red circle with stuck out tongue

Moderators: Site Moderators, FAHC Science Team

ph0b
Posts: 6
Joined: Tue Apr 14, 2020 12:23 pm

Re: red circle with stuck out tongue

Post by ph0b »

9168 is the one just before, it's very recent and I'm not expecting it to fail (nor the new one to fix it then..), if the issue in your post was already with this driver, that means I need to investigate it more seriously, please confirm or let me know if it happens again.
PeteHobbis
Posts: 11
Joined: Fri Feb 12, 2021 10:42 am
Location: uk

Re: red circle with stuck out tongue

Post by PeteHobbis »

Thanks! Will do. It's resumed ok for now. It does have this in the log:

Code: Select all

15:50:19:Trying to access database...
15:50:19:Successfully acquired database lock
15:50:19:FS00:Initialized folding slot 00: cpu:5
15:50:19:FS01:Initialized folding slot 01: gpu:60:0 GP108M [GeForce MX250]
15:50:19:WARNING:FS02:Guessing ambiguous GPU to OpenCL device mapping for 02: gpu:0:2 CML GT2 [UHD Graphics].  Consider upgrading your graphics driver or manually setting ``opencl-index`` in this slot's configuration.
15:50:19:FS02:Initialized folding slot 02: gpu:0:2 CML GT2 [UHD Graphics]
.. so I'm going to see if I can see what value I should set opencl-index to.

..Think I've done that; explicitly set the index of the Nvidia GPU to 1 and the UHD Graphics to 2. Don't think that was related to the problem (but what do I know...)
PeteHobbis
Posts: 11
Joined: Fri Feb 12, 2021 10:42 am
Location: uk

Re: red circle with stuck out tongue

Post by PeteHobbis »

It just did another restart (happens at 16:26). Here's the log, selected just Slot 02:

