Print 103 comment(s) - last by omnicronx.. on Apr 18 at 12:00 AM

Intel spills the rest of the beans on its new 45nm architecture, slated for launch this winter

With the launch and excitement of Intel's Silverthorne-based Atom processors behind it, Intel is turning its sights to the more salient and profitable next generation architecture for desktop, server, and mobile processors. Intel used the Spring IDF 2008 as a showcase for its Nehalem processor architecture.

Intel's Nehalem is truly a radical architecture departure from Intel thanks to its integrated memory controller that will support triple-channel DDR3-1333 memory. This won't be the only design element taken almost verbatim from AMD's playbook; Intel also plans to incorporate the new QuickPath Interface on Nehalem. QuickPath is almost identical in spirit and implementation to AMD's current interconnect technology, HyperTransport.

The first available Nehalem processors will be built on the existing 45nm manufacturing process, will incorporate SSE4 instructions, and will feature four fully integrated cores. Each core will have its own dedicated 256KB L2 cache and each core will share an 8MB of L3 cache pool.  The bulk of these 731 million transistor processors are dedicated to cache.

Event demonstrations at the Shanghai Intel Developer Forum, occurring now until the end of the week, show A1 silicon Bloomfield-based Nehalem processors at IDF at a speedy 3.2 GHz.

Like the 533 MHz variants of Intel's new Silverthorne-based Atom processors, Nehalem will also incorporate Simultaneous Multithreading (SMT) which is also known as Hyper-Threading (HT). 

Intel senior vice president Patrick Gelsinger confirmed that Xeon MP versions of Nehalem will eventually incorporate eight cores per processor, one upping the current Penryn-derived Dunnington processor the company plans to announce later this year.  These octo-core Nehalem processors will also use the newest iteration of Hyper-Threading, bringing the total count to 16 threads per chip.  And of course, these processors can be used in quad-socket configurations, bringing the processor market to 64 threads per mainboard.

Current Intel roadmaps peg the Nehalem launch date in Q4 2008, with a simulteanous rollout across servers and desktops. Since Nehalem uses a new architecture and transport bus, existing motherboards will not work with the new processors. 

Comments     Threshold

This article is over a month old, voting and posting comments is disabled

sounds familiar
By acejj26 on 4/2/2008 1:12:10 PM , Rating: 3
Didn't AMD showcase a 3.0 GHz Barcelona over a year ago? However they still haven't shipped anything close to that. What is the probability that Nehalem ships at or around this speed?

RE: sounds familiar
By KristopherKubicki (blog) on 4/2/2008 1:17:53 PM , Rating: 4
You're 100% correct on that. Last year I was criticized for mentioning that AMD's roadmap topped out at 2.6 GHz yet they demonstrated a 3.0 GHz chip. This time around, Intel's roadmap at least has a 3.2 GHz XE model on its roadmap. That will likely be the debut chip, with more mainstream chips coming in 2009.

RE: sounds familiar
By System48 on 4/2/2008 1:26:42 PM , Rating: 2
Exactly what I was going to say. I actually wish they would have a few slower models for the initial release, something that I could afford.

RE: sounds familiar
By ImSpartacus on 4/2/2008 2:59:13 PM , Rating: 2
That hurts them. They may not be up to snuff on production, so they can satisfy a low ultra-high end demand for a while until all of their fabs are cookin out chips, then they can support a larger mid-range userbase.

And they can leach $1k+ out of each sale versus 200-300$, so early adopters that may want to get a nehalem, but would normally want a ~$300 chip will get a $1000 chip (although that isn't very common).

RE: sounds familiar
By wordsworm on 4/4/2008 12:22:55 PM , Rating: 2
My guess is fabricating high end chips efficiently takes some time for serious refinement. How many bunk chips get produced at the high end for every good chip? Essentially it makes more sense to do things just the way they are.

RE: sounds familiar
By ImSpartacus on 4/6/2008 12:45:05 PM , Rating: 2
Something tells me the first high end chips that roll out aren't binned quite as high as the full production high end chips. I have no proof to back it up, but I am just assuming.

RE: sounds familiar
By batman4u on 4/2/2008 1:29:37 PM , Rating: 2
still, if they ship a 2.8Ghz CPu.... it will be rather Fast.

AMD must move quick....which sadly i doubt

RE: sounds familiar
By eye smite on 4/2/08, Rating: 0
RE: sounds familiar
By StevoLincolnite on 4/2/2008 10:01:55 PM , Rating: 5
AMD didn't invent the On-Die memory controller.

RE: sounds familiar
By eye smite on 4/2/08, Rating: 0
RE: sounds familiar
By redbone75 on 4/2/2008 11:45:40 PM , Rating: 5
No but they've had the most success with it and there's no denying that.

Didn't you mean to say "they've had their greatest success thus far" with it? There's no denying the benefit the on-die controller has had for AMD's architecture, but it tends to be a moot point considering the success of the Core architecture which doesn't have an on-die memory controller.

Yes, Intel is moving to an on-die controller, but they've already proven they can best AMD without copying them. To say anything otherwise smacks of fanboyism.

