A few more details...

http://www.techreport.com/onearticle.x/12127
http://www.techreport.com/onearticle.x/12130
http://www.anandtech.com/cpuchipsets/intel...doc.aspx?i=2955
http://realworldtech.com/page.cfm?NewsID=3...=03-28-2007#369

Looks like K8L will have quite a bit of competition.

This post has been edited by ikanayam: Mar 29 2007, 07:12 AM

going to post the same topic, but u were faster .

anyway, the 1st thing came into my mind when i saw the details of nahelem, OMG, wtf..., what will AMD do? even if K10(previously known as K8L) did surpass C2D as AMD claimed, it wont last long(a year?), Penryn may or may not perform better than K10, but we can assure that Nahelem will gv AMD a serious headache. look at this.this will gv a better picture.

*Intel seems to introduce new architecture every 2 years, hmm.....while AMD release their new architecture in 3-4 years.

AMD also releases more incremental architectural mini updates than intel however.

1 good thing about this stiff competition is, "we will get super cheap multicore cpu ". if not because of Core, we wouldnt get AMD3600 X2 at RM265 (and it's going to get cheaper next month ).

This post has been edited by edwin3210: Mar 29 2007, 07:25 AM

Cheap but ultra-thin margins won't keep any company in business for long.

But if K10 can't compete, AMD will die then no more competition. Prices will go sky high again.

This is cool,new core will be having integrated memory controller. This means the new mobos will not be having the northbirdge controller in the mobo already like AMD one ?

Why intel want to turn into FSB1600 so fast? The FSB1333 processor not release to the market yet!

1600FSB, SSE4, low power consume, high performance, it great or intel, proud being intel user... hehe

This is what we called "Technology grows".1600FSB providing higher bandwidth than 1333FSB,that means more instructions can be send at the same time.

what bout the price???for sure it will be pricey...

New hw when 1st start to come out of course sure pricey la.Just take a look at 76GT's nowadays.

Big competition in fact. *Rumours* said, 10% - 40% performance advantage over K8L.

northbirdge or southbridge memory controller

& have u look at AMD's chipset even though their processor already embedded the memory controller, but their own chipset still got north & south bridge wonder why??

which generation of AMD processor u mean?

The nb didn't just have the memory controller. Most high bandwidth I/O like the AGP/PCI/PCI-E interface are handled by the nb.

Btw, the Penryn is a LGA479, and Nehalem is a LGA950

LGA 479? So that mean it smaller than the current LGA775?

It's SQ35mm, that's all for now. I cant disclose more

hm... less pins? Sounds a little weird to me. 479 sounds very familiar, maybe that is the mobile version?

socket 478 + 1 = 479

I'm no EE based, but AFAIK, it depends on the contact pin current rating and bandwidth requirement -Xdb @ YGHZ

oh man, I wanted AMD to take back the crown this time.

if intel and AMD take turns going on the podium, we can expect better competition, better product, cheaper price from both.

But if AMD loose for the second time, intel is going to jack the price up for sure.

LGA479?? I thought they said last time when LGA775 release that they wanna make 1 universal socket... now wanna do LGA479 pulak...

Based on info I have kucingfight is correct on the size but pin/pad/ball count is 478 not 479.

Penryn on desktops/workstations (Wolfdale etc) will be on existing LGA775/771.

For Nehalem the pin count I know so far is more than kucing's number.

thus the 478/479 is for Mobile only?

Yes, I think it's called Socket P.
I'm not sure if "P" stands for "Penryn", but for LGA775 a.k.a. Socket T the "T" stood for the cancelled "Tejas" proc.

All my info could be wrong; there's too many damn codenames to remember.
FYI all the codenames are geographical places where Intel has a strong influence.

I'm not very EE either, but the Conroe used LGA775, and Penryn will have the same power envelope and higher FSB so a reduction in pin count would be quite strange to me.


That sounds more like it. And it does sound likely that Nehalem would easily have >1000 pins, looking at current AMD solutions. Unless CSI is a really, really high clocked serial bus, lol.

I can pretty much confirm the info on Penryn.

There's actually a few variants of the Nehalem core and the only info I have is on the higher-end server parts. Kucing might be right if he was talking about the mainstream versions of Nehalem.

Information on Nehalem is pretty scarce even internally (and some are pretty interesting!). But do expect quite a few changes from the current PC platform.

Kucing: I think you mentioned before you work with 1 of the substrate suppliers - is that correct?

i agree with u...

amd can no fight any longer...
intel had oredy release it core2quad but amd still fumbling behind...
but it is no good either...there will be no competition...