Code: Select all

*********************** Log Started 2021-02-22T15:50:19Z ***********************
15:50:19:WARNING:FS02:Guessing ambiguous GPU to OpenCL device mapping for 02: gpu:0:2 CML GT2 [UHD Graphics].  Consider upgrading your graphics driver or manually setting ``opencl-index`` in this slot's configuration.
15:50:19:FS02:Initialized folding slot 02: gpu:0:2 CML GT2 [UHD Graphics]
15:50:54:FS02:Unpaused
15:50:54:WU01:FS02:Starting
15:50:54:WU01:FS02:Running FahCore: "C:\Program Files (x86)\FAHClient/FAHCoreWrapper.exe" C:\ProgramData\FAHClient\cores/cores.foldingathome.org/win/64bit/22-0.0.13/Core_22.fah/FahCore_22.exe -dir 01 -suffix 01 -version 706 -lifeline 12688 -checkpoint 15 -opencl-platform 1 -opencl-device 0 -gpu-vendor intel -gpu 0 -gpu-usage 100
15:50:54:WU01:FS02:Started FahCore on PID 8784
15:50:54:WU01:FS02:Core PID:15132
15:50:54:WU01:FS02:FahCore 0x22 started
15:50:55:WU01:FS02:0x22:*********************** Log Started 2021-02-22T15:50:54Z ***********************
15:50:55:WU01:FS02:0x22:*************************** Core22 Folding@home Core ***************************
15:50:55:WU01:FS02:0x22:       Core: Core22
15:50:55:WU01:FS02:0x22:       Type: 0x22
15:50:55:WU01:FS02:0x22:    Version: 0.0.13
15:50:55:WU01:FS02:0x22:     Author: Joseph Coffland <joseph@cauldrondevelopment.com>
15:50:55:WU01:FS02:0x22:  Copyright: 2020 foldingathome.org
15:50:55:WU01:FS02:0x22:   Homepage: https://foldingathome.org/
15:50:55:WU01:FS02:0x22:       Date: Sep 19 2020
15:50:55:WU01:FS02:0x22:       Time: 02:35:58
15:50:55:WU01:FS02:0x22:   Revision: 571cf95de6de2c592c7c3ed48fcfb2e33e9ea7d3
15:50:55:WU01:FS02:0x22:     Branch: core22-0.0.13
15:50:55:WU01:FS02:0x22:   Compiler: Visual C++ 2015
15:50:55:WU01:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
15:50:55:WU01:FS02:0x22:             -DOPENMM_GIT_HASH="\"189320d0\""
15:50:55:WU01:FS02:0x22:   Platform: win32 10
15:50:55:WU01:FS02:0x22:       Bits: 64
15:50:55:WU01:FS02:0x22:       Mode: Release
15:50:55:WU01:FS02:0x22:Maintainers: John Chodera <john.chodera@choderalab.org> and Peter Eastman
15:50:55:WU01:FS02:0x22:             <peastman@stanford.edu>
15:50:55:WU01:FS02:0x22:       Args: -dir 01 -suffix 01 -version 706 -lifeline 8784 -checkpoint 15
15:50:55:WU01:FS02:0x22:             -opencl-platform 1 -opencl-device 0 -gpu-vendor intel -gpu 0
15:50:55:WU01:FS02:0x22:             -gpu-usage 100
15:50:55:WU01:FS02:0x22:************************************ libFAH ************************************
15:50:55:WU01:FS02:0x22:       Date: Sep 7 2020
15:50:55:WU01:FS02:0x22:       Time: 19:09:56
15:50:55:WU01:FS02:0x22:   Revision: 44301ed97b996b63fe736bb8073f22209cb2b603
15:50:55:WU01:FS02:0x22:     Branch: HEAD
15:50:55:WU01:FS02:0x22:   Compiler: Visual C++ 2015
15:50:55:WU01:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
15:50:55:WU01:FS02:0x22:   Platform: win32 10
15:50:55:WU01:FS02:0x22:       Bits: 64
15:50:55:WU01:FS02:0x22:       Mode: Release
15:50:55:WU01:FS02:0x22:************************************ CBang *************************************
15:50:55:WU01:FS02:0x22:       Date: Sep 7 2020
15:50:55:WU01:FS02:0x22:       Time: 19:08:30
15:50:55:WU01:FS02:0x22:   Revision: 33fcfc2b3ed2195a423606a264718e31e6b3903f
15:50:55:WU01:FS02:0x22:     Branch: HEAD
15:50:55:WU01:FS02:0x22:   Compiler: Visual C++ 2015
15:50:55:WU01:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
15:50:55:WU01:FS02:0x22:   Platform: win32 10
15:50:55:WU01:FS02:0x22:       Bits: 64
15:50:55:WU01:FS02:0x22:       Mode: Release
15:50:55:WU01:FS02:0x22:************************************ System ************************************
15:50:55:WU01:FS02:0x22:        CPU: Intel(R) Core(TM) i7-10510U CPU @ 1.80GHz
15:50:55:WU01:FS02:0x22:     CPU ID: GenuineIntel Family 6 Model 142 Stepping 12
15:50:55:WU01:FS02:0x22:       CPUs: 8
15:50:55:WU01:FS02:0x22:     Memory: 15.79GiB
15:50:55:WU01:FS02:0x22:Free Memory: 10.77GiB
15:50:55:WU01:FS02:0x22:    Threads: WINDOWS_THREADS
15:50:55:WU01:FS02:0x22: OS Version: 6.2
15:50:55:WU01:FS02:0x22:Has Battery: true