RE: sounds familiar
By vignyan on 4/3/2008 1:08:46 AM , Rating: 2
Point well made. Adding to that, i think the usage of same technology means little. its like saying that Daily tech copied Inquirer. Both are tech blogs and by far Daily tech is much better than Inq. even though Inq had used it first with quite some success.. :)

Not all processors are made equal.. And On-die memory controller does have a lot of limitations (processor upgrades to support newer memories, socket stability) which are commonly seen as problems with AMD (ignoring the under-performance issue)... Think! :P

RE: sounds familiar
By JumpingJack on 4/3/2008 3:23:52 AM , Rating: 3
Yes, it was a good point... it takes some study and reading to understand the memory hierarchy, mem+bus+cache work together to server one purpose, bring data and instructions to the core and keep it fed.

There are differnt design and implementation choices at each juncture, which is better a fast mem bus + small cache or slow mem bus + large cache. It depends really, the size and detail of the cache is dictated by performance goals at design, account for mem access latencies and speed.

The IMC allows AMD to implement smaller cache footprints while by suffering less far call penalties going to main memory compared to the current Intel approach, however, a large enough cache reduces misses such that much fewer (costly) memory accesses are required reducing the need for a fast mem bus.

This works for Intel really well for small memory footprints, and small working sets (i.e. DT/mobile like applications), their cache can be overwhelmed and performance held back though in some server workloads as shown in SpecFP_rate measurments and HPC applications.

For general purpose, Intel has demonstrated that an IMC is not the end all beat all that AMD would want you to think it is.

RE: sounds familiar
By eye smite on 4/3/08, Rating: 0
RE: sounds familiar
By DOSGuy on 4/3/2008 1:37:36 AM , Rating: 4
You're kidding, right? The Core 2 has not hit a bottleneck; it's one of the most overclockable architectures ever produced. Intel doesn't need to copy AMD to keep that going. They could sell much faster Core 2 processors, but they haven't needed to.

What happens next is where things get interesting. Intel already has a superior architecture that can clock to 4 GHz and beyond, and they're following that up with a processor that has a built-in memory controller and adding a second thread per core. They're moving much faster than they need to with the current lack of competition. If I didn't know better, I might think they were trying to run AMD out of business. Naturally they don't want to have a monopoly for legal reasons, but they definitely seem to be trying to grab as much of the pie as they can get away with.

RE: sounds familiar
By NullSubroutine on 4/3/2008 4:14:24 AM , Rating: 3
I think some people on these tech sites forget alot about how the CPU business world works.

AMD had the fastest chips around for quite a few years, did they reign supreme as far as dominating the market? No, of course not.

Having the fastest chip does not equal business success, all it succeeds in doing is getting a bunch of tech nerds all exicted about how many FPS they can get in their games.

I like to get the fastest computer gear as much as the next guy, but in terms of business AMD having or not having the fastest chip does not mean they will win or lose.

What matters is how many chips you sell and the most chips you sell are in the OEM cheap/mid range desktops/laptops like Dell, HP, etc. The majority of people buying PCs cannot tell the difference between a 2ghz dual core vs a 4ghz quad core. What they do understand is a computer that costs $500 vs that costs $2000.

AMD doesn't need the fastest processors to make fanboys of either side happy(or the 'fanboys of "whatever is fastest"') to survive. They need to produce products that allows them to remain competitive while getting enough market penetration into OEM's to sell volumes of chips.

As far as Nelahem (however you spell it I forgot), it doesnt have anything to do with 'maintaining supriority over desktop computing' it has to do with producing a chip that scales as good as the Opteron does when more core are introduced into the system, where the Opteron still has an advantage.

The reason why you see Intel not producing faster binned processors is because there is no competition and for them to produce faster binned processors (even though they have head room) means they will have lower yields. Unless their market % is threatened they will not lower yields (and lose money).

RE: sounds familiar
By NullSubroutine on 4/3/2008 7:27:10 AM , Rating: 2

96.6% of all CPUs sold are below $200. I rest my case!

RE: sounds familiar
By Etsp on 4/3/2008 11:10:44 AM , Rating: 2
If I were you, I wouldn't rest any case based solely on a link to fudzilla... If I remember correctly, fudzilla was started by the ATI fanboy that used to write for the Inq a while back...

RE: sounds familiar
By NullSubroutine on 4/3/2008 1:11:58 PM , Rating: 2
I posted what I have known for quite a while, I only saw what was said at Fudzilla after posting it. It was from Mercury Research I believe, not Fudzilla. It is true there is no source link, but its possible its one of those subscriber only. It's possible to see the same stats elsewhere soon.

RE: sounds familiar
By B3an on 4/3/2008 3:02:35 AM , Rating: 2
I honestly couldn't care less what company has the fastest chip. But you're obviously a massive fan boi Eye Smite. Yet you call others fan boi's...
It's really pathetic and immature. Please grow up kid.

RE: sounds familiar
By JumpingJack on 4/3/2008 3:18:07 AM , Rating: 2
The only evidence of a bottleneck is in HPC and high working set applications that reside mostly in the server space. Applications scale well with core speed even on slower bus speeds, even for quad cores. The data is clear and is published all over the net.

