SETI@Home not using my GPU

Questions and Answers : Windows : SETI@Home not using my GPU
Message board moderation

To post messages, you must log in.

1 · 2 · Next

AuthorMessage
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826704 - Posted: 25 Oct 2016, 23:11:12 UTC

10/25/2016 5:59:07 PM | | Starting BOINC client version 7.6.22 for windows_x86_64
10/25/2016 5:59:07 PM | | log flags: file_xfer, sched_ops, task
10/25/2016 5:59:07 PM | | Libraries: libcurl/7.45.0 OpenSSL/1.0.2d zlib/1.2.8
10/25/2016 5:59:07 PM | | Data directory: C:\ProgramData\BOINC
10/25/2016 5:59:07 PM | | Running under account hardliner
10/25/2016 5:59:07 PM | | CUDA: NVIDIA GPU 0: GeForce GT 610 (driver version 372.90, CUDA version 8.0, compute capability 2.1, 2048MB, 1956MB available, 156 GFLOPS peak)
10/25/2016 5:59:07 PM | | OpenCL: NVIDIA GPU 0: GeForce GT 610 (driver version 372.90, device version OpenCL 1.1 CUDA, 2048MB, 1956MB available, 156 GFLOPS peak)
10/25/2016 5:59:07 PM | | Host name: hardliner-PC
10/25/2016 5:59:07 PM | | Processor: 4 GenuineIntel Intel(R) Core(TM) i3-4160 CPU @ 3.60GHz [Family 6 Model 60 Stepping 3]
10/25/2016 5:59:07 PM | | 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 htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 vmx tm2 pbe fsgsbase bmi1 smep bmi2
10/25/2016 5:59:07 PM | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
10/25/2016 5:59:07 PM | | Memory: 15.95 GB physical, 31.90 GB virtual
10/25/2016 5:59:07 PM | | Disk: 111.69 GB total, 44.41 GB free
10/25/2016 5:59:07 PM | | Local time is UTC -5 hours
10/25/2016 5:59:07 PM | | VirtualBox version: 5.0.12
10/25/2016 5:59:07 PM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 8028538; resource share 100
10/25/2016 5:59:07 PM | | No general preferences found - using defaults
10/25/2016 5:59:07 PM | | Reading preferences override file
10/25/2016 5:59:07 PM | | Preferences:
10/25/2016 5:59:07 PM | | max memory usage when active: 8166.43MB
10/25/2016 5:59:07 PM | | max memory usage when idle: 14699.57MB
10/25/2016 5:59:07 PM | | max disk usage: 44.46GB
10/25/2016 5:59:07 PM | | (to change preferences, visit a project web site or select Preferences in the Manager)
10/25/2016 5:59:07 PM | SETI@home | Task 17mr10ab.31428.67.9.36.208_0 is 62.89 days overdue; you may not get credit for it. Consider aborting it.
10/25/2016 6:03:23 PM | | No general preferences found - using defaults
10/25/2016 6:03:23 PM | | Reading preferences override file
10/25/2016 6:03:23 PM | | Preferences:
10/25/2016 6:03:23 PM | | max memory usage when active: 8166.43MB
10/25/2016 6:03:23 PM | | max memory usage when idle: 14699.57MB
10/25/2016 6:03:23 PM | | max disk usage: 44.46GB
10/25/2016 6:03:23 PM | | Number of usable CPUs has changed from 4 to 3.
10/25/2016 6:03:23 PM | | max CPUs used: 3
10/25/2016 6:03:23 PM | | (to change preferences, visit a project web site or select Preferences in the Manager)
ID: 1826704 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1826716 - Posted: 25 Oct 2016, 23:37:21 UTC - in response to Message 1826704.  

Your account
Preferences for this project
Make sure "Use NVIDIA GPU" is checked, and if it isn't, edit the preferences (on the correct location, if you use more than one), then add the check mark at Use NVIDA GPU, before saving those preferences.
Last have BOINC contact the project (BOINC Manager, Advanced view, Projects tab, Select Seti, click Update).
ID: 1826716 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826726 - Posted: 26 Oct 2016, 0:48:34 UTC - in response to Message 1826716.  

It was already checked.
ID: 1826726 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15691
Credit: 84,761,841
RAC: 28
United States
Message 1826736 - Posted: 26 Oct 2016, 2:38:33 UTC - in response to Message 1826726.  

