Intel talks Penryn, quad-core mobile chip due in 2008

Now everyone waiting for Santa Rosa Macs have reason to wait further.

I was just going to say the same thing. These are the chips those with G4 books are waiting to upgrade to. Add to that a third version of Leopard and these systems will kick some real ass.:)

MacWorld has an aritcle with a bit more info on the new chips and Santa Rosa platform for those who are interested.

You can get it here (http://www.macworld.com/news/2007/04/16/santarosa/index.php?lsrc=mwrss).

I thought the stated goal of providing a Penryn-based quad core mobile processor that could go into a an iMac was exactly what a lot of people have been asking for, no?

Also, according to the MacWorld article:
Underscoring how close these chips are to commercial availability, Eden showed off a laptop running a Penryn mobile processor at a press event ahead of the companys Intel Developer Forum conference, which starts in Beijing Tuesday. The product is pretty healthy, Eden said.
Seems we may be seeing these things faster than many expected. :D

Seems like a perfect fit for the iMac where battery life is no concern but high performance in a small package is.

"...but I don't see it running so fast into the mainstream because I don't believe there will be enough threaded applications that will justify the tradeoffs,"

C'MON DEVELOPERS DEVELOPERS, DEVELOPERS!

Get your multi-threaded butts in gear!

Now though, all of a sudden Penryn refers to *every* chip in that refresh, and confoundingly, the mobile variant has been pushed back to 2008, with quad core even further out.

Like Merom, Penryn is the code name of the family design, and the mobile chip.

Merom family:

Mobile: Merom
Desktop: Conroe
Workstation: Woodcrest

Penryn family:

Mobile: Penryn
Desktop: ?
Workstation: ?

and confoundingly, the mobile variant has been pushed back to 2008, with quad core even further out. This is especially confusing to me because I was expecting Nehalem to be out in late 2008. How can that be true now? Is mobile Penryn going to have a 6-month shelf life?

Napa: current platform, Merom 65nm mobile processor
Santa Rosa platform: first half of 2007, Merom 65nm mobile processor
Santa Rosa platform refresh: first half of 2008, Penryn 45nm mobile processor
+ quad-core Penryn mobile processor to be released in 2008
New microarchitecture: 2008, Nehalem family, 45nm mobile processor.

According to this Intel slide (http://www.hardocp.com/image.html?image=MTE3NTEwMDMxMXQ3YWVINUoxb2ZfMV8xX 2wuanBn).

C'MON DEVELOPERS DEVELOPERS, DEVELOPERS!

Get your multi-threaded butts in gear!

They are working on it. It's one of the hardest areas in software development.

I think the last part of your statement is the most interesting of possibilities for Apple: namely will they offer a CPU upgrade service for their Santa Rosa platforms when Penryn becomes available?

I could see that causing a lot of excitement if Apple offered it through their Genius Bars.
:wow: :wow: :wow:

The only time I remember Apple ever doing that was when they moved to the PPC. I bought an Apple board to put into my 950 that let me dual boot into either a 68xxx environment, or a PPC one.

But, I don't remember Apple ever offering any others.

The advantage to having Intel chips is that you can always buy them retail, and insert them yourself (as long as it isn't soldered!!), or have a technician do it for you.

The disadvantage to Intel chips is that we can no longer get the almost infinite chip upgrades we used to enjoy up 'till the G5 series.

Normally, you can only move to the next higher chip on the same socket, which wasn't much. Now, you can put a 2 core chip in a 1 core socket, or a 4 core in a 2 core socket, as long as the chip exists for that socket. Better than nothing.

You call that technology? I could solder that thing by hand.

Just kidding.

So is this guy saying that Penryn will be pin-to-pin socket-compatible with Santa Rosa chips? If so then Santa Rosa WILL be a good time to buy... provided Apple doesn't freaking solder the chips into the board.

-Clive

You call that technology? I could solder that thing by hand.

Just kidding.

