[Wien] Intel EMT64 OT

[Stefaan Cottenier]

> Besides this, we found that surprisingly 2 WIEN jobs (on one cpu) can
> "gain" some time; i.e. while one job runs eg. 1h, 2 jobs in (k-)parallel
> do not need 2h, but some 10-20 % less !!??
> 
> (PS: we do not see this on our "old" 2.6 GHz P4)

Is that the same effect as mentioned in 

http://zeus.theochem.tuwien.ac.at/pipermail/wien/2005-March/004901.html  ?

That was observed on a normal P4 (2.2 or 2.4 GHz).

Stefaan

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm