Intel 45nm Fab Process Launched And Penryn Preview

NinjaKicks writes "Intel has decided to make public details of their new 45nm manufacturing process and also has broken news that next-gen Penryn core processors are running various versions of Windows and Vista successfully. Penryn will offer a host of core tweaks over Conroe, larger cache sizes, and SSE4 support. Also, although clock speeds will be increased, processors based on Penryn should fall within the same thermal power range as Conroe. Word is Penryn will also be compatible with some of the existing motherboards on the market while others will need either a BIOS update or perhaps other board-level changes."

Re:

[Harmonious Botch]

It will when I get one.

Re:

[Guy Harris]

But does it run linux?

Yes [intel.com]. (Just search for the "L" word.)

Re:

[cp.tar]

Can I see the clock speed boosted? Not everything can be parallelized and besides I don't think anyone at Microsoft knows how to.

Who knows, maybe we're looking at the days of assembly programming again... you know, the days of well-written, optimized software?

The ever-growing processor speed had all but removed the need for optimization; maybe the long-forgotten art is facing a revival...

I have been convinced...

[Belial6]

I have been convinced for a long time that software bloat is not a problem. You touch on the reason. For the last decade, it has been cheaper to throw more hardware at a problem than it has been to optimize code. At some point in time, there will likely be a stall in speeding up hardware. When that happens we have a many years of continuing our computer speed ups via software optimizations. Heck, I know that I write inefficient code all the time. It is a simple cost/benefit choice. My clients do not want to pay tens of thousands of dollars to solve a problem that can be solved with $1000 worth of hardware. It's not that I couldn't optimize my code, and it's not that I wouldn't love to optimize my code. It's just the most companies don't want to pay for it.

Re:

[cp.tar]

It's not that I couldn't optimize my code, and it's not that I wouldn't love to optimize my code. It's just the most companies don't want to pay for it.

I have encountered the same problem regarding good translations. I could do them, and I'd love to do them, but no-one in my country would pay me their worth.

Re:

[Raenex]

At some point in time, there will likely be a stall in speeding up hardware.

Yes, that's been the case for at least 4 years now. That's why there's been the push for multiple cores. The Free Lunch is Over [www.gotw.ca]

Re:

[Surt]

Most significant software projects already have a performance optimization phase. You run a profiler, find out where your application spends 90% of its time, and you fix that. The fact that software today in some cases seems slow mostly has to do with it doing more, not a lack of optimization. There are exceptions, but by and large most software cannot be made even twice as fast without loss of functionality.

Re:

[Surt]

OpenOffice and MS Office, while superficially similar do significantly different work. OpenOffice is multiplatform, which means its presentation layer and file system layers at least have to be very generalized, and that will account for most of what you experience as slow. MS Office gets to use native APIs, and unpublished APIs that allow it to be faster than any competitive application on the windows platform. Compare that to MS Office for Mac, which everyone experienced as horrible compared to the win

Re:

[shankarunni]

Can I see the clock speed boosted? Not everything can be parallelized and besides I don't think anyone at Microsoft knows how to.

Another blurb in TFA talks about this:
HK + MG Combined:

• Drive current increased >20%, (>20% higher performance) OR
• source-drain leakage reduced >5x

What this means is that you can get higher performance (~20%) at the cost of higher power consumption (on the order of today's processors), OR you can get the same performance at substantially (not 1/5x, though) reduced power. The first few Penryn processors are apparently targeted at the Mobile market, so we can see where they are going with thi

Re:

[Joe The Dragon]

In the sever market the power consumption of the FB-DIMM's are alot higher then ECC DDR 2

Re:

[Ghoser777]

I hope you realize that clock speed is only one measure of the performance of a machine, and that increasing clock speed can trade off with other important factors.

Re:

[dreddnott]

While Intel's ridiculously inefficient Netburst core might be the impetus for your post, that's not Business as Usual.

When Intel moved from the 80386 to the 80486, the FPU was integrated for the first time, as was onboard cache, and instruction execution rates nearly doubled on a clock-for-clock basis. The eventual clock speed of the 80486 was 100MHz, three times the speed of the fastest Intel 80386 at 33MHz (AMD released 133MHz and 40MHz versions of the 80486 and 80386, respectively).

Going from the 80486 t

Re:

[init100]

They may give us 8 cores at 4 Ghz instead .. but that's cheap crap, you can bet the compilers and apps for it will be donkey inefficient. I hope a competitor realizes the importance of instructions per second.

I hope you realize that there are some physical limits and constraints that cannot be broken, or can be broken at a massive disadvantage for other parameters. If I don't remember wrong, power consumption and therefore heat emission is proportional to the square or even the cube (at least nonlinear) of the clock speed at a certain manufacturing process. So you might have a 33 GHz processor (10x speed increase compared to what we have today) but the power consumption would increase from about 100 watts to 1

Re:

[trimbo]

Not everything can be parallelized

Most things that desperately need to be parallelized can be when someone takes the time to do it. What's the most CPU intensive thing the average user does on their computer? Media encoding? Gaming? Both of these are ripe for parallelization if someone spends the time to do it. Even high end computational uses like fluid dynamics and 3D rendering are parallelizable.

The multi-core strategy has been superb for those who already have parallelized needs and a dire l

Is this a major breakthrough?

[kestasjk]

• ~2x improvement in transistor density, for either smaller chip size or increased transistor count
• ~30% reduction in transistor switching power
• >20%improvement in transistor switching speed or >5x reduction in source-drain leakage power
• >10x reduction in gate oxide leakage power

As a layman this sounds like a pretty massive improvement. Is this a major breakthrough or is this progress as usual?

Re:

[marcosdumay]

I'd classify it as a minor breaktrough, such things happen every few years but are a huge gain at once.

But feature size isn't everything.

Re:Is this a major breakthrough?

[Bender_]

This is the first time since 1969 that a major modification to the MOSFET gate stack occured. In fact it is fairly major. I should remind you that this is a structure that is replicated around 1e19 times each year and is responsible for the biggest part of the 270 Billion US$ semiconductor market.

At least ten years of work in academia and industry and billions of dollars were poured into this. Intel is the first company to make the move and introduce high-k.

(Yes, there were a few minor modifications to the SiO2/Poly stack in between: Plasma nitridation and numerous improvements on SiO2 growth)

FTFA

[Aaron England]

This is a show of strength if you will, and an impressive one at that. How impressive? We'll wrap-up here with a few quotes from Gordon Moore (Intel), Professor Dimitri Antoniadis (MIT), and Yoshio Nishi (Stanford) telling you what they think of Intel's achievements.

"The implementation of high-k and metal gate materials marks the biggest change in transistor technology since the introduction of polysilicongate MOS transistors in the late 1960s" - Gordon Moore

"The Intel 45-nm CMOS technology marks a historic milestone for the semiconductor industry. Similar to the transition from single metal (Al) gate to polysilicon gate that has allowed optimal nFET and pFET design, the introduction of dual metal with high-k-insulator gate-stack opens the path for optimal design of both types of FETs, at insulator thicknesses necessary for continuing device scaling that are impossible to reach with the industry-standard silicon-dioxide-based insulators. Many options of high-k gate-stacks have been the target of intense industry and academic research for many years now, but Intel's demonstration of a manufacturable dual-metal/high-k solution is a remarkable first." - Prof. Dimitri Antoniadis

"It is a huge break through to replace more than three decade's long successful polysilicon gate technology with a new high-k+metal gate technology. Though the combination of high-k dielectrics and metal gate electrode for advanced CMOS has been extensively studied by many researchers around the world as the ideal MOS gate structure, the technical hurdle to bring the technology to manufacturing floor has been believed still too high for the 45nm node. As a researcher in this field, I am pleasantly surprised by the announcement and would like to congratulate Intel researchers for their success that Intel has demonstrated 45nm microprocessors with their high-k and metal gate technology. Even though specific metal and high-k material have not been disclosed at this moment, this is a revolutionary step toward the world of sub-50nm CMOS integrated circuits, as this new technology will drastically improve transistor performance in all fronts of electrical specifications, resulting in significant improvement of IC performance." - Yoshio Nishi

Re:FTFA

[stevesliva]

"The implementation of high-k and metal gate materials marks the biggest change in transistor technology since the introduction of polysilicon MOS transistors in the late 1960s" - Gordon Moore

I don't know, I may have to disagree with his eminence on this one... but, parsing his statement a little more finely, he does specifically mention transistor technology. I still view this as an evolutionary refinement of CMOS, and not as big as the transition from bipolar to CMOS for mainstream processors. It is a bigger deal than strained silicon. And by specifying "transistor" he of course sidesteps the comparision to the similar chemical reengineering of the back-end metal stack that came with the introduction of copper and low-k dielectrics. I speculate that like those changes, though, the implementation of the process changes will be relatively transparent to the circuit designers. Yes, the models change, hopefully the subthreshold leakage goes way down, but you've still got the G,D,S,B paradigm... right?