The data does not support your thesis, in fact it argues quite the opposite.

RE: sounds familiar
By lordsaytor on 4/3/2008 10:24:08 AM , Rating: 2
In your infinite wisdom, please give me some links to sites that show AMD cpus run games faster than Intel. And please, I don't give a rats damm if AMD can run a virus scan faster or if it can put extract files out of a .RAR file faster. I just care if there is an AMD that can enable games to run at higher framerates.

And I don't care if Intel has been copying AMD, I honestly don't care. If AMD doesn't catch up, then my money goes to Intel. It's that simple.

RE: sounds familiar
By eye smite on 4/3/08, Rating: -1
RE: sounds familiar
By jRaskell on 4/3/2008 12:27:58 PM , Rating: 5
Generally speaking, when an individual comes along and makes a given statement, the responsibility lies in their hands to provide actual support for said statements. Of course, I'm referring here to actual debates. People slinging insults in ever single comment aren't really debating anything. They're just trolling.

RE: sounds familiar
By eye smite on 4/3/08, Rating: -1
RE: sounds familiar
By lordsaytor on 4/5/2008 3:25:47 PM , Rating: 2
Why are we even caring what this retard is saying? Let him bask in his AMD glory. He's probably posting on this forum just to get under people's skin.

None of of his posts make any sense anyways. And then he'll reply by either saying you're an idiot or that you're too lazy to do research. Or that he doesn't feel compelled to post any links proving that his almighty AMD is better.

Truly a miserable loser.

RE: sounds familiar
By Adonlude on 4/9/2008 4:28:21 PM , Rating: 1
Wow, you're a waste of space if I've ever seen one. Your argument regarding Intel copying AMD's 5yr old tech is bs as well. You need to look farther back, a few decades even. What you will find is that once upon a time Intel made AMD. AMD was a second source for Intel invented technology. AMD was a mindles production house who decided to sue some technology rights out from under Intel and become an intelligent company of their own. They have been competing with Intel ever since... well, up until C2D that is :-)

I'd say look it up but you should probably spend your time finishing your high school homework.

RE: sounds familiar
By omnicronx on 4/18/2008 12:00:14 AM , Rating: 2
I think you need a history lesson, IBM forced Intel to have a secondary chip manufacturer as part of their contract. AMD did not just 'sue some technology rights out from under Intel', Intel tried to break their contract. In fact some could argue that if Intel never made this move, AMD would still be a secondary producer of Intel chips today.

In February 1982, AMD signed a contract with Intel, becoming a licensed second-source manufacturer of 8086 and 8088 processors. IBM wanted to use the Intel 8088 in its IBM PC, but IBM's policy at the time was to require at least two sources for its chips. AMD later produced the Am286 under the same arrangement, but Intel canceled the agreement in 1986 and refused to convey technical details of the i386 part. AMD challenged Intel's decision to cancel the agreement and won in arbitration, but Intel disputed this decision. A long legal dispute followed, ending in 1994 when the Supreme Court of California sided with AMD. Subsequent legal disputes centered on whether AMD had legal rights to use derivatives of Intel's microcode. In the face of uncertainty, AMD was forced to develop "clean room" versions of Intel code.

RE: sounds familiar
By Adonlude on 4/9/2008 4:29:17 PM , Rating: 1
Wow, you're a waste of space if I've ever seen one. Your argument regarding Intel copying AMD's 5yr old tech is bs as well. You need to look farther back, a few decades even. What you will find is that once upon a time Intel made AMD. AMD was a second source for Intel invented technology. AMD was a mindles production house who decided to sue some technology rights out from under Intel and become an intelligent company of their own. They have been competing with Intel ever since... well, up until C2D that is :-)

I'd say look it up but you should probably spend your time finishing your high school homework.

RE: sounds familiar
By lordsaytor on 4/5/2008 3:33:27 PM , Rating: 1
I'm an idiot? well so is your whore of a mother. You're an idiot, you're an idiot, you're an idiot. Yeah I notice thats the only thing you can say when people disagree with you. And since I'm so ignorant as you claim, I decided to blurt an insult towards your mother.

RE: sounds familiar
By rudolphna on 4/3/2008 11:51:59 AM , Rating: 5
wow you my friend are a complete idiot that must not read anything but AMD fanboy websites. I like AMD too, but even i know that Intel has a far superior architecture. The Core2 can be overclocked to beyond 4Ghz on AIR cooling. Can AMD claim as much? Even with watercooling i was unable to get the AMD Athlon X2 +5000 black edition beyond 3.6ghz stable. It would not boot over 3.4. Doesnt exactly strike me as better, when with a ZEROtherm BTF-90 i can get my Intel E6750 to 4Ghz. every benchmark i have ever run, at same clock speeds (both at 3Ghz) have favored the Intel, except for AMDs slight lead in Memory latency. 3dmark, pcmark, everest, sandra, all highly favor the Core chips. Face it eyesmite. The K8 architecture is no longer competetive performance wise. Try switching to an Intel Core 2 System and you might change your mind. Never been bottlenecked by the FSB before, so i dont think it will until we start seeing 8 core or more CPUs on one FSB. Try reading Anandtech, and you will see the truth.