15:50:55:WU01:FS02:0x22: On Battery: false
15:50:55:WU01:FS02:0x22: UTC Offset: 0
15:50:55:WU01:FS02:0x22:        PID: 15132
15:50:55:WU01:FS02:0x22:        CWD: C:\ProgramData\FAHClient\work
15:50:55:WU01:FS02:0x22:************************************ OpenMM ************************************
15:50:55:WU01:FS02:0x22:   Revision: 189320d0
15:50:55:WU01:FS02:0x22:********************************************************************************
15:50:55:WU01:FS02:0x22:Project: 13439 (Run 13063, Clone 20, Gen 1)
15:50:55:WU01:FS02:0x22:Unit: 0x00000000000000000000000000000000
15:50:55:WU01:FS02:0x22:Digital signatures verified
15:50:55:WU01:FS02:0x22:Folding@home GPU Core22 Folding@home Core
15:50:55:WU01:FS02:0x22:Version 0.0.13
15:50:56:WU01:FS02:0x22:  Checkpoint write interval: 50000 steps (5%) [20 total]
15:50:56:WU01:FS02:0x22:  JSON viewer frame write interval: 10000 steps (1%) [100 total]
15:50:56:WU01:FS02:0x22:  XTC frame write interval: 250000 steps (25%) [4 total]
15:50:56:WU01:FS02:0x22:  Global context and integrator variables write interval: 25000 steps (2.5%) [40 total]
15:50:56:WU01:FS02:0x22:There are 3 platforms available.
15:50:56:WU01:FS02:0x22:Platform 0: Reference
15:50:56:WU01:FS02:0x22:Platform 1: CPU
15:50:56:WU01:FS02:0x22:Platform 2: OpenCL
15:50:56:WU01:FS02:0x22:  opencl-device 0 specified
15:50:57:WU01:FS02:0x22:Attempting to create OpenCL context:
15:50:57:WU01:FS02:0x22:  Configuring platform OpenCL
15:51:24:WU01:FS02:0x22:  Using OpenCL on platformId 1 and gpu 0
15:51:24:WU01:FS02:0x22:Completed 700000 out of 1000000 steps (70%)
15:54:18:WU01:FS02:0x22:Completed 710000 out of 1000000 steps (71%)
15:58:09:WU01:FS02:0x22:Completed 720000 out of 1000000 steps (72%)
16:02:19:WU01:FS02:0x22:Completed 730000 out of 1000000 steps (73%)
16:06:27:WU01:FS02:0x22:Completed 740000 out of 1000000 steps (74%)
16:10:32:WU01:FS02:0x22:Completed 750000 out of 1000000 steps (75%)
16:10:33:WU01:FS02:0x22:Checkpoint completed at step 750000
16:14:40:WU01:FS02:0x22:Completed 760000 out of 1000000 steps (76%)
16:18:53:WU01:FS02:0x22:Completed 770000 out of 1000000 steps (77%)
16:23:05:WU01:FS02:0x22:Completed 780000 out of 1000000 steps (78%)
16:26:55:WU01:FS02:0x22:An exception occurred at step 788892: Particle coordinate is nan
16:26:55:WU01:FS02:0x22:ERROR:98: Attempting to restart from last good checkpoint by restarting core.
16:26:55:WU01:FS02:0x22:Folding@home Core Shutdown: CORE_RESTART
16:26:55:WARNING:WU01:FS02:FahCore returned: CORE_RESTART (98 = 0x62)
16:26:55:WU01:FS02:Starting
16:26:55:WU01:FS02:Running FahCore: "C:\Program Files (x86)\FAHClient/FAHCoreWrapper.exe" C:\ProgramData\FAHClient\cores/cores.foldingathome.org/win/64bit/22-0.0.13/Core_22.fah/FahCore_22.exe -dir 01 -suffix 01 -version 706 -lifeline 12688 -checkpoint 15 -opencl-platform 1 -opencl-device 0 -gpu-vendor intel -gpu 0 -gpu-usage 100
16:26:55:WU01:FS02:Started FahCore on PID 2556
16:26:55:WU01:FS02:Core PID:5628
16:26:55:WU01:FS02:FahCore 0x22 started
16:26:56:WU01:FS02:0x22:*********************** Log Started 2021-02-22T16:26:55Z ***********************
16:26:56:WU01:FS02:0x22:*************************** Core22 Folding@home Core ***************************
16:26:56:WU01:FS02:0x22:       Core: Core22
16:26:56:WU01:FS02:0x22:       Type: 0x22
16:26:56:WU01:FS02:0x22:    Version: 0.0.13
16:26:56:WU01:FS02:0x22:     Author: Joseph Coffland <joseph@cauldrondevelopment.com>
16:26:56:WU01:FS02:0x22:  Copyright: 2020 foldingathome.org
16:26:56:WU01:FS02:0x22:   Homepage: https://foldingathome.org/
16:26:56:WU01:FS02:0x22:       Date: Sep 19 2020
16:26:56:WU01:FS02:0x22:       Time: 02:35:58
16:26:56:WU01:FS02:0x22:   Revision: 571cf95de6de2c592c7c3ed48fcfb2e33e9ea7d3
16:26:56:WU01:FS02:0x22:     Branch: core22-0.0.13
16:26:56:WU01:FS02:0x22:   Compiler: Visual C++ 2015
16:26:56:WU01:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
16:26:56:WU01:FS02:0x22:             -DOPENMM_GIT_HASH="\"189320d0\""
16:26:56:WU01:FS02:0x22:   Platform: win32 10
16:26:56:WU01:FS02:0x22:       Bits: 64
16:26:56:WU01:FS02:0x22:       Mode: Release
