AMD RX570 Constantly Sending/Downloading Incomplete WU

[alxbelu]

I've got an R9 290x (matching GPU-Z Device ID):
0x1002:0x67b0:1:5:Hawaii [Radeon R9 200/300X Series]

I've seen the following projects fail: 11746, 11747, 11752, 11759, 11764, 11776, 11781, 14533.
But it's worth noting that I have also never been assigned the only other GPU projects that are also >165k atoms: 11753, 11758, 11770. (i.e. I suspect these would also fail)

[bruce]

My hunch is that AMD may have shot themselves in the foot by releasing so many different GPU genrations with the same binary code identifying the drivers.

This problem has been escalated to the OpenMM developers.

[geokilla]

I have an ASUS RX570 4GB (Hynix) clocked at 1300/1750 with the Device ID 1002 67DF - 1043 04C2. According to the log, seems like Project 11747, 11764, and 11776 were the ones that gave me an error overnight.

Code: Select all

05:34:07:WU00:FS01:0x22:*********************** Log Started 2020-03-23T05:34:06Z ***********************
05:34:07:WU00:FS01:0x22:*************************** Core22 Folding@home Core ***************************
05:34:07:WU00:FS01:0x22:       Type: 0x22
05:34:07:WU00:FS01:0x22:       Core: Core22
05:34:07:WU00:FS01:0x22:    Website: https://foldingathome.org/
05:34:07:WU00:FS01:0x22:  Copyright: (c) 2009-2018 foldingathome.org
05:34:07:WU00:FS01:0x22:     Author: John Chodera <john.chodera@choderalab.org> and Rafal Wiewiora
05:34:07:WU00:FS01:0x22:             <rafal.wiewiora@choderalab.org>
05:34:07:WU00:FS01:0x22:       Args: -dir 00 -suffix 01 -version 705 -lifeline 7968 -checkpoint 15
05:34:07:WU00:FS01:0x22:             -gpu-vendor amd -opencl-platform 0 -opencl-device 0 -gpu 0
05:34:07:WU00:FS01:0x22:     Config: <none>
05:34:07:WU00:FS01:0x22:************************************ Build *************************************
05:34:07:WU00:FS01:0x22:    Version: 0.0.2
05:34:07:WU00:FS01:0x22:       Date: Dec 6 2019
05:34:07:WU00:FS01:0x22:       Time: 21:30:31
05:34:07:WU00:FS01:0x22: Repository: Git
05:34:07:WU00:FS01:0x22:   Revision: abeb39247cc72df5af0f63723edafadb23d5dfbe
05:34:07:WU00:FS01:0x22:     Branch: HEAD
05:34:07:WU00:FS01:0x22:   Compiler: Visual C++ 2008
05:34:07:WU00:FS01:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /Ox /MT
05:34:07:WU00:FS01:0x22:   Platform: win32 10
05:34:07:WU00:FS01:0x22:       Bits: 64
05:34:07:WU00:FS01:0x22:       Mode: Release
05:34:07:WU00:FS01:0x22:************************************ System ************************************
05:34:07:WU00:FS01:0x22:        CPU: Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
05:34:07:WU00:FS01:0x22:     CPU ID: GenuineIntel Family 6 Model 58 Stepping 9
05:34:07:WU00:FS01:0x22:       CPUs: 4
05:34:07:WU00:FS01:0x22:     Memory: 15.96GiB
05:34:07:WU00:FS01:0x22:Free Memory: 13.59GiB
05:34:07:WU00:FS01:0x22:    Threads: WINDOWS_THREADS
05:34:07:WU00:FS01:0x22: OS Version: 6.2
05:34:07:WU00:FS01:0x22:Has Battery: false
05:34:07:WU00:FS01:0x22: On Battery: false
05:34:07:WU00:FS01:0x22: UTC Offset: -4
05:34:07:WU00:FS01:0x22:        PID: 3620
05:34:07:WU00:FS01:0x22:        CWD: C:\Users\Vernon\AppData\Roaming\FAHClient\work
05:34:07:WU00:FS01:0x22:         OS: Windows 10 Home
05:34:07:WU00:FS01:0x22:    OS Arch: AMD64
05:34:07:WU00:FS01:0x22:********************************************************************************