RE: sounds familiar
By rudolphna on 4/3/2008 11:53:42 AM , Rating: 2
sorry i meant i cannot boot over 3.6 and it is not stable over 3.4

RE: sounds familiar
By eye smite on 4/3/08, Rating: 0
RE: sounds familiar
By arjunp2085 on 4/3/2008 2:54:07 PM , Rating: 2

True Core2 is a far better architecture
this happened only after AMD SHOWED THE WAY


RE: sounds familiar
By rudolphna on 4/3/2008 4:27:42 PM , Rating: 5
idiot. when was the last time you actually used an Intel system? Stop being an AMD fanboy. Im not talking about servers, which the CPU isnt nearly as important as Harddisk throughput. Its not a preference, its FACT that intel CPUs are far superior to AMD CPU. And dont you dare call people chilren, when you are obviously in denial, and are being very childish right now! why do you think AMD is superior when Intel has better performance? I like AMD too, i would LOVE to see AMD come back to competetiveness, i loved the Athlon XP, and Athlon64, but it just doesnt have the performance that the Intel Core 2 has! Granted, AMD also owns ATi now, which also needs to get its act together to produce more decent cards. The AMD 3xxx series of GPU is fantastic, but we need more. When AMD comes out with a more competetive processor performance wise, then you can talk. As it is, the Phenom isnt yet close in single-threaded performance to Intel C2D.

RE: sounds familiar
By eye smite on 4/3/08, Rating: 0
RE: sounds familiar
By theprodigalrebel on 4/3/2008 3:57:12 AM , Rating: 4
Obvious troll is obvious.

RE: sounds familiar
By lordsaytor on 4/3/2008 10:19:26 AM , Rating: 1
Who gives a flying fcuk about ethics? Whoever makes a faster cpu is the one people will support.
And you must really be one hell of a retard if you say that AMD only needs to wait for Intel to underestimate them again. It's the same as saying, well I'm sure I'll win the 100m sprint at the Olympics if everyone else underestimates me and starts slowing down. Yeah that is one excellent attitude to have. It's people like you that cause AMD to bleed money so damm badly. Yeah lets just wait and wait and wait and wait for Intel to make an inferior product.

I loved AMD. I had an Athlon XP +1400 (i think) and I had an Athlon venice +3000 and they were great cpus. But how can you bleeping still stick with AMD??? It just boggles me.

RE: sounds familiar
By TheOneStorm on 4/7/2008 9:57:38 AM , Rating: 2
I'm sort of agree, but I just wish AMD did better. I've been a hardcore AMD fan for years. I've owned upwards around 10 or so AMD's, ranging from the original 64-series, and then later the X2 series. However, it really does seem that Intel is biting back with much more force. This along with the Atom's for the small/energy saving PCs is really going to hurt AMD :( I like the competition between the two companies, but it looks like Intel is on a rampage.

RE: sounds familiar
By 16nm on 4/2/2008 6:16:17 PM , Rating: 3
These octo-core Nehalem processors will also use the newest iteration of Hyper-Threading, bringing the total count to 16 threads per core.

Kris, I'm not totally familiar with the newest iteration of Intel Hyper-Threading but I am semi certain that that should have read:
These octo-core Nehalem processors will also use the newest iteration of Hyper-Threading, bringing the total count to 2 threads per core.

RE: sounds familiar
By Alpha4 on 4/2/2008 6:45:32 PM , Rating: 3
Even more accurate would be the assumption that he meant "16 threads per chip".

RE: sounds familiar
By KristopherKubicki (blog) on 4/2/2008 8:03:20 PM , Rating: 2
Sorry, that was the intended message. It's been corrected.

RE: sounds familiar
By retrospooty on 4/2/2008 1:38:03 PM , Rating: 2
Regardless... Intel (lately) is NOT like AMD. Intel is firing on all pistons, while AMD is fluttering.

Imagine a Core2 quad CPU with the same appx clock speeds, internal memory controller, triple channel DDR3 and several other speed enhancements. This thing is going to rock!

RE: sounds familiar
By acejj26 on 4/2/2008 1:41:09 PM , Rating: 5
Intel's 45 nm launch is not indicative of a company firing on all pistons. However, their performance lead has made their own fluttering irrelevant. They have time to iron out their problems, whereas AMD does not.

RE: sounds familiar
By KristopherKubicki (blog) on 4/2/2008 2:16:13 PM , Rating: 4
Things aren't completely liquid at Intel, as demonstrated by the 45nm quad-core botched launch. Granted, it's better executed than other things we've seen.

RE: sounds familiar
By BSMonitor on 4/2/08, Rating: -1
RE: sounds familiar
By dgingeri on 4/2/2008 3:36:07 PM , Rating: 3
Botched? Facts? I haven't heard any problems with the 45nm launch except for all of these "speculative" claims that there is a shortage? Mostly by AMD buffs like you.