Is it that you don't have any GPU work? In BOINC Manager, under the Task tab, in the Application column, do you see any applications indicating OpenCL?
ID: 1826736 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826739 - Posted: 26 Oct 2016, 3:01:18 UTC - in response to Message 1826736.  

I have one that says that it's progress is 0.001%, status says Running (0.0169 CPUs + 1 NVIDIA GPU).

The other 2 say Ready to start (0.0169 CPUs + 1 NVIDIA GPU)

So, none indicate OpenCL.
ID: 1826739 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15691
Credit: 84,761,841
RAC: 28
United States
Message 1826768 - Posted: 26 Oct 2016, 9:54:16 UTC - in response to Message 1826739.  

Ah, my bad. The NVidia read differently. The first line you point out indicates you are indeed using the GPU.
ID: 1826768 · Report as offensive
Profile BilBg
Volunteer tester
Avatar

Send message
Joined: 27 May 07
Posts: 3720
Credit: 9,385,827
RAC: 0
Bulgaria
Message 1826773 - Posted: 26 Oct 2016, 11:28:42 UTC - in response to Message 1826704.  

You have 2 tasks "SETI@home v8 v8.12 (opencl_nvidia_SoG)" - "Sent 9 Sep 2016" but still not computed:
http://setiathome.berkeley.edu/results.php?hostid=8028538&offset=20&show_names=0&state=1&appid=

Also "Application details" for "SETI@home v8 8.12 windows_intelx86 (opencl_nvidia_SoG)" show:
Number of tasks completed 0
Consecutive valid tasks 0
Average turnaround time 53.95 days <-- the other apps on your computer show here much less
http://setiathome.berkeley.edu/host_app_versions.php?hostid=8028538

Was this computer OFF for a long time?

Or do the GPU tasks/apps stall?
(e.g. if you pause/resume tasks or restart BOINC those tasks start from 0% - which means they did not really compute (but BOINC shows fake "Progress"))
On this GPU (GeForce GT 610) the tasks may take "long" (2-10 h (?)) but not days.
If the GPU driver crashed - Windows need restart (try that first if the computer was used for a long time without restart)

When the GPU tasks run do you see any GPU load?
 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 
ID: 1826773 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826789 - Posted: 26 Oct 2016, 13:35:43 UTC - in response to Message 1826773.  

This computer stays on almost all the time. Sometimes I shut it off for maybe a day or two. I guess it depends on what you mean for a long time.

Yes, I would say the GPU tasks stall. Since I installed BOINC and selected SETI@Home, I've seen the program recognize I have an NVIDIA GPU but it has never used it.

I've rebooted the computer multiple times, i.e. after Windows Updates, after installing and uninstalling programs, etc.

I have never seen any GPU tasks run.
ID: 1826789 · Report as offensive
rob smith Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer moderator
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 22247
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1826809 - Posted: 26 Oct 2016, 16:35:53 UTC

As you state that you have the NVIDIA GPU enabled, and appear to have a couple of tasks lined up for it we have to do a little more thinking and digging :-(

First, you state that you are only re-booting the machine when Windows does an update. Do you allow Windows to update hardware drivers, in particular do you let it update the graphics drivers - doing so is a known source of issues when trying to use the GPU for computational purposes as Micro Soft have a (very bad) habit of distributing drivers which do not have the correct bits required for computational applications - I see that the driver you have installed does not have CUDA support, only OpenCL support, this implies that there are some important bits of the driver missing. Turn OFF the Windows update of drivers, then get a copy of the driver for your card and operating system from the Nvidia web site (the download is over 300MB), run the install program, using the "advanced" option to allow a CLEAN installation, make sure you select both CUDA and OpenCL support if the option is available, by default the Nvidia supplied drivers. Doing a clean installation will result in the old driver being totally removed and a new one being installed, during which time the screen may go black for some time, and you may have to reboot.
Second, have a look on the BOINC manager to see what the "Suspend GPU computing when computer is in use" is set to, and the associated use time value is. (Advanced view, options, computing preferences)

Good hunting
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1826809 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826850 - Posted: 26 Oct 2016, 22:53:42 UTC - in response to Message 1826809.  

I do not let Windows update the drivers. After doing a fresh install of the OS, I only install the drivers. I do not install the software that comes on the CD with the drivers. I do this because in the past, the software was blocking Windows from updating itself. I learned elsewhere to download 2 updates that will allow Windows to automatically download software updates.