16:26:56:WU01:FS02:0x22:Maintainers: John Chodera <john.chodera@choderalab.org> and Peter Eastman
16:26:56:WU01:FS02:0x22:             <peastman@stanford.edu>
16:26:56:WU01:FS02:0x22:       Args: -dir 01 -suffix 01 -version 706 -lifeline 2556 -checkpoint 15
16:26:56:WU01:FS02:0x22:             -opencl-platform 1 -opencl-device 0 -gpu-vendor intel -gpu 0
16:26:56:WU01:FS02:0x22:             -gpu-usage 100
16:26:56:WU01:FS02:0x22:************************************ libFAH ************************************
16:26:56:WU01:FS02:0x22:       Date: Sep 7 2020
16:26:56:WU01:FS02:0x22:       Time: 19:09:56
16:26:56:WU01:FS02:0x22:   Revision: 44301ed97b996b63fe736bb8073f22209cb2b603
16:26:56:WU01:FS02:0x22:     Branch: HEAD
16:26:56:WU01:FS02:0x22:   Compiler: Visual C++ 2015
16:26:56:WU01:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
16:26:56:WU01:FS02:0x22:   Platform: win32 10
16:26:56:WU01:FS02:0x22:       Bits: 64
16:26:56:WU01:FS02:0x22:       Mode: Release
16:26:56:WU01:FS02:0x22:************************************ CBang *************************************
16:26:56:WU01:FS02:0x22:       Date: Sep 7 2020
16:26:56:WU01:FS02:0x22:       Time: 19:08:30
16:26:56:WU01:FS02:0x22:   Revision: 33fcfc2b3ed2195a423606a264718e31e6b3903f
16:26:56:WU01:FS02:0x22:     Branch: HEAD
16:26:56:WU01:FS02:0x22:   Compiler: Visual C++ 2015
16:26:56:WU01:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
16:26:56:WU01:FS02:0x22:   Platform: win32 10
16:26:56:WU01:FS02:0x22:       Bits: 64
16:26:56:WU01:FS02:0x22:       Mode: Release
16:26:56:WU01:FS02:0x22:************************************ System ************************************
16:26:56:WU01:FS02:0x22:        CPU: Intel(R) Core(TM) i7-10510U CPU @ 1.80GHz
16:26:56:WU01:FS02:0x22:     CPU ID: GenuineIntel Family 6 Model 142 Stepping 12
16:26:56:WU01:FS02:0x22:       CPUs: 8
16:26:56:WU01:FS02:0x22:     Memory: 15.79GiB
16:26:56:WU01:FS02:0x22:Free Memory: 9.57GiB
16:26:56:WU01:FS02:0x22:    Threads: WINDOWS_THREADS
16:26:56:WU01:FS02:0x22: OS Version: 6.2
16:26:56:WU01:FS02:0x22:Has Battery: true
16:26:56:WU01:FS02:0x22: On Battery: false
16:26:56:WU01:FS02:0x22: UTC Offset: 0
16:26:56:WU01:FS02:0x22:        PID: 5628
16:26:56:WU01:FS02:0x22:        CWD: C:\ProgramData\FAHClient\work
16:26:56:WU01:FS02:0x22:************************************ OpenMM ************************************
16:26:56:WU01:FS02:0x22:   Revision: 189320d0
16:26:56:WU01:FS02:0x22:********************************************************************************
16:26:56:WU01:FS02:0x22:Project: 13439 (Run 13063, Clone 20, Gen 1)
16:26:56:WU01:FS02:0x22:Unit: 0x00000000000000000000000000000000
16:26:56:WU01:FS02:0x22:Digital signatures verified
16:26:56:WU01:FS02:0x22:Folding@home GPU Core22 Folding@home Core
16:26:56:WU01:FS02:0x22:Version 0.0.13
16:26:56:WU01:FS02:0x22:  Checkpoint write interval: 50000 steps (5%) [20 total]
16:26:56:WU01:FS02:0x22:  JSON viewer frame write interval: 10000 steps (1%) [100 total]
16:26:56:WU01:FS02:0x22:  XTC frame write interval: 250000 steps (25%) [4 total]
16:26:56:WU01:FS02:0x22:  Global context and integrator variables write interval: 25000 steps (2.5%) [40 total]
16:26:56:WU01:FS02:0x22:There are 3 platforms available.
16:26:56:WU01:FS02:0x22:Platform 0: Reference
16:26:56:WU01:FS02:0x22:Platform 1: CPU
16:26:56:WU01:FS02:0x22:Platform 2: OpenCL
16:26:56:WU01:FS02:0x22:  opencl-device 0 specified
16:26:57:WU01:FS02:0x22:Attempting to create OpenCL context:
16:26:57:WU01:FS02:0x22:  Configuring platform OpenCL
16:27:41:WU01:FS02:0x22:  Using OpenCL on platformId 1 and gpu 0
16:27:41:WU01:FS02:0x22:Completed 750000 out of 1000000 steps (75%)
16:32:08:WU01:FS02:0x22:Completed 760000 out of 1000000 steps (76%)
16:36:47:WU01:FS02:0x22:Completed 770000 out of 1000000 steps (77%)
16:41:04:WU01:FS02:0x22:Completed 780000 out of 1000000 steps (78%)
16:45:19:WU01:FS02:0x22:Completed 790000 out of 1000000 steps (79%)
Joe_H
Site Admin
Posts: 7936
Joined: Tue Apr 21, 2009 4:41 pm
Hardware configuration: Mac Pro 2.8 quad 12 GB smp4
MacBook Pro 2.9 i7 8 GB smp2
Location: W. MA

