How do you overclock with out a Front Side Bus? Beside more voltage.
Will Nehalem kill OCing?
Look at the CPU-Z screenie. See that 133??? You can raise that. But thats only to OC the CPU frequency to a higher speed. In order to OC the memory link you will need to OC the QuickPath and thats a whole different story. It has its own bus speed and voltage too.
You will need to learn a whole new way to OC with Nehalem. But it shall be fun. New stuff always is.
I agree that the article doesn't say much more than what we already knew, but it's not bad like the Inq or Fudzilla, because they aren't making performance claims, just presenting raw, albiet old news, facts about it.
I am a bit concerned about the reports of the very slight edge Nehalem seems to have on a roughly equivalent Core 2 in single threaded apps. It would seem to me that Nehalem should blow away a C2 even in single threads. Can anyone shed some light on that?
Judging by the very little information I've seen, Nehalem isn't a whole lot faster than a core2 in single threaded apps. The IMC and hyperthreading are the major changes in the new architecture and neither one is going to do a whole lot to help out most single threaded desktop applications.
But what about the sheer processing power? Or is Nehalem just a C2 reworked with the IMC, Hyperthreading and more pins? I'm confused.
Some comparisons I've seen on the web (forget which site, might even have been here) showed it around 20% faster, clock per clock. But I guess we'll have to wait for Intel to drop the NDAs before we find out for sure.
I think people would be pretty disappointed if it's not at least that much faster than a Core 2, given that clock speeds won't increase by much.
Cinebench shows us only a 2% increase in core-to-core performance from Penryn to Nehalem at the same clock speed. For applications that don't go out to main memory much and can stay confined to a single core, Nehalem behaves very much like Penryn. Remember that outside of the memory architecture and HT tweaks to the core, Nehalem's list of improvements are very specific (e.g. faster unaligned cache accesses).