So is this guy saying that Penryn will be pin-to-pin socket-compatible with Santa Rosa chips? If so then Santa Rosa WILL be a good time to buy... provided Apple doesn't freaking solder the chips into the board.

-Clive

That does seem to be what they are talking about. But, it is likely that Apple will solder the chip to the board in the laptops. It's the iMac where this takes on greater significance.

Unless Apple surprises us with the portable line.

That does seem to be what they are talking about. But, it is likely that Apple will solder the chip to the board in the laptops. It's the iMac where this takes on greater significance.

Unless Apple surprises us with the portable line.

Let's hope Apple decides to surprise us.

This could alleviate some folks' concerns about the upgrade path for the iMac. If all you had to do to upgrade both the graphics card and CPU was to take it into an Apple Store and let them upgrade you, I think a lot of people might suddenly have a different opinion of the iMac.

Although the hardcore DIYs are going to whine even so. :rolleyes:

Everything I read, and everyone I speak to thinks that the move to 45 nm is one of the most important to date, even more important that the move to 65 nm.

There seems to be a threshold that was passed with 45 nm. For Intel, it's Nehalem, for example. That's something they haven't wanted to do before now. With most of the problems of 65 nm solved, 45 nm will be able to do things that were only hoped for with 65 nm, but never accomplished.

One major area is cpu speed. We're beginning to see that rise again. And to those who think that it isn't important, think again.

Let's not overlook the new memory structures that are supposed to come with Penryn MBs. I have heard that Intel is going to look more like an AMD memory set-up. Supposed to be much faster and better able to feed multiple cores.

That comes with Nehalem. That will have the memory controller on the core, just as AMD has now. The chips will also bring back Hyperthreading.

For those who think that AMD will catch up with Barcleona, uh uh, it ain't gonna happen. At best, AMD will move closer, but then will fall further behind in 2008.

Just think, Intel has moved as far ahead of AMD as they have, WITHOUT using those technologies

Oh well, I had hoped for the new memory controller on Penryn, but a Penryn Mac Pro is my next machine. :D

I am hoping for a November purchase, if not sooner.

Try this on for size:

http://www.reghardware.co.uk/2007/04/16/intel_rapid_santa_rosa_ramp/

apple should put a DESKTOP CPU in the I-mac and come out with a headless mid-range mac as well

I have a feeling Apple has thought about that. From what I know of this chips, Apple can either had a desktop CPU in the iMac -or- make the iMac quite a bit smaller now that it currently is.

However, I have a feeling that Apple will keep with the low-power processors and make the next iMac super slim. The reasoning, I think, is that customers look at appearance and want to know if it can run their programs. To a lesser extent they look at the speed of the processor. Most people buying an iMac aren't wondering what cryptic Intel names chip is being used.

Apple is also thinking about "quiet". A Conro, despite all of its virtues, is not going to be as cool, use as little power, or be as quiet.

Great news! Better technology is coming in the future!

This kind of post always makes me laugh a bit. They could announce any upgraded processor is coming out in a year and everyone would post the exact same responses.

It's at the same time comforting that yes, the future holds smaller and faster computers and yes, apple insider posts will never change!

The one thing I miss about PPC is the simple naming convention IBM gave their processors.
PPC970FX, PPC970MP, 7407?

That's hard. Bonus points if you can name the processors "Apple name".

I should have made myself clear. I'm referring to the marketing names, not the internal naming convention.

Core 2 Duo, Core 2 Quad, Xeon.

I just think what you said is wrong.

:smokey:

Seems like a perfect fit for the iMac where battery life is no concern but high performance in a small package is.

My laptop spends 98 percent of it time connected to a power source, if I need more battery I can get an extra one. CPU POWER is king.

Like Merom, Penryn is the code name of the family design, and the mobile chip.

Merom family:

Mobile: Merom
Desktop: Conroe
Workstation: Woodcrest

Penryn family:

Mobile: Penryn
Desktop: ?
Workstation: ?