Is this the reason the 45nm chips are out of stock everywhere and finding the top clock rate chip, the e8500, is near impossible? Because AMD fans just think there is a shortage?

RE: sounds familiar
By deeznuts on 4/2/2008 3:50:09 PM , Rating: 2
Funny, I see QX9650s everywhere, Been using mine for months without trouble.

RE: sounds familiar
By 4wardtristan on 4/2/2008 7:23:39 PM , Rating: 2
just because you have been using yours fine for months doesnt mean that there isnt a shortage??

RE: sounds familiar
By shiznit on 4/2/2008 4:59:46 PM , Rating: 2
Intel 45nm is doing just fine, the scarcity is intentional to clear 65nm stock first.

RE: sounds familiar
By Doormat on 4/2/2008 5:03:45 PM , Rating: 3
Which is why we're starting to see the Q6600 at $200. Right as the 9x50s hit, the Q6600 price tanks. Hmmm...

RE: sounds familiar
By BSMonitor on 4/2/08, Rating: -1
RE: sounds familiar
By Armorize on 4/2/2008 8:11:31 PM , Rating: 2
I read here at DT awhile ago that intel claimed they thought they might have an erratum in their processors that might not show up for a long time and no one might even notice but they were holding back to make sure. I heard/read about it sometime in january
when the initial release of the 45nm and x48 chipset was set to occur.

heres a link dated Jan 16th from here at DT (which im surprised no one remembers)
and heres another same date.

Its questionable if there really is/was an erratum in their processors or if they were doing it to get rid of the x38 chipset and 65nm. Eliminating the x38's that are in stock and waiting to release the x48 (which is out now for the most part) makes sense so that they dont screw their partners who have leftover practically brand new chipsets laying around.

The processors are another thing. They started a mini price war at the release of phenom and havent really dropped their prices very much since then. I have seen sites like newegg dropping the prices a few dollars but nothing big. the q9300 is in stock at newegg and tigerdirect at the time of my post. the q9450 is out of stock at newegg. and the q9550 is hiding somewhere in a warehouse still as far as ive seen. A lot of distrubuters are displaying a big release sometime around the 16th of april of the 45nm. I bet by then we'll see massive amounts of them too. Thats my 2 cents.

RE: sounds familiar
By retrospooty on 4/2/2008 3:02:15 PM , Rating: 4
Was it botched, or are they holding back because AMD has no real competitive product?

The fastest CPU's have been released (Core 2 quad extremes)... How is it that the high end CPU's work, but the low end are having issues? Easy, there are no issues. Intel is maximizing profit since AMD has nothing compelling to offer.

RE: sounds familiar
By imperator3733 on 4/2/2008 5:15:59 PM , Rating: 2
I think it's because of AMD not being competetive. Why would Intel want to hurt the sales of all their 65nm chips when there is no reason to? Yet another way that Phenom's problems are hurting consumers. Hopefully AMD gets Deneb performing quite well and they don't underestimate Intel again.

RE: sounds familiar
By Cogman on 4/2/2008 2:41:27 PM , Rating: 2
There is still a part of me the feels that Intel is already starting to hold back because of lack of competition. They have the lead, so why release faster processors? Whats the rush?

RE: sounds familiar
By eye smite on 4/2/08, Rating: 0
RE: sounds familiar
By Roy2001 on 4/2/2008 6:38:36 PM , Rating: 1
Didn't AMD showcase a 3.0 GHz Barcelona over a year ago?
================================================= ========
I smell sour grape. Intel showcased Conroe at 2.66Ghz and final release topped at 3.0Ghz. I guess you ignored that.

RE: sounds familiar
By KristopherKubicki (blog) on 4/2/2008 8:02:22 PM , Rating: 2
I'm not defending the original poster, but AMD's roadmap never intended a 3.0 GHz processor, and they will not have one before the 45nm transition. It's already been confirmed with roadmaps that they will not ramp past 2.6 GHz even with the B3 silicon.

By Master Kenobi (blog) on 4/2/2008 1:28:10 PM , Rating: 3
Goodie. I've been rolling along nicely on my E6600 (Obtained at launch) so will be jumping on one of these as soon as they launch. Just have to factor in the cost of new memory (6GB) and a new motherboard.

*Note in Tripple channel configurations you buy memory in sets of 3, not 2. Last I checked DDR3 is supposed to come in 2GB Dimm's and higher. :P

RE: Waiting
By AstroCreep on 4/2/2008 2:06:12 PM , Rating: 3
*Note in Tripple channel configurations you buy memory in sets of 3, not 2. Last I checked DDR3 is supposed to come in 2GB Dimm's and higher. :P

Really? Three DIMMs?
Sorry, but that sounds...odd. :/ Literally and figuratively.

Well, I guess we'll see how well it works soon enough.

RE: Waiting
By Master Kenobi (blog) on 4/2/2008 3:56:52 PM , Rating: 2
Yes, so it looks like this.

On cheap systems instead of 2 Dim slots you get 3.
On high end systems instead of 4 Dim slots you get 6.

