Message boards :
Application Code Discussion :
Requesting but not getting new tasks for NVIDIA GPU
Message board moderation
Author | Message |
---|---|
Send message Joined: 26 May 20 Posts: 23 Credit: 672,651,687 RAC: 39,379 |
Linux x86_64 For a couple of weeks now I have two pc's that cant get any GPU tasks, 3 other pc's get them just fine. Here is the startup code, you can see it's requesting NVIDIA tasks but it never gets any. Before a couple of weeks ago both pc's were executing NVIDIA tasks just fine. 11-Feb-2023 20:39:36 [---] Starting BOINC client version 7.22.0 for x86_64-suse-linux-gnu 11-Feb-2023 20:39:36 [---] log flags: file_xfer, sched_ops, task 11-Feb-2023 20:39:36 [---] Libraries: libcurl/7.87.0 OpenSSL/3.0.7 zlib/1.2.13 brotli/1.0.9 zstd/1.5.2 libidn2/2.3.4 libpsl/0.21.2 (+libidn2/2.3.4) libssh/0.10.4/openssl/zlib nghttp2/1.51.0 11-Feb-2023 20:39:36 [---] Data directory: /home/erbenton/boinc 11-Feb-2023 20:39:36 [---] CUDA: NVIDIA GPU 0: NVIDIA GeForce RTX 2060 (driver version 525.85, CUDA version 12.0, compute capability 7.5, 5919MB, 5919MB available, 6739 GFLOPS peak) 11-Feb-2023 20:39:36 [---] CUDA: NVIDIA GPU 1: NVIDIA GeForce GTX 1660 Ti (driver version 525.85, CUDA version 12.0, compute capability 7.5, 5937MB, 5937MB available, 5668 GFLOPS peak) 11-Feb-2023 20:39:36 [---] libc: version 2.37 11-Feb-2023 20:39:36 [---] Host name: erb1 11-Feb-2023 20:39:36 [---] Processor: 12 GenuineIntel Intel(R) Core(TM) i7-3960X CPU @ 3.30GHz [Family 6 Model 45 Stepping 7] 11-Feb-2023 20:39:36 [---] 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 cpuid aperfmperf 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 lahf_lm epb ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid xsaveopt dtherm ida arat pln pts md_clear flush_l1d 11-Feb-2023 20:39:36 [---] OS: Linux openSUSE: openSUSE Tumbleweed [6.1.10-1-default|libc 2.37] 11-Feb-2023 20:39:36 [---] Memory: 31.27 GB physical, 16.00 GB virtual 11-Feb-2023 20:39:36 [---] Disk: 309.64 GB total, 188.64 GB free 11-Feb-2023 20:39:36 [---] Local time is UTC -8 hours 11-Feb-2023 20:39:36 [---] Config: use all coprocessors 11-Feb-2023 20:39:36 [Milkyway@Home] General prefs: from Milkyway@Home (last modified 20-Jun-2020 17:48:32) 11-Feb-2023 20:39:36 [Milkyway@Home] Computer location: home 11-Feb-2023 20:39:36 [Milkyway@Home] General prefs: no separate prefs for home; using your defaults 11-Feb-2023 20:39:36 [---] Reading preferences override file 11-Feb-2023 20:39:36 [---] Preferences: 11-Feb-2023 20:39:36 [---] - When computer is in use 11-Feb-2023 20:39:36 [---] - 'In use' means mouse/keyboard input in last 3.0 minutes 11-Feb-2023 20:39:36 [---] - max CPUs used: 12 11-Feb-2023 20:39:36 [---] - Use at most 100% of the CPU time 11-Feb-2023 20:39:36 [---] - suspend if non-BOINC CPU load exceeds 90% 11-Feb-2023 20:39:36 [---] - max memory usage: 21.89 GB 11-Feb-2023 20:39:36 [---] - When computer is not in use 11-Feb-2023 20:39:36 [---] - max CPUs used: 12 11-Feb-2023 20:39:36 [---] - Use at most 100% of the CPU time 11-Feb-2023 20:39:36 [---] - suspend if non-BOINC CPU load exceeds 90% 11-Feb-2023 20:39:36 [---] - max memory usage: 23.45 GB 11-Feb-2023 20:39:36 [---] - Leave apps in memory if not running 11-Feb-2023 20:39:36 [---] - Store at least 2.00 days of work 11-Feb-2023 20:39:36 [---] - Store up to an additional 3.00 days of work 11-Feb-2023 20:39:36 [---] - max disk usage: 6.00 GB 11-Feb-2023 20:39:36 [---] - (to change preferences, visit a project web site or select Preferences in the Manager) 11-Feb-2023 20:39:36 [---] Setting up project and slot directories 11-Feb-2023 20:39:36 [---] Checking active tasks 11-Feb-2023 20:39:36 [Einstein@Home] URL http://einstein.phys.uwm.edu/; Computer ID 12885175; resource share 100 11-Feb-2023 20:39:36 [Milkyway@Home] URL http://milkyway.cs.rpi.edu/milkyway/; Computer ID 966838; resource share 100 11-Feb-2023 20:39:36 [---] Setting up GUI RPC socket 11-Feb-2023 20:39:36 [---] Checking presence of 39 project files 11-Feb-2023 20:39:36 Initialization completed 11-Feb-2023 20:39:36 [Milkyway@Home] Sending scheduler request: To fetch work. 11-Feb-2023 20:39:36 [Milkyway@Home] Requesting new tasks for NVIDIA GPU 11-Feb-2023 20:39:38 [Milkyway@Home] Scheduler request completed: got 0 new tasks 11-Feb-2023 20:39:38 [Milkyway@Home] Project requested delay of 91 seconds[/code] |
Send message Joined: 16 Mar 10 Posts: 213 Credit: 108,368,205 RAC: 4,285 |
MilkyWay tasks are OpenCL, not CUDA, and BOINC hasn't spotted OpenCL drivers so you need to install the NVIDIA OpenCL stuff. Not sure how to do that on your openSUSE - I think making sure you have an OpenCL ICD loader (ocl-icd-linopencl1 on my Ubuntu systems) should do the trick... You can check the existing OpenCL devices with clinfo... Cheers - Al. P.S. the best place for queries like this is probably the Number Crunching forum or the Unix/Linux forum -- you might've got an answer from an openSUSE user! :-) |
Send message Joined: 26 May 20 Posts: 23 Credit: 672,651,687 RAC: 39,379 |
Yep, libOpenCL.so (opencl client driver bindings) was missing, installing it fixed things on both systems - thanks Apparently some update removed the lib, why? i don't know, but now its fixed |
©2024 Astroinformatics Group