Uh... no. There was no "Merom" family. Merom was always only the Mobile chip for what throughout 2006 was referred to first as the "Next Generation Microarchitecture" and then simply "Core 2". Those were the names for the family of chips that consisted of Merom, Conroe, Woodcrest, Kentsfield and Clovertown.

And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).

Napa: current platform, Merom 65nm mobile processor
Santa Rosa platform: first half of 2007, Merom 65nm mobile processor
Santa Rosa platform refresh: first half of 2008, Penryn 45nm mobile processor
+ quad-core Penryn mobile processor to be released in 2008
New microarchitecture: 2008, Nehalem family, 45nm mobile processor.

According to this Intel slide (http://www.hardocp.com/image.html?image=MTE3NTEwMDMxMXQ3YWVINUoxb2ZfMV8xX 2wuanBn).

Exactly, that's what I'm saying -- previously, until Intel started releasing more details last month, Penryn was supposed to be a mobile chip to be released in 2007, alongside a desktop chip with another name; now it's a "family" whose mobile variant will be released in 2008. Furthermore, that mobile Penryn, its later quad-core brother, and Nehalem, a completely new architecture, are going to all be squeezed into that one year. It just seems strange to me, enough so that I'm starting to think that the Mobile version of Nehalem will have to wait for 2009. I would point out that the very fact that mobile Penryn is coming out in '08 is a blow to the whole 2-year "tick-tock" cycle Intel has been hyping. The last "tick" was in 2006, so the "tock" was expected in 2007, but no more.

This isn't sudden. Penyrn has always stood for their first iteration of their 45 nm process. Just the way that Core, and then Core 2 stands for the 65 nm chips, exzcept for the very new, and end of process cycle 4 core chips.

No; Core and Core 2 are the marketing names for two different architectures, whereas Penryn is a codename, like Yonah. Presumably Penryn will be marketed as Core 2 as well, since this is just a die shrink and not a new architecture. But no, as I indicated above, Penryn didn't always stand for the entire 45nm line, it had previously been just one of the chips in that line. Likewise, back when Core was the current model, we knew Intel had plans for a new microarch with three codenames, one for each chip in that line.

Nehalem will be for the newer chips coming out somewhere in the first half of next year. The two will be around, and share developement for a while.

Everything I've read indicates mid-late 2008 for Nehalem. What I'm saying is that it seems strange that they would squeeze both the (mobile) die shrink, the quad core of that die shrink, and the brand new arch into the first let's say 9 months of 2008, yet release virtually no new mobile processors in 2007 besides a speed bump when Santa Rosa comes out (2.33GHz to 2.4.. big whoop). It's just a little disappointing and confusing is all.

Seems like a perfect fit for the iMac where battery life is no concern but high performance in a small package is.

I agree, but Apple apparently doesn't; they could have quad-core, 2.93GHz iMacs now if they wanted, but they prefer to stick with Merom for some reason. If it's just pin compatibility, then maybe they will upgrade when this new processor comes out. On the other hand, if they really are excessively concerned with fan noise and/or not letting their consumer desktop outperforming their pro laptop, then no.

Not quite. The Core 2 family was Merom, Conroe and Woodcrest, the Core 3 will be Penryn, Wolfton, and Tigerton. I think that Nehalem will have a new name.

This would be spot on based on what the hardware sites were reporting a few months ago, but they've now changed it and the Penryn name now covers the entire gamut of 45nm processors. Doesn't make any sense based on past precedents, but there you have it.

Are you sure Penryn will be Core 3, though? I would think they'd stick with the Core 2 brand since Penryn is just a shrunken Core 2.

And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).

Whatever they had said, Penryn is the name for the first line of 45 nm chips.

Exactly, that's what I'm saying -- previously, until Intel started releasing more details last month, Penryn was supposed to be a mobile chip to be released in 2007, alongside a desktop chip with another name; now it's a "family" whose mobile variant will be released in 2008. Furthermore, that mobile Penryn, its later quad-core brother, and Nehalem, a completely new architecture, are going to all be squeezed into that one year. It just seems strange to me, enough so that I'm starting to think that the Mobile version of Nehalem will have to wait for 2009. I would point out that the very fact that mobile Penryn is coming out in '08 is a blow to the whole 2-year "tick-tock" cycle Intel has been hyping. The last "tick" was in 2006, so the "tock" was expected in 2007, but no more.

Not exactly. Penyrn is the tick, and Nehalem is the tock. You're forgetting that all of these lines overlap. The tick is still ticking while the tock starts its tocking.

No; Core and Core 2 are the marketing names for two different architectures, whereas Penryn is a codename, like Yonah. Presumably Penryn will be marketed as Core 2 as well, since this is just a die shrink and not a new architecture. But no, as I indicated above, Penryn didn't always stand for the entire 45nm line, it had previously been just one of the chips in that line. Likewise, back when Core was the current model, we knew Intel had plans for a new microarch with three codenames, one for each chip in that line.

You're contradicting yourself. Core and Core 2 were different architectures (to a certain extent). Penyrn and Nehalen will also be different architectures as well. There are names given that are changed once the chips come out as well.

Everything I've read indicates mid-late 2008 for Nehalem. What I'm saying is that it seems strange that they would squeeze both the (mobile) die shrink, the quad core of that die shrink, and the brand new arch into the first let's say 9 months of 2008, yet release virtually no new mobile processors in 2007 besides a speed bump when Santa Rosa comes out (2.33GHz to 2.4.. big whoop). It's just a little disappointing and confusing is all.

I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.

I agree, but Apple apparently doesn't; they could have quad-core, 2.93GHz iMacs now if they wanted, but they prefer to stick with Merom for some reason. If it's just pin compatibility, then maybe they will upgrade when this new processor comes out. On the other hand, if they really are excessively concerned with fan noise and/or not letting their consumer desktop outperforming their pro laptop, then no.

They ARE exceffively concerned with fan noise. Actually, I would say obsessively instead. Consumers are used to hearing nothing from their Tv's audio systems, etc. Apple is trying to make their computers for the home meet that expectation.

[/quote]
This would be spot on based on what the hardware sites were reporting a few months ago, but they've now changed it and the Penryn name now covers the entire gamut of 45nm processors. Doesn't make any sense based on past precedents, but there you have it.

Are you sure Penryn will be Core 3, though? I would think they'd stick with the Core 2 brand since Penryn is just a shrunken Core 2.[/QUOTE]

I don't think we'll see "Core 3".

And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).

I don't know, on Intel's site (http://www.intel.com/technology/architecture/45nm_core2/index.htm) the code name is used to describe the whole family. It's not really important, though. :)

I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.

I think you're right, Intel won't refresh the CPU and the platform simultaneously. Santa Rosa will debut with Merom in May, Penryn is slated to hit production later this year and will be paired with Santa Rosa.

first half of 2006, new mobile platform: Napa (with Yonah mobile processor)
fall 2006, new microarchitecture: Merom 65nm mobile processor (in Napa platform)
first half of 2007, new mobile platform: Santa Rosa (with existing Merom mobile processor)
fall 2007, processor die shrink: Penryn 45nm (in Santa Rosa platform)
first half of 2008, new mobile platform: Montevina (with existing Penryn mobile processor)
fall 2008, new microarchitecture: Nehalem 45nm (in Montevina platform)

If there won't be a Core 3, then what's the differentiation between the lower speed/performance Core 2 parts and the new Penryn line cores?

I think Core 3 sounds logical.

It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.

Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.

Don't worry, time isn't standing still as it was with the PPC.

I know. I'm just pointing out that, and the release date, are a change from a few months ago.

Uhh... I don't think it really matters whether we designate the die shrink the "tock" or the architecture change. Yonah was a die shrink, Merom/Conroe/Woodcrest was a new arch, Penryn will be a die shrink, Nehalem, a new arch.

It doesn't matter what we think. This is Intel's ball. They do the naming, not us. They say that the die shrink is the tick, and the architecture improvements are the tock. It makes perfect sense.

