Nehalem Info from hkepc

[mAJORD]

OMG!!!

That's 2x the performance per clock of Conroe in SuperPI!!

And check the cache size : 64KB L1 and 8MB L2.That's what I wanted to see!!

Failed maths?

I see about 16%-17% /clock compared with Yorkfield which is pretty decent.

[Origin_Unknown]

he said conroe though... not yorkfeild

[Craftyman.]

Woo! A.Wake forgot about that! can't wait

[Zytek_Fan]

Woo! A.Wake forgot about that! can't wait

It's supposed to come out late this year

[savantu]

Maybe I'm wrong, but if you check that cpu-z screenshot you will see:

FSB 444
Multiplier x6.0 (6-10)

Maybe that SPI score is at 4440MHz, because at idle SpeedStep is working.

But Nehalem does not use FSB so...

I refuse to believe QC Nehalem runs in early steppings at 4.44GHz. I'd say that is an ES with unlocked multipliers.Probably , it had a 266MHz FSB clock and was OC to 444 , multiplier dropped accordingly to 6.

I mean wtf , 20% better than Core per clock and running 40% faster ?

That's 70% better performance than Core.

Failed maths?

I see about 16%-17% /clock compared with Yorkfield which is pretty decent.

See above.I must say , I'm perfectly satisfied with only 20% per clock and 40% higher frequency from the start .I must admit such a scenario would be really bad news for the green team.

[largon]

The CPU-Z on this shot looks very outdated (somewhere ver. 1.3x) and the verification of the SPI checksum says Incorrect checksum!.

Because SuperPi validation service is broken atm.

[Zytek_Fan]

I refuse to believe QC Nehalem runs in early steppings at 4.44GHz. I'd say that is an ES with unlocked multipliers.Probably , it had a 266MHz FSB clock and was OC to 444 , multiplier dropped accordingly to 6.

I mean wtf , 20% better than Core per clock and running 40% faster ?

That's 70% better performance than Core.




See above.I must say , I'm perfectly satisfied with only 20% per clock and 40% higher frequency from the start .I must admit such a scenario would be really bad news for the green team.

Remember the part where Intel said that Nehalem is the biggest change in CPUs since Pentium Pro?

And it is very possible that 4.4ghz could be achieved with early silicon. 45nm production was ironed out with Penryn, and remember when we first started seeing results for Conroe? 4ghz was achieved quite easily

[Jowy Atreides]

While it's nice and all with new awesome expectations/promises among new products which this news is FULL of it also sucks a bit for my wallet as I have intended to hold onto Penryn for a while as Nehalem will prolly require a full upgrade for me, and this architecture sounds like it could have a serious lead over Core 2 Duo so it could be difficult holding onto C2D a long time.

Nehalem = Intel strenghtening the remaining weak points in Core 2 Duo.

ah RPGWizard, you forget that not everyone is like us

sell your existing pc when transferring to nehalem,
pick the right time when the average pc user sees your 4Ghz oc'd pc as a godly machine and the new sockets still haven't hit mainstream

I've free upgraded my pc everytime,

eg. I've went from a 7900 to an 8600gts to an ati 3850 without spending a penny

it's all about timing

[Shintai]

Remember the part where Intel said that Nehalem is the biggest change in CPUs since Pentium Pro?

And it is very possible that 4.4ghz could be achieved with early silicon. 45nm production was ironed out with Penryn, and remember when we first started seeing results for Conroe? 4ghz was achieved quite easily

I think its wrong to say the biggest change is anything regarding the cores themself. What Intel is saying is the move of PCIe, IMC and for lowend GPU to the die/package is the biggest step since the L2 cache that was moved to the PPro.

[STaRGaZeR]

I refuse to believe QC Nehalem runs in early steppings at 4.44GHz. I'd say that is an ES with unlocked multipliers.Probably , it had a 266MHz FSB clock and was OC to 444 , multiplier dropped accordingly to 6.

I mean wtf , 20% better than Core per clock and running 40% faster ?

That's 70% better performance than Core.




See above.I must say , I'm perfectly satisfied with only 20% per clock and 40% higher frequency from the start .I must admit such a scenario would be really bad news for the green team.

