Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
![]() |
World Community Grid Forums
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
No member browsing this thread |
Thread Status: Active Total posts in this thread: 272
|
![]() |
Author |
|
comancheace
Cruncher Joined: Aug 1, 2013 Post Count: 14 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Hi bozz4science! First of all thank you for supporting Portugal in this Pandemic! A big thank you from Portugal! Don't worry there will be many more available! I only got 2 but I think they were more long because in the same computer they took the other time 2 minutes and these took abou half an hour. I think were long run tasks! (BETA OpenPandemics - GPU 7.21 (opencl_nvidia_102))
----------------------------------------Good luck next time! Thank you! Kind regards! ![]() ![]() |
||
|
Ragnarsdad
Cruncher United Kingdom Joined: Jul 25, 2018 Post Count: 6 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
First work unit today on an old AMD HD 5850 on Catalyst version 15.7.1
Workunit is currently stalled at 10.56% and has been for some time, will give it another hour before i abort. Application BETA - OpenPandemics - COVID-19 - GPU 7.21 (opencl_ati_102) Name BETA_OPN1_0020075_00170 State Running Received 24/02/2021 18:50:46 Report deadline 26/02/2021 18:50:45 Resources 0.955 CPUs + 1 AMD/ATI GPU Estimated computation size 31,450 GFLOPs CPU time 00:00:36 CPU time since checkpoint 00:00:04 Elapsed time 01:22:23 Estimated time remaining 11:40:21 Fraction done 10.526% Virtual memory size 407.32 MB Working set size 216.71 MB Directory slots/8 Process ID 7596 Progress rate 3.960% per hour Executable wcgrid_beta29_autodockgpu_7.21_windows_x86_64__opencl_ati_102 |
||
|
JEagleton
Cruncher Joined: Dec 31, 2004 Post Count: 1 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Getting machine freeze-ups that require a reboot, generally when suspending tasks. They seem to run ok. This is on an AMD A10 with on-chip GPU.
2/24/2021 2:46:49 PM | | Starting BOINC client version 7.16.11 for windows_x86_64 2/24/2021 2:46:49 PM | | log flags: file_xfer, sched_ops, task 2/24/2021 2:46:49 PM | | Libraries: libcurl/7.47.1 OpenSSL/1.0.2s zlib/1.2.8 2/24/2021 2:46:49 PM | | Data directory: C:\ProgramData\BOINC 2/24/2021 2:46:49 PM | | Running under account JPE 2/24/2021 2:46:50 PM | | OpenCL: AMD/ATI GPU 0: AMD Radeon(TM) R7 Graphics (driver version 3075.13, device version OpenCL 2.0 AMD-APP (3075.13), 6568MB, 6568MB available, 553 GFLOPS peak) 2/24/2021 2:46:50 PM | | Windows processor group 0: 4 processors 2/24/2021 2:46:50 PM | | Host name: DMAXREC2 2/24/2021 2:46:50 PM | | Processor: 4 AuthenticAMD AMD A10-7700K Radeon R7, 10 Compute Cores 4C+6G [Family 21 Model 48 Stepping 1] 2/24/2021 2:46:50 PM | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 htt pni ssse3 fma cx16 sse4_1 sse4_2 popcnt aes f16c syscall nx lm avx sse4a osvw xop wdt fma4 topx page1gb rdtscp fsgsbase bmi1 2/24/2021 2:46:50 PM | | OS: Microsoft Windows 10: Professional x64 Edition, (10.00.19041.00) 2/24/2021 2:46:50 PM | | Memory: 14.94 GB physical, 17.19 GB virtual 2/24/2021 2:46:50 PM | | Disk: 237.42 GB total, 4.14 GB free 2/24/2021 2:46:50 PM | | Local time is UTC -5 hours 2/24/2021 2:46:50 PM | | No WSL found. 2/24/2021 2:46:50 PM | | VirtualBox version: 6.1.14 |
||
|
Crystal Pellet
Veteran Cruncher Joined: May 21, 2008 Post Count: 1324 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
What are your experiences with performance so far? What cards are you running and what are average runtimes? I got some resends on an integrated graphics AMD 6400T apuScreen unusable, I discovered after lifting the closed laptop lid, but doing some BETA work and 4 cores busy with 4 OPN1 cpu-tasks. GPU 40 autodocks: BETA_OPN1_0020021_00085_2 GPU (opencl_ati_102) elapsed time 03:34:22 - CPU time 00:13:12 |
||
|
ThreadRipper
Veteran Cruncher Sweden Joined: Apr 26, 2007 Post Count: 1322 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Getting machine freeze-ups that require a reboot, generally when suspending tasks. They seem to run ok. This is on an AMD A10 with on-chip GPU. 2/24/2021 2:46:49 PM | | Starting BOINC client version 7.16.11 for windows_x86_64 2/24/2021 2:46:49 PM | | log flags: file_xfer, sched_ops, task 2/24/2021 2:46:49 PM | | Libraries: libcurl/7.47.1 OpenSSL/1.0.2s zlib/1.2.8 2/24/2021 2:46:49 PM | | Data directory: C:\ProgramData\BOINC 2/24/2021 2:46:49 PM | | Running under account JPE 2/24/2021 2:46:50 PM | | OpenCL: AMD/ATI GPU 0: AMD Radeon(TM) R7 Graphics (driver version 3075.13, device version OpenCL 2.0 AMD-APP (3075.13), 6568MB, 6568MB available, 553 GFLOPS peak) 2/24/2021 2:46:50 PM | | Windows processor group 0: 4 processors 2/24/2021 2:46:50 PM | | Host name: DMAXREC2 2/24/2021 2:46:50 PM | | Processor: 4 AuthenticAMD AMD A10-7700K Radeon R7, 10 Compute Cores 4C+6G [Family 21 Model 48 Stepping 1] 2/24/2021 2:46:50 PM | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 htt pni ssse3 fma cx16 sse4_1 sse4_2 popcnt aes f16c syscall nx lm avx sse4a osvw xop wdt fma4 topx page1gb rdtscp fsgsbase bmi1 2/24/2021 2:46:50 PM | | OS: Microsoft Windows 10: Professional x64 Edition, (10.00.19041.00) 2/24/2021 2:46:50 PM | | Memory: 14.94 GB physical, 17.19 GB virtual 2/24/2021 2:46:50 PM | | Disk: 237.42 GB total, 4.14 GB free 2/24/2021 2:46:50 PM | | Local time is UTC -5 hours 2/24/2021 2:46:50 PM | | No WSL found. 