Re: red circle with stuck out tongue

Post by Joe_H »

Jonazz wrote:Would it -in theory- be possible to create WUs in the future where the Intel IGPUs and CPU fold together?
In theory this would be possible. The current Gromacs code that Core_A8 is based on includes support for using a GPU to accelerate some vector operations. This support has been tested with some discrete GPUs when Core_A8 in its early stages of development.

That said, there are some issues to be dealt with before this can be rolled out to use by F@h clients. First exact levels of OpenCL support required need to be determined and tested for. Next the client and server code will need some new code to handle this setup and usage of the hardware. For example, now the client detects the CPU and GPU separately and creates two separate folding slots. To use them together would require adjustments to the code so a single slot assigned to both hardware is able to be created.
Image

iMac 2.8 i7 12 GB smp8, Mac Pro 2.8 quad 12 GB smp6
MacBook Pro 2.9 i7 8 GB smp3
PeteHobbis
Posts: 11
Joined: Fri Feb 12, 2021 10:42 am
Location: uk

Re: red circle with stuck out tongue

Post by PeteHobbis »

PeteHobbis wrote:It just did another restart (happens at 16:26). Here's the log,
(snip)

That unit (project:13439 run:13063 clone:20 gen:1) finished successfully after its single core restart.
PeteHobbis
Posts: 11
Joined: Fri Feb 12, 2021 10:42 am
Location: uk

Re: red circle with stuck out tongue

Post by PeteHobbis »

..but the next one (Project 13439, Run 13125, Clone 23, Gen 1) has done a restart at about 16%:

