reading: https://askubuntu.com/questions/821341/how-to-enable-cpu-platform-for-opencl-applications, https://wiki.tiker.net/OpenCLHowTo
ID: 66082 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66083 - Posted: 4 Jan 2017, 16:36:09 UTC

[AF>EDLS]GuL

Thanks for the tips.

The first link, in the fist line, clearly indicates that the article applies to AMD Processing Cores. Since I have a NVIDIA, I don't think that applies to me.

The second link looked more promising. However, I have all of the "ICD" and "OPENCL" installed (at least I think I do).

I wonder if there are any "debug" switches that might give more verbose output indicating why my CL programs don't compile.

In the meantime, I am racking up lots of credit on Einstein.
ID: 66083 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66084 - Posted: 4 Jan 2017, 18:10:44 UTC - in response to Message 66083.  


Thanks for the tips.

The first link, in the fist line, clearly indicates that the article applies to AMD Processing Cores. Since I have a NVIDIA, I don't think that applies to me.

You're welcome.

The first link applies to AMD CPUs, as you have. Don't forget that part of the job is done on CPU. If opencl is not available there, it may fail.

Cheers
ID: 66084 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
wb8ili

Send message
Joined: 18 Jul 10
Posts: 76
Credit: 635,998,708
RAC: 0
Message 66089 - Posted: 6 Jan 2017, 19:22:54 UTC

captianjack and [AF>EDLS]GuL -

For captianjack in particular -

I finally got around to installing BOINC from the UBUNTU SYNAPTIC. YOU WERE CORRECT! That fixed my "invalid work unit" problem on one computer. And the "unknown driver" message disappeared. Two more computers to go as soon as the work runs out on those.

When I installed BOINC there must have been 20 additional libraries installed. I bet one of those was the reason the CL program didn't compile.

Thanks for the help.
ID: 66089 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile [AF>EDLS]GuL
Avatar

Send message
Joined: 5 Jun 08
Posts: 21
Credit: 245,803,013
RAC: 0
Message 66090 - Posted: 7 Jan 2017, 7:42:39 UTC - in response to Message 66089.  

Great ! Happy crunching and happy new year !
ID: 66090 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · Next

Message boards : News : GPU Issues Mega Thread

©2024 Astroinformatics Group