Intel Core i7 Processors [models & pricing] ! !

[Jacky]

What exactly does CrystalMark 2004R3 do and why is nehalem slightly slower than penryn overall? I guess it's a single threaded benchmark?
What relevance does it have for realworld testing? I know the sieve of eratosthenes and fibonacci calculations are realworld algorithms, but are they (and all the others) relevant to real software?

[Metroid]

What exactly does CrystalMark 2004R3 do and why is nehalem slightly slower than penryn overall?

Is it?

Nehalem 3.20 = 27.0k
Penryn 3.20 = 21.8k

I'm not sure if the hard drive is the same, because the difference is huge, other than that all the results were kindly expected for me.

Metroid.

[Jacky]

Is it?

Nehalem 3.20 = 27.0k
Penryn 3.20 = 21.8k

I'm not sure if the hard drive is the same, because the difference is huge, other than that all the results were kindly expected for me.

Metroid.

You're right, I meant the ALU+FPU scores, which look like CPU-only scores to me. The others may be influenced by GPU/hard drive and I'm not sure why the GPU (GDI, D2D, OGL?) scores are so much higher with nehalem...

[gundamit]

Sorry if this is off topic ...

I stopped hardware purchases in order to prep my wallet for i7. Not sure I'll be an early adopter but I think I can justify my purchase since my curiosity about the new CPU has a practical gaming angle. Currently I'm running 5 instances of EQ2 on a Q6600 @3.43ghz with 8gig of memory on an old Asus 965 mobo. My main toon gets his own rig. All is well and it runs smooth and problem free outside of the fact the mobo/4x2gb memory combo is holding the OC down a bit. EQ2 is an odd game in that if offloads some of the graphics work on the CPU. Can't really crank the graphics without a lot of CPU power. Old 8800GTX doesn't seem to have problems rendering at 16x10x5.

I can't help wondering how I would fare with an i7 and GTX 280. Sony just issued a multi core patch and I'm wondering how it'll assign the workload with HT. Not that I need more rendering power or FPS since I mostly just look at my main toon's 24" screen.

Meh. Reading this post makes me think I'm stretching my "practical" gaming reasoning a bit for an i7, buts it more than most gamers have. Crunchers on the other hand ...

[Jacky]

What exactly does CrystalMark 2004R3 do and why is nehalem slightly slower than penryn overall? I guess it's a single threaded benchmark?
What relevance does it have for realworld testing? I know the sieve of eratosthenes and fibonacci calculations are realworld algorithms, but are they (and all the others) relevant to real software?

Can anyone elaborate?

I see it is 32 bit, so now that macro-ops fusion is enable in 64bit this should give a boost of a couple percent to nehalem in contrast to C2D in realworld 64bit code. Thus they'd be at least eqal in FPU/ALU tests I guess.
Why is nehalem faster in the GPU tests, does anyone know? (it seems they also make us of the CPU?)

Are there any 3dmark experts here?
Could someone compare nehalem with penryn: http://ocxtreme.org/forumenus/showth...?t=3978&page=7 (link used to work)
Nehalem 3,2ghz, 9800 GTX+ default
memory IIRC: tripple channel 800mhz (7-7-7-21)
scores 62781 in 3dmark01.

[Blauhung]

Can anyone elaborate?

I see it is 32 bit, so now that macro-ops fusion is enable in 64bit this should give a boost of a couple percent to nehalem in contrast to C2D in realworld 64bit code. Thus they'd be at least eqal in FPU/ALU tests I guess.
Why is nehalem faster in the GPU tests, does anyone know? (it seems they also make us of the CPU?)

Are there any 3dmark experts here?
Could someone compare nehalem with penryn: http://ocxtreme.org/forumenus/showth...?t=3978&page=7 (link used to work)
Nehalem 3,2ghz, 9800 GTX+ default
memory IIRC: tripple channel 800mhz (7-7-7-21)
scores 62781 in 3dmark01.

I can venture a guess as to 3D performance. Latency and bandwidth from CPU to PCIe are both greatly improved through using a direct QPI link to the PCI controller on the X58 chipset. There might also be several improvements on the controller to make use of these new found boosts.