After typing that, I went and double checked my Windows Update history and it does not show any downloads and/or installation of anything related to NVIDIA.

I do not have a check next to "Suspend GPU computing when computer is in use."

In a couple of hours, I will reply again when I reinstall the drivers for my card.
ID: 1826850 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826860 - Posted: 27 Oct 2016, 0:07:23 UTC - in response to Message 1826809.  
Last modified: 27 Oct 2016, 0:10:17 UTC

10/26/2016 7:03:20 PM | | Starting BOINC client version 7.6.22 for windows_x86_64
10/26/2016 7:03:20 PM | | log flags: file_xfer, sched_ops, task
10/26/2016 7:03:20 PM | | Libraries: libcurl/7.45.0 OpenSSL/1.0.2d zlib/1.2.8
10/26/2016 7:03:20 PM | | Data directory: C:\ProgramData\BOINC
10/26/2016 7:03:20 PM | | Running under account hardliner
10/26/2016 7:03:20 PM | | CUDA: NVIDIA GPU 0: GeForce GT 610 (driver version 375.63, CUDA version 8.0, compute capability 2.1, 2048MB, 1943MB available, 156 GFLOPS peak)
10/26/2016 7:03:20 PM | | OpenCL: NVIDIA GPU 0: GeForce GT 610 (driver version 375.63, device version OpenCL 1.1 CUDA, 2048MB, 1943MB available, 156 GFLOPS peak)
10/26/2016 7:03:20 PM | | Host name: hardliner-PC
10/26/2016 7:03:20 PM | | Processor: 4 GenuineIntel Intel(R) Core(TM) i3-4160 CPU @ 3.60GHz [Family 6 Model 60 Stepping 3]
10/26/2016 7:03:20 PM | | 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 htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 vmx tm2 pbe fsgsbase bmi1 smep bmi2
10/26/2016 7:03:20 PM | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
10/26/2016 7:03:20 PM | | Memory: 15.95 GB physical, 31.90 GB virtual
10/26/2016 7:03:20 PM | | Disk: 111.69 GB total, 40.94 GB free
10/26/2016 7:03:20 PM | | Local time is UTC -5 hours
10/26/2016 7:03:20 PM | | VirtualBox version: 5.0.12
10/26/2016 7:03:20 PM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 8028538; resource share 100
10/26/2016 7:03:20 PM | | No general preferences found - using defaults
10/26/2016 7:03:20 PM | | Reading preferences override file
10/26/2016 7:03:20 PM | | Preferences:
10/26/2016 7:03:20 PM | | max memory usage when active: 8166.43MB
10/26/2016 7:03:20 PM | | max memory usage when idle: 14699.57MB
10/26/2016 7:03:20 PM | | max disk usage: 40.99GB
10/26/2016 7:03:20 PM | | (to change preferences, visit a project web site or select Preferences in the Manager)
10/26/2016 7:03:20 PM | SETI@home | Task 17mr10ab.31428.67.9.36.208_0 is 63.93 days overdue; you may not get credit for it. Consider aborting it.
10/26/2016 7:03:41 PM | SETI@home | task 17mr10ab.31428.67.9.36.208_0 aborted by user
10/26/2016 7:03:41 PM | SETI@home | Starting task 12au16aa.10035.12337.8.35.104_2

This is the event log after doing what you suggested. As you can also see, I ended up aborted the task that was way overdue then BOINC Manager downloaded a new task.

CUDA and OpenCL support is not a option to select during install.
ID: 1826860 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15691
Credit: 84,761,841
RAC: 28
United States
Message 1826869 - Posted: 27 Oct 2016, 1:12:25 UTC - in response to Message 1826850.  
Last modified: 27 Oct 2016, 1:13:54 UTC

I do not let Windows update the drivers. After doing a fresh install of the OS, I only install the drivers. I do not install the software that comes on the CD with the drivers. I do this because in the past, the software was blocking Windows from updating itself. I learned elsewhere to download 2 updates that will allow Windows to automatically download software updates.


This may be part of the problem. In order to use the GPU for crunching, the vendor-specific libraries must be installed. So while BOINC is able to see the card and identify it correctly, the GPU applications cannot link to the missing libraries so it can be used for crunching. I'm assuming, of course, that you're literally only loading the drivers and not the full driver package from NVidia.