Intel roadmap from 65nm to 32nm tech. ( AMD killer )

not just that, amd just introduce 65nm architecture but intel prepare 45nm and incoming year 32nm, new architecture, more core, higher FSB, more cache, build-in memory controller...

amd will "bungkus" lio...

Never ever write off AMD; they're the Rocky Balboa of the processor world (always get up even after getting hit in the chin).
They've got great engineers + a little help from IBM.

Respect to the men in green.

AMD used to sux too, back in the old old days. When they are poor and tiny. Hot AMD that burned itself up.

but their athlon XP and AMD64 took the world by surprise.

despite their lack of resources, they were able to take down intel for many years. Until Core came along.

So, now... with the profit they've obtained from athlon and AMD64, they are way richer than the thunderbird era.

so expect them to cook up something super top secret and powerful. Real soon.

Something to SURPRISE us again!!.

Nothing super secret left about K8L which is coming soon-ish.
Whether it's super powerful is yet to be determined.

well, there is still a super secret - Where is the damn benchmark?

I don't know, but from what i assume were the best case comparative figures that have been released by AMD so far, it seems that it's not going to wipe out intel, especially not Penryn. I hope there will be surprises, but at this point i don't think it will be significantly better than any intel offerings at the time, at least in the single chip desktop space. In the server space, would bet that the K8L will win, especially in 4 socket or more systems.

Also as an aside, i just realized that the high-k + metal gate tech solves a lot of problems with using germanium channel transistors, which will probably replace silicon in the not so near future since it's a lot faster. So this new gate tech seems to be a much better long term improvement than most people realize so far.

This post has been edited by ikanayam: Apr 3 2007, 06:59 AM

According to knowledgable ppl germanium is very difficult to work with - the fabs needs to be a couple of factors cleaner than normal fabs. Plus germanium itself is expensive compared to good old Si.

Yes. A large part of that problem was that the previous dielectric used for Si transistors (SiO2) don't work very well with Ge channels. The high-k hafnium based dielectrics fix that part of the problem. Ge (~900C) melts at a much lower temperature than Si (~1400C), and the use of metal gates fixes that problem because they don't have to be doped at 900C like the polySi gates.

It is extremely unlikely that they will use Ge wafers because Ge is very unstable compared to silicon (which is the other big problem). Just the transistor channels will be Ge. The improvements are substantial, potentially ~2x electron mobility and ~4x hole mobility improvement. Cost of the material itself is not that big a deal, Hafnium used in the high-k dielectrics is not exactly cheap or abundant either. But these things won't be used a lot, just on the transistor channels, which are only a few atoms thick and a few tenths or hundreds of atoms wide. Plus current chips are already using SiGe (15-20% Ge IIRC) to strain the silicon channel.

Fabs today are a LOT cleaner than yesterday, so i don't see why tomorrow's fabs can't be cleaner than today. What i think might be a bigger potential problem is the fact that Ge has a much lower band gap than Si, so it's a lot more prone to leakage issues caused by temperature increases.

This post has been edited by ikanayam: Apr 3 2007, 09:03 AM

more Penryn speculation. it just a mere speculation, dont take it as a fact, spam that author if u wish.

*who need OC anyway, with 400fsb, it give me hell lot of performance boost from current C2D.

This post has been edited by edwin3210: Apr 3 2007, 09:09 AM

Dont forget the failure of Intel's 90nm + the netbus architecture also contribute a lot to the success of AthlonXP & AMD64.

Is the current C2D bandwidth limited in most situations? I don't think so. The faster FSB will probably help some of the SPECFP scores nicely though. And also to compete against what i believe will be AMD's streaming FP performance advantage in the K8L.

This post has been edited by ikanayam: Apr 3 2007, 09:22 AM

From a cost and rampability perspective it is a big issue. A major strength of Intel compared to AMD is they are able to balance cost and rampability (Craig Barrett's doctrine of "Manufacturing Muscle"): cheaper strained silicon vs expensive SOI, dry etch 45nm vs immersion litho etc.



The 90nm process wasn't bad - Netburst was the problem. The Pentium-M was on 90nm and what a world of difference vs Prescott. The Northwood's were pretty good too.

I can see them delaying certain things like SOI, which is not THAT big a performance boost, and also comes with some downsides (floating body effect etc), so it is a fair tradeoff. I think part of the reason for AMD using SOI is because they are in a joint process development with IBM, and IBM is the one that develops the process for the most part, and IBM is big on SOI. But i doubt Intel will lag behind for something as big as a switch to Ge. Just like they were ahead in the switch to High-k + metal.