Code: Select all

18:12:31:WU03:FS02:0x22:  Using OpenCL on platformId 1 and gpu 0
18:12:31:WU03:FS02:0x22:Completed 0 out of 1000000 steps (0%)
18:12:31:WU03:FS02:0x22:Checkpoint completed at step 0
18:16:30:WU03:FS02:0x22:Completed 10000 out of 1000000 steps (1%)
18:20:24:WU03:FS02:0x22:Completed 20000 out of 1000000 steps (2%)
18:24:18:WU03:FS02:0x22:Completed 30000 out of 1000000 steps (3%)
18:28:12:WU03:FS02:0x22:Completed 40000 out of 1000000 steps (4%)
18:32:13:WU03:FS02:0x22:Completed 50000 out of 1000000 steps (5%)
18:32:13:WU03:FS02:0x22:Checkpoint completed at step 50000
18:36:24:WU03:FS02:0x22:Completed 60000 out of 1000000 steps (6%)
18:40:31:WU03:FS02:0x22:Completed 70000 out of 1000000 steps (7%)
18:44:29:WU03:FS02:0x22:Completed 80000 out of 1000000 steps (8%)
18:48:46:WU03:FS02:0x22:Completed 90000 out of 1000000 steps (9%)
18:53:15:WU03:FS02:0x22:Completed 100000 out of 1000000 steps (10%)
18:53:15:WU03:FS02:0x22:Checkpoint completed at step 100000
18:57:35:WU03:FS02:0x22:Completed 110000 out of 1000000 steps (11%)
19:01:57:WU03:FS02:0x22:Completed 120000 out of 1000000 steps (12%)
19:06:14:WU03:FS02:0x22:Completed 130000 out of 1000000 steps (13%)
19:10:49:WU03:FS02:0x22:Completed 140000 out of 1000000 steps (14%)
19:15:57:WU03:FS02:0x22:Completed 150000 out of 1000000 steps (15%)
19:15:57:WU03:FS02:0x22:Checkpoint completed at step 150000
19:20:23:WU03:FS02:0x22:Completed 160000 out of 1000000 steps (16%)
19:23:51:WU03:FS02:0x22:An exception occurred at step 167667: Particle coordinate is nan
19:23:51:WU03:FS02:0x22:ERROR:98: Attempting to restart from last good checkpoint by restarting core.
19:23:51:WU03:FS02:0x22:Folding@home Core Shutdown: CORE_RESTART
19:23:51:WARNING:WU03:FS02:FahCore returned: CORE_RESTART (98 = 0x62)
19:23:52:WU03:FS02:Starting
19:23:52:WU03:FS02:Running FahCore: "C:\Program Files (x86)\FAHClient/FAHCoreWrapper.exe" C:\ProgramData\FAHClient\cores/cores.foldingathome.org/win/64bit/22-0.0.13/Core_22.fah/FahCore_22.exe -dir 03 -suffix 01 -version 706 -lifeline 12688 -checkpoint 15 -opencl-platform 1 -opencl-device 0 -gpu-vendor intel -gpu 0 -gpu-usage 100
19:23:52:WU03:FS02:Started FahCore on PID 1108
19:23:52:WU03:FS02:Core PID:13752
19:23:52:WU03:FS02:FahCore 0x22 started
19:23:52:WU03:FS02:0x22:*********************** Log Started 2021-02-22T19:23:52Z ***********************
19:23:52:WU03:FS02:0x22:*************************** Core22 Folding@home Core ***************************
19:23:52:WU03:FS02:0x22:       Core: Core22
19:23:52:WU03:FS02:0x22:       Type: 0x22
19:23:52:WU03:FS02:0x22:    Version: 0.0.13
19:23:52:WU03:FS02:0x22:     Author: Joseph Coffland <joseph@cauldrondevelopment.com>
19:23:52:WU03:FS02:0x22:  Copyright: 2020 foldingathome.org
19:23:52:WU03:FS02:0x22:   Homepage: https://foldingathome.org/
19:23:52:WU03:FS02:0x22:       Date: Sep 19 2020
19:23:52:WU03:FS02:0x22:       Time: 02:35:58
19:23:52:WU03:FS02:0x22:   Revision: 571cf95de6de2c592c7c3ed48fcfb2e33e9ea7d3
19:23:52:WU03:FS02:0x22:     Branch: core22-0.0.13
19:23:52:WU03:FS02:0x22:   Compiler: Visual C++ 2015
19:23:52:WU03:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
19:23:52:WU03:FS02:0x22:             -DOPENMM_GIT_HASH="\"189320d0\""
19:23:52:WU03:FS02:0x22:   Platform: win32 10
19:23:52:WU03:FS02:0x22:       Bits: 64
19:23:52:WU03:FS02:0x22:       Mode: Release
19:23:52:WU03:FS02:0x22:Maintainers: John Chodera <john.chodera@choderalab.org> and Peter Eastman
19:23:52:WU03:FS02:0x22:             <peastman@stanford.edu>
19:23:52:WU03:FS02:0x22:       Args: -dir 03 -suffix 01 -version 706 -lifeline 1108 -checkpoint 15
19:23:52:WU03:FS02:0x22:             -opencl-platform 1 -opencl-device 0 -gpu-vendor intel -gpu 0
19:23:52:WU03:FS02:0x22:             -gpu-usage 100
19:23:52:WU03:FS02:0x22:************************************ libFAH ************************************
19:23:52:WU03:FS02:0x22:       Date: Sep 7 2020
19:23:52:WU03:FS02:0x22:       Time: 19:09:56
19:23:52:WU03:FS02:0x22:   Revision: 44301ed97b996b63fe736bb8073f22209cb2b603
19:23:52:WU03:FS02:0x22:     Branch: HEAD
19:23:52:WU03:FS02:0x22:   Compiler: Visual C++ 2015
19:23:52:WU03:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
19:23:52:WU03:FS02:0x22:   Platform: win32 10
19:23:52:WU03:FS02:0x22:       Bits: 64
19:23:52:WU03:FS02:0x22:       Mode: Release
19:23:52:WU03:FS02:0x22:************************************ CBang *************************************
19:23:52:WU03:FS02:0x22:       Date: Sep 7 2020
19:23:52:WU03:FS02:0x22:       Time: 19:08:30
19:23:52:WU03:FS02:0x22:   Revision: 33fcfc2b3ed2195a423606a264718e31e6b3903f
19:23:52:WU03:FS02:0x22:     Branch: HEAD
19:23:52:WU03:FS02:0x22:   Compiler: Visual C++ 2015
19:23:52:WU03:FS02:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /O2 /Ob3 /Zc:throwingNew /MT
19:23:52:WU03:FS02:0x22:   Platform: win32 10
19:23:52:WU03:FS02:0x22:       Bits: 64
19:23:52:WU03:FS02:0x22:       Mode: Release
19:23:52:WU03:FS02:0x22:************************************ System ************************************
19:23:52:WU03:FS02:0x22:        CPU: Intel(R) Core(TM) i7-10510U CPU @ 1.80GHz
19:23:52:WU03:FS02:0x22:     CPU ID: GenuineIntel Family 6 Model 142 Stepping 12
19:23:52:WU03:FS02:0x22:       CPUs: 8
19:23:52:WU03:FS02:0x22:     Memory: 15.79GiB
19:23:52:WU03:FS02:0x22:Free Memory: 8.90GiB
19:23:52:WU03:FS02:0x22:    Threads: WINDOWS_THREADS
19:23:52:WU03:FS02:0x22: OS Version: 6.2
19:23:52:WU03:FS02:0x22:Has Battery: true
19:23:52:WU03:FS02:0x22: On Battery: false
19:23:52:WU03:FS02:0x22: UTC Offset: 0
19:23:52:WU03:FS02:0x22:        PID: 13752
19:23:52:WU03:FS02:0x22:        CWD: C:\ProgramData\FAHClient\work
19:23:52:WU03:FS02:0x22:************************************ OpenMM ************************************
19:23:52:WU03:FS02:0x22:   Revision: 189320d0
19:23:52:WU03:FS02:0x22:********************************************************************************
19:23:52:WU03:FS02:0x22:Project: 13439 (Run 13125, Clone 23, Gen 1)
19:23:52:WU03:FS02:0x22:Unit: 0x00000000000000000000000000000000
19:23:52:WU03:FS02:0x22:Digital signatures verified
19:23:52:WU03:FS02:0x22:Folding@home GPU Core22 Folding@home Core
19:23:52:WU03:FS02:0x22:Version 0.0.13
19:23:52:WU03:FS02:0x22:  Checkpoint write interval: 50000 steps (5%) [20 total]
19:23:52:WU03:FS02:0x22:  JSON viewer frame write interval: 10000 steps (1%) [100 total]
19:23:52:WU03:FS02:0x22:  XTC frame write interval: 250000 steps (25%) [4 total]
19:23:52:WU03:FS02:0x22:  Global context and integrator variables write interval: 25000 steps (2.5%) [40 total]
19:23:52:WU03:FS02:0x22:There are 3 platforms available.
19:23:52:WU03:FS02:0x22:Platform 0: Reference
19:23:52:WU03:FS02:0x22:Platform 1: CPU
19:23:52:WU03:FS02:0x22:Platform 2: OpenCL
19:23:52:WU03:FS02:0x22:  opencl-device 0 specified
19:23:53:WU03:FS02:0x22:Attempting to create OpenCL context:
19:23:53:WU03:FS02:0x22:  Configuring platform OpenCL
19:24:36:WU03:FS02:0x22:  Using OpenCL on platformId 1 and gpu 0
19:24:36:WU03:FS02:0x22:Completed 150000 out of 1000000 steps (15%)
19:29:10:WU03:FS02:0x22:Completed 160000 out of 1000000 steps (16%)
19:33:40:WU03:FS02:0x22:Completed 170000 out of 1000000 steps (17%)
19:37:53:WU03:FS02:0x22:Completed 180000 out of 1000000 steps (18%)
19:42:07:WU03:FS02:0x22:Completed 190000 out of 1000000 steps (19%)
Neil-B
Posts: 1996
Joined: Sun Mar 22, 2020 5:52 pm
Hardware configuration: 1: 2x Xeon E5-2697v3@2.60GHz, 512GB DDR4 LRDIMM, SSD Raid, Win10 Ent 20H2, Quadro K420 1GB, FAH 7.6.21
2: Xeon E3-1505Mv5@2.80GHz, 32GB DDR4, NVME, Win10 Pro 20H2, Quadro M1000M 2GB, FAH 7.6.21 (actually have two of these)
3: i7-960@3.20GHz, 12GB DDR3, SSD, Win10 Pro 20H2, GTX 750Ti 2GB, GTX 1080Ti 11GB, FAH 7.6.21
Location: UK