Typical of current systems you can load 2 Dimm's per memory channel. So Dual Channel systems are configured typically in 2 or 4 slot arrays.

Tri Channel systems will be arrayed in 3 or 6 slot configurations (1 slot per channel and 2 slots per channel respectively)

RE: Waiting
By imperator3733 on 4/2/2008 5:18:05 PM , Rating: 3
I thought the triple-channel controllers were only on the high-end Nehalems and the mainstream chips are supposed to still have dual-channel controllers.

RE: Waiting
By Master Kenobi (blog) on 4/2/2008 7:10:16 PM , Rating: 2
I'm not sure if this is a function of the system board or the CPU though. If it's the CPU then I expect the $300+ chips will be in the tripple channel range and anything less to end up dual channel. I'm thinking this feature is specific to the system board though.

RE: Waiting
By imperator3733 on 4/2/2008 9:09:53 PM , Rating: 2
I think it has to do with the fact that the high-end systems are using LGA1366 while the midrange chips will use LGA1160. LGA1160 doesn't have the pins for a triple channel controller.

RE: Waiting
By Kougar on 4/2/2008 7:43:15 PM , Rating: 2
Actually that is not quite true. Mainstream and cheap systems get a different platform, Lynnfield. ;)

Lynnfield is LGA1160 and sticks to using a dual-channel memory topology. This was geared for the mainstream market.

Bloomfield is LGA1366 and as you already said goes for triple-channel memory. This one is the extreme/enthusiast market grade chip.

RE: Waiting
By Master Kenobi (blog) on 4/3/2008 8:12:23 AM , Rating: 2
Got a link to information on that subject? I'm could use a good read.

RE: Waiting
By crystal clear on 4/3/2008 9:59:45 AM , Rating: 3
The best & most reliable reference material should be this-

Inside Nehalem: Intel's Future Processor and System

By: David Kanter

Currently, there are six variants of Nehalem slated to be released in the future. Gainestown is a Xeon DP product that is more or less the baseline for all Nehalem implementations as described in this article. It is a quad-core, 8MB L3 cache design with 2 QPI links and a triple channel DDR3 integrated memory controller. Bloomfield is more or less the same device, but targeted at the high-end desktop market, rather than servers. Both Gainestown and Bloomfield will come out towards the end of this year, likely in Q4 – although Bloomfield may not have SMT enabled.

Next up are Auburndale, Havendale and Clarksfield, which are a dual-core desktop, a dual-core mobile and a quad-core mobile processor. These three products are where the bulk of the differentiation will be needed. Power and clocking features will be used to distinguish desktop and mobile processors, and may even be used within the mobile market to stratify ultra-mobile parts versus mainstream parts. In general, the dual-core products (note all dual-core codenames end in “dale”, while quad-cores end in “field” or “town”) will continue to be the mainstream for both desktop and especially notebook systems (for power reasons). These mainstream CPUs will ship with smaller caches, perhaps 2-4MB, fewer memory channels (probably 2) and SMT disabled. There will also be a lot of options with respect to the chipset and graphics. Intel will aggressively push options that integrate the chipset and graphics in the same package – but OEMs are very likely to want some CPUs to use with third party chipsets from NVIDIA, SiS and the like (although how NVIDIA’s QPI license plays out is unclear right now), as well as some with discrete graphics. The quad-core Clarksfield is a little harder to pin down, as that is probably aimed at mobile gaming or workstations – where integrated graphics makes little sense, but an integrated memory controller and large L3 cache would be a boon.

The last Nehalem based product to come to market will be Beckton (or Nehalem EX), the Xeon MP variant, which is slated for 2009. At this point in time, very little has been said publicly about the product. However, it is possible to speculate with some degree of accuracy. Considering Dunnington is a 6-core design, Beckton will be at least 6 cores, but more likely 8. Since Beckton will contain at least as many cores, it will probably need at least as much cache as Dunnington. Beckton will have at least 3 and a half QPI links, so that the CPUs in a four socket system will be fully connected, but they may very well include more links to encourage further scalability. Beckton may also raise the virtual and physical addressing limits, based upon DRAM density, DIMM capacity and market demand for large memory configurations.

RE: Waiting
By Kougar on 4/3/2008 7:56:14 PM , Rating: 3
Off the top of my head, a link on Lynnfield:

For more info on Lynnfield and everything else regarding Nehalem in general:

While I ordinarilly wouldn't link to a wiki as proof of something, whomever designed the table under "Variants" here has all the information I've ever come across aggregated nicely.

RE: Waiting
By BSMonitor on 4/2/2008 3:04:46 PM , Rating: 2
Same here! Running smoothly at 3GHz, no tweaking.

But I wouldn't count on desktop Nehalem any time soon. No competition for Penryn let alone another processor that bumps the AMD/Intel performance gap even further.

RE: Waiting
By DudemanX on 4/2/2008 3:32:54 PM , Rating: 2
I too got an E6600 at launch too and am really happy with it. I don't see a huge need to jump on Nehalem right at release since the E6600 hits 3ghz easily and should still be pretty fast. I plan on waiting until Westmere which will be the 32nm refresh. It will probably have like 6 cores, more cache, and DD3 should be a lot cheaper by that time. Just a thought.