I'm not contradicting myself at all. Penryn is not a new arch -- it's just a shrink of an existing one. Nehalem, on the other hand, is new.

Yonah = Core = a hybrid arch of Pentium-M and new features
Merom/Conroe/etc = Core 2 = "next generation" microarch
Penryn = a shrunken Core 2 with higher clockspeeds
Nehalem = a brand new architecture

I'm not saying Penryn is insignificant, it's just more evolution than revolution. It's just a die shrink, whereas Core->Core 2 was a new arch altogether, so I am supposing that "Core 3" will refer to a new arch, and thus Nehalem, as well. It seems pretty obvious to me.

Peryrn also has changes, it's not just a die shrink. There are notable improvements over the current Core 2 designs.

This is a good article detailing most of what we can expect from both Penyrn and Nehalem.

http://www.extremetech.com/article2/0,1697,2108905,00.asp

I hope that's true (where are you "reading" this though? All the new info suggests otherwise), I just don't understand why rumor sites and hardware sites are reporting "early 2008" for mobile Penryn without mentioning that it's a push back from the original date. Imagine the screaming if Apple announced a product and then pushed it back.. oh, wait ;)

Mobile Penyrn has apparently been pushed back because of design changes which were enumerated in the Article about them that I linked to yesterday.

I'll have to look some more for articles with more about the dates if you are really interested. I don't think that 6 months is all really that important though.

Why not?

I just don't think that Intel will continue with that naming convention.

Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.

If you read the article I posted, you would see that Intel considered the tick not to be Core, but to be the processors before it, the last Pentium 4, Northwood. The tock was then the Core 2.

I just don't think that Intel has an interest in using "Core 3" as a product name. That's all. I'm not so sure why you think it's so important that they do.

The Nehalem is a bigger departure from, according to Intel, pretty much any other cpu design of theirs in recent years. I think they will want to differentiate it from what has gone before.

That's not true (MacSuperiority, this is my opinion, as your post *is* true but with an added bit of speculation).

There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.

For the purpose of full disclosure, I hate the Intel "Core" name. Maybe the Nehalem chips will be "Intel Nehalem 4 quad/octo" or some equally terrible name like that. Maybe I just like AMD too much.

Yuk! I just noticed that I hadn't done spell checking.

Core Duo= Yonah. Still based on the Pentium M architecture that spawned Dothan and Banias.

Core2 Duo- Based on the Merom core which means Conroe/Woodcrest

They are most definitely different cores. The FP units in Merom are more closely aligned with Netburst arch CPU. Intel basically took the best of Pentium M power management and took Netburst arch...bred them and voila. Merom.

Nehalem should be called a different core since it's quite a significant change as Melgross has stated.

That's just Intel's marketing talk because they don't want to admit how much of a screw-up Netburst was. In reality, the Core 2 microarchitecture is almost entirely an evolutionary step from Pentium M.

Netburst wasn't really a screwup though.

No one anticipated the leakage and other problems they would have. That affected everyone. Remember IBM's 3 GHz promise? That was due to that problem as well. We were supposed to see 4 GHz G5's, at least. IBM was talking about 5 and 6 GHz successors as well. What happened there?

AMD was lucky on two fronts. They had designs that were actually closer to the G5 in some ways, so had higher performance at lower clocks. And they were so far behind on process, that they were able to benieit from the solutions that both Intel and IBM came up with.

It hasn't helped them now though. As we can now see, their designs aren't that good. It's only the on-board memory controller that's keeping them in the race, and it was the only thing that kept them slightly ahead of Netburst back then.

Core Solo - single core
Core Duo - two cores
Core Quad - four cores

Solo, Duo, Quad, Octo - to mention no of cores rite?

Core, Core 2, Core 3 - to mention architecture changes rite?

After reading all the posts, i am confused now :(

The original number of cores for those lines was only one reason Intel used those naming conventions, and not the most important one at all.

