4 cores in 1,Conroe E6600 8Mb Cache,Kentsfield result@MSI 975X

[Haltech]

OMG.. I just dribbled on myself... Anyone have a an idea as to ballpark pricing on one of these badboys when they are released? $1100? $1500?

[n00b 0f l337]

I pass out, I come back to, I hit refresh and I hit my head on the floor again...
Damn these updates get better and better, but wheres the OC'age!

[iterations]

Hah, well there we go: 3.2GHz Quad Core with 1400+MHz Bus, on stock voltage!!!

You are the man, Coolaler!

[iterations]

OMFG, look at those everest scores.

[n00b 0f l337]

Also could we get some 266 x 9 = 2400, so something like 300 x 8 = 2400 to see if its a fsb starved chip for nn_steps sake?

[dogsx2]

stock vcore limit

I sure hope these chips have as many(like Conroe) ES start floating around soon so I can get one.

[ethernal]

You realize that you are calculating that 54% performance increase between chips with two different clock speeds?

The scaling is almost perfectly linear:

Single CPU: 63 seconds
Quad Core: 19 seconds

63/(19*4) = 0.82

So there is about an 18% decrease from theoretical max.


The 8 core AMD HT enabled system shows a 4.73x (best case) speed up with 8 cores.

4.73 / 8 = 0.59

Which is a 41% decrease from theoretical max.

Which one do you think is scaling better?

Interesting eh?

Well, I corrected my mistake before I read your post (I blame my poor typing skills for my late post. )

Now, I don't mean to nitpick, but when you keep the decimals, it's only 80%. While not a significant change, it does matter. Statistics are evil, and 2% here and there begin to add up.

Second, comparing a 4-core system to an 4-chip 8-Core system is completely unfair. At 8 chips, bandwidth limitations certainly begin to show. If you're going to compare scaling, compare a 4-core Opteron setup to the Kentsfield. Mind you, I'd certainly hope that the Kentsfield would scale better considering it's a single chip - but at least be fair about the comparisons.

[cMw]

omg pls pls pls bench 3D PLS


dare i say a possible 30k in 05 with the right cards ?

[lutjens]

Personally, I hope the chip ships with an 1066MHz FSB and not the 1333MHz FSB...keeps the multiplier up.

I wouldn't be ideal for stock running CPUs (bottleneck), but it would sure help when pinning the northbridge at 333FSB. It would also provide hope for OEM machines, like Dell, to be overclocked.

[metro.cl]

keep it coming coolaler.

Please run some 3d benchs

[coolaler]

3DMark
cpu defult & vga 7950g2x oc 620/700
3d01



3d03



3d05



3d06

[sora3]

Holy batman! Makes mince meat of AMD...

[coolaler]

aquamark3

[KGB]

Would be great to see a comparison chart of comparitive speeds etc,any chart makers?

[Rickster_64]

What more can you say............. BRUTAL!

[Absolute_0]

Did you catch the load temp @ quad 100% load?

[accord99]

Not to be a downer, but that is only a 54% performance increase going from 2 cores to 4 cores, as opposed to an 86% increase going from 1 core to 2 cores (in overall score).

Hard to say if it's from the FSB or because they are seperated dies, but there is certainly a noticable scaling drop.

It's the program, Cinebench scales poorly past 2 cores. A quad 2.4GHz Opteron 250 scores 335/1062 by comparison, which is only 3.17x.

http://www.3dfluff.com/mash/cbtop.php

[coolaler]

quad spi1m

[[XC] hipno650]

the only thing that remotely competes is conroe. what cooling at 3.2 (please say air PLEASE) try some oced 3d scores with dual oced 1900xtx's

[Mikesnav]

holy ****!

[sluflyer06]

it is air...its in the pics.

[Bloody_Sorcerer]

someone at AMD just passed out? No, I think someone at AMD just grinned to himself and played with a K8L ES...
2k7 could be interesting!

[XFxGeforced]

someone at AMD just passed out? No, I think someone at AMD just grinned to himself and played with a K8L ES...
2k7 could be interesting!

that's what I'm talking about

just a thought, how would this compare to a quad dual-core opteron setup?

[alpha0ne]

But I've only just got used to using 2 cores

[iterations]

How would this compare to a quad dual-core opteron setup?

heh, well for one it would be about 400% less expensive.