Re:

[WaZiX]

Yes, the models change, hopefully the subthreshold leakage goes way down, but you've still got the G,D,S,B paradigm... right?
riiiiight!

Re:

[warrior]

I think this is just a lot of Intel FUD. There are other semiconductor companies that will have similar improvements in their designs as well. One that I think is most interesting that Intel will not have is called HOT - Hybrid Orientation Technology. This is only possible for the vendors that use an SOI process. Basically, HOT allows for the Si crystal to be oriented in two different ways, one way for PFETs and one for NFETs. What this means is that we no longer have to choose which FET is fastest in

Re:

[Bender_]

I can tell you this is not FUD. If you follow the literature about this subject closely you will notice that there is no report about a metal usable for a pMOS transistosr. Many companies are not significantly ahead of that. I expect some pretty interesting publications later this year. But it still takes several years to get a new material into production. Intel has already made big strides in putting high-k into production while other companies may still be in the screening process. I believe they have a

Re:

[Bender_]

also: HOT and SOI are quite expensive, it saves a lot of money (at least now) to engineer around those solutions.

Re:

[warrior]

The cost of a 12-inch bulk wafer is about $400, an SOI wafer $600. The back-end processing for each is $2000+ ( slightly more for bulk for additional junction engineering to get the additional performance ). The cost difference is about a wash. I guess SOI does take a cost hit when it comes to yield. I'm not trying to take anything away from Intel's accomplishment, but they're not the only ones working on exciting new technologies. I think they're just shouting about this because they're the first ones

Re:

[Bender_]

AFAIR Intel presented some interesting technologies studies on SOI a couple of years ago.

Your wafer cost figures are off, but I will rather not comment due to lack of public sources. Still, in most parts of the semiconductor business 10% cost difference is not a wash but determines whether you make profit or not. It may work for a short while if you have a very high margin product (like a technologically superior CPU), but then you are suddenly in a price war...

Re:

[Mycroft_VIII]

I doubt it's out of spite, if it would make them more money they'd do it. They are a publicly traded company and as such the focus is profit.
They may have adopted the N.I.H. attitude in for pr reasons e.g.: "We're Intell, we lead not follow!".
Or perhaps they felt the cost at the time was prohibitive relative to the advantages and by the time the tech was cheap enough to implement they already had something more promising (p

Re:

[Ant P.]

If they can build a high-end chip that produces less waste heat than the 386, _that_ would be a breakthrough.

Re:

[shankarunni]

As a layman this sounds like a pretty massive improvement. Is this a major breakthrough or is this progress as usual?

Depends on your definition of "breakthrough". Breakthroughs aren't what they were 30 years ago. This one gives us maybe 10 additional years on the Moore's law curve. Sounds like a middling leap at best.

Re:Is this a major breakthrough?

[RicktheBrick]

If one has a penny and doubles it one has $.02. If one has a million dollars and doubles it one has 2 million dollars. Most people would consider the latter to be a more important improvement. It is the same for microprocessors, doubling now is that much greater than it was 30 years ago.

Re:

[acidrain]

If all you have is $20 in your pocket and no idea how you are going to earn money, getting another $20 means a lot more than handing a second billion to a billionaire. Processing speed is becoming meaningless on the desktop for most users. This is mostly relevant to servers now that we are moving to thin clients in the form of web-browsers, and expecting more an more processing from webservers.

Re:Is this a major breakthrough?

[brejc8]

Yes and No.
There are two improvements here which are happening at the same time. Process shrink (which happens all the time) and the use of High-K dielectric (which is something reather new in the mass manufacture feild anyway)

These 2 are just due to process shrink and nothing special:
  * ~2x improvement in transistor density, for either smaller chip size or increased transistor count
  * ~30% reduction in transistor switching power

This one is interesting and the OR should be regaded as an XOR.
  * >20%improvement in transistor switching speed or >5x reduction in source-drain leakage power
Basicly the individual transistors become tunable to decide if they should be fast or low power. Critical path ones will be fast and others will be low power.

And this one is a breakthrough:
  * >10x reduction in gate oxide leakage power
With static power now accounting for up to 50% of all power this is excelent.