05:34:07:WU00:FS01:0x22:Project: 11776 (Run 0, Clone 9859, Gen 1)
05:34:07:WU00:FS01:0x22:Unit: 0x00000004287234c95e7433609d1c1f05
05:34:07:WU00:FS01:0x22:Reading tar file core.xml
05:34:07:WU00:FS01:0x22:Reading tar file integrator.xml
05:34:07:WU00:FS01:0x22:Reading tar file state.xml
05:34:07:WU00:FS01:0x22:Reading tar file system.xml
05:34:08:WU00:FS01:0x22:Digital signatures verified
05:34:08:WU00:FS01:0x22:Folding@home GPU Core22 Folding@home Core
05:34:08:WU00:FS01:0x22:Version 0.0.2
05:34:21:WU00:FS01:0x22:ERROR:exception: Error invoking kernel sortShortList: clEnqueueNDRangeKernel (-5)
05:34:21:WU00:FS01:0x22:Saving result file ..\logfile_01.txt
05:34:21:WU00:FS01:0x22:Saving result file science.log
05:34:21:WU00:FS01:0x22:Folding@home Core Shutdown: BAD_WORK_UNIT
05:34:21:WARNING:WU00:FS01:FahCore returned: BAD_WORK_UNIT (114 = 0x72)
05:34:21:WU00:FS01:Sending unit results: id:00 state:SEND error:FAULTY project:11776 run:0 clone:9859 gen:1 core:0x22 unit:0x00000004287234c95e7433609d1c1f05
05:34:21:WU00:FS01:Uploading 8.00KiB to 40.114.52.201
05:34:21:WU00:FS01:Connecting to 40.114.52.201:8080
05:34:22:WU02:FS01:Connecting to 65.254.110.245:8080
05:34:22:WARNING:WU02:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:34:22:WU02:FS01:Connecting to 18.218.241.186:80
05:34:22:WARNING:WU02:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:34:22:ERROR:WU02:FS01:Exception: Could not get an assignment
05:34:22:WU02:FS01:Connecting to 65.254.110.245:8080
05:34:22:WARNING:WU02:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:34:22:WU02:FS01:Connecting to 18.218.241.186:80
05:34:22:WARNING:WU02:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:34:22:ERROR:WU02:FS01:Exception: Could not get an assignment
05:34:42:WARNING:WU00:FS01:WorkServer connection failed on port 8080 trying 80
05:34:42:WU00:FS01:Connecting to 40.114.52.201:80
05:34:45:WU00:FS01:Upload 100.00%
05:35:22:WU02:FS01:Connecting to 65.254.110.245:8080
05:35:22:WARNING:WU02:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:35:22:WU02:FS01:Connecting to 18.218.241.186:80
05:35:22:WARNING:WU02:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:35:22:ERROR:WU02:FS01:Exception: Could not get an assignment
05:35:47:WU00:FS01:Upload complete
05:35:47:WU00:FS01:Server responded WORK_ACK (400)
05:35:47:WU00:FS01:Cleaning up
05:36:59:WU02:FS01:Connecting to 65.254.110.245:8080
05:36:59:WARNING:WU02:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:36:59:WU02:FS01:Connecting to 18.218.241.186:80
05:37:00:WU02:FS01:Assigned to work server 140.163.4.231
05:37:00:WU02:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 140.163.4.231
05:37:00:WU02:FS01:Connecting to 140.163.4.231:8080
05:39:00:WU02:FS01:Downloading 11.98MiB
05:39:07:WU02:FS01:Download 28.70%
05:39:13:WU02:FS01:Download 39.66%
05:39:19:WU02:FS01:Download 51.66%
05:39:25:WU02:FS01:Download 95.49%
05:39:25:WU02:FS01:Download complete
05:39:25:WU02:FS01:Received Unit: id:02 state:DOWNLOAD error:NO_ERROR project:11747 run:0 clone:319 gen:6 core:0x22 unit:0x000000138ca304e75e6a7fc6814b8a0b
05:39:25:WU02:FS01:Starting
