Segmentation Fault During genconfig

[lackita]

During tuning as part of the genconfig command, I keep getting a segmentation fault. Here's my output:

$ ./katago genconfig -model g170-b40c256x2-s2383550464-d716628997.bin.gz -output generated.cfg

=========================================================================
RULES

What rules should KataGo use by default for play and analysis?
(chinese, japanese, korean, tromp-taylor, aga, chinese-ogs, new-zealand, bga, stone-scoring, aga-button):
japanese

=========================================================================
SEARCH LIMITS

When playing games, KataGo will always obey the time controls given by the GUI/tournament/match/online server.
But you can specify an additional limit to make KataGo move much faster. This does NOT affect analysis/review,
only affects playing games. Add a limit? (y/n) (default n):


NOTE: No limits configured for KataGo. KataGo will obey time controls provided by the GUI or server or match script
but if they don't specify any, when playing games KataGo may think forever without moving. (press enter to continue)


When playing games, KataGo can optionally ponder during the opponent's turn. This gives faster/stronger play
in real games but should NOT be enabled if you are running tests with fixed limits (pondering may exceed those
limits), or to avoid stealing the opponent's compute time when testing two bots on the same machine.
Enable pondering? (y/n, default n):

=========================================================================
GPUS AND RAM

Finding available GPU-like devices...
Found OpenCL Device 0: AMD BONAIRE (DRM 2.50.0, 4.15.0-91-generic, LLVM 9.0.1) (AMD) (score 11000101)

Specify devices/GPUs to use (for example "0,1,2" to use devices 0, 1, and 2). Leave blank for a default SINGLE-GPU config:
 

By default, KataGo will cache up to about 3GB of positions in memory (RAM), in addition to
whatever the current search is using. Specify a max in GB or leave blank for default:


=========================================================================
PERFORMANCE TUNING

Specify number of visits to use test/tune performance with, leave blank for default based on GPU speed.
Use large number for more accurate results, small if your GPU is old and this is taking forever:


Specify number of seconds/move to optimize performance for (default 5), leave blank for default:

2020-04-07 14:48:45-0400: Loading model and initializing benchmark...

Running quick initial benchmark at 16 threads!
2020-04-07 14:48:45-0400: nnRandSeed0 = 6905691009999129495
2020-04-07 14:48:45-0400: After dedups: nnModelFile0 = g170-b40c256x2-s2383550464-d716628997.bin.gz useFP16 auto useNHWC auto
2020-04-07 14:48:49-0400: Found OpenCL Platform 0: Clover (Mesa) (OpenCL 1.1 Mesa 20.1.0-devel (git-82597c4 2020-04-06 bionic-oibaf-ppa))
2020-04-07 14:48:49-0400: Found 1 device(s) on platform 0 with type CPU or GPU or Accelerator
2020-04-07 14:48:49-0400: Found OpenCL Device 0: AMD BONAIRE (DRM 2.50.0, 4.15.0-91-generic, LLVM 9.0.1) (AMD) (score 11000101)
2020-04-07 14:48:49-0400: Using OpenCL Device 0: AMD BONAIRE (DRM 2.50.0, 4.15.0-91-generic, LLVM 9.0.1) (AMD) OpenCL 1.1 Mesa 20.1.0-devel (git-82597c4 2020-04-06 bionic-oibaf-ppa)
2020-04-07 14:48:49-0400: Loaded tuning parameters from: /home/lackita/.katago/opencltuning/tune6_gpuAMDBONAIREDRM2500415091genericLLVM901_x19_y19_c256_mv8.txt
2020-04-07 14:49:01-0400: OpenCL backend: Model version 8
2020-04-07 14:49:01-0400: OpenCL backend: Model name: g170-b40c256x2-s2383550464-d716628997

numSearchThreads = 16: 0 / 3 positions, visits/s = -nan (0.0 secs)      Segmentation fault (core dumped)

I'm happy to provide more info, if there are other logs that would be useful.

[lightvector]

Your OpenCL drivers are probably buggy. See this issue:
#182

[lackita]

Yeah, that definitely looks like the problem, thanks for the advice.