Re: red circle with stuck out tongue

Post by Neil-B »

My gut instinct is a heat issue .. are you monitoring temps? .. on dgpus that message might imply oc stability issues but on a igpu I would hazard a guess at heat related instabilities if not driver (which I think you discounted)
2x Xeon E5-2697v3, 512GB DDR4 LRDIMM, SSD Raid, W10-Ent, Quadro K420
Xeon E3-1505Mv5, 32GB DDR4, NVME, W10-Pro, Quadro M1000M
i7-960, 12GB DDR3, SSD, W10-Pro, GTX1080Ti
i9-10850K, 64GB DDR4, NVME, W11-Pro, RTX3070

(Green/Bold = Active)
PeteHobbis
Posts: 11
Joined: Fri Feb 12, 2021 10:42 am
Location: uk

Re: red circle with stuck out tongue

Post by PeteHobbis »

I haven't been; I did for a while just after I first installed F@H. Set it to monitor just now; over the last twenty minutes, the CPU cores and the CPU graphics core are all saying 69-72 C. Course, nothing's going wrong just now..
Thanks!
PeteHobbis
Posts: 11
Joined: Fri Feb 12, 2021 10:42 am
Location: uk

Re: red circle with stuck out tongue

Post by PeteHobbis »

I had another WU from project 13439 abort after a second 'particle coordinate is nan', so I set the igpu to finish; it completed that last unit successfully after one core restart. I've left the igpu paused for now.
bruce
Posts: 20824
Joined: Thu Nov 29, 2007 10:13 pm
Location: So. Cal.

