Intel Nehalem Working at 3.2GHz Pictured

[Donnie27]

I really hope this won't be like that demoed 3GHz Phenom...

And I'd like to know single-thread perfomance too.

If anything, Intel will leave themselves some wiggle room. They've learned from their mistakes. They've not pulled an AMD 3GHz snafu since Core Launched.

[Donnie27]

Soon..

Hehehe!

[Shintai]

30% in heavy multithreading over C2 doesn't sound that high... I expected something like that in single-thread and a LOT more in MT.

Its isolated core to core. In heavy multithreading and such they talk about up to 2x performance over Core 2. And about 15% in singlethreaded. And it would be over 45nm Core 2. But even 30% faster clock for clock and 3.2Ghz demoed...So the fastest just gets even faster

AMD is in for a very rough ride. Intel also demos stuff they can delievr. Not some fake PR stunts. Just look back on 65 and 45nm Core 2. We always got it pretty clear.

[ethernal]

HT is still a fake trick imho....

flame me all you like

How is it a fake trick? I mean, I guess it "tricks" the task manager. But as far as being a "trick", it's no more a trick (as another poster pointed out) than OoO execution, branch prediction, or basically any other component of a modern x86 processor. It's not fair to decode those big x86 instructions down into "micro operations". It's not fair that AMD uses an IMC. It's a cheap trick!

Customers care about the raw processing power of a CPU. Hyperthreading is a great way to increase potential performance for a relatively low cost in terms of heat and die area. All it is doing is making more efficient use of the unused execution units. Indeed, your Core2 processor is probably only using 2.5 out of 4 execution units at one. Rarely it uses all four and more often it uses two or three. Sometimes it's stuck at pushing through only one instruction (or just sitting idle because of a pipeline stall).

This goes back to someone complaining about how they would prefer that Intel tries to increase single threaded performance. I don't think you appreciate how difficult that is. Already, AMD and Intel use tricks to make their processors perform that would make your head spin. Out of Order execution is incredibly complex, especially in the way it is implemented in today's processors. Branch prediction can only get so accurate (Intel learned that with Netburst). A processor can only complete so many instructions at one.

Sure, it's possible to create a fifty-issue wide CPU that has billions of transistors and looks more like a GPU in construction than a CPU. But quite frankly, save for a few small synthetics, more often than not only a few instructions would be passing through them. There is only so much you can complete in one cycle without having dependency issues. You simply can't do this until you know that.

Which goes back to hyperthreading. If you have execution units that are empty, why not fill them up? Sounds pretty fair to me.

My only concern with Nahalem is the small cache sizes. When you are doing hyperthreading, you are basically splitting the cache needs (although I'm sure the dominant process is given priority). With Nahalem's effective L2 cache size (L2-L1) being only 192K, it's going to be interesting to see how it deals with the often thrown around "cache-thrashing" word.

[STaRGaZeR]

If anything, Intel will leave themselves some wiggle room. They've learned from their mistakes. They not pulled an AMD 3GHz snafu since Core Launched.

You have to admit that maybe they didn't pull it because they didn't have to do so

But I agree, that 3,2GHz Nehalem sounds wonderful

[Craftyman.]

Higher IPC, higher clocks... sounds fantastic!

[Frank M]

[...]

Besides cache-thrashing I'd add a perhaps even more important factor:
single-threaded performance.
Netburst with HT1 enabled incurred a performance hit at single-threaded
applications. With a native quad-core I don't see the need for even more
virtual cores, since there are barely any applications taking advantage of
even 4 cores, not to mention 8. Might be useful in the server/hpc space
for maxing out the capability of the chip, but imo it's useless for desktop,
and if it can't be disabled, then it is also be detrimental to (single-threaded)
performance

[dinos22]

hmmmmm i wonder what lack of L2 cache will do for superpi and 3dmark01 heheh

[Epsilon84]

Netburst with HT1 enabled incurred a performance hit at single-threaded
applications.

No it didn't.

http://www.anandtech.com/showdoc.aspx?i=1746&p=6

[M.Beier]

... Pure p0rn0graphy !

I'd really like to see a little sneak preview of a nice SPI 1M at 3.2ghz

[Zytek_Fan]

http://youtube.com/watch?v=5k19pa970Is

[NotFred]

I want.... Badly!

Big question is, could I delay my Q3 system rebuild enough that I can get my hands on one of these!

[r4gm4n]

sorry if this has been asked but when is it due?
Q4?

[Zytek_Fan]

sorry if this has been asked but when is it due?
Q4?

Server and workstation parts will arrive sometime in Q4 08, and desktop will start trickling in in Q1 09.

[r4gm4n]

great thanks
Now have to deceide weather to do that upgrade in may or not...

[Shadowmage]

Intel has been pretty clear on several occasions that this is not a return of HyperThreading, it's all new.
Still, many news sites continue to call it that.

//Andreas

I don't think you understand. Hyperthreading is the marketing name for Simultaneous Multithreading. It is exactly the return of HT, but they didn't screw up the implementation this time.

[Movieman]

sorry if this has been asked but when is it due?
Q4?

Tomorrow...OH, sorry,you meant when is it due "retail"...

[Donnie27]

You have to admit that maybe they didn't pull it because they didn't have to do so

But I agree, that 3,2GHz Nehalem sounds wonderful

QFT! Why lie when you don't have to I think Creative Labs could learn something here as well.

[Donnie27]

Tomorrow...OH, sorry,you meant when is it due "retail"...

OK LOL!, stop that crap right now!

[Donnie27]

No it didn't.

Sure, but when has facts ever stopped the Hyperthreading or Hype-threading as some called it, bashing.

[Donnie27]

I don't think you understand. Hyperthreading is the marketing name for Simultaneous Multithreading. It is exactly the return of HT, but they didn't screw up the implementation this time.

They didn't screw it up last time. They just didn't have the processor powerful to pull it off as well. Yet, I was happier with my P4 than I was with my AthlonXP and only went with a 3500+ as my main Game Rig. Left the P4 crunching movies and etc.... Just sold it 3 months ago

[Movieman]

OK LOL!, stop that crap right now!

Alright, I'm sorry, your right.. It might be Friday not Thursday!
Not sure if overnighted or two day..

[Frank M]

Tomorrow...OH, sorry,you meant when is it due "retail"...

"Hey, wake up! You've been dreaming all along. Not even last night's storm
could wake you. There you go."

Daydreaming again, huh?

(Reminds me I should go do some nightdreaming... it's 4:29AM... damn thesis)

[Movieman]

"Hey, wake up! You've been dreaming all along. Not even last night's storm
could wake you. There you go."

Daydreaming again, huh?

(Reminds me I should go do some nightdreaming... it's 4:29AM... damn thesis)

Whaaaa? Huh????Oh...Darn..

[adamsleath]

this is highly relevant