Beignet: self-test failed: (3, 7, 5) + (5, 7, 3) returned (6, 7, 5) on Linux 4.9.92 with a i7-8550U
EDIT: Filled issue on their Gitlab: https://gitlab.freedesktop.org/beignet/beignet/issues/80
When running Davinci Resolve on Manjaro Linux with Kernel 4.9.92-1 on my new Dell XPS 13 9370 with the Intel i7-8550U w/620 graphics, I get the following issue:
Intel i7-8550U Intel UHD Graphics 620 Dell XPS 13 9370 Linux 4.9.92-1 Beignet 1.3.2-2 Davinci Resolve 14.3-1
~ > resolve
ActCCMessage Already in Table: Code= 2282, Mode= 0, Level= 0, CmdKey= 8, Option= 0
ActCCMessage Already in Table: Code= c005, Mode= 13, Level= 1, CmdKey= -1, Option= 0
ActCCMessage Already in Table: Code= c006, Mode= 13, Level= 1, CmdKey= -1, Option= 0
ActCCMessage Already in Table: Code= c007, Mode= 13, Level= 1, CmdKey= -1, Option= 0
log4cxx: No appender could be found for logger (UI).
log4cxx: Please initialize the log4cxx system properly.
QSocketNotifier: Can only be used with threads started with QThread
New connection received.
Beignet: self-test failed: (3, 7, 5) + (5, 7, 3) returned (6, 7, 5)
See README.md or http://www.freedesktop.org/wiki/Software/Beignet/
Beignet: disabling non-working device
Connection is closed.
14.3 (#014)
Main thread starts: EF7A4000
resolve: AppConfig.cpp:159: void AppConfig::LoadAllSiteInfo(): Assertion `m_SiteEnabledIdx > 0' failed.
Aborted (core dumped)
A test is clearly failing, which is disabling the openCL device, and causing the application to crash. If I add the self test ignore I get:
export OCL_IGNORE_SELF_TEST=1
~ > resolve
ActCCMessage Already in Table: Code= 2282, Mode= 0, Level= 0, CmdKey= 8, Option= 0
ActCCMessage Already in Table: Code= c005, Mode= 13, Level= 1, CmdKey= -1, Option= 0
ActCCMessage Already in Table: Code= c006, Mode= 13, Level= 1, CmdKey= -1, Option= 0
ActCCMessage Already in Table: Code= c007, Mode= 13, Level= 1, CmdKey= -1, Option= 0
log4cxx: No appender could be found for logger (UI).
log4cxx: Please initialize the log4cxx system properly.
QSocketNotifier: Can only be used with threads started with QThread
New connection received.
Beignet: self-test failed: (3, 7, 5) + (5, 7, 3) returned (6, 7, 5)
See README.md or http://www.freedesktop.org/wiki/Software/Beignet/
Beignet: Warning - overriding self-test failure
Beignet: Warning - overriding self-test failure
Connection is closed.
14.3 (#014)
Main thread starts: A6255000
resolve: AppConfig.cpp:159: void AppConfig::LoadAllSiteInfo(): Assertion `m_SiteEnabledIdx > 0' failed.
Aborted (core dumped)
Happy to help test any fixes, I believe this is an issue with Beignet, not Resolve, but if you think that isn't the case I can try and log an issue with them too.
Thanks
@ruiling-song @xionghul @guoyejun @HeJunyan
This issue still persists. :(
Same here, the issue pops up in the terminal when I start Nuke, so definitely not a resolve specific thing
CPU : i5-7200U
Kernel : 4.19.6
Beignet : 1.3.2-5
Distro : Fedora 29
@bag-man @hellozee I am sorry I didn't take care of this bug. right now, Beignet is not actively maintained anymore. I don't have any idea what's wrong behind the error message. One thing I can think of is to run the beignet unit tests see if you can get some hint from failure cases . And I strongly suggest you to try intel-compute-runtime at https://github.com/intel/compute-runtime which is used to replace Beignet.
I have a similar issue: Beignet: self-test failed: (3, 7, 5) + (5, 7, 3) returned (6, 1064921688, 5)
Ran the unit tests:
summary:
total: 1046 run: 1005 pass: 1005 fail: 0 pass rate: 1.000000
Intel(R) Core(TM) i7-4510U CPU @ 2.00GHz beignet 1.3.2+12+gfc5f430c-1 Kernel: 4.19.8-2
@ruiling nice, the failed tests message disappear once started using the compute-runtime, I can now use OpenCL in Blender Cycles
Bisecting points to commit f805337, blanking doNegAddOptimization method fixes the problem on my 4250U.
Try it if you're on a pre-Gen8 chip.
Commit f805337 seems to fix it.
However, I would like to point out that DaVinci Resolve core dumps when using any of Intel's OpenCL drivers. Please notice that incompatible OpenCL drivers should be uninstalled as they may cause Resolve to crash (e.g. uninstall opencl-mesa if you're using a proprietary equivalent).
https://wiki.archlinux.org/index.php/DaVinci_Resolve