The intel 90nm high speed process optimized for the Prescott was terrible. The leakage was bad, about half of the on current, since they optimized it for all out speed. I would be extremely shocked if the Pentium-M used the exact same 90nm process.

Penryn's not really a big deal because again the current LGA775 platform/chipsetwould become insufficient to support the higher bus speed and also supplying the required power for it to work.

Granted that if it is going to be a high speed bus, it would mean a debut for its DDR3 product/chipset as well which if most of you people have been upgrading thus far would mean a higher $$$ for the upgrade.

What is the point of it when the consumer CPU market is low on margin and this technology would mean that at anytime when it becomes available, the server market would not benefit from its adoption owing to the high price of platform + RAM.



Anandtech's Take

for every massive gain in micro architecture, it will usually call for a change in the platform/chipset as well which is $$$.

For the the inadequacy of the previous pre-5000 series Xeon, Intel would not have to introduce the newer S5000 chipset to support the newer Xeon 5000 series.

This post has been edited by cre8tif: Apr 3 2007, 07:39 PM

wah.. not bad.. when i see some ppls replies .. they are talking as if amd goin to die ... if amd die ... it will be almost impossible to buy a graphic card / processor / motherboard in future .. nvidia and intel gonna conquer .. coz the price will be jacked sky high.. i'm seeing intel fanboys getting soo excited lol .. but they dont even notice what will happen if amd die.. hehe well .. didn't really bother about them. .i still support the smaller company .. coz their low and mid end still worth for money you pay about K8L .. its not K8L .. it is K10 .. weather it is failure or not .. it will seat on current amd AM2/new AM2+ socket.. amd even thinking of released a 8 core processor on a single socket.. those new intel chips.. you gonna require new motherboard.. maybe new ram .. so on... so every time intel release now processor you need new mobo ? hehe this is cool ... for some ppl it doesn't matter .. coz they keep on changing their mobo and so on... but not good for normal consumer .. so i think amd should really focus on low and and mid end instead of high end.. coz high end stuff is not really that important ... right now ... amd stil can survive with their current line of product.. nothing wrong with it ... whether 65nm or 45 nm ... comparing to 90nm amd proc and 65nm c2d ... the power usage is almost the same.. just that i notice .. intel is just copying amd all the way ... with the integrated graphic chip on the processor and integrated memory controller ... the most cekap part is .. AMD64 / X86-64 .. which created by amd.. intel applied their own processor with EM64T which is same technology by amd ..hmmm so nowdays i'm seeing .. AMD is getting more creative than intel .. just intel is trying to kill amd with their capacity advantage .. they have tons of money and can create new technology easily .. even 32nm .. so we'll wait and see whether amd gonna die or not

This post has been edited by Creative: Apr 4 2007, 05:51 PM

intel is showing reports of profit loss over a few consequetive terms for now, and their earning per chips sold are also very thin now........but so does AMD haha.......so it's going to be harder for them to survive but this also means more creative strategy needed........

hoepfully they are force to push the quad core to a more friendly price sooner....... may be end of this year or so.......... haha

Let a paid fanboi retort:

1. Integrated mem controller and integrated graphics - done back in 1999 IIRC on Tinma which was cancelled. But from Tinma came Banias.

2. Guess who copied the original x86?

3. Do monopolies mean higher prices for everyone? Not necessarily.

4. High end is not important? You obviously don't understand the microprocessor business. The high-end with its high margins supports the mid/low-end business.

Oh you really like to use elipsis don't you? Hard to read your post.

cks2k2, AMD already released the integrated memory controller which is exist in market and you are talking about product which isn't released at all and non of the consumer even seen it in action so no point there for you to argue about it. Then about x86 back then, AMD been making processor for intel and they have agreement to share their technology each other so nothing wrong with the x86 at that time, but now in return amd created x86-64 and intel is sharing it. Both companies are sharing the instructions sets such as SSE and so on. What i am trying to explain is intel just getting lazy and amd getting more creative these days. Maybe you dont get the point. but then i dont come here to argue or anything, just trying to explain where some ppl dont really realize about whats happening but they just throw their words just like that. How many geeks buying high end pc where a cpu company could make enough money out of high end stuff? just go and check the statistics yourself where majority of consumers goes for low or mid most of the times. Not everyone are gamer, the high end does produce high margin but then it is very rare. Now i'm out of this forum, you all can argue all you want:) tata

How is intel getting lazy? As far as i can see, they're really flexing their strength, especially lately.

Also, the high end CPU costs about the same to make as the low end one because they are the same chip (assuming the difference is in clocks). So however many more dollars it is priced above the lower end chip just means more profit.