FS#62110 - [cuda] system hangs on P2P bandwidth test
Attached to Project:
Community Packages
Opened by Alex (aletan) - Friday, 22 March 2019, 09:10 GMT
Last edited by Sven-Hendrik Haase (Svenstaro) - Tuesday, 26 March 2019, 12:55 GMT
Opened by Alex (aletan) - Friday, 22 March 2019, 09:10 GMT
Last edited by Sven-Hendrik Haase (Svenstaro) - Tuesday, 26 March 2019, 12:55 GMT
|
Details
Description:
I'm running two TITAN Xp GPUs with nvidia driver version 418.56, on Arch Linux x86_64. When I execute nvidia-smi I'm getting all the information about both of the GPUs: +-----------------------------------------------------------------------------+ | NVIDIA-SMI 418.56 Driver Version: 418.56 CUDA Version: 10.1 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 TITAN Xp Off | 00000000:17:00.0 Off | N/A | | 23% 37C P8 9W / 250W | 2MiB / 12196MiB | 0% Default | +-------------------------------+----------------------+----------------------+ | 1 TITAN Xp Off | 00000000:65:00.0 On | N/A | | 26% 43C P8 20W / 250W | 251MiB / 12192MiB | 0% Default | +-------------------------------+----------------------+----------------------+ But when I execute simple P2P bandwidth test from cuda package /opt/cuda/samples/1_Utilities/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest my system hangs. Additional info: * package version(s) Repository : community Name : cuda Version : 10.0.130-2 Description : NVIDIA's GPU programming toolkit Architecture : x86_64 URL : http://www.nvidia.com/object/cuda_home.html Licenses : custom:NVIDIA Groups : None Provides : cuda-toolkit cuda-sdk Depends On : gcc7-libs opencl-nvidia nvidia-utils gcc7 Optional Deps : gdb: for cuda-gdb java-runtime: for nsight and nvvp Conflicts With : None Replaces : cuda-toolkit cuda-sdk Download Size : 1316.93 MiB Installed Size : 3023.75 MiB Packager : Sven-Hendrik Haase <svenstaro@gmail.com> Build Date : Mon 24 Sep 2018 09:14:18 AM MSK Validated By : MD5 Sum SHA-256 Sum Signature Steps to reproduce: 1) cd /opt/cuda/samples/1_Utilities/p2pBandwidthLatencyTest/ 2) make 3) ./p2pBandwidthLatencyTest |
This task depends upon
Closed by Sven-Hendrik Haase (Svenstaro)
Tuesday, 26 March 2019, 12:55 GMT
Reason for closing: Deferred
Additional comments about closing: See comments
Tuesday, 26 March 2019, 12:55 GMT
Reason for closing: Deferred
Additional comments about closing: See comments
Comment by loqs (loqs) - Friday, 22
March 2019, 18:46 GMT
Comment by Alex (aletan) -
Saturday, 23 March 2019, 05:20 GMT
Comment by
Sven-Hendrik Haase (Svenstaro) -
Saturday, 23 March 2019, 08:09 GMT
Comment by loqs (loqs) - Saturday,
23 March 2019, 09:26 GMT
Comment by Alex (aletan) - Tuesday,
26 March 2019, 09:04 GMT
Is the issue specific to 418.56?
There was not the issue in nvidia driver 415 and kernel 4.20.
There really isn't anything here to do from a packaging
perspective that I can see. Please report a bug to nvidia.
Please try the patch from
https://bbs.archlinux.org/viewtopic.php?id=244919
Thank you! I'll report the issue to the nvidia package.