If you get one of these, be careful. This bad WU failed on 9 machines and had the additional insult of putting my 1060 in a state where it failed the next WU. Luckily I happened to catch it because of the super long DL times here and rebooted, fixing the problem. Here's the WU, there are most likely more like this floating around:

https://www.gpugrid.net/workunit.php?wuid=12205143

It's possible that it only locks up the GPU with the CUDA80 app as all the other machines were running CUDA65.

This bad WU failed on 9 machines and had the additional insult of putting my 1060 in a state where it failed the next WU.

Edit: now 10 machines...

This bad WU failed on 9 machines and had the additional insult of putting my 1060 in a state where it failed the next WU.

Edit: now 10 machines...

Probably 8 errors and 2 'ghost' downloads. I usually have at least 1 'ghost' in the system at all times on my main system. It shows there is a 7th WU out there, but the machine itself shows that task as not being on it and the logs and xml shows that WU never even existed.