Re: red circle with stuck out tongue

Post by bruce »

Jonazz wrote:Would it -in theory- be possible to create WUs in the future where the Intel IGPUs and CPU fold together?
Joe_H wrote:In theory this would be possible. The current Gromacs code that Core_A8 is based on includes support for using a GPU to accelerate some vector operations. This support has been tested with some discrete GPUs when Core_A8 in its early stages of development.

That said, there are some issues to be dealt with before this can be rolled out to use by F@h clients. First exact levels of OpenCL support required need to be determined and tested for. Next the client and server code will need some new code to handle this setup and usage of the hardware. For example, now the client detects the CPU and GPU separately and creates two separate folding slots. To use them together would require adjustments to the code so a single slot assigned to both hardware is able to be created.
Using the iGPU concurrently with the CPU (whether on the same WU or on different WUs :!: ) would compound the potential for heat dissipation issues. While I'm in favor of continuing development of the concept of using both features on a single WU, all the heat from both devices ends up going through a potentially weak common path to air. We can expect to see more instabilities on overheated CPU-iGPU devices due to a weak heatsink.
Last edited by bruce on Wed Feb 24, 2021 5:44 pm, edited 1 time in total.
Reason: Corrected spelling ... Was dGPU; Is iGPU (in last sentence.)
void
Posts: 9
Joined: Tue Feb 09, 2021 7:34 am

Re: red circle with stuck out tongue

Post by void »

Jonazz wrote:
bruce wrote:FACTS:
The Intel iGPs are extremely slow compared to other GPUs. Also if you also fold with a CPU slot, it will slow down, increasing your total throughput only slightly. In other words, don't expect much.

Speed it really important to FAH projects and slow GPUs do slow down the whole project. Therefore assignments to your iGP will often be throttled. There may or may not be specific projects that will benefit from assigning WUs to Intel iGPs.
Would it -in theory- be possible to create WUs in the future where the Intel IGPUs and CPU fold together?
It is possible to not waste CPU time to service (i)GPU but it requires some efforts from Folding@home developers. CPU+iGPU is more efficient than CPU only. I have posted details and sample source code here.
void
Posts: 9
Joined: Tue Feb 09, 2021 7:34 am

Re: red circle with stuck out tongue

Post by void »

bruce wrote:Using the iGPU concurrently with the CPU (whether on the same WU or on different WUs :!: ) would compound the potential for heat dissipation issues.
Modern CPUs automatically adjust CPU/iGPU frequencies to achieve desired TDP. Please see my benchmarks at the link above (that's distributed.net client but idea is the same). Performance improves, power consumption (heat dissipation) does not increase.
bruce wrote:While I'm in favor of continuing development of the concept of using both features on a single WU, all the heat from both devices ends up going through a potentially weak common path to air. We can expect to see more instabilities on overheated CPU-dGPU devices due to a weak heatsink.
dGPU?
bruce
Posts: 20824
Joined: Thu Nov 29, 2007 10:13 pm
Location: So. Cal.

Re: red circle with stuck out tongue

Post by bruce »

No. it should say iGPU. Corrected in the original post but not in your quote of it.
Ale_F
Posts: 3
Joined: Sun Mar 07, 2021 9:13 am

Re: red circle with stuck out tongue

Post by Ale_F »

I tried to use iGPU on my i7100. All works fine. Compared to CPU only, I found that the improvement is near zero because the iGPU works at max 5% (which is not related to FAH).
I removed the gpu-beta option, but at restart the red tongue remain. Interestingly, if I check on FAH Control, slowly, but the slot is folding and a CPU core is busy.

So, what is the system to remove totally the red tongue and move the CPU slot to fold... a real CPU WU (like the other two cores)?
bruce
Posts: 20824
Joined: Thu Nov 29, 2007 10:13 pm
Location: So. Cal.

Re: red circle with stuck out tongue

Post by bruce »

One possibilitY: see my reply here

It really helps if you include the beginning of the log. (It saves a lot of guessing.)
Post Reply