You don't need to install the drivers from the CD (in fact I would bet that those drivers don't have the CUDA libraries either because the drivers on the CD are from the manufacturer). Simply download the correct drivers from http://www.geforce.com/drivers and install them.
ID: 1826869 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826887 - Posted: 27 Oct 2016, 3:43:34 UTC - in response to Message 1826869.  

I did that earlier. That's what rob smith suggested I do.
ID: 1826887 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1826919 - Posted: 27 Oct 2016, 10:53:12 UTC
Last modified: 27 Oct 2016, 10:55:52 UTC

Could you turn on some of the debug flags for me?
BOINC Manager->View->Advanced view->Options->Event Log options...->check coproc_debug, cpu_sched_debug and sched_op_debug->OK

At this point exit BOINC and restart it:
BOINC Manager->File->Exit->Acknowledge if you have Exit dialog on.
Start->All Programs->BOINC->BOINC Manager.

Next tell BOINC to contact the server:
BOINC Manager->Projects tab->select Seti@Home->click Update.

Wait about a minute, then open the event log, BOINC Manager->Tools->Event Log (or press CTRL+SHIFT+E).
Now copy and post all the lines (Copy All).
ID: 1826919 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826954 - Posted: 27 Oct 2016, 14:41:16 UTC - in response to Message 1826919.  