05:39:25:WU02:FS01:Running FahCore: "C:\Program Files (x86)\FAHClient/FAHCoreWrapper.exe" C:\Users\Vernon\AppData\Roaming\FAHClient\cores/cores.foldingathome.org/v7/win/64bit/Core_22.fah/FahCore_22.exe -dir 02 -suffix 01 -version 705 -lifeline 1692 -checkpoint 15 -gpu-vendor amd -opencl-platform 0 -opencl-device 0 -gpu 0
05:39:25:WU02:FS01:Started FahCore on PID 6204
05:39:25:WU02:FS01:Core PID:6128
05:39:25:WU02:FS01:FahCore 0x22 started
05:39:26:WU02:FS01:0x22:*********************** Log Started 2020-03-23T05:39:25Z ***********************
05:39:26:WU02:FS01:0x22:*************************** Core22 Folding@home Core ***************************
05:39:26:WU02:FS01:0x22:       Type: 0x22
05:39:26:WU02:FS01:0x22:       Core: Core22
05:39:26:WU02:FS01:0x22:    Website: https://foldingathome.org/
05:39:26:WU02:FS01:0x22:  Copyright: (c) 2009-2018 foldingathome.org
05:39:26:WU02:FS01:0x22:     Author: John Chodera <john.chodera@choderalab.org> and Rafal Wiewiora
05:39:26:WU02:FS01:0x22:             <rafal.wiewiora@choderalab.org>
05:39:26:WU02:FS01:0x22:       Args: -dir 02 -suffix 01 -version 705 -lifeline 6204 -checkpoint 15
05:39:26:WU02:FS01:0x22:             -gpu-vendor amd -opencl-platform 0 -opencl-device 0 -gpu 0
05:39:26:WU02:FS01:0x22:     Config: <none>
05:39:26:WU02:FS01:0x22:************************************ Build *************************************
05:39:26:WU02:FS01:0x22:    Version: 0.0.2
05:39:26:WU02:FS01:0x22:       Date: Dec 6 2019
05:39:26:WU02:FS01:0x22:       Time: 21:30:31
05:39:26:WU02:FS01:0x22: Repository: Git
05:39:26:WU02:FS01:0x22:   Revision: abeb39247cc72df5af0f63723edafadb23d5dfbe
05:39:26:WU02:FS01:0x22:     Branch: HEAD
05:39:26:WU02:FS01:0x22:   Compiler: Visual C++ 2008
05:39:26:WU02:FS01:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /Ox /MT
05:39:26:WU02:FS01:0x22:   Platform: win32 10
05:39:26:WU02:FS01:0x22:       Bits: 64
05:39:26:WU02:FS01:0x22:       Mode: Release
05:39:26:WU02:FS01:0x22:************************************ System ************************************
05:39:26:WU02:FS01:0x22:        CPU: Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
05:39:26:WU02:FS01:0x22:     CPU ID: GenuineIntel Family 6 Model 58 Stepping 9
05:39:26:WU02:FS01:0x22:       CPUs: 4
05:39:26:WU02:FS01:0x22:     Memory: 15.96GiB
05:39:26:WU02:FS01:0x22:Free Memory: 13.64GiB
05:39:26:WU02:FS01:0x22:    Threads: WINDOWS_THREADS
05:39:26:WU02:FS01:0x22: OS Version: 6.2
05:39:26:WU02:FS01:0x22:Has Battery: false
05:39:26:WU02:FS01:0x22: On Battery: false
05:39:26:WU02:FS01:0x22: UTC Offset: -4
05:39:26:WU02:FS01:0x22:        PID: 6128
05:39:26:WU02:FS01:0x22:        CWD: C:\Users\Vernon\AppData\Roaming\FAHClient\work
05:39:26:WU02:FS01:0x22:         OS: Windows 10 Home
05:39:26:WU02:FS01:0x22:    OS Arch: AMD64
05:39:26:WU02:FS01:0x22:********************************************************************************
05:39:26:WU02:FS01:0x22:Project: 11747 (Run 0, Clone 319, Gen 6)
05:39:26:WU02:FS01:0x22:Unit: 0x000000138ca304e75e6a7fc6814b8a0b
05:39:26:WU02:FS01:0x22:Reading tar file core.xml
05:39:26:WU02:FS01:0x22:Reading tar file integrator.xml
05:39:26:WU02:FS01:0x22:Reading tar file state.xml
05:39:27:WU02:FS01:0x22:Reading tar file system.xml
05:39:29:WU02:FS01:0x22:Digital signatures verified
05:39:29:WU02:FS01:0x22:Folding@home GPU Core22 Folding@home Core
05:39:29:WU02:FS01:0x22:Version 0.0.2
05:39:41:WU02:FS01:0x22:ERROR:exception: Error invoking kernel sortShortList: clEnqueueNDRangeKernel (-5)
