| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Support
Forum: GPU Support Forum
Thread: GPU Work Units - Post Your Tech Support Questions Here |
| No member browsing this thread |
|
Thread Status: Active Thread Type: Sticky Thread Total posts in this thread: 290
|
|
| Author |
|
|
goben_2003
Advanced Cruncher Joined: Jun 16, 2006 Post Count: 145 Status: Offline Project Badges: 
|
<use_all_gpus>1</use_all_gpus> in cc_config.xml Thanks. I'll try to snatch some of the WUs now. I think that is to tell BOINC not to only use the most powerful GPU, as by default it will only use 1 gpu; whichever it thinks is more powerful. I think that should be the GTX 950 though. If you are still having problems, please post the lines for the video cards from the event log when BOINC starts up. They should look something like this: 29-Apr-2021 08:53:47 [---] CUDA: NVIDIA GPU 0: GeForce RTX 2060 (driver version 456.71, CUDA version 11.1, compute capability 7.5, 4096MB, 3550MB available, 5126 GFLOPS peak) 29-Apr-2021 08:53:47 [---] OpenCL: NVIDIA GPU 0: GeForce RTX 2060 (driver version 456.71, device version OpenCL 1.2 CUDA, 6144MB, 3550MB available, 5126 GFLOPS peak) 29-Apr-2021 08:53:47 [---] OpenCL: Intel GPU 0: Intel(R) UHD Graphics 630 (driver version 27.20.100.8681, device version OpenCL 2.1 NEO, 13045MB, 13045MB available, 221 GFLOPS peak)  |
||
|
|
tech4theworld
Cruncher Joined: May 16, 2011 Post Count: 2 Status: Offline Project Badges: 
|
Thank you for responding. I followed the most reliable process in the DDU documentation (network disconnected, safe mode, two passes), but result is still 2 OpenCL instances per GPU in the log.
----------------------------------------This was resolved by installing the latest Windows 10 Feature update. Best Regards [Edit 1 times, last edit by tech4theworld at May 2, 2021 11:07:54 PM] |
||
|
|
JKarhu
Cruncher Joined: Apr 5, 2021 Post Count: 5 Status: Offline |
Hello all, novice cruncher here.
Ever after the stress test started, all the OPNG tasks I got have failed: <core_client_version>7.16.14</core_client_version> <![CDATA[ <message> process exited with code 10 (0xa, -246)</message> <stderr_txt> wcgrid_opng_autodockgpu_7.28_x86_64-apple-darwin__opencl_ati_102 -jobs OPNG_0033224_00026.job -input OPNG_0033224_00026.zip -seed 517684644 -wcgruns 1950 -wcgdpf 39 INFO: Using gpu device from app init data 0 INFO:[03:31:39] Start AutoGrid... autogrid4: Successful Completion. INFO:[03:34:50] End AutoGrid... INFO:[03:34:51] Start AutoDock for OB3ZINC001186948805--7jji_002_mgltools--TYR380_inert.dpf(Job #0)... GPU not found: type=ATI, opencl_device_index=1, device_num=0 Error: boinc_get_opencl_ids() failed with error -1 03:34:51 (54242): called boinc_finish(10) </stderr_txt> ]]> This is the setup I run: OpenCL: AMD/ATI GPU 0: AMD Radeon RX 580 Compute Engine (driver version 1.2 (Nov 10 2020 01:48:16), device version OpenCL 1.2, 8192MB, 8192MB available, 864 GFLOPS peak) OpenCL CPU: Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz (OpenCL driver vendor: Apple, driver version 1.1, device version OpenCL 1.2) Processor: 8 GenuineIntel Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz [x86 Family 6 Model 158 Stepping 9] Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clfsh ds acpi mmx fxsr sse sse2 ss htt tm pbe pni pclmulqdq dtes64 mon dscpl vmx est tm2 ssse3 fma cx16 tpr pdcm sse4_1 sse4_2 x2apic movbe popcnt aes pcid xsave osxsave seglim64 tsctmr avx rdrand f16c OS: Mac OS X 10.14.6 (Darwin 18.7.0) I am really new to this stuff. Can somebody give me some directions, where should I start the troubleshoot? The OPNG tasks were working fine before the stress test started... Thank you very much in advance! |