10/27/2016 9:38:59 AM | | Starting BOINC client version 7.6.22 for windows_x86_64
10/27/2016 9:38:59 AM | | log flags: file_xfer, sched_ops, task, coproc_debug, cpu_sched_debug, sched_op_debug
10/27/2016 9:38:59 AM | | Libraries: libcurl/7.45.0 OpenSSL/1.0.2d zlib/1.2.8
10/27/2016 9:38:59 AM | | Data directory: C:\ProgramData\BOINC
10/27/2016 9:38:59 AM | | Running under account hardliner
10/27/2016 9:38:59 AM | | [coproc] launching child process at C:\Program Files\BOINC\boinc.exe
10/27/2016 9:38:59 AM | | [coproc] relative to directory C:\ProgramData\BOINC
10/27/2016 9:38:59 AM | | [coproc] with data directory "C:\ProgramData\BOINC"
10/27/2016 9:38:59 AM | | CUDA: NVIDIA GPU 0: GeForce GT 610 (driver version 375.63, CUDA version 8.0, compute capability 2.1, 2048MB, 1968MB available, 156 GFLOPS peak)
10/27/2016 9:38:59 AM | | OpenCL: NVIDIA GPU 0: GeForce GT 610 (driver version 375.63, device version OpenCL 1.1 CUDA, 2048MB, 1968MB available, 156 GFLOPS peak)
10/27/2016 9:38:59 AM | | [coproc] NVIDIA library reports 1 GPU
10/27/2016 9:38:59 AM | | [coproc] No ATI library found.
10/27/2016 9:38:59 AM | | Host name: hardliner-PC
10/27/2016 9:38:59 AM | | Processor: 4 GenuineIntel Intel(R) Core(TM) i3-4160 CPU @ 3.60GHz [Family 6 Model 60 Stepping 3]
10/27/2016 9:38:59 AM | | 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 htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 vmx tm2 pbe fsgsbase bmi1 smep bmi2
10/27/2016 9:38:59 AM | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
10/27/2016 9:38:59 AM | | Memory: 15.95 GB physical, 31.90 GB virtual
10/27/2016 9:38:59 AM | | Disk: 111.69 GB total, 47.63 GB free
10/27/2016 9:38:59 AM | | Local time is UTC -5 hours
10/27/2016 9:38:59 AM | | VirtualBox version: 5.0.12
10/27/2016 9:38:59 AM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 8028538; resource share 100
10/27/2016 9:38:59 AM | | No general preferences found - using defaults
10/27/2016 9:38:59 AM | | Reading preferences override file
10/27/2016 9:38:59 AM | | Preferences:
10/27/2016 9:38:59 AM | | max memory usage when active: 8166.43MB
10/27/2016 9:38:59 AM | | max memory usage when idle: 14699.57MB
10/27/2016 9:38:59 AM | | max disk usage: 47.70GB
10/27/2016 9:38:59 AM | | (to change preferences, visit a project web site or select Preferences in the Manager)
10/27/2016 9:38:59 AM | | [cpu_sched_debug] Request CPU reschedule: Prefs update
10/27/2016 9:38:59 AM | | [cpu_sched_debug] Request CPU reschedule: Startup
10/27/2016 9:38:59 AM | | [cpu_sched_debug] Request CPU reschedule: Not idle
10/27/2016 9:38:59 AM | | [cpu_sched_debug] Request CPU reschedule: periodic CPU scheduling
10/27/2016 9:38:59 AM | | [cpu_sched_debug] schedule_cpus(): start
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] reserving 1.000000 of coproc NVIDIA
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] add to run list: 12au16aa.10035.12337.8.35.104_2 (NVIDIA GPU, FIFO) (prio -1.000000)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] add to run list: 11fe16ab.7768.284456.9.36.55_0 (CPU, FIFO) (prio -1.027329)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] add to run list: 11jl16ab.7068.379287.8.35.146.vlar_0 (CPU, FIFO) (prio -1.030929)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] add to run list: 11jl16ab.7068.379287.8.35.247.vlar_0 (CPU, FIFO) (prio -1.034528)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] add to run list: 13fe16ab.23083.885.8.35.189.vlar_1 (CPU, FIFO) (prio -1.038128)
10/27/2016 9:38:59 AM | | [cpu_sched_debug] enforce_run_list(): start
10/27/2016 9:38:59 AM | | [cpu_sched_debug] preliminary job list:
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 0: 12au16aa.10035.12337.8.35.104_2 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 1: 11fe16ab.7768.284456.9.36.55_0 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 2: 11jl16ab.7068.379287.8.35.146.vlar_0 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 3: 11jl16ab.7068.379287.8.35.247.vlar_0 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 4: 13fe16ab.23083.885.8.35.189.vlar_1 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | | [cpu_sched_debug] final job list:
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 0: 12au16aa.10035.12337.8.35.104_2 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 1: 11fe16ab.7768.284456.9.36.55_0 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 2: 11jl16ab.7068.379287.8.35.146.vlar_0 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 3: 11jl16ab.7068.379287.8.35.247.vlar_0 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] 4: 13fe16ab.23083.885.8.35.189.vlar_1 (MD: no; UTS: no)
10/27/2016 9:38:59 AM | SETI@home | [coproc] Assigning NVIDIA instance 0 to 12au16aa.10035.12337.8.35.104_2
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] scheduling 12au16aa.10035.12337.8.35.104_2
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] scheduling 11fe16ab.7768.284456.9.36.55_0
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] scheduling 11jl16ab.7068.379287.8.35.146.vlar_0
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] scheduling 11jl16ab.7068.379287.8.35.247.vlar_0