05:39:41:WU02:FS01:0x22:Saving result file ..\logfile_01.txt
05:39:41:WU02:FS01:0x22:Saving result file science.log
05:39:41:WU02:FS01:0x22:Folding@home Core Shutdown: BAD_WORK_UNIT
05:39:42:WARNING:WU02:FS01:FahCore returned: BAD_WORK_UNIT (114 = 0x72)
05:39:42:WU02:FS01:Sending unit results: id:02 state:SEND error:FAULTY project:11747 run:0 clone:319 gen:6 core:0x22 unit:0x000000138ca304e75e6a7fc6814b8a0b
05:39:42:WU02:FS01:Uploading 2.62KiB to 140.163.4.231
05:39:42:WU02:FS01:Connecting to 140.163.4.231:8080
05:39:42:WU00:FS01:Connecting to 65.254.110.245:8080
05:39:42:WARNING:WU00:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:39:42:WU00:FS01:Connecting to 18.218.241.186:80
05:39:42:WARNING:WU00:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:39:42:ERROR:WU00:FS01:Exception: Could not get an assignment
05:39:43:WU00:FS01:Connecting to 65.254.110.245:8080
05:39:43:WU00:FS01:Assigned to work server 140.163.4.241
05:39:43:WU00:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 140.163.4.241
05:39:43:WU00:FS01:Connecting to 140.163.4.241:8080
05:41:02:ERROR:WU00:FS01:Exception: 10002: Received short response, expected 512 bytes, got 0
05:41:02:WU00:FS01:Connecting to 65.254.110.245:8080
05:41:02:WARNING:WU00:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:41:02:WU00:FS01:Connecting to 18.218.241.186:80
05:41:03:WU00:FS01:Assigned to work server 40.114.52.201
05:41:03:WU00:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 40.114.52.201
05:41:03:WU00:FS01:Connecting to 40.114.52.201:8080
05:41:04:WU02:FS01:Upload complete
05:41:04:WU02:FS01:Server responded WORK_ACK (400)
05:41:04:WU02:FS01:Cleaning up
05:41:24:WARNING:WU00:FS01:WorkServer connection failed on port 8080 trying 80
05:41:24:WU00:FS01:Connecting to 40.114.52.201:80
05:41:45:ERROR:WU00:FS01:Exception: Failed to connect to 40.114.52.201:80: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.
05:42:39:WU00:FS01:Connecting to 65.254.110.245:8080
05:42:39:WARNING:WU00:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:42:39:WU00:FS01:Connecting to 18.218.241.186:80
05:42:39:WARNING:WU00:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:42:39:ERROR:WU00:FS01:Exception: Could not get an assignment
05:45:16:WU00:FS01:Connecting to 65.254.110.245:8080
05:45:17:WARNING:WU00:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:45:17:WU00:FS01:Connecting to 18.218.241.186:80
05:45:17:WU00:FS01:Assigned to work server 40.114.52.201
05:45:17:WU00:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 40.114.52.201
05:45:17:WU00:FS01:Connecting to 40.114.52.201:8080
05:45:38:WARNING:WU00:FS01:WorkServer connection failed on port 8080 trying 80
05:45:38:WU00:FS01:Connecting to 40.114.52.201:80
05:45:59:ERROR:WU00:FS01:Exception: Failed to connect to 40.114.52.201:80: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.
05:49:31:WU00:FS01:Connecting to 65.254.110.245:8080
05:49:31:WARNING:WU00:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:49:31:WU00:FS01:Connecting to 18.218.241.186:80
05:49:31:WU00:FS01:Assigned to work server 128.252.203.10
05:49:31:WU00:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 128.252.203.10
05:49:31:WU00:FS01:Connecting to 128.252.203.10:8080
05:49:48:WU01:FS00:Connecting to 65.254.110.245:8080
