It looks like cutting corners didn't work.
https://lists.debian.org/debian-devel/2017/06/msg00308.html
9 replies (most recent on top)
http://www.fudzilla.com/news/43964-skylake-and-kaby-lake-cpus-have-broken-hyper-threading
😂😂😂😂😂😂😂😂😂😂😂😂😂😂
All down hill since Andy, bottom hit with BK!
AG used to say "ship the sh--". Does anyone here remember?
The fact that it was not found for two years is very scary. Gobs of results/data could have been corrupted without anyone noticing...
I don't really understand the problem myself (I'm a network engineer), but considering that it just has been found, 2 years after Skylake release, how bad can it be? My home setup with 6700K is running just fine, with HT enabled.
Sad but i would bet zero of BKs staff would understand the erratum. Even sadder, I bet less than half the ee/ce/cs engineers would.
What does this even mean?
Problem: Under complex micro-architectural conditions, short loops
of less than 64 instructions that use AH, BH, CH or DH
registers as well as their corresponding wider register
(e.g. RAX, EAX or AX for AH) may cause unpredictable
system behavior. This can only happen when both logical
processors on the same physical processor are active.
Implication: Due to this erratum, the system may experience
unpredictable system behavior.
Seems there is a microcode update for most steppings which is pretty routine. But there was this bit in the thread ...
If you get any lines with a model number that is neither 78 or 94, or
the stepping is not 3, you will have to disable hyper-threading as
described on choice 2, below.
Where is Canon, still DOA due to failure of 10nm