10/27/2016 9:38:59 AM | SETI@home | [cpu_sched_debug] scheduling 13fe16ab.23083.885.8.35.189.vlar_1
10/27/2016 9:39:00 AM | | [cpu_sched_debug] enforce_run_list: end
10/27/2016 9:39:14 AM | SETI@home | update requested by user
10/27/2016 9:39:15 AM | SETI@home | sched RPC pending: Requested by user
10/27/2016 9:39:15 AM | SETI@home | [sched_op] Starting scheduler request
10/27/2016 9:39:15 AM | SETI@home | Sending scheduler request: Requested by user.
10/27/2016 9:39:15 AM | SETI@home | Reporting 7 completed tasks
10/27/2016 9:39:15 AM | SETI@home | Requesting new tasks for CPU
10/27/2016 9:39:15 AM | SETI@home | [sched_op] CPU work request: 2834.67 seconds; 0.00 devices
10/27/2016 9:39:15 AM | SETI@home | [sched_op] NVIDIA GPU work request: 0.00 seconds; 0.00 devices
10/27/2016 9:39:17 AM | SETI@home | Scheduler request completed: got 0 new tasks
10/27/2016 9:39:17 AM | SETI@home | [sched_op] Server version 707
10/27/2016 9:39:17 AM | SETI@home | Not sending work - last request too recent: 165 sec
10/27/2016 9:39:17 AM | SETI@home | Project requested delay of 303 seconds
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 10jl16ab.17895.93737.14.41.17_0
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 10jl16ab.17895.93737.14.41.194_1
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 10jl16ab.15033.80137.16.43.78_1
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 10jl16ab.15033.80137.16.43.41_0
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 11jl16ab.19107.370289.6.33.31_0
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 11jl16ab.19107.370289.6.33.16_1
10/27/2016 9:39:17 AM | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 11fe16ab.7672.8656.14.41.251_0
10/27/2016 9:39:17 AM | SETI@home | [sched_op] Deferring communication for 00:05:03
10/27/2016 9:39:17 AM | SETI@home | [sched_op] Reason: requested by project
10/27/2016 9:40:00 AM | | [cpu_sched_debug] Request CPU reschedule: periodic CPU scheduling
10/27/2016 9:40:00 AM | | [cpu_sched_debug] schedule_cpus(): start
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] reserving 1.000000 of coproc NVIDIA
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] add to run list: 12au16aa.10035.12337.8.35.104_2 (NVIDIA GPU, FIFO) (prio -1.000000)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] add to run list: 11fe16ab.7768.284456.9.36.55_0 (CPU, FIFO) (prio -1.027329)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] add to run list: 11jl16ab.7068.379287.8.35.146.vlar_0 (CPU, FIFO) (prio -1.030929)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] add to run list: 11jl16ab.7068.379287.8.35.247.vlar_0 (CPU, FIFO) (prio -1.034528)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] add to run list: 13fe16ab.23083.885.8.35.189.vlar_1 (CPU, FIFO) (prio -1.038128)
10/27/2016 9:40:00 AM | | [cpu_sched_debug] enforce_run_list(): start
10/27/2016 9:40:00 AM | | [cpu_sched_debug] preliminary job list:
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 0: 12au16aa.10035.12337.8.35.104_2 (MD: no; UTS: no)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 1: 11fe16ab.7768.284456.9.36.55_0 (MD: no; UTS: no)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 2: 11jl16ab.7068.379287.8.35.146.vlar_0 (MD: no; UTS: no)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 3: 11jl16ab.7068.379287.8.35.247.vlar_0 (MD: no; UTS: no)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 4: 13fe16ab.23083.885.8.35.189.vlar_1 (MD: no; UTS: no)
10/27/2016 9:40:00 AM | | [cpu_sched_debug] final job list:
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 0: 12au16aa.10035.12337.8.35.104_2 (MD: no; UTS: yes)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 1: 11fe16ab.7768.284456.9.36.55_0 (MD: no; UTS: yes)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 2: 11jl16ab.7068.379287.8.35.146.vlar_0 (MD: no; UTS: yes)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 3: 11jl16ab.7068.379287.8.35.247.vlar_0 (MD: no; UTS: yes)
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] 4: 13fe16ab.23083.885.8.35.189.vlar_1 (MD: no; UTS: yes)
10/27/2016 9:40:00 AM | SETI@home | [coproc] NVIDIA instance 0; 1.000000 pending for 12au16aa.10035.12337.8.35.104_2
10/27/2016 9:40:00 AM | SETI@home | [coproc] NVIDIA instance 0: confirming 1.000000 instance for 12au16aa.10035.12337.8.35.104_2
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] scheduling 12au16aa.10035.12337.8.35.104_2
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] scheduling 11fe16ab.7768.284456.9.36.55_0
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] scheduling 11jl16ab.7068.379287.8.35.146.vlar_0
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] scheduling 11jl16ab.7068.379287.8.35.247.vlar_0
10/27/2016 9:40:00 AM | SETI@home | [cpu_sched_debug] scheduling 13fe16ab.23083.885.8.35.189.vlar_1
10/27/2016 9:40:00 AM | | [cpu_sched_debug] enforce_run_list: end
ID: 1826954 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1826959 - Posted: 27 Oct 2016, 15:56:13 UTC - in response to Message 1826954.  
Last modified: 27 Oct 2016, 15:57:37 UTC