05:49:48:WARNING:WU01:FS00:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:49:48:WU01:FS00:Connecting to 18.218.241.186:80
05:49:48:WARNING:WU01:FS00:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:49:48:ERROR:WU01:FS00:Exception: Could not get an assignment
05:49:52:WARNING:WU00:FS01:WorkServer connection failed on port 8080 trying 80
05:49:52:WU00:FS01:Connecting to 128.252.203.10:80
05:50:13:ERROR:WU00:FS01:Exception: Failed to connect to 128.252.203.10:80: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond.
05:56:22:WU00:FS01:Connecting to 65.254.110.245:8080
05:56:22:WARNING:WU00:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
05:56:22:WU00:FS01:Connecting to 18.218.241.186:80
05:56:22:WARNING:WU00:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
05:56:22:ERROR:WU00:FS01:Exception: Could not get an assignment
06:07:28:WU00:FS01:Connecting to 65.254.110.245:8080
06:07:28:WU00:FS01:Assigned to work server 128.252.203.10
06:07:28:WU00:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 128.252.203.10
06:07:28:WU00:FS01:Connecting to 128.252.203.10:8080
06:08:05:WU00:FS01:Downloading 86.24MiB
06:08:11:WU00:FS01:Download 90.31%
06:08:12:WU00:FS01:Download complete
06:08:12:WU00:FS01:Received Unit: id:00 state:DOWNLOAD error:NO_ERROR project:11764 run:0 clone:2799 gen:14 core:0x22 unit:0x0000001380fccb0a5e6d84c71dbe84f7
06:08:12:WU00:FS01:Starting
06:08:12:WU00:FS01:Running FahCore: "C:\Program Files (x86)\FAHClient/FAHCoreWrapper.exe" C:\Users\Vernon\AppData\Roaming\FAHClient\cores/cores.foldingathome.org/v7/win/64bit/Core_22.fah/FahCore_22.exe -dir 00 -suffix 01 -version 705 -lifeline 1692 -checkpoint 15 -gpu-vendor amd -opencl-platform 0 -opencl-device 0 -gpu 0
06:08:12:WU00:FS01:Started FahCore on PID 1188
06:08:12:WU00:FS01:Core PID:8080
06:08:12:WU00:FS01:FahCore 0x22 started
06:08:13:WU00:FS01:0x22:*********************** Log Started 2020-03-23T06:08:12Z ***********************
06:08:13:WU00:FS01:0x22:*************************** Core22 Folding@home Core ***************************
06:08:13:WU00:FS01:0x22:       Type: 0x22
06:08:13:WU00:FS01:0x22:       Core: Core22
06:08:13:WU00:FS01:0x22:    Website: https://foldingathome.org/
06:08:13:WU00:FS01:0x22:  Copyright: (c) 2009-2018 foldingathome.org
06:08:13:WU00:FS01:0x22:     Author: John Chodera <john.chodera@choderalab.org> and Rafal Wiewiora
06:08:13:WU00:FS01:0x22:             <rafal.wiewiora@choderalab.org>
06:08:13:WU00:FS01:0x22:       Args: -dir 00 -suffix 01 -version 705 -lifeline 1188 -checkpoint 15
06:08:13:WU00:FS01:0x22:             -gpu-vendor amd -opencl-platform 0 -opencl-device 0 -gpu 0
06:08:13:WU00:FS01:0x22:     Config: <none>
06:08:13:WU00:FS01:0x22:************************************ Build *************************************
06:08:13:WU00:FS01:0x22:    Version: 0.0.2
06:08:13:WU00:FS01:0x22:       Date: Dec 6 2019
06:08:13:WU00:FS01:0x22:       Time: 21:30:31
06:08:13:WU00:FS01:0x22: Repository: Git
06:08:13:WU00:FS01:0x22:   Revision: abeb39247cc72df5af0f63723edafadb23d5dfbe
06:08:13:WU00:FS01:0x22:     Branch: HEAD
06:08:13:WU00:FS01:0x22:   Compiler: Visual C++ 2008
06:08:13:WU00:FS01:0x22:    Options: /TP /nologo /EHa /wd4297 /wd4103 /Ox /MT
06:08:13:WU00:FS01:0x22:   Platform: win32 10
06:08:13:WU00:FS01:0x22:       Bits: 64