RE: Waiting
By Master Kenobi (blog) on 4/2/2008 4:00:26 PM , Rating: 2
The shrink refreshes aren't supposed to change the architecture too much (or number of cores). That is saved for new architecures according to Intel's Tick Tock cycle. I prefer to jump on the new architectures since the shrink/refreshes only bring a 5-10% advantage. New architectures tend to offer considerable improvements over the last gen.

RE: Waiting
By imperator3733 on 4/2/2008 5:20:32 PM , Rating: 2
They could add more cores with Westmere, just like they're doing with Dunnington. Of course it would probably only be for the server chips, but there might be some enthusiast chips with more cores.

Nahalem? Where's Penryn?
By Etern205 on 4/2/2008 3:53:20 PM , Rating: 2
With the Nehalem coming out soon, this really puts me into the position should I go with a Q9450 or X3350 with my current setup.

Should I just wait for the Nahalem, sell my parts and then build a new system because as of right now the 45nm mainstream quads are no where to be found and if there is, it's in limited quanitites!

Where the hell are the 45nm quads!?

RE: Nahalem? Where's Penryn?
By Master Kenobi (blog) on 4/2/2008 4:02:59 PM , Rating: 2
Penryn was always a stop-gap measure from the start. I personally prefer to jump on architecure cycles rather than buy during shrink cycles.

RE: Nahalem? Where's Penryn?
By KristopherKubicki (blog) on 4/2/2008 4:28:18 PM , Rating: 2
It's not really stop-gap ... Intel's architecture cycle is planned 2 year architecture changes followed one year later by the process node shrink of the same architecture.

RE: Nahalem? Where's Penryn?
By Master Kenobi (blog) on 4/2/2008 4:36:01 PM , Rating: 2
I thought Penryn launched a little later than originally intended.

RE: Nahalem? Where's Penryn?
By imperator3733 on 4/2/2008 5:23:04 PM , Rating: 2
Penryn's release date does make that seem likely. Conroe launched mid-2006, Nehalem is supposed to be late-2008, so why was Penryn very late 2007/early 2008? I think they had planned it for late 2007.

By KristopherKubicki (blog) on 4/2/2008 8:05:07 PM , Rating: 2
The server chips were considerably earlier though.

RE: Nahalem? Where's Penryn?
By shiznit on 4/2/2008 5:02:48 PM , Rating: 2
Valid method, but I prefer the other way around. Penryn should last me at least 18 months while Nehalem and DDR3 prices settle down.

By Master Kenobi (blog) on 4/2/2008 7:07:52 PM , Rating: 2
Yea, I'm skipping over Penryn entirely. My E6600 Conroe has served me well.

Here we go again...
By nordicpc on 4/2/2008 2:04:47 PM , Rating: 4
The QuickPath Interconnect will support triple-channel DDR3-1333 memory.

The QPI doesn't support any memory interface to speak of, the processor's integrated memory controller supports the interface. QPI will support communication between the processor and the MCP (or whatever Intel will call it).

RE: Here we go again...
By JumpingJack on 4/3/2008 3:14:41 AM , Rating: 2
This is correct, there is a subtle difference in terminology.

QuickPath architecture refers to the combiantion of on-die memory controller and QuickPath interconnect.

QuickPath interconnect is the branded name for the serial point to point links, formerly referenced as CSI.

RE: Here we go again...
By vignyan on 4/3/2008 5:06:29 AM , Rating: 2
At last... Thanks for bringing that to light.. before me! :D

Looking forward
By Elementalism on 4/2/2008 1:37:37 PM , Rating: 2
I am looking forward to this chip in my next machine. But the only thing that worries me is that anemic L2 cache. Yes it has a fat L3 cache, but that means lost cycles.

RE: Looking forward
By webdawg77 on 4/2/2008 2:02:27 PM , Rating: 2
The small size of L2 cache shouldn't matter because of the QuickPath Interconnect (QPI). This is virtually the same as HyperTransport for AMD.

AMD remained very competitive (and beyond) when HT was introduced even though it had very small L2 cache compared to Intel.

Intel's QPI will more than makeup for the reduced L2 cache along with the substantial L3 cache.

RE: Looking forward
By StormEffect on 4/2/2008 5:16:52 PM , Rating: 2
If the L3 works properly, the L2 should do its job without much downtime.

And the L3 should be assisted by the now on-die memory controller. No?

Can AMD stop Intel's Tick Tock?
By Proteusza on 4/2/2008 3:26:13 PM , Rating: 3
With its own Flip Flop?

RE: Can AMD stop Intel's Tick Tock?
By vignyan on 4/3/2008 5:08:53 AM , Rating: 2
lol.. Nice rhyme.. obviously rated down! Anyways, I cant stop remembering the "bearer of white spear" in the movie 10000BC... His name was tick tock.. :D

By lordsaytor on 4/3/2008 10:29:52 AM , Rating: 1
Haha nice one!! 10000BC is the worst movie I've ever watched on a 50 foot screen in my whole miserable life.