I believe that 4440Mhz can be achievable with the actual silicon revision. Nehalem is Core based, and Core, in its beginnings (65nm) clocked like hell.

If that SS is not fake it is a huge boost IMO, and I'm more than satisfied. But I'll give my final judgement when Intel launches them. Or at least when they release the final specs.

Bad news for the green team since when, almost 2 years? And we will have bad news for another 2 I think...

[Vapor]

nehalem spi 1m run.. don't know is it true.. but it's nice score

http://infomars.fr/forum/index.php?showtopic=1524

Known fake...
http://www.xtremesystems.org/forums/...6&postcount=21

[Zytek_Fan]

Known fake...
http://www.xtremesystems.org/forums/...6&postcount=21

Wow, that's quite old then

[mAJORD]

Savantu, Suggesting it has 70% or whatever IPC improvment over core is as ridiculous as the stupid expectations people had for Phenom. Only it's you getting excited this time.

Face it, it's either clocked to 4.4 ghz (impressive), or it's a BS screenshot.

[informal]

Savantu, Suggesting it has 70% or whatever IPC improvment over core is as ridiculous as the stupid expectations people had for Phenom. Only it's you getting excited this time.

Face it, it's either clocked to 4.4 ghz (impressive), or it's a BS screenshot.

It's a known fake,as Vapor said it.It dates back from 2006,i now remember that thread i posted in it with my invisible ES keyboard => lookie here
BTW,topic title was,back then :"Intel's newest ES chip". LoL

Here's the original quote(the date was 06-29-2006, 08:29 PM):

COMPGEEK is right
Intel Core 3 Octo is the real name (but logo above is chopped as you can see)
based on Nehalem 45nm 8-core 8Mb shared cache
CSI disabled
Spi1M WR @ Nehalem 2.66 stock
Here is a nice way of getting around the NDA, say its fake,lol
ok this might be fake

The link to the post:
http://www.xtremesystems.org/forums/...6&postcount=21


Savantu,in future don't jump so fast .
Shintel on the other hand took this "SPi record" and "Nehalem" screen shot quite soberly (at least better than the rest of intel fanclub).
EDIT:just to add that it's needless to say Nehalem taped-out quite recently so from that perspective there is no way(at all) this "screen shot" could be real.That dude was just messing around in a thread that started with a joke("Insane inside",first post in that thread).

PS I still type on that ES keyboard of mine,it's still way better than anything out there j/k

[hollo]

sorry this is replying to a post you made over a month ago, but i've just read the thread..

When thinking about it. I would also make a quite real and possible statement that nVidia is out of the chipset business in 2010/2011. VIA knows this and already abandon Intel chipsets. Because look at the Ibexpeak. Its basicly the same AMD will have with their cores in 2010 or so. And the IGP market is also 100% AMD/Intel with on CPU IGPs. I think this is also why AMD puts less and less effort on highend discrete GFX. And another bold statement would be that around 2013-2015 everything the Ibexpeak and AMD equal will be on the CPUs. That can yield some seriously small corporate/parents desktops with a CPU+memory+SSD basicly

i'm not sure what you're thinking will happen in 2010/11 but i think it looks pretty good for nvidia in the short term.. just referring to the performance/mainstream, cos i'm not sure how things will happen with bloomfield-

making a southbridge for an IMC cpu should be a lot easier than making a chipset that has to host a memory controller and route all the information between the controller and the CPU via a front side bus, like LGA775, and nVidia might have an opportunity like they did with socket 939 where they had the best chipsets around. the on-die PCI-e would be connected to a nVidia chipset that would then connect to two or more SLI capable PCI-e slots... and nVidia get to keep their SLI chipset monopoly with very few issues, just like they have it on AMD systems. with the latency improvements from an on-die PCI-e link, say it was PCI-e 2.0 x16, i'm pretty sure that two high end nVidia cards would do very well... more than two might get a bit stressed. depends how much bandwidth Intel gives to the on-die PCI-e on the mainstream part.