Thank you.
You can turn off cpu_sched_debug and turn on cpu_sched and task_debug.
Also leave on file_xfer, sched_ops, and task (as these are the defaults).
Plus leave coproc_debug and cpu_op_debug on.
(BOINC Manager->Options->Event Log options...)
(With the above flags, wait about 5 minutes, then copy and post the log from the event log, last 50 or so lines).

I also see you changed back from your previous log:
10/25/2016 6:03:23 PM | | Number of usable CPUs has changed from 4 to 3.
10/25/2016 6:03:23 PM | | max CPUs used: 3

.. to using all four CPU cores?
Not sure if that's a good idea on an Nvidia card when using CUDA, but I'll leave that for an Nvidia prof to tell. I thought it was OpenCL that likes to have a free a CPU core, not sure if CUDA does that as well.
ID: 1826959 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826975 - Posted: 27 Oct 2016, 17:14:01 UTC - in response to Message 1826959.  

I did not find cpu_op_debug in Event Log options but I did make the other changes.

I changed the number of CPUs thinking that if I freed up a CPU, it would get one of the tasks that included my NVIDIA GPU to start. Obviously, that is incorrect so I did switch it back to using all 4 of the CPUs.

New event log after changes:

10/27/2016 12:13:05 PM | | Starting BOINC client version 7.6.22 for windows_x86_64
10/27/2016 12:13:05 PM | | log flags: file_xfer, sched_ops, task, coproc_debug, cpu_sched, sched_op_debug
10/27/2016 12:13:05 PM | | log flags: task_debug
10/27/2016 12:13:05 PM | | Libraries: libcurl/7.45.0 OpenSSL/1.0.2d zlib/1.2.8
10/27/2016 12:13:05 PM | | Data directory: C:\ProgramData\BOINC
10/27/2016 12:13:05 PM | | Running under account hardliner
10/27/2016 12:13:05 PM | | [coproc] launching child process at C:\Program Files\BOINC\boinc.exe
10/27/2016 12:13:05 PM | | [coproc] relative to directory C:\ProgramData\BOINC
10/27/2016 12:13:05 PM | | [coproc] with data directory "C:\ProgramData\BOINC"
10/27/2016 12:13:05 PM | | CUDA: NVIDIA GPU 0: GeForce GT 610 (driver version 375.63, CUDA version 8.0, compute capability 2.1, 2048MB, 1961MB available, 156 GFLOPS peak)
10/27/2016 12:13:05 PM | | OpenCL: NVIDIA GPU 0: GeForce GT 610 (driver version 375.63, device version OpenCL 1.1 CUDA, 2048MB, 1961MB available, 156 GFLOPS peak)
10/27/2016 12:13:05 PM | | [coproc] NVIDIA library reports 1 GPU
10/27/2016 12:13:05 PM | | [coproc] No ATI library found.
10/27/2016 12:13:05 PM | | Host name: hardliner-PC
10/27/2016 12:13:05 PM | | Processor: 4 GenuineIntel Intel(R) Core(TM) i3-4160 CPU @ 3.60GHz [Family 6 Model 60 Stepping 3]
10/27/2016 12:13:05 PM | | 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 htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 vmx tm2 pbe fsgsbase bmi1 smep bmi2
10/27/2016 12:13:05 PM | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
10/27/2016 12:13:05 PM | | Memory: 15.95 GB physical, 31.90 GB virtual
10/27/2016 12:13:05 PM | | Disk: 111.69 GB total, 47.73 GB free
10/27/2016 12:13:05 PM | | Local time is UTC -5 hours
10/27/2016 12:13:05 PM | | VirtualBox version: 5.0.12
10/27/2016 12:13:05 PM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 8028538; resource share 100
10/27/2016 12:13:05 PM | | No general preferences found - using defaults
10/27/2016 12:13:05 PM | | Reading preferences override file
10/27/2016 12:13:05 PM | | Preferences:
10/27/2016 12:13:05 PM | | max memory usage when active: 8166.43MB
10/27/2016 12:13:05 PM | | max memory usage when idle: 14699.57MB
10/27/2016 12:13:05 PM | | max disk usage: 47.80GB
10/27/2016 12:13:05 PM | | (to change preferences, visit a project web site or select Preferences in the Manager)
10/27/2016 12:13:05 PM | SETI@home | [coproc] Assigning NVIDIA instance 0 to 12au16aa.10035.12337.8.35.104_2
10/27/2016 12:13:06 PM | SETI@home | [task] task_state=EXECUTING for 12au16aa.10035.12337.8.35.104_2 from start
10/27/2016 12:13:06 PM | SETI@home | [cpu_sched] Restarting task 12au16aa.10035.12337.8.35.104_2 using setiathome_v8 version 812 (opencl_nvidia_SoG) in slot 4
10/27/2016 12:13:06 PM | SETI@home | [task] task_state=EXECUTING for blc3_2bit_guppi_57451_23521_HIP63406_0015.28765.831.17.26.41.vlar_0 from start
10/27/2016 12:13:06 PM | SETI@home | [cpu_sched] Restarting task blc3_2bit_guppi_57451_23521_HIP63406_0015.28765.831.17.26.41.vlar_0 using setiathome_v8 version 800 in slot 1
10/27/2016 12:13:06 PM | SETI@home | [task] task_state=EXECUTING for 13fe16ab.23083.885.8.35.102.vlar_1 from start
10/27/2016 12:13:06 PM | SETI@home | [cpu_sched] Restarting task 13fe16ab.23083.885.8.35.102.vlar_1 using setiathome_v8 version 800 in slot 2
10/27/2016 12:13:06 PM | SETI@home | [task] task_state=EXECUTING for 13fe16ab.23083.885.8.35.7.vlar_0 from start
10/27/2016 12:13:06 PM | SETI@home | [cpu_sched] Restarting task 13fe16ab.23083.885.8.35.7.vlar_0 using setiathome_v8 version 800 in slot 3
10/27/2016 12:13:06 PM | SETI@home | [task] task_state=EXECUTING for blc3_2bit_guppi_57451_23521_HIP63406_0015.28765.831.17.26.38.vlar_0 from start
10/27/2016 12:13:06 PM | SETI@home | [cpu_sched] Restarting task blc3_2bit_guppi_57451_23521_HIP63406_0015.28765.831.17.26.38.vlar_0 using setiathome_v8 version 800 in slot 0
ID: 1826975 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1826978 - Posted: 27 Oct 2016, 17:30:53 UTC - in response to Message 1826975.  
Last modified: 27 Oct 2016, 17:32:06 UTC