2/24/2021 2:46:50 PM | | VirtualBox version: 6.1.14 Perhaps you ran into the same issue that I did with driver timeout on an AMD A10 7850K iGPU. You can loon in this thread for my previous posts on the matter. With latest AMD drivers I did always get a message about driver timeout and then PC just froze and had to be reset the hard way. ![]() Join The International Team: https://www.worldcommunitygrid.org/team/viewTeamInfo.do?teamId=CK9RP1BKX1 AMD TR2990WX @ PBO, 64GB Quad 3200MHz 14-17-17-17-1T, RX6900XT @ Stock AMD 3800X @ PBO AMD 2700X @ 4GHz |
||
|
robertmiles
Senior Cruncher US Joined: Apr 16, 2008 Post Count: 443 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
It's getting a bit cold here in my apartment, so I would appreciate some WU's to heat up my GPU..... ![]() I'm currently using Milkyway@Home workunits for that purpose, since GPUGRID currently has none available. |
||
|
Speedy51
Veteran Cruncher New Zealand Joined: Nov 4, 2005 Post Count: 1297 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
100 batches Out of curiosity will GPU batch have the same number of tasks in it as a CPU batch? I may be jumping the gun with this question. In terms of statistics. When the GPU app goes live will all statistics be counted as one or will be the GPU statistics and CPU statistics? Example CPU results returned: 995,058 GPU results returned: 2,985,174 or will they be displayed as a total of: 3,980,232 result returned per day I believe it would be nice if we could have statistics for both the CPU and GPU application. If this cannot be done because it's too hard to divide the statistics I do understand ![]() [Edit 3 times, last edit by Speedy51 at Feb 25, 2021 3:13:25 AM] |
||
|
bozz4science
Advanced Cruncher Germany Joined: May 3, 2020 Post Count: 104 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
I happened to wonder about the very same question yesterday!
----------------------------------------![]() AMD Ryzen 3700X @ 4.0 GHz / GTX1660S Intel i5-4278U CPU @ 2.60GHz |
||
|
Rickjb
Veteran Cruncher Australia Joined: Sep 17, 2006 Post Count: 666 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Hi all.
----------------------------------------I haven't received any of these GPU betas so far, but then I've only enabled GPU crunching on 1 machine, a 3770K with its integral Intel HD4000 GPU that has an OpenCL1.2** driver ([Edit] according to Geeks3D's GPU Caps Viewer and TPU's GPU-Z[/edit]). Has anyone received any betas for such a machine, and what was your experience? I have an AMD HD7870 card that crunched a lot of HCC WUs back in the day, plus an untested Geforce GTX770 card that was in a desktop machine junked in the street, and intend installing these when the GPU work is more frequent. The other issue that I haven't seen mentioned is the total amount of work anticipated for the SARS-CoV-2 drug search. Introducing GPU Autodock4 might mean that this phase of the search ends very quickly, which is what's needed when a pandemic strikes. But if crunching is planned to go on for a longer time, I'll obtain some more capable GPU cards. [Edit2]: the clinfo.exe program says that the HD4000 only supports OpenCL1.1, but the current versions of GPU Caps Viewer and GPU-Z say OpenCL1.2 ! I wonder what version BOINC/WCG will detect? [edit2] [Edit:] Falconet has answered my questions in his post that is a few below this one: * OpenCL 1.1 is not supported and 1.1 cards wil be blocked from receiving further work (but see above re OpenCL on HD4000). * OPN1 was said by WCG to be a "huge" project Thanks, Falconet [/edit] [Edit 3 times, last edit by Rickjb at Feb 27, 2021 7:41:24 AM] |
||
|
Jim1348
Veteran Cruncher USA Joined: Jul 13, 2009 Post Count: 1066 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Out of curiosity will GPU batch have the same number of tasks in it as a CPU batch? No, there will be more. You can read this thread for the posts by uplinger, but here is the latest: https://www.worldcommunitygrid.org/forums/wcg...d,43206_offset,200#652226 I don't think they have determined the final size yet. |
||
|
|
![]() |