Intel Nehalem Mainboard and CPU Picture Debut...

[saaya]

what chipset is that? looks like p35?

thanks for posting this here sxs112!

[Blauhung]

Those slots on the board doesn't looks like to be FB-DIMMs.

really unless you know which way to stick it in, or actually counted pins, they both look ~the same. Unless there are 2 types of memory controllers on the same chip, DP server and high end desktop are both gona be the the same memory.

[Blauhung]

what chipset is that? looks like p35?

thanks for posting this here sxs112!

Tylersburg and ICH10

[Zytek_Fan]

Gasp

[iadstudio]

I think this pic is just for show, as all the other coolers are missing too (NB etc)

Don't shoot me if this is s stupid question, but I thought Nahelm had on-die memory controller and would net be using a NB.

[Shintai]

Don't shoot me if this is s stupid question, but I thought Nahelm had on-die memory controller and would net be using a NB.

For servers and extreme. The NB is only used for PCIe and CSI. Just like with AMD.

For desktops PCIe is on the CPU.

[SKYMTL]

Ummm....isn't that the upcoming (Q2 2008) Gigabyte GA7-TESH series workstation motherboard that was shown at CES? :S

[LexDiamonds]

thats hot. sexy sexy

[pH(x)]

That looks damned good.

[Donnie27]

Oh yeah baby!

[Blauhung]

For servers and extreme. The NB is only used for PCIe and CSI. Just like with AMD.

For desktops PCIe is on the CPU.

yup, tylersburg is basically there to collect all the QPI's and talk to the ICH10

[xVeinx]

So the server version has a secretary for a "north bridge" then?

[duploxxx]

For desktops PCIe is on the CPU.

still no roadmap seen that clearly states it will be on the cpu.... except for the old specs offcourse

[bot@xs]

screw on sockets on the board, nice. replaceable in case of bend pin.
replaceable bios, nice but the fan headers a placed screwy.
there has to be cooling added
24-pin power plug on the bottom while both 4 pin plugs are on the top.
why are they so far apart, i foresee mesy wiring

[Movieman]

Slick looking setup.. Now we need to get some speed into that bugger
As to SP1M,I can do 15.562s on a dual clover at 3157.
I'd guess a dual Harpertown would be in the 12s range at 4000mhz
Wonder what this will do at even 3000mhz?

[saaya]

Tylersburg and ICH10

tylersburg... huhmmm confusing intel chipset names and number sheme... so this is... the successor of... the 5400 chipset?

[Movieman]

tylersburg... huhmmm confusing intel chipset names and number sheme... so this is... the successor of... the 5400 chipset?

Correct, but where the Seaburg 5400 chipset is a small advance over the 5100 BlackCreek chipset, this is a "big" jump.
Whole new game,like Netburst to C2D..

[NH|Delph1]

Eagerly awaits Intel's phone call telling us to come over and play with it

//Andreas

[Movieman]

Eagerly awaits Intel's phone call telling us to come over and play with it

//Andreas

Books flight to Sweden so I can go with you!

[StealthyFish]

I don't think you're supposed to release those . How'd you get your hands on one.. or is that picture taken in the lab? . B1's should be out in a few weeks ^^.

[Omastar]

p3 @ 1ghz needs ~160 seconds

So this A1 rev Nehalem is actually slower, clock for clock, than a 1GHz P3 in Super Pi?

[socket]

what about pins side?

[Blauhung]

So this A1 rev Nehalem is actually slower, clock for clock, than a 1GHz P3 in Super Pi?

Production will probably C-something, I'd be willing to bet that just about every chip (specially a new uArch) starts out very very slow on early stepping.

[Movieman]

Production will probably C-something, I'd be willing to bet that just about every chip (specially a new uArch) starts out very very slow on early stepping.

Everything I know about engineering( which isn't much) is first make it work, then make it work better(faster,less heat,etc)
My guess is that they start at a slow speed to see if the theory actually works in practice,then look at all the individual components to see any potential flaws and then they start to make it go faster.
Just a guess but maybe closer to the truth than we know.

[flippin_waffles]

Everything I know about engineering( which isn't much) is first make it work, then make it work better(faster,less heat,etc)
My guess is that they start at a slow speed to see if the theory actually works in practice,then look at all the individual components to see any potential flaws and then they start to make it go faster.
Just a guess but maybe closer to the truth than we know.

Sounds very familiar.