06:08:13:WU00:FS01:0x22:       Mode: Release
06:08:13:WU00:FS01:0x22:************************************ System ************************************
06:08:13:WU00:FS01:0x22:        CPU: Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
06:08:13:WU00:FS01:0x22:     CPU ID: GenuineIntel Family 6 Model 58 Stepping 9
06:08:13:WU00:FS01:0x22:       CPUs: 4
06:08:13:WU00:FS01:0x22:     Memory: 15.96GiB
06:08:13:WU00:FS01:0x22:Free Memory: 13.57GiB
06:08:13:WU00:FS01:0x22:    Threads: WINDOWS_THREADS
06:08:13:WU00:FS01:0x22: OS Version: 6.2
06:08:13:WU00:FS01:0x22:Has Battery: false
06:08:13:WU00:FS01:0x22: On Battery: false
06:08:13:WU00:FS01:0x22: UTC Offset: -4
06:08:13:WU00:FS01:0x22:        PID: 8080
06:08:13:WU00:FS01:0x22:        CWD: C:\Users\Vernon\AppData\Roaming\FAHClient\work
06:08:13:WU00:FS01:0x22:         OS: Windows 10 Home
06:08:13:WU00:FS01:0x22:    OS Arch: AMD64
06:08:13:WU00:FS01:0x22:********************************************************************************
06:08:13:WU00:FS01:0x22:Project: 11764 (Run 0, Clone 2799, Gen 14)
06:08:13:WU00:FS01:0x22:Unit: 0x0000001380fccb0a5e6d84c71dbe84f7
06:08:13:WU00:FS01:0x22:Reading tar file core.xml
06:08:13:WU00:FS01:0x22:Reading tar file integrator.xml
06:08:13:WU00:FS01:0x22:Reading tar file state.xml
06:08:13:WU00:FS01:0x22:Reading tar file system.xml
06:08:14:WU00:FS01:0x22:Digital signatures verified
06:08:14:WU00:FS01:0x22:Folding@home GPU Core22 Folding@home Core
06:08:14:WU00:FS01:0x22:Version 0.0.2
06:08:28:WU00:FS01:0x22:ERROR:exception: Error invoking kernel sortShortList: clEnqueueNDRangeKernel (-5)
06:08:28:WU00:FS01:0x22:Saving result file ..\logfile_01.txt
06:08:28:WU00:FS01:0x22:Saving result file science.log
06:08:28:WU00:FS01:0x22:Folding@home Core Shutdown: BAD_WORK_UNIT
06:08:28:WARNING:WU00:FS01:FahCore returned: BAD_WORK_UNIT (114 = 0x72)
06:08:28:WU00:FS01:Sending unit results: id:00 state:SEND error:FAULTY project:11764 run:0 clone:2799 gen:14 core:0x22 unit:0x0000001380fccb0a5e6d84c71dbe84f7
06:08:28:WU00:FS01:Uploading 8.00KiB to 128.252.203.10
06:08:28:WU00:FS01:Connecting to 128.252.203.10:8080
06:08:29:WU02:FS01:Connecting to 65.254.110.245:8080
06:08:29:WU02:FS01:Assigned to work server 128.252.203.10
06:08:29:WU02:FS01:Requesting new work unit for slot 01: READY gpu:0:Ellesmere XT [Radeon RX 470/480/570/580] from 128.252.203.10
06:08:29:WU02:FS01:Connecting to 128.252.203.10:8080
06:08:49:WARNING:WU00:FS01:WorkServer connection failed on port 8080 trying 80
06:08:49:WU00:FS01:Connecting to 128.252.203.10:80
06:08:49:WU00:FS01:Upload 100.00%
06:08:50:WARNING:WU02:FS01:WorkServer connection failed on port 8080 trying 80
06:08:50:WU02:FS01:Connecting to 128.252.203.10:80
06:09:11:ERROR:WU02:FS01:Exception: 10002: Received short response, expected 512 bytes, got 0
06:09:12:WU02:FS01:Connecting to 65.254.110.245:8080
06:09:12:WARNING:WU02:FS01:Failed to get assignment from '65.254.110.245:8080': No WUs available for this configuration
06:09:12:WU02:FS01:Connecting to 18.218.241.186:80
06:09:12:WARNING:WU02:FS01:Failed to get assignment from '18.218.241.186:80': No WUs available for this configuration
06:09:12:ERROR:WU02:FS01:Exception: Could not get an assignment
06:09:26:WU00:FS01:Upload complete
06:09:26:WU00:FS01:Server responded WORK_ACK (400)
06:09:26:WU00:FS01:Cleaning up

