AMD's 3GHz K10 to break 30,000 3DMark06 (Inq)

[Shintai]

Anyone got the exact SM2/SM3 scores for a standard 2900XT crossfire setup?

[v_rr]

So we have to assume the SM2 and SM3 scores will be lower with the slower cards used. even with kinc/shaminos 100Mhz higher clocked 2900XTs, they would have to score a CPU score of 21000. Or about the same as a 12½Ghz Core 2 Quad.

You can assume something like that.
First HD 2900 XT in crossfire can benefict a lot from PCI-E 2.0
Second the K10 CPU ofers lot of bandwith that is very need in crossfire rigs.

Remember that you are testing not only K10 but also RD790 and also HD 2900 that have support for PCI-E 2.0, and that till now were only working in PCI-E 1.0

I totally agree with DilTech.
Unlikely, but not impossible....

[Metroid]

Well I knew the great performance advantage Phenom has over Conroe since some manager pictures had been leaked 3 months ago but this is quite high to what I was expecting from Phenom, maybe because on that occasion it was clocked at 1.8 and not at 3.0 GHz, many strange things happened in this article as the pictures were gone with his stolen laptop. Well I just want to see how much it can overclock and by the way this is a synthetic benchmark. So I do not add that much on it.

[Shintai]

You can assume something like that.
First HD 2900 XT in crossfire can benefict a lot from PCI-E 2.0
Second the K10 CPU ofers lot of bandwith that is very need in crossfire rigs.

Remember that you are testing not only K10 but also RD790 and also HD 2900 that have support for PCI-E 2.0, and that till now were only working in PCI-E 1.0

I totally agree with DilTech.
Unlikely, but not impossible....

PCI-E 2.0 would add close to nothing. Unless you remove the bridges

[[XC] flat-four]

Will the additional bandwidth of pci-e 2.0 help with the crossfire scores? Isn't it possible that an AMD chipset/AMD cpu/AMD GPUs run more efficiently than the c2q rig with the higher clocked cpu?

[over@locker886]

Numbers with Shamino and Kinc SM2.0 and SM3.0 scores

I think AMD can't 21000+ on 3Ghz..

[DilTech]

Yes but you are talking about a AMD X2 at 3Ghz being roughly equal to a 2.4Ghz C2D. That is entirely plausible, but a C2D at over 5Ghz not being equal to a 3Ghz K-10? Not happening.

3Ghz X2? More like closer to 4 ghz. I can't remember exactly what good ol' MM had on his FX for his old 20k WR, but it could be crushed on air and stock voltage by the lowest C2D without even trying, even with the cards on air.

[Metroid]

Numbers with Shamino and Kinc SM2.0 and SM3.0 scores

I think AMD can't 21000+ on 3Ghz..

These numbers are wrong. Please fix it.

[xlink]

No way that a dual 2900XT @ 830/900will break 30,000 even in the next 5 years


2.5GHz = 23.768 and 3GHZ = 30,000 ,,,,,,,,,, wake up

the memory might be running @ settings pre OC...

[Piotrsama]

Where's Shintai?

Rumor says he has a new laptop with some pics he doesn't want anybody to see
j/k

On topic: Very unlikely.

And INq hehe plz half of the stuff they post is crap

And the other half is not worth the read

[Gautam]

Just to play the devil's advocate, why not try thinking in terms of P4 vs A64?

[over@locker886]

These numbers are wrong. Please fix it.

What numbers? In news , cards ran slower speed, so need 21k+ cpu score..!

[CraptacularOne]

3Ghz X2? More like closer to 4 ghz. I can't remember exactly what good ol' MM had on his FX for his old 20k WR, but it could be crushed on air and stock voltage by the lowest C2D without even trying, even with the cards on air.

Actually an AMD X2 at 3Ghz is about on par with a 2.4Ghz C2D

[DilTech]

Just to play the devil's advocate, why not try thinking in terms of P4 vs A64?

Exactly.

Again though, I'm not saying I believe this article, but it's Definitely not impossible.

[railer]

I wonder how many hits INQ got by posting this BS article. Way to do business

[CraptacularOne]

Just to play the devil's advocate, why not try thinking in terms of P4 vs A64?

Do you really think that if that were the case that AMD would keep their mouths shut about it? I'm sure someone would have "slipped" or "leaked" some credible info

[kiwi]

62 replies, 137 views. Wow, excellent rumor!

[SnipingWaste]

This could be a duel socket mobo with 2 quad core K10s doing the benches.

[xVeinx]

It could, but then they would have probably mentioned that, don't you think?

[Metroid]

What numbers? In news , cards ran slower speed, so need 21k+ cpu score..!

SM2= 10581
SM3= 11798
CPU= 21000?

SM2+SM3 = 22379

He said the score was 30031. So to be precise AMD Phenom clocked at 3.0 processor needs a score of 7653 points to beat that and that is not impossible.

[gillll]

very strange the man ran the machine himself.

The particular piece of equipment that was briefly in our possession allowed us to run 3DMark06, the most important to overclockers worldwide, and Everest 4.0, our favourite memory benchmark

i think he'd know the diff between dual and single socket mobo.? won't he?

[Gautam]

I'm not putting much faith in the article at all. All I made was a simple statement.

Also most people here don't seem to fully understand how 3DMark06 works. The SM2 and SM3 scores would certainly go up significantly in conjunction with this much additional CPU power potentially.

[berk]

Erm...i'm gonna get some shares just in case.

[CraptacularOne]

SM2= 10581
SM3= 11798
CPU= 21000?

SM2+SM3 = 22379

He said the score was 30031. So to be precise AMD Phenom clocked at 3.0 processor needs a score of 7653 points to beat that.

lmao...you need to read up on how the scores add up on 3Dmark06 It's not just a sum of all 3 scores.....lol

[Shintai]

SM2= 10581
SM3= 11798
CPU= 21000?

SM2+SM3 = 22379

He said the score was 30031. So to be precise AMD Phenom clocked at 3.0 processor needs a score of 7653 points to beat that.

http://mekk.homeip.net/3dmarkcalc/3D...culator1.2.zip

Use the calculator. 3Dmark06 aint calculated like that. They have different weights in the final score.