onboard GFX would also be pretty easy for nVidia with the mainstream nehalem - an onboard GPU connects directly to the on-die PCI-e controller, or is disabled if a seperate GFX card is connected. hybrid SLI would be a piece of cake. nVidia's integrated GPU business will compete with nehalem's on-die GPU eventually... who knows how that'll pan out, but it'd be amazing if nVidia was pushed out of integrated GPUs. an on-die GPU may have some advantages, but nVidia could make a low powered GPU (maybe with its own memory, like the new ATI AM2+ GPU chipset) that'd run rings around any forseeable AMD or Intel on-die GPU with a flick of their wrist. just pair the nVidia onboard GPU with a "on-die GPU"-free nehalem. presumably there'll be some (heat/overclocking?) advantages (at least initially) to having a "on-die GPU"-free nehalem, and many people may prefer to get a plain nehalem with a nVidia GPU chipset over a gfx-nehalem for certain builds (HTPC for example).

it depends how powerful the on-die GPUs from AMD and Intel will be. i'm pretty sure that to start with they'll be absolute rubbish, basically because of TDP restraints. and nVidia have already shown that they're willing to give away onboard GPUs by promising to put them on all their future chipsets.

i can see the market becoming more interesting/diverse, but i can't see why nVidia would become a non-player in chipsets and onboard GPUs. and for SLI, so long as there are discrete graphics cards nVidia can cling to their SLI monopoly by requiring it to run through a certain chipset, and i don't see anything that would stop them. raytracing seems to be a much larger threat, but that's more a long-term issue. it's hard to see what nVidia would sell if i could render high resolution games at high frame rates with raytracing on my 22nm native 16 core 32 thread CPU...

[Boogerlad]

that nehalem superpi run might be legit because if it's running at 444 qpi (fsb), and is 1333 from the cpu-z screen shot, that would indicate that it's probably the highend 4/8core nehalem because it uses triple channel ram, so 444*3 channel = 1332 fsb/ qpi effectivly. i think

[PkG.1337]

thx to vapor and informal who clear this up
comon ppl
lmao

[informal]

Boogerlad,read my previous post(2 posts above yours)..
It's not true,it's dating back from 2006 and it's a joke made in another "joke" thread.
Damn i hate to be a party pooper.

EDIT:

Thanks for joining the party and clearing things up PkG.1337,you made quite a stir with your post back then ,now history repeats itself again hehe .
Your little chop even made it to the Nordic Hardware ,congrats

[PkG.1337]

Boogerlad,read my previous post(2 posts above yours)..
It's not true,it's dating back from 2006 and it's a joke made in another "joke" thread.
Damn i hate to be a party pooper.

QFT
5min photochop in 2006 posted in a joke thread turn in to this

[informal]

Savantu's IPC and clock dreams have just shattered .But hey,it was fun back then in 2006,it's even funnier now .

PS Who's the girl in your avatar

[PkG.1337]

Savantu's IPC and clock dreams have just shattered .But hey,it was fun back then in 2006,it's even funnier now .

PS Who's the girl in your avatar

BoA, korean singer

[JumpingJack]

EDIT:just to add that it's needless to say Nehalem taped-out quite recently so from that perspective there is no way(at all) this "screen shot" could be real.That dude was just messing around in a thread that started with a joke("Insane inside",first post in that thread).
j/k

Actually, Nehalem probably taped out last summer, because Intel showed a working demo at the Fall IDF if I recall. http://www.anandtech.com/cpuchipsets...oc.aspx?i=3102 16 threads, 8 cores in a 2P system.

Jack

[informal]

Hi Jack.Yes I'm aware of that and my point was that it(the thread) was still much earlier than the actual tape-out happened.One year earlier if we want to be exact.

[Epsilon84]

Savantu's IPC and clock dreams have just shattered .But hey,it was fun back then in 2006,it's even funnier now .

Quite smug for someone whose own clock and IPC dreams were shattered a mere 3 months ago...

[Craftyman.]

Actually, Nehalem probably taped out last summer, because Intel showed a working demo at the Fall IDF if I recall. http://www.anandtech.com/cpuchipsets...oc.aspx?i=3102 16 threads, 8 cores in a 2P system.

Jack

Glad to see you're still around, jack. Loved to read your posts back on Tom's