[DarkFoss]

I've got an R9 290x (matching GPU-Z Device ID):
0x1002:0x67b0:1:5:Hawaii [Radeon R9 200/300X Series]
I've seen the following projects fail: 11746, 11747, 11752, 11759, 11764, 11776, 11781, 14533.
But it's worth noting that I have also never been assigned the only other GPU projects that are also >165k atoms: 11753, 11758, 11770. (i.e. I suspect these would also fail)

I've had 11741 and 11753 fail as well as the ones you have. I haven't seen 11758, 11770 either.
Only drivers I have used are 20.2.2 and 20.3.1. R9 Fury X. I wonder if more than 4gb of vram is required for wu's 165k and up?

[MrFrizzy]

Just to add to this discussion, I have a 5700 XT and have had no failures on any of the projects mentioned in this thread except for 14551 (which gave a different error: viewtopic.php?f=66&t=32825). I have had p14533 process all the way through and send the results to the server only to have the server dump the results, but no errors in the client side. Perhaps the source of the error isn't present on Navi cards?

Successful projects (tracked in the spreadsheet in my sig): 11741-11752, 11755, 11759, 11762-11764, 11776-11778, 11780, 11781

Driver: 20.2.2

Similar post here: viewtopic.php?f=74&t=32991

[geokilla]

I've got an R9 290x (matching GPU-Z Device ID):
0x1002:0x67b0:1:5:Hawaii [Radeon R9 200/300X Series]
I've seen the following projects fail: 11746, 11747, 11752, 11759, 11764, 11776, 11781, 14533.
But it's worth noting that I have also never been assigned the only other GPU projects that are also >165k atoms: 11753, 11758, 11770. (i.e. I suspect these would also fail)

I've had 11741 and 11753 fail as well as the ones you have. I haven't seen 11758, 11770 either.
Only drivers I have used are 20.2.2 and 20.3.1. R9 Fury X. I wonder if more than 4gb of vram is required for wu's 165k and up?

I don't think it's a VRAM issue. But it's hard to say since I haven't received any GPU projects all day.

Finally got Project 11751 (Run 0, Clone 6654, Gen 10) running right now. It ha 1,000,000 steps, with my RX570 4GB now running at 1400/1900. According to GPU-Z, the dedicated memory (VRAM?) used is under 1GB. Keep in mind I'm opening various Windows too.

Earlier today I got the following in my log:

Code: Select all

Project 11764 (Run 0, Clone 6426, Gen 12)
ERROR:exception: Error invoking kernel sortShortList: clEnqueueNDRangeKernel (-5)
Folding@home Core Shutdown: BAD_WORK_UNIT
FahCore returned: BAD_WORK_UNIT (114 = 0x72)
Sending unit results: id:01 state:SEND error:FAULTY project:11764 run:0 clone:6426 gen:12 core:0x22 unit:0x0000000f80fccb0a5e71130162f1be76

Edit: Now running Project: 11757 (Run 0, Clone 1927, Gen 27) and so far so good. Dedicated memory (VRAM?) usage is 1.1GB.

[JiiPee]

My hunch is that AMD may have shot themselves in the foot by releasing so many different GPU genrations with the same binary code identifying the drivers.

This problem has been escalated to the OpenMM developers.

No they haven't. 470/480/570/580/590 are all polaris cards and based exactly same GPU. They are like Intel desktop CPU's what has been refreshed now many years, only providing little more clock, nothing else.
Same story with some lower tier polaris cards.

So basicly 480 and 580 are exactly same card, 580 just have higher clocks and 590 is same card, it's made with new node but it's still exactly same card, new node just allowed them to push clocks even higher.

[Joe_H]

No, they are not all Polaris cards, the 470 and 480 are Ellesmere. But even if they were, the details of the implementation are enough different between them that it makes a lot of difference in how some code interacts with them. And as you mention, the 590 is even based on a different chip from the 570/580.

Basically your argument is that they are all the same, and the details do not bear that out. Functionally for displaying video they may appear identical, but compute usage may depend on other details that do matter.

[geokilla]

My hunch is that AMD may have shot themselves in the foot by releasing so many different GPU generations with the same binary code identifying the drivers.