About the confusion: Don't worry, we are all confused, as always. :)

The engineers at Intel knew there would be problems. Netburst was the bastard child of marketers who had no idea what went into chip design.

And for you to say that AMD's core design "isn't that good", you should stop acting like you know about core design, because that's entirely untrue.

Really? How very interesting.

So, Netburst was designed by marketing people? Perhaps you should read up on the technical history of the chip familly. At the time they were doing it, there were very few people who criticized what they were doing.

The reason why I said that AMD's design weren't very good, is because, even as Netburst failed to advance the last 18 months of its life because of the finally realised leakage problems, AMD's "superior designs, even with the on die memory controller, only managed to eck out about a 15%, on average, performance advantage.

As soon as Intel understood that Netburst was going nowhere, they changed. Even using old Pentium 3 designs, with improvements, they were able to move ahead of AMD. With Core 2, they moved well beyond AMD. As much as 40%

During the last 18 months, a long time in processor design, AMD has gone nowhere. The new socket, the updated K8, nothing has made a dent in Intel's leading position.

Barcelona is the first shot they have of catching up, and it will debut at only 2.3 GHz, because they can't get it any higher, on the same process shrink that Intel is delivering 3 GHz 4 core parts.

So, I'm not impressed with AMD's designs.

They only looked good because Intel had problems moving Netburst up in speed due to the unexpected leakage problems. Once Intel changed their direction, the poverty of AMD's design labs became apparent.

They are working on it. It's one of the hardest areas in software development.

Writing multi-threaded mac apps isn't very hard. It isn't as easy, however, for Windows, but it's still my opinion that only dumb programmers have problems getting stuff multi-threaded. Yes, there are plenty of dumb programmers out there, but they're not working for the companies that make high-performance software. If there are some utility apps and the like that aren't well multi-threaded, that's not going to be much of a problem. What's more important is that the Adobe suite, Mac OS, and other major apps are nicely multi-threaded. This seems to be the case already.

Any one have a guess when in May 2007 Santa rosa will be released?

Any one have a guess when in May 2007 Santa rosa will be released?

http://computershopper.com/shoptalk/2007/03/07/intel_centrino_pro_set_to_laun

The 9th, possibly.

http://computershopper.com/shoptalk/2007/03/07/intel_centrino_pro_set_to_laun

The 9th, possibly.

Did you to buy those huge copies of Computershopper from the newsstands like I did?

'fraid not. I merely searched for any information on a proper date, and this came up. ;)

That was a big part of computer history. I still keep two copies for historical reasons.

Haven't we learned that clockspeed doesn't equal performance?

No, we haven't.

The MHz myth was itself a myth.

Look, there is a great deal of misunderstanding about all of this. MHz matters. Indeed it does!

Where the concept goes wrong is when one compares different architectures.

Comparing the same architecture gives results that make sense. A chip of the same line will always perform better if it runs faster. That's pretty simple. If you compare totally different chip families, then the equation breaks down. A 2.5 GHz chip from one family may be as powerful as a 3.0 GHz chip from another family. But, if you are comparing the same families through their speed ramps, that will hold true. So, you can still make a comparison. AMD did that with the naming of their chips. They used to name them according to the INTEL speed they would perform at (at least, according to AMD).

Intel and AMD went in different directions. Intel always had the better process technology. Because of that, they were able to produce chips that AMD couldn't, e.g.. long pipelined architectures. That gave the chips great speed, and as long as the shrinking process technologies were up to it, an insurmountable lead over AMD, which over most of its history, was hapless.

AMD, on the other hand, not having as good a good process technology, needed to work around that. They found a way with their designs, which like the PPC, relied more on width than length, so to speak.

This only began to work once the 90 nm process shrink came about. Until then, smaller processes led to less current, which led to less total power, which led to less heat, which led to faster chips, which led to Intel kicking the crap out of AMD, year after year.

But, when the 90 nm shrink led to a suddenly huge increase in leakage, as well as other power related problems, Intel's relentless march to the ultimate speed came to a grinding halt.