Re:

[Bender_]

That is not entirely correct. Intel had basically maxed out SiON previously, I doubt they could have gained that much in performance without high-k.

Re:

[dabraun]

And this one is a breakthrough:
    * >10x reduction in gate oxide leakage power
With static power now accounting for up to 50% of all power this is excelent.

I hate to be pedantic, but you can't have a "10x reduction" in anything, a 1x reduction is zero. What does this really mean? 90% reduction (1/10th remaining)?

Re:

[x2A]

"I hate to be pedantic"

no you don't, you love it :-p

Both

[try_anything]

Moore's Law says that massive improvements ARE progress as usual, but people have been so pessimistic about the future of Moore's Law that giving it a new lease on life counts as a major breakthrough.

Re:

[cnettel]

Actually, for a long time, the refinements were highly in the field of litography, decreasing the wavelength and so on. Performance made breakthroughs, the actually technology "just" progressed. The last few years, that's been coupled with a lot more materials research. True, that's been going on for decades as well, but lots of the supposed advancements during the 80s never made it. Now, it seems like we actually need to reevaluate every piece of the process to do those things.

Re:

[wtarreau]

* ~2x improvement in transistor density, for either smaller chip size or increased transistor count
* ~30% reduction in transistor switching power
* >20%improvement in transistor switching speed or >5x reduction in source-drain leakage power
* >10x reduction in gate oxide leakage power
As a layman this sounds like a pretty massive improvement. Is this a major breakthrough or is this progress as usual?

While not a major breakthrough per se, it demonstrates intel's commitment to work on architectural evo

Re:

[dreddnott]

Slow down, cowboy, although you are spot on with the L1 cache size, Intel's Pentium 4 never had a cache size of less than 262,144 bytes, and from the more efficient Northwood on (January 2002), cache size ranged from 524,288 to 2,049,152 bytes (trying to avoid a mebi vs. mega debate).

The reason your Pentium III handily outpaces Pentium 4s of higher clockspeed has more to do with the inefficient Netburst core having an excessively deep pipeline that allowed higher clocking but lowered IPC and penalised branc

More (Better?) Coverage

[Anonymous Coward]

http://dailytech.com/Life+With+Penryn/article5869. htm [dailytech.com]
http://www.msnbc.msn.com/id/16839253/ [msn.com]
http://money.cnn.com/2007/01/27/technology/bc.micr ochips.reut/index.htm?cnn=yes [cnn.com]
http://www.nytimes.com/2007/01/27/technology/27chi p.html?em&ex=1170046800&en=59a4d10473c4a8c8&ei=508 7%0A [nytimes.com]
http://news.com.com/Chip+companies+entering+their+ metal+period/2100-1006_3-6153962.html [com.com]
http://anandtech.com/cpuchipsets/showdoc.aspx?i=29 15 [anandtech.com]

Still on the FSB

[Joe The Dragon]

If you are going to the make the chips smaller how hard is it to come out with a true quad-core?
Havening 2 duel-cores linked by a fsb bus will get in the way even faster as the speed of the cpu gets higher.
And a 4 cpu quad-core sever will likely choke up at the chipset to ram link as well as the chipset to chipset link.

Also if your duel quad-core workstation only have has the pci-e lanes for 1 x16 slot and the 8 other ones are used for the chipset to chipset link amd based ones will blow it away even more so with KL8 cpus. Right now an 2 cpu amd board has 4 pci-e x16 slots running at x16 x8 x16 x8 with 2 x4 lanes left over + each cpu can have a HTX slot or other HT based chip hook up to it.

Re:

[RightSaidFred99]

Unfortunately (for your point) this has been proven wrong. The FSB works fine up to 2P machines. Intel will soon be quad FSB machines which should work very well for machines up to and including 4P/16Core. The proof is in the pudding, benchmarks show that the FSB limitation is only meaningful in a very few instances, and in most cases the superior uArch of Core2 more than makes up for it.

As for K8L, looks interesting - we'll have to see. If you think it's going to have a broad 40% improvement over Cor

Re:

[Joe The Dragon]

quad FSB machines may still choke up at the chipset with all of the cpus needing the use the same link to get to ram.

Even if the K8L is %1-%5 faster it still kills Intel in sever / workstation chip sets in terms of number of pci-e lanes and Intel has no to way to better a high-end duel cpu quad-core amd KL8 system.
as there 2 cpu system uses FB-DIMMs and only has 20-22 pci-e lanes with no sli.