||
|
|
Falconet
Master Cruncher Portugal Joined: Mar 9, 2009 Post Count: 3295 Status: Offline Project Badges:
|
Jkarhu,
----------------------------------------Error: boinc_get_opencl_ids() failed with error -1 - Maybe purge the installed driver and install again? The reported number, 864 GFLOPS, seems low. Not just because one of the PC's in my house has one of these cards and the reported value is much higher but also because that 864 value is even lower than the one reported from my RX 550. So yes, my advice would be a clean driver install. Other than that, I can't really help since I don't have a Mac and have no experience with Mac OS. AMD Ryzen 5 1600AF 6C/12T 3.2 GHz - 85W AMD Ryzen 5 2500U 4C/8T 2.0 GHz - 28W AMD Ryzen 7 7730U 8C/16T 3.0 GHz [Edit 1 times, last edit by Falconet at May 2, 2021 8:35:26 PM] |
||
|
|
JKarhu
Cruncher Joined: Apr 5, 2021 Post Count: 5 Status: Offline |
Weirdly enough, my issue seemed to fix itself. I did not update anything, only relaunched BOINC again. I thought I had already done that, so go figure.
|
||
|
|
hnapel
Advanced Cruncher Netherlands Joined: Nov 17, 2004 Post Count: 82 Status: Offline Project Badges: 
|
I've got 2 NVIDIA GPU's of the same type in my PC, I've configured app_config.xml to allow for 16 GPU jobs total, but at some point only got 4 to process, to my surprise they all ended up being procesed by 'device 0' an none on 'device 1', so isn't there some mechanism to spread them over all the devices more evenly?
|
||
|
|
retsof
Former Community Advisor USA Joined: Jul 31, 2005 Post Count: 6824 Status: Offline Project Badges: 
|
I have a GPU that has been running for 24 1/2 hours and is still at it? Is it still good?
----------------------------------------Most of them have been very short, but the expire date for everything after it is only about 5 hours from how.
SUPPORT ADVISOR
Work+GPU i7 8700 12threads School i7 4770 8threads Default+GPU Ryzen 7 3700X 16threads Ryzen 7 3800X 16 threads Ryzen 9 3900X 24threads Home i7 3540M 4threads50% |
||
|
|
platinumjsi
Cruncher Joined: Aug 12, 2010 Post Count: 37 Status: Offline Project Badges:
|
So the units seem to be running fine on my 3090 but it's hardly breaking a sweat, for the first few mins the GPU is fully idle, it then kicks into gear but with really low utilization, and max 120w power draw (it's a 350w GPU).
----------------------------------------Average GPU load is about 10% with the odd very short spike to 90%  Is the app just really badly optimised?  [Edit 1 times, last edit by platinumjsi at May 4, 2021 9:45:30 AM] |
||
|
|
goben_2003
Advanced Cruncher Joined: Jun 16, 2006 Post Count: 145 Status: Offline Project Badges:
|
So the units seem to be running fine on my 3090 but it's hardly breaking a sweat, for the first few mins the GPU is fully idle, it then kicks into gear but with really low utilization, and max 120w power draw (it's a 350w GPU). Average GPU load is about 10% with the odd very short spike to 90% Is the app just really badly optimised? Yes. I run 10 at a time on my 2060m to keep it's avg utilization % in the high 90s. How many are you running simultaneously? |
||
|
|
platinumjsi
Cruncher Joined: Aug 12, 2010 Post Count: 37 Status: Offline Project Badges:
|
Just the one unit
---------------------------------------- |
||
|
|
|