During that same period, IBM found it had the same problem. But, IBM, like AMD, was running chips that already had a wider path, and other differences, that gave them greater processing power at a lower clock.

Because of that, when Intel took 9 months to raise the clock of their chips from 3.06 GHz to 3.31 GHz, both IBM, and AMD, were able to raise theirs by a larger percentage, because they were at a lower clock to begin with.

But, even at the peak of AMD's newfound dominance, their fastest chips never were more than about 15% better than Intel's. IBM's were about 5% less in performance than Intels, and about 20% less than AMD's.

Remember that with all of this, AMD had the on-die memory controller, and Hypertransport. Both of those gave AMD all of their performance advantages, proving that their basic chip designs in and of themselves were no better than those of Intel, possibly a bit worse, and about the same as those from IBM.

Intel's Hyperthreading had no use on most programs, and indeed, was blamed for actually slowing down its performance often, as programs weren't designed to take advantage of it.

You must have noticed that the very first generation of chips that left the Netburst line moved easily past the best that AMD could offer.

The generation past that moved far past AMD's best chips.

With all of that, the best is yet to come from Intel. In 2008 we will see on-die memory controllers, the return of Hyperthreading, now that programs will be able to use it, a much better vector processor, and even a rival to Hypertransport.

What's a chip company like AMD to do?

They can't afford to do the R&D that Intel routinely invests in. One thing they will do is to wait until Intel does the R&D, and copy it with some curves of their own, assuming that Intel doesn't patent them first.

But, they are again, a full process shrink behind. that only makes it worse.

And don't think that Intel isn't holding back!

Apple's coming out with factory authorized 3.0 GHz Cloverdales, significantly faster than the standard 2.66 GHz versions, shows that Intel's designs are reliable enough to sell to a high profile customer at faster than announced speeds.

In fact, Intel's chips overclock so well, that many in the industry think that Intel is deliberately underclocking them.

On the other hand, AMD's recent chips hardly overclock at all, showing that they have barely any margin.

It's been thought that Intel is teasing AMD with these speeds, daring them to attempt a faster chip, which they will trump as soon as it's announced.

At any rate, 2008 should be an eventful year for us in Macland.

I know enough about CPU architecture to at least compare the CPUs (thanks Anandtech)

Quite honestly if we were talking about Cell and AMD/Intel clockspeed wouldn't give us much info. However with Barcelona we know that AMD has what a 3 or 4 issue core. I believe it's 3 so the at best they are matching the Intel chips. So clockspeed makes a huge difference.

Then you movie to caching and memory bandwith which AMD has advantage with as Melgross has stated until Nehalem at least.

I see AMD keeping up but not surpassing Intel. I want AMD to stay close enough to keep Intel honest. So if I build a PC it'll be with an AMD CPU.

So what is a realistic estimate of seeing these penryns in macbook pros, late 07, or earlyish 08

Apple is certainly going through some changes. We can't even rely on "Apple Tuesdays" anymore. I have tried to run the numbers but I can't find any path that seems more likely than another path based on previous history.

The factors I use in my attempt to find an answer: age of current system
mobo redesign difficulty
availability of new processor
remaining stock of current processor
cost difference of processor
performance difference
power usage difference
There are other factors that I can't possibly know. I've also read--on one site--that the Gilo (65nm) as the successor to Merom, but I think Apple will stick with Merom until the Penryn is out. If I had to guess, I'd say that we won't see Penryn until April 2008.

So what is a realistic estimate of seeing these penryns in macbook pros, late 07, or earlyish 08

I think Intel's stance on Penryn mobile is early 2008 so I agree with Solipsism

http://www.intel.com/pressroom/archive/releases/20070328fact.htm?iid=pr1_marqsub_20070328r

if we read the article carefully, it states Core 2 Quad

PENRYN - Core 2 - with newer CPU numbers
NEHALEM - Core 3

Yes, I discussed that in another post. Intel added to those families later, but the original numbers held true.