View Single Post
Old 05-24-2005, 03:13 AM   #11
LennonCook
Jack Burton
 

Join Date: November 10, 2001
Location: Bathurst & Orange, in constant flux
Age: 38
Posts: 5,452
Quote:
Originally posted by Hivetyrant:
That's what I meant, as you said they can technicaly only process one thing at a time, but they switch between them so damn fast you don't notice.
Sure, but that's not hyperthreading, or even a processor function. That's an operating system function. The processor doesn't know about applications, it only does math. Cross-referencing with the Wikipedia article on it, Vaskez's explanation seems about right... especially the bit about "plain english" [img]smile.gif[/img]

EDIT: HTML hates whitespace... and here I was thinking they ignored each other.
EDIT (again): Took out a small bit of misinformation...

And here's Intel's explanation:
Quote:
Hyper-Threading Technology enables this thread-level parallelism (TLP) by duplicating the architectural state on each processor, while sharing one set of processor execution resources. When scheduling threads, the operating system treats the two distinct architectural states as separate 'logical' processors. This allows multiprocessor capable software to run unmodified on twice as many logical processors.
[ 05-24-2005, 03:49 AM: Message edited by: LennonCook ]
LennonCook is offline   Reply With Quote