I did not find cpu_op_debug in Event Log options

Sorry, that was a typo from me, meant to leave on sched_op_debug, which you have done. :)

I changed the number of CPUs thinking that if I freed up a CPU, it would get one of the tasks that included my NVIDIA GPU to start. Obviously, that is incorrect so I did switch it back to using all 4 of the CPUs.

Well, it's not incorrect, I just don't know if it's needed for CUDA. Therefore leaving that to someone who does know.

But seeing how BOINC is now executing a task on your GPU using the OpenCL application, it might be wise to tell BOINC to use 3 cores again and leave the fourth free for the GPU:
10/27/2016 12:13:05 PM | SETI@home | [coproc] Assigning NVIDIA instance 0 to 12au16aa.10035.12337.8.35.104_2
10/27/2016 12:13:06 PM | SETI@home | [task] task_state=EXECUTING for 12au16aa.10035.12337.8.35.104_2 from start
10/27/2016 12:13:06 PM | SETI@home | [cpu_sched] Restarting task 12au16aa.10035.12337.8.35.104_2 using setiathome_v8 version 812 (opencl_nvidia_SoG) in slot 4


(Earlier when I looked in your task list, I only saw the CUDA50 task, but now I see you also still have those two (one, two) SoG tasks which use OpenCL and have a deadline of the 31st of October, so still time enough to finish them).

Edit: In the end I think it was your drivers that were flummoxed. The driver reinstall fixed that.
ID: 1826978 · Report as offensive
hardliner

Send message
Joined: 9 Sep 15
Posts: 12
Credit: 3,634,877
RAC: 1
United States
Message 1826988 - Posted: 27 Oct 2016, 17:47:15 UTC - in response to Message 1826978.  

How can you tell that installing the new drivers fixed the issue?

I ask because I still see the 3 tasks that include my NVIDIA GPU and they have yet to do anything even though one of them says it's running but I've seen it sit at 0.001% before and I ended up having to abort that task since it expired back in August.
ID: 1826988 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1826994 - Posted: 27 Oct 2016, 18:02:52 UTC - in response to Message 1826988.  

How can you tell that installing the new drivers fixed the issue?

Good question! I cannot from here, but we can add another debug flag that can show that. Tasks like these should checkpoint every so often to write their state to disk. This in case somewhere along the way something goes awry and BOINC has to be restarted, that you don't have to start the task from the start.

You can add a check mark to checkpoint_debug in the Event Log options to enable this flag. There is another flag with a lot more details that we can add as well, but since that one will poll the system several times per second and dump all that information into the Event Log, I'll hold off with offering that one for now.
ID: 1826994 · Report as offensive
1 · 2 · Next

Questions and Answers : Windows : SETI@Home not using my GPU


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.