(01-30-2011, 11:51 AM)ryancollins Wrote:(01-30-2011, 04:03 AM)smackjack22 Wrote: How about YOU explain to me, why my new i7 @ 1.7 GHz (~2000 MIPS per 100% load per core -> ~12000 MIPS for 600% load) is twice as fast than my old P4 @ 2GHz (~1000 MIPS per 100% load -> ~500 MIPS for 50% load) even though my P4 is clearly "faster" by 300 MHz?
i7 has more cores and turbo boost
Did you see the "per 100% load" part?
A single core CPU can have up to 100% load, while for a dualcore it'd be 200% and so on.
Without this %-ranking, I wouldn't be able to accurately measure the power of a single core CPU, as the benchmark would never achieve a 100% load (let's not forget that Windows needs some MHz too)
Not to mention that Turbo boost alone won't make up for the +100% performance.
Also Turbo boost works best, when not all cores are loaded. In this benchmark they were clearly all busy (or else I wouldn't have got 12'000 MIPS @ 600%) which means that the clock rate would've been 1.8 GHz with Turbo boost... not exactly a good explanation, don't you think?
No, the correct answer was already given by NaturalViolence.
It's not the clock rate that makes the difference nor is it the number of cores, it's the architecture.
Coincidence does not exist.
We only believe it does, because we never know what happens beyond our visions and thoughts.
We only believe it does, because we never know what happens beyond our visions and thoughts.