Octo-core on the desktop?
By OddTSi on 4/2/2008 3:55:53 PM , Rating: 2
You mention in the article that octo-core Xeon processors are coming, will Intel also be releasing octo-core desktop processors as well or will we have to wait a while for that?

RE: Octo-core on the desktop?
By winterspan on 4/2/2008 6:28:56 PM , Rating: 2
For Nehalem 45nm at least, "octo-core" will be limited to MP (4+ socket) Xeons.
Standard DP (2 socket) servers and workstations (like Mac Pro) will use quad-core just like the desktops (and high-end laptops).
Also, current schedule has the 8-core Xeon MP not ready for another year after Nehalem launches in Q4 2008, which seems to be the trend with Intel's MP server chips ala Tigerton.

for the editor:
. Each physical core in a single Nehalem processor is paired up with its own virtual core. As a result, the processor is treated as having eight threads/processors.

Wrong. Each physical core is paired up with TWO virtual cores.

RE: Octo-core on the desktop?
By PlasmaBomb on 4/8/2008 9:58:11 AM , Rating: 2
Wrong. Each physical core is paired up with TWO virtual cores.

Sorry, try again...

what does nehalem mean for ddr3 pricing?
By nerdye on 4/2/2008 9:37:54 PM , Rating: 2
I'm curious how the ddr3 pricing will become after nehalem is released, I can imagine that it will increase greatly.

This reminds me of the ddr2 pricings that went sky high after the launch of core 2 duo. Pentium 4 was the first adopter of ddr2 and it was met with minimal gains over ddr1 on that platform, then core 2 duo the cpu that really took advantage of it was released and all the sudden ddr2 got really expensive.

Now we have core 2 duo which is the first adopter of ddr3, and achieves minimal to good gains from it on the super high end of things. Once nehalem comes out can we expect the super expensive ddr3 modules to be priced even higher?

By Silver2k7 on 4/10/2008 6:48:03 PM , Rating: 2
"I'm curious how the ddr3 pricing will become after nehalem is released, I can imagine that it will increase greatly."

DDR3 is already = 3-4x more expensive than DDR2

If Nehalem will use it im sure production will increase and price will become lower..

Who's on first ?
By snarky on 4/3/2008 9:56:55 AM , Rating: 2
So Quickpath idea is copied from Hypertransport ?? and AMD copied that idea from... DEC Alpha?? ...which is owned by...

RE: Who's on first ?
By Master Kenobi (blog) on 4/3/2008 12:58:41 PM , Rating: 2
Quickpath is considerably different than Hypertransport. While it serves the same function, Quickpath has the neat ability to function on Electric interconnets, light based interconnects, or a hybrid of the two. Hypertransport would not work in it's current form on a light based interconnect.

By jimpaka on 4/2/2008 2:13:53 PM , Rating: 2
These octo-core Nehalem processors will also use the newest iteration of Hyper-Threading, bringing the total count to 16 threads per core. And of course, these processors can be used in quad-socket configurations, bringing the processor market to 64 threads per mainboard.

Not 16 threads per core, 16 threads per CPU.

ps: Intel pwnz.

RE: typo
By lordsaytor on 4/3/2008 10:34:40 AM , Rating: 1
Seriously. 2 threads per core at 8 cores per cpu. That is just insane. And yes Intel absolutely pwnz (Ala 10 headshots in a row in CS)

More info on Nehalem & QuickPath
By Murst on 4/2/2008 2:40:19 PM , Rating: 3


Sure, there's a lot of marketing stuff, but this architecture does look like it will be more revolutionary than evolutionary. Probably not as much as P4 -> C2, but its still pretty good.

Octal cores? Sweet!
By DeepBlue1975 on 4/2/2008 4:36:58 PM , Rating: 2
I'll wait for the 8x version to get interested.
I doubt I will really notice a huge difference changing my q6600 for a quad penryn or a quad nehalem when it gets out.
Specially considering the fact that by the time nehalem comes out, I'll need to ditch my actual motherboard and memory, so, if I am going to have to pay big bucks, I'll rather get a really big improvement in performance and only octal cores will mean that to kind of step up for me.

Rendering, encoding / decoding multiple video files, and being able to heavily multitask benefits a lot from multiple cores.
Though I find it hard for gamers and the likes to even justify getting a quad core as of now, so they rather get some "nehalemons" with only two cores or otherwise they will make a full line of CPUs fall under a niche market or those who blindly believe in a multicore hype by thinking that every using scenario will take advantage of a lot of CPU cores.

DDR3 1337
By CryptoQuick on 4/5/2008 2:11:55 AM , Rating: 2
You know I'mma have to bump this up to 1337 MHz

By cooldude 345 on 4/5/2008 7:17:30 PM , Rating: 2
how could you still be a fanboi of amd after all that has ha[ppened if anything it is you who is the idoit not those who support intel

"Let's face it, we're not changing the world. We're building a product that helps people buy more crap - and watch porn." -- Seagate CEO Bill Watkins

Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki