View Single Post
  #8   (View Single Post)  
Old 1st November 2018
IdOp's Avatar
IdOp IdOp is offline
Too dumb for a smartphone
Join Date: May 2008
Location: twisting on the daemon's fork(2)
Posts: 867

Thanks for reviewing that and explaining.

Originally Posted by ibara View Post
OK, so you have a dual core CPU that is theoretically capable of hyperthreading, but in fact has no smt on the cores themselves.
I don't know very much about these things, but that makes sense. So in terms of practical implications, I would guess

(a) since there is no hyper-threading going on, no need to worry about the associated vulnerability;

(b) if there was a hypothetical CPU like this which did have hyper-threaded cores, then top, and the dmesg, would show cpu0 through cpu3 ?

Actually I have 3 other PCs with Pentium 4 variants. One has hyper-threading (though I recently turned it off). One would have had hyper-threading, but Intel disabled it to make it cheaper. The other doesn't. I should check what OpenBSD dmesg says about HTT for all of these.

You should be able to confirm this by running top(1) on 6.4 or -current and noticing that there is activity on both cores during normal use.
I will try that maybe tomorrow. One problem is, to run this machine I need to bring it and the monitor & keyboard into another room, set it up, then take it away again when done ... progress can be slow.
Reply With Quote