Hey Mulyadi, On Thu, Oct 21, 2010 at 9:59 PM, Mulyadi Santosa <mulyadi.santosa@xxxxxxxxx> wrote: > Hi.. > > IMHO it is the "in cache" speed which is folded unlinearly. Due to > L1/L2/L3 nature, it might be that the whole code is already in the > same cache line thus subsequent call doesn't fetch anything from RAM. > This is assuming everything is (almost) perfectly cache aligned. > > BTW, are all the codes executed? or are we hitting 10/90 percent scenario here? > In my module I am doing a "wbinvd" which invalidates the cache. So it must definitely try to fetch from RAM as there will be a cache miss. I am _mostly_ sure that I am messing up MTRR. Not enough documentation out there for it. I just tried disabling only MTRR(without using the above module) and the slowdown is still there. Even after re-enabling MTRR range, the slowdown persists.(check my other mail for details). Regards, Andev -- To unsubscribe from this list: send an email with "unsubscribe kernelnewbies" to ecartis@xxxxxxxxxxxx Please read the FAQ at http://kernelnewbies.org/FAQ