Re:

[dreddnott]

Actually, IBM and AMD, as partners, will also be using this new 0.45 process in their new chips, but it may take them longer to get there than Intel.

As an AMD fanboy, I was actually very happy to see the release of the Core and Core 2 chips - Intel was willing to admit that Netburst was a mistake, and they forced AMD to lower their dual-core CPU prices by 40%-60% in one fell swoop.

Re:

[networkBoy]

you know something funny?
NetBurst was not a mistake...
I have two high end machines. A Prescott 3.6 GHz machine and a core2duo extreme edition machine. the core2duo is faster in all apps, yes. In games and such it kicks ass, yes. In the one app where I *really* care, repetitive mathematical transforms the core2duo is faster, by only 5% and it has double the ram of the Prescott, interesting eh?

Now while I will gladly concede that if you're a gamer the Prescott was abysmal; for scientific, encryption, and

Re:Still on the FSB

[antifoidulus]

2 duel-cores

Spelling Nazi time: It's dual! Dual! It's only "duel" if your processors are firing pistols at each other from 10 paces at dawn!

Re:

[coredog64]

It doesn't have to be pistols -- it could be mortars.

Re:

[networkBoy]

I think positrons would be more app. in this instance, no?

Re:

[fitten]

Alternatively, you could have one core computing as fast as it can and the other one "uncomputing" what the first one did... ;)

I wonder if they have tiny banjos.

Re:

[Aadain2001]

If you are going to the make the chips smaller how hard is it to come out with a true quad-core?

Not very. It just takes time to go through all the design -> verification -> layout -> production steps that all new processors require. Yes, the two dual-core processors in a single package is a minor cheat, but it's not meant to be the only quad-core Intel produces. It simply let the consumer have a quad-core chip now which will help push software manufacturers produce programs that utilize the p

Re:

[Joe The Dragon]

I am talking about amd's up coming single cpu quad-cores

Re:

[Aadain2001]

And Intel has up coming signal chip quad-core CPUs. To think they don't have one in their pipeline would be ignorant.

Windows and Vista?

[solevita]

news that next-gen Penryn core processors are running various versions of Windows and Vista successfully

I know Microsoft told us that Vista was new and all, but I didn't know it was this new!

The biggest advance

[Anonymous Coward]

I don't know why everyone is going gaga over this processor technology, when it's clear that the biggest advance is that they've made Windows run successfully.

Must have taken an army of late night patch coding wizards.

Re:

[rbanffy]

Wish I had modpoints. +1 funny for you.

I mainly find it funny because I usually don't run Windows. If I did, I would feel something a little bitter added to the funny mix, kind of a Dilbert strip.

Re:

[markdavis]

news that next-gen Penryn core processors are running various versions of Windows and Vista successfully

Actually, the article does not say "various versions of Windows and Vista successfully". It says: "Intel said it had already manufactured prototype microprocessor chips in the new 45-nanometer process that run on three major operating systems: Windows, Mac OS X and Linux."

Yes, you read that right.... they actually said "Linux". :) Of course, it is not a surprise it can run Linux (that is a major "

Re:

[eebra82]

I am not sure what you're trying to tell us? I don't think anyone is in doubt that newer CPU:s are typically for high-end users, but Intel is also targeting power efficiency among other things. Plus, some people also want to upgrade because using old hardware isn't very reliable.

Obviously, Intel must advance with more powerful processors to compete. If not, there would never be any vast software development either. Surely you must admit that running Office 2007 on a six-year-old computer isn't a very goo

high capacitance

[dlenmn]

In the article, they keep on talking about high capacitance as if it's a good thing, but I was under the impression that you want to minimize the capacitance to let the transistor switch faster. Am I wrong? Is the article wrong? Is this a different capacitance that they're talking about?

Re:

[NMerriam]

In the article, they keep on talking about high capacitance as if it's a good thing, but I was under the impression that you want to minimize the capacitance to let the transistor switch faster. Am I wrong? Is the article wrong? Is this a different capacitance that they're talking about?

I interpreted it to mean that the high capacitance referred to the low level of leakage -- ie, more energy stays inside the path as productive power rather than radiating as heat or creating static interference with nearb

Re:

[WhiplashII]

In a CMOS-like technology, you want overall capacitance as small as possible - because you have to charge and discharge that capacitor once per cycle. A first order approximation of power used is 0.5*Capacitance*(voltage squared). A first order approximation of the speed of the device is voltage*current/capacitance (where current is an exponential function of voltage). This means that from a circuit perspective, capacitance is the root of all evil (it both slows you down and uses up power).

When you look

Re:

[Sebastopol]

Actually, drop the 0.5 if you are talking about a cycle, you have to assume the energy enters and leaves in a complete cycle.

So how many GHz?

[rbarreira]

So does this mean that the "future improvements will be on number of cores, not on individual core speeds" state of things in CPUs isn't true anymore? Anyone have any quotes on how much raw performance these 45nm CPUs will attain?

Re:

[Wesley Felter]

It's still mostly true. Going from a 3.0 GHz Conroe to ~3.7 GHz Penryn is only a 30-40% performance increase, but we want a 100% increase. So we can expect that the number of cores and frequency will both increase.

What low K will the Penryn use?

[cyfer2000]

TFA didn't mention anything about the Low K part, anybody has any information? Porous MSSQ? Porous SiLK? Porous Black Diamond (if it exists)?

Re:

[Bender_]

This article offers some hints:

http://www.fabtech.org/content/view/2079 [fabtech.org]

Re:

[cyfer2000]

It looks like a new generation of Aurora. I guess they must introduced kind of pores in the Aurora. Or something else, I can't imagine the doped silicon oxide alone can reach such low K. But I also can't imagine how to make pores in Aurora too. Or maybe they simply figured out a way to keep the dielectric value low at small scale. Comparing to the porous MSSQ used in AMD/IBM 45nm product, I bet Aurora is better in reliability.

Re:

[cyfer2000]

This article http://www.eetimes.eu/production/196701258 [eetimes.eu] implies that the Black Diamond can reach K value of 2.4, but the mechanical properties is even worse than porous SSQ filem. Thus Aurora should be able to reach 2.4 too.

Well then...

[Wicko]

Sounds to me like they went to reach as far ahead of AMD-ATI as possible, to keep their lead. God I love competition.

Intel's more informative site

[Abtin]

The link in the main article is paraphrased from http://www.intel.com/technology/silicon/45nm_techn ology.htm [intel.com]

IBM and Intel both a anounced major breakthrough

[ysegalov]

You are missing the point here. IBM and intel, on the same day (Friday), independently announced [washingtonpost.com] a breakthrough in transistor design. Now isn't this strange? The biggest advance in transistors in the last 40 years or so - and two different companies announce it on the same day?!?!? Fishy.

Re:

[dreddnott]

I posted links to similar articles as a reply to the FP (an anonymous troll), but I hadn't read your article.

Initially I interpreted it as Intel and IBM cooperating on researching the new hafnium-based technology (this is the interpretation that Wikipedia's Hafnium article [wikipedia.org] currently uses), but on further reading I realised that they were doing this quite independently, and AMD, Sony, and Toshiba were partnered with IBM on this research.

IBM may be basing the 4 to 6 GHz clock speeds of its new POWER chips on

Re:

[edxwelch]

AMD will have a process with the low k thingy one year after Intel. I suspect IBM delibrately made their announcement on the same day to take the wind out of Intels sails, even though they're a year behind.

they'll be friendly with existing boards?

[ystar]

so eventually can I drop a 45nm shrink into my c2d macbook?

Re:

[maztuhblastah]

Nope. The Macbook's proc, like most laptops, isn't socketed.

Re:

[Aristocat_Faust]

is that you, Jeff K?

Re:

[dagamer34]

O_o

Re:

[ratbag]

If you're a company or uni then overclocking your servers (definitely) or desktops (probably) really isn't an option. Even as a consumer, surely you'd be wondering if it's worth the potential warranty issues, especially if you've got to stump up for "higher grade memory and a non-crappy motherboard"?

Re:

[julesh]

that "free speed" comes at the cost of a higher grade of memory (adding $100+)

To be fair, you probably get a greater performance improvement from increasing the FSB speed than you do from increasing the processor speed, so this may well be worth it.

Re:Who cares about clock speed, just overclock

[MoxFulder]

A production E4300 running at 1.8 GHz can be run at 3 GHz on stock air cooling.

Didn't you get the news? The clock speed race is sooooo 2005. For everything but the most CPU-bound number-crunching applications, increasing clock speed is no longer very desirable.

Today it's all about PERFORMANCE PER WATT (crucial for server farms and portables) and on-chip parallelism/SMP (useful for everything from desktop GUIs to web serving to RTOS embedded systems).

Re:

[eknagy]

Is there any chance that they will produce 1-Watt (silent), low-transistor count (cheap) Pentium 2 / Pentium 3 / SDRAM133 replacements with this new technology? Combined with Solid State Disks, plenty much of old hardware could be saved and lots of users (like my fiance or my sister) would be happy with a P2 or P3 class refurbished machine, provided there is at least 256 RAM to run a browser and some office applications.
Not to mention thin clients or second/third world countries.

Re:

[Doppler00]

Not a very good chance. They do that in the embedded space sometimes but usually they don't use brand new process technology for it. I mean, the Pentium 2, and Pentium 3 architectures are not as advanced. Why waste new technology on old architectures? It's more likely they will have embedded versions of Core 2 or more likely they will have an ultra low power 1GHz or 500 MHz processor. And honestly, for Intel there is no market for third world countries, so unless there is a billionaire philanthropist willi

Re:

[eknagy]

It's not a waste - from one "new technology" processor you can make 4..16(?) P3-compatible processors, as they are more simple, consist less transistors and even -maybe- you can re-design them a bit better. So, think about 50 USD processors and 2 G potential customers and not about 400 USD processors and 10 M potential customers.

Plus, all those users who *like their machines as they are* and *do not want to migrate to new computer/OS/technology* and *want to keep their system working* might pay for it - to

Re:

[Doppler00]

Yeah, it's funny they are still pushing performance/per/watt. I certainly don't hope they are doing that on the desktop space. Consumers don't give a crap about power efficiency of their products. You can't even get people to replace 2, 60 watt light bulbs in their house, why would they care about performance per watt? It only matters for servers.

Also, there are several classes of applications and problems that cannot be handled well with multiple cores, no matter how much you wish it would. You could have

Re:

[MoxFulder]

Yeah, it's funny they are still pushing performance/per/watt. I certainly don't hope they are doing that on the desktop space. Consumers don't give a crap about power efficiency of their products. You can't even get people to replace 2, 60 watt light bulbs in their house, why would they care about performance per watt? It only matters for servers.

Well, *I* for one care about power efficiency of my desktop. I've gone over to compact fluorescent bulbs (12 W, 60 W equiv) exclusively. I imagine anyone who ca

Re:

[Raenex]

I can't think of a single REAL WORLD task that is so massively un-parallelizable that I would prefer a single 3 GHz core over many 2 GHz cores.

Games. Go read some Carmack quotes. He wants a single CPU that goes faster, not many cores. Also, for my desktop I can't think of too many applications that will make use of more cores. I'm not confident that parallel optimization for your average application will occur. I'd definitely take a single 3GHz CPU over two 2GHz cores.

Re:

[Raenex]

Also, there are several classes of applications and problems that cannot be handled well with multiple cores, no matter how much you wish it would. You could have a 3Ghz single core vs. a 2GHz 128 core, and the 3GHz machine may be faster. I think the GHz race will need to continue someday, just not with silicon. Quantum computers here we come!

So, umm, what are these applications that can't benefit from parallel computers but that can benefit from quantum computers? It sounds like you think a quantum com

Re:

[julesh]

A production E4300 running at 1.8 GHz can be run at 3 GHz on stock air cooling

And if that's possible with a 65nm chip, even just the normal benefits of scaling suggest that 4GHz should be attainable from an equivalent 45nm chip. And it sounds like this generation is going to give intel better than normal improvements, so I'd expect to see 5-6GHz from Penryn cores with air cooling, assuming the data paths can switch fast enough (I expect Intel have designed it with some headroom, so this is likely to be the

Error in TFA

[dreddnott]

The article linked above refers to "Halfnium", with is both an element that does not exist and a gross misspelling of Hafnium [wikipedia.org] , which is the new High-K replacement for silicon dioxide. It's also worth pointing out that both IBM and Intel announced this breakthough [yahoo.com] almost simultaneously, and AMD will reap the windfall benefits through its own partnership with IBM (they will move to the 0.45 process some time in 2008). AMD has also announced a low-K breakthrough that they will be implementing in their 0.65 process as well.

To give Intel sole credit [betanews.com] for this breakthrough might be a little inaccurate.

Re:

[cattlebruiser]

> The article linked above refers to "Halfnium" I think that's a typo. The actual substance is called "Unobtanium" and was originally used to drill down to the center of the Earth.