This problem has been escalated to the OpenMM developers.

No they haven't. 470/480/570/580/590 are all polaris cards and based exactly same GPU. They are like Intel desktop CPU's what has been refreshed now many years, only providing little more clock, nothing else.
Same story with some lower tier polaris cards.

So basically 480 and 580 are exactly same card, 580 just have higher clocks and 590 is same card, it's made with new node but it's still exactly same card, new node just allowed them to push clocks even higher.

This person is correct. The RX480 and RX580 are basically overclocked versions of their predecessors. That's why a lot of people flash their RX480 and RX470 with their successors BIOS, to access more free performance.

See this review on AnandTech covering the launch of the RX580 and RX570.

At the high end is AMD’s new midrange contender, the Radeon RX 580. Like the RX 480 before it, this is a fully enabled Polaris 10 GPU.

Joining the RX 580 in today’s launch is the Radeon RX 570. Like its more powerful sibling, this is an enhanced version of its RX 400 series predecessor, the RX 470. We’re looking at the same cut-down Polaris 10 GPU with 32 of 36 CUs enabled, but again clockspeeds are increased.

Basically, the RX580 and RX570 are considered Polaris 20, while RX470 and RX480 are considered Polaris 10.

[JiiPee]

No, they are not all Polaris cards, the 470 and 480 are Ellesmere. But even if they were, the details of the implementation are enough different between them that it makes a lot of difference in how some code interacts with them. And as you mention, the 590 is even based on a different chip from the 570/580.

Basically your argument is that they are all the same, and the details do not bear that out. Functionally for displaying video they may appear identical, but compute usage may depend on other details that do matter.

And Ellesmere = Polaris 10.

Like other person already said, you can flash 580 bios to 480 card.
590 is Polaris 30
570/580 is Polaris 20
470/480 is Polaris 10

And Polaris 20 & 30 are just Polaris 10 refresh. 590 is made on GloFo 12nm node but it use same mask as 580. AMD just had to release something on that year and they came up with this 590.
All thouse chips are exactly same size 232mm2 and using exactly same count of transistors 5,7billions.

If you wonder whats difference witn GloFo 14nm and 12nm node, they are about same and clients can use 14nm masks on 12nm node.

https://fuse.wikichip.org/news/1497/vls ... ance-12lp/

GlobalFoundries 12LP (12nm Leading-Performance) is a full platform extension of their 14LPP process. What this means is that for the most part, GlobalFoundries 14nm platform is compatible with 12LP. GlobalFoundries has also widened their platform offering to a number of other key sectors including the automotive industry with automotive grade 2 compliant fabs and a wider portfolio of RF IPs.

In order to introduce improvements while minimizing design rework, GlobalFoundries kept the design rules pretty much the same.

[gmez]

I'm not convinced that this is an AMD only Gpu issue. Although I have an RX 570 and have experienced this myself, when I go and look and my work units that fail under the WU status I notice that both other AMD and NVIDIA gpus have sometimes attempted those work units and also failed.

[MrFrizzy]

I'm not convinced that this is an AMD only Gpu issue. Although I have an RX 570 and have experienced this myself, when I go and look and my work units that fail under the WU status I notice that both other AMD and NVIDIA gpus have sometimes attempted those work units and also failed.

Can you post logs from any of those projects running on nVidia hardware and showing the specific error: "Error invoking kernel sortShortList: clEnqueueNDRangeKernel (-5)"? I have not seen any reports of nVidia cards experiencing this issue, only GCN based AMD cards (Navi works fine).

[_r2w_ben]

I'm not convinced that this is an AMD only Gpu issue. Although I have an RX 570 and have experienced this myself, when I go and look and my work units that fail under the WU status I notice that both other AMD and NVIDIA gpus have sometimes attempted those work units and also failed.

Based on my research, it could happen on nVidia hardware as well. It's less likely but could occur if a work unit was using double precision. FAH normally uses single or mixed precision for GPU work units.

I looked up specs on cards going back to the 6x0 series on CompuBench. (The site is slow but the Info tab for a card lists a lot of OpenCL variables.) These cards all appear to have a CL_DEVICE_LOCAL_MEM_SIZE of 48KB. GCN cards have 32KB and Navi bumped that value to 64KB.