Re: hyperthreading or not
On 1/24/06, Jo Shields <jo.shields@comlab.ox.ac.uk> wrote:
> The problem with hyperthreading is that there's only a bare minimum of
> distinct hardware - almost all resources are shared. notably, a pipeline
> stall on one thread (where the pipelines on a p4 are ridiculously long)
> will flufh the hyperthread's pipeline too.
That kind of defeats the purpose, doesn't it? The idea of HT was to
increase the utilisation of core CPU groups by having two threads
ready for dispatch. If one thread stalls, the other thread could still
dispatch operations, unless... the stall affects both threads.
That would certainly explain the minimal performance gain of HT. On
the desktop it is still nice to have.
Thomas
Reply to: