Comments Locked

55 Comments

Back to Article

  • nandnandnand - Sunday, February 22, 2015 - link

    The grammar in this article is horrendous.
  • Murloc - Sunday, February 22, 2015 - link

    the paragraph after the second image has something wrong in it I think. The rest didn't seem wrong to me although it's complicated stuff so it's not exactly easy-flowing, not understanding much doesn't help of course :P
  • Klug4Pres - Sunday, February 22, 2015 - link

    I have to agree. My favourite sentence is:

    "Hot on the lips regarding Moore’s Law challenges comes down to future integrated systems, specifically 2.5D (separate dies on an interposer) and 3D (stacked dies)."
  • Klug4Pres - Sunday, February 22, 2015 - link

    *Agree with nandnandnand
  • DigitalFreak - Sunday, February 22, 2015 - link

    I thought for a second that they hired Jason Mick from DailyTech to write this article...
  • Frangelina - Sunday, February 22, 2015 - link

    Be a happy unilinguist. Moreover, people from the math/non-verbal world, non native English speaker, are even more challenged.
  • dishayu - Monday, February 23, 2015 - link

    Dr. Ian Cutress is from the UK, as far as I remember.
  • StevoLincolnite - Thursday, February 26, 2015 - link

    I have been reading Anandtech for over a decade, overall I have a firm enough understanding of it all.

    This article left me confused.
    I mean... Masking?
    I know multiple terminology in this industry can mean the same thing, but I had assumed people in general meant "Patterning" in this context where Intel already does multi-patterning to boost yields, it's only natural to increase that as you drop down in lithography whilst keeping all else the same.
  • mkozakewich - Monday, February 23, 2015 - link

    Hah, I thought the same thing. There was a sentence with a 'while' that just kind of ended without a counterpoint.

    Things seemed better after the first few paragraphs, though.
  • ingwe - Sunday, February 22, 2015 - link

    Crazy stuff. I am curious to see how small things will actually get.
  • melgross - Sunday, February 22, 2015 - link

    Most chip experts still believe that 5nm may be impossible. I guess we'll just have to wait a good five to seven years to see.
  • witeken - Monday, February 23, 2015 - link

    Mark Bohr has recently said that he doesn't see the end of Moore's Law within 10 years (visibility beyond 10 years has always been low). Note that even though the node is called 5nm, most of its feature sizes will be substantially bigger.
  • III-V - Monday, February 23, 2015 - link

    Still believe? As of when? It's been generally regarded that we can move past 5nm for a couple of years now.
  • BOMBOVA - Tuesday, February 24, 2015 - link

    even though it is far off, say maybe ten years, there is now, some features recognized in nature, that may translate to building 5 nm devices, such as memory cells, gold for example at its smallest scale will make for 5 nm structures, by the simple fact in nature they are bountiful. it is all in assembly now, :) stack my chips, 20 per die, and put lots of light pipes in, Cheers. i am a believer in nature.
  • Samus - Sunday, February 22, 2015 - link

    Eventually they will implode :)
  • jjj - Sunday, February 22, 2015 - link

    I am more curious about the Marvell presentation:
    "If chip-design engineers had also looked at the financial optimizations of the overall process, they would have built things differently. They should have realized that certain functions are better grouped into highly specialized integrated circuits that could easily and seamlessly talk to each other without compromising the overall system costs. The key to making this happen is what i call the Lego Block approach of designing integrated circuits. However , in order for the Lego Block approach to materialize, we need to change the way we architect our devices. We need to do many things. Define a new chip-to-chip interconnect protocol , take advantage of multi-chip-module packaging and high-speed SerDes technology ,redefine the memory hierarchy to take advantage of 3D solid-state memory instead of blindly increasing the DRAM size in our devices, repartition DRAM to serve different logical functions instead of building gigantic single-die DRAM to serve every function, change the way we build DRAM,so that they are optimized more for performance and power efficiency instead of capacity and redefine what should be done in hardware versus software. In short, we need to change our way of thinking and be brave enough to reject common wisdom. If we fail to take action, soon we will no longer see cost savings. On the other hand, if we succeed, we willsee life beyond the end of Moore's Law"

    Maybe it's too complex to be practical and against the interests of many chipmakers but it is interesting.
    No idea if anyone is working on it but i would be curious about the feasibility of a smart interposer where you have "dumb" compute units and memory on an interposer that acts like an interconnect and system agent (as Intel calls the uncore now). So the interposer manages the package and if it was programmable you don't need to fully design it for each specific package, plus you can do software upgrades at any time. Micron's Hybrid Memory Cube is a logic die with dumb DRAM dies stacked on it, a smart interposer would be a somewhat similar concept except the interposer manages the entire system (package).

    Unrelated but any clue if anyone is looking into making 3D GPUs? Actual 3D like 3D NAND not chip stacking. Ofc the GPU core is a hell of a lot more complex than a NAND cell but it is a repetitive structure that appears up to a few thousands times on a single die so it kinda makes sense to try to go 3D.
  • name99 - Monday, February 23, 2015 - link

    3D logic is problematic because, while you win on wire length and density, you lose on power dissipation. It's not clear how far you can push it. You MAY be able to get to two layers, if you carefully arrange the lower power blocks (eg memory structures) on top of the higher power blocks (logic), but you may not be able to go further than that.

    I'm not sure what Marvell is saying that's any different from what, say ARM does today. The most actionable part seems to be a call for more use of specialized DRAMs rather than one single pool of system DRAM. Maybe that makes sense, but it doesn't seem to be a massive change.
  • antialienado - Sunday, February 22, 2015 - link

    I still run on a 45 nm processor, and see no reason for upgrading.

    Hec. I know people running on 65 nm Quad Core, and there is not enough gain in performance to justify upgrading.

    The cost is too high (mother, memory, processor, GPU, power), and the gains negligible.
  • jjj - Sunday, February 22, 2015 - link

    Don't blame it on the process.. What happened is that Intel has no competition and got way greedy. They have smaller and smaller dies despite integrating more and more on the die.
    Assuming you have a Nehalem , that one was 263 mm^2 and here a die shot where you can see that the cores and the cache are the bulk of the die http://images.anandtech.com/reviews/cpu/intel/neha...
    A Haswell based 4770k is 177mm2 and the cores and cache are a much smaller part of the chip http://images.anandtech.com/doci/7003/Screen%20Sho...
    We could have 8 cores at reasonable prices,but they make more money by not giving us that since nobody else is actually competing and regulators are sleeping.
  • voicequal - Sunday, February 22, 2015 - link

    Intel has chosen to invest the extra die area into the iGPU and fixed function units like H.264 encode/decode. Arguably these have benefited the mainstream more by eliminating the cost for discrete graphics. For raw CPU/$, the 6-core i7-5820K is nothing to sneeze at. That being said, more competition is rarely bad for the consumer.
  • jjj - Sunday, February 22, 2015 - link

    No ,Intel has chose to rip us off, because they can.
    Some chipset functionality migrated too . For the GPU we pay and we don't need it. As you mention they make a chip without GPU, they have a chip for us except it's not in the normal price range, it's a lot more so it becomes irrelevant in consumer.
    They started to screw us over hard with Gulftown 5 years ago and they have no intention what so ever to change direction or even not make it much worse. We will keep getting less for more as long as nobody bothers them (hell look at die size and pricing for Core M, the actual chip on that module is 82mm2 and , as per AT, the price at launch was $281- great price for a mobile class SoC lol).
    They need to be able to make more money while selling less and to afford to waste many billions every year to fail in mobile.So we get heavy marketing BS and crappy chips at crazy prices.
    The upside is that anyone that behaves like that, ends up choking on it.
  • stadisticado - Sunday, February 22, 2015 - link

    Or, on the other side of things, we could allow capitalism to operate without getting the government involved. Silicon for computers only accounts for ~25% of WW wafer shipments and continues to shrink. Intel is hardly in a monopolistic position when considering the entire logic and apps processor ecosystem. Further, they continue to charge what the market will bear - since when is that a crime? Finally, you seem to have some misapprehension that cost is directly correlated to area, which leads me to believe you don't understand litho scaling or multi-patterning and how they increase cost gen-on-gen.

    Disclaimer: jjj is a known troll, but hopefully my comment will be edifying for others.
  • cactusdog - Monday, February 23, 2015 - link

    Nope didn't work. The other guy made a reasonable comment about lack of competition, (which has been a much discussed issue for a few years now) and you degraded to conversation by making political statement.
  • ZeroPointEF - Monday, February 23, 2015 - link

    I don't like the high prices that Intel charges, but I think the profits are necessary to fund further R&D. It seems like cost to get smaller is increasing geometrically rather then exponentially.
  • jcromano - Tuesday, March 17, 2015 - link

    How do "geometrically" and "exponentially" differ? I always thought they meant the same thing.

    Geometric Series (with common ratio r=2): 1, 2, 4, 8, 16, . . .
    Exponential Series (e^(kn) with k = ln 2, starting from n=0): 1, 2, 4, 8, 16, . . .
  • Guest8 - Sunday, February 22, 2015 - link

    They only lost a billion in mobile. The rest is fixed R&D.
  • TheJian - Monday, February 23, 2015 - link

    They lose that every quarter. It's beyond losing 4B a year now. Some are asking them to DROP mobile (I think they should just buy NV and out ARM, well, ARM so to speak), like JP Morgan. If they continue to lose 4B+ per year investors will get nervous at some point.

    http://blogs.barrons.com/techtraderdaily/2014/05/0...
    Google jp morgan intel mobile loss and you can read stories all over. They either need to fab more for others, or buy NV and fab their stuff which would allow them to catch Qcom etc. Imagine a 10nm X1 and you get the point (or whatever NV is on by then) and coming even a bit before others. Imagine the damage they'd do with a 10nm gpu...LOL. Without doing this I believe ARM will slowly kill Intel's ability to invest in R&D to keep up with their fab enemies.

    Intel needs to respond before ARM (anyone on ARM, NV, Qcom etc) puts out a 75-100w chip that runs in a usual PC box complete with NVlink gpu from NV. As apps/games amp up on mobile with 64bit now and larger mem, storage etc, we'll eventually see the box I'm talking about to replace WINTEL. Make no mistake they all want a piece of WINTEL's total revenue. That box will probably come with multiple FREE operating systems and a huge drop in cpu price (say $200 vs. Intel's 350 for top consumer cpus). We're talking a tri/quad boot of steamOS, linux (some version), Android etc. Intel margins drop then, windows will sell less (hence the push for crap like common core so they can data-mine 300+ stats on your kids, data the kids tell them about YOU, your religion etc etc instead of sell OS) and they could possibly end up with far less market than they have today. I could easily see ARM owning 20-50% of the desktops in a decade or less. NV is clearly heading toward making a box without PCIE, no need for Hypertransport, x86, Infiniband etc. Nvlink for the bus stuff will be all that is needed, and a great cpu by then to pair with their gpu in a normal 500w etc box. You'll have apps like the full adobe suite etc on there by then, gaming that looks just like a PC etc. Porting is getting easier between ARM/Intel and many games are released on multiple platforms today at once.

    Wintel has trouble ahead if Intel can't figure out how to make a deal with Jen/Nvidia, which may be impossible (too much hate and he's said only if he's CEO of Intel after it so far). They can't afford to buy Qcom/Samsung/Apple, and AMD is a loser on all fronts compared to NV now. At some point soon, Intel may not even be able to afford NV as cars, grid (1000 testing it now), and at some point mobile/PC add more to their stock price. As gaming takes over mobile, NV will look better and better there. Currently mobile is not quite pushing things enough to REQUIRE NV/AMD gpu power/driver experience, game dev exp with their hardware etc. If AMD is to survive they need to get their best mobile foot forward before the games get here that require it. Apps will follow shortly after games push the hardware requirements up. I like where we're headed though :) With AMD sucking wind, I'm merrily looking forward to ARM owning a share of the PC pie (meaning any ARM vendor in a PC like box, hopefully NV, speaking as a gamer that is).

    I see better pricing ahead as ARM moves up the PC chain from chromebooks/low end notebook type stuff. I could like a tri-boot PC, with no WINTEL inside for $200-300 off (that being free OS+$150 off Intel's $350 chips). We may even get a break on the gpu side if someone emerges that can't be sued to take over AMD's place, meaning ARM, Qcom, Apple, etc. I don't really count IMG.L here, as they make almost nothing compared to the rest yearly. They'll die or be bought as the race heats up or perhaps be sued out of existence (can't fight a R&D war with 60mil a year and a lawsuit on top from NV). We'll have to see if anyone can make a gpu without using NV/AMD/Intel IP. I'd expect an AMD suit once NV's is over assuming they win, if AMD has anything to sue over. Intel is a big question mark here, as I'm not sure about how much gpu IP they have, but they lost to NV so...Who knows.

    Having said that, I'm fairly certain all the other players have less gpu IP than Intel for current PC tech (last decade or two, where the patents being trampled came from and now starting to be used fully in mobile). We'll know in a few months on that front I guess as the suit evolves. It wasn't called the 'wild west of patent infringement' by anandtech for nothing ;) Their problem is they all picked on a company who can afford to go to trial for a decade and laugh. This isn't Intel vs. AMD here, as NV can survive 100mil/year or more in a suit easily for a multi-billion payoff overall and licensing their GPU IP forever to them all for even more fees on top of willful infringement. A jury would want to stick it to highly profitable companies like Qcom, Apple, Samsung (especially the last one not being american). Apple will come after they win vs. the others or Apple will be smart enough to deal if it ends really ugly for the others.

    At any rate, Intel can't give their chips away forever, especially with fabs catching up and an ARM Armada working together to take down Wintel. I'd include Valve/SteamOS here too in the arm group as I think it will be running on NV socs soon (Gabe hates MS, their store, BillG etc). That is a no-brainer for NV, and even Valve if they want DirectX/Windows dead, and linux/steamOS to take over. Valve doesn't really care if Intel dies, but ARM is the way to help kill windows/DirectX for sure and push stuff like OpenGL for all. He's not a huge fan of consoles either, so again go arm, and get great GPU's over there in a PC like box, then apps.
  • Speedfriend - Monday, February 23, 2015 - link

    1.5bn windows users able to buy windows laptop for $250 couldn't give a sh*t about an aRM box with some crappy free OS on it. Ther box you are talking about would be in compatition with PS4 and XBox One, not normal PCs. Wintel exists because despite everyone's moaning, it actually works. I have 10 applications open at once on my work PC and hardly every swithc it off. Nothing crashes unlike my iPad or Android tabelts where apps crash daily, and where any sort of multitasking is a joke. I have moved to a windows tablet now because it is just better.
  • Klimax - Monday, February 23, 2015 - link

    TheJian: Keep dreaming. Won't happen You ignored way too many things, skipped inconvenient facts, used extremely faulty basis for faulty extrapolation or outright jumped to your favorite conclusion. ARM won't have much further success nor Android. (Even where they could have, Intel and MS already have taken care of)

    Your post is about has about 1% relation with reality.
  • Guest8 - Monday, February 23, 2015 - link

    No the loses are still $4 billion a year this year it is expected to decrease as the contra revenue decreases. As an Intel stock holder I know the breakdowns and I am not nervous at all. I understand developing IP from scratch and design wins take time and money. Their Moorefield SoC is already at the level of A7 / Snapdragon 805. All of your other fantasies aren't going to happen. No one is going to catch Intel at this point in x86. ARM is 4+ generations behind in server chip design. That's at least a decades lead if ARM can make advancements every 2 years like Intel can.

    http://www.forbes.com/sites/kurtmarko/2014/12/10/a...

    ARM will not be able to scale up unless Samsung makes it happen which is still a long shot. Their "14nm" process is only a half shrink which means it is not as efficient as Intels 14nm and costs are going up instead of down unlike Intel. Technical factors aside you should know the economics do not work. Great quote from Russ Fisher former industry insider at investment site seekingalpha.com

    "The foundry industry is spending about $25 billion per year to supply Apple and QCOM with about a total of $12 billion per year in product ($7 billion to Apple and $5 billion to QCOM) That can't work. The author should write about what a bankrupt and hopeless strategy that is. Then to make matters worse, Apple bounces their business, (or plans to) from TSMC to Samsung and back again. How can that work?"

    With foundries scrambling for the limited amount of profit dollars from Apple and Qualcomm there isn't enough money on the comparatively low margin ARM SoC business to fund R&D like Intel can from the x86 business they dominate. Intel just reported a record breaking revenue quarter, which includes the negative revenue from mobile. Looks like they can afford to keep with their strategy. Intel has shown x86 can scale down ARM has yet demonstrate the ability to scale up. Even in Chromebooks reviewers noted the x86 powered variants can handle tasks much faster than ARM based ones. You are welcome to ignore economic realty and keep dreaming.
  • mkozakewich - Monday, February 23, 2015 - link

    Your entire argument is that you're a gamer and they don't make graphicsless chips at a lower price for you.

    I personally like the longer battery life.
  • voicequal - Sunday, February 22, 2015 - link

    I'd guess you would't be as satisfied with 45nm on your smart phone.
  • TeXWiller - Sunday, February 22, 2015 - link

    Rather than anything related to Flash, the domino register file experiment sound like chip-by-chip longevity and reliability optimization for embedded systems. The partial government funding should support that viewpoint.
  • Frenetic Pony - Sunday, February 22, 2015 - link

    Eugh, 3-5 groups and EUV. 3-5 stuff is poisonous (literally, you have to deal with environmental issues and etc.) as well as being more expensive than silicon. EUV has a huge amount of problems, from requiring multiple patterning to increasing amounts of manufacturing isolation being needed. Intel seems bent on running itself into the dead end of Moore's law while ignoring the obvious advantages of materials other than silicon and the established alternatives.

    Graphene can be produced in large quantities, isolated from the environment, reliably given a controllable bandgap, and with the charge carrier mobility and severely low leakage make any advancement in Moore's law even into single molecules obsolete and useless in comparison. And while there are still challenges it's a lot more exciting to see clockspeeds potentially scaling to hundreds of gigahertz and above, with optical data transfer (easily doable into transitions with graphene) to feed data from memory there's little reason we can't scale to that.

    Even if graphene somehow proves too onerous, though it hasn't so far, there's other alternatives like black phosphorous and other 2d carbon allotropes to choose from that could produce similar to better results. Who needs overly clever engineering design and plowing billions into ever higher resolution lithography when you can just run at a high enough clockspeed (And low enough voltage) to make a single core with a new material outpace hundreds of silicon based cores?
  • Michael Bay - Sunday, February 22, 2015 - link

    What makes you think intel is not researching their options in this field also?
    They sat on their 3d transistor technology for years if not a decade, we may well see something not on conventional silicon from them, but only when they drain it completely as a tecnology.
  • stadisticado - Sunday, February 22, 2015 - link

    As Mr. Bay says, you're presuming Intel (or the other foundries) aren't investigating these things. Graphene is indeed interesting but logic die built on that process don't meet current consumer needs. Additionally, I haven't seen any news relating to wafer processing suppliers (ASML, Hitachi, TEL, etc.) getting behind that tech. Even if an Intel wanted to move, they can't go it alone - they need the whole industry to shift at once.
  • patrickjp93 - Sunday, February 22, 2015 - link

    Graphene is nowhere near ready for CMOS processes. If it was IBM and Samsung would be gunning for it right this very moment. No one knows how to mass produce and interpose it the way you are insinuating, especially not to the high degree of purity required.
  • DanNeely - Monday, February 23, 2015 - link

    IBM sold it's foundry division to Global Foundries a few weeks ago. AFAIK the saile included the R&D portion of that business as well
  • Khenglish - Monday, February 23, 2015 - link

    Intel is heavily researching 3-5 semiconductors. Their job offers are targetting engineers with 3-5 research experience. Going 3-5 would require HUGE fabrication changes, and 3-5 materials cost much more than Si which makes this path look dim, or at least very distant to me. 3-5 is also no magic solution. You go higher band-gap and get lower leakage and lower performance, or lower band gap with higher performance and higher leakage. There is no way to get more performance and lower leakage.

    Where have you seen graphene mass produced? Last I heard a square cm cost over $1M to manufacture, let alone actually successfully doping it. Remember that graphene must be a sheet of single atoms. Just having a single extra or missing atom has serious ramifications on device operation.

    So it's not so simple, "WTF IS INTEL THINKING THEY NO NOTHING THEY ARE JUST MILKING US", finding something better than CMOS in Silicon while costing similar amounts is not trivial.
  • AbelDD - Thursday, February 26, 2015 - link

    So then what on your guys thoughts on POET Technologies?

    "POET has been developed to include novel function architectures utilizing gallium arsenide
    GaAs wafers, which enable the production of ICs that can be manufactured with processing speeds substantially in excess of those
    currently obtained by ICs fabricated utilizing silicon wafers and complementary metal oxide semiconductor (“CMOS”) technology.
    In addition, the POET technology incorporates positive and negative heterostructure field effect transistors (“HFETs”) as well as
    positive and negative heterojunction bipolar transistors (“HBTs on a single GaAs wafer, thus substantially broadening the capabilities
    of GaAs device technology,”), allowing for much improved power efficiency and speed, in addition to the combination of analog and
    digital circuits in a single chip design.
    A further innovation of POET would enable the design and implementation of optical and electronic devices within a single chip.
    Using various device combinations the simultaneous fabrication of electronic and optical circuitry on a single integrated circuit device
    is possible, an achievement that has not been accomplished using the silicon-based technologies currently dominating the market.
    Anticipated key benefits of this optoelectronic integration capability include: (i) faster circuit/device speeds; (ii) lower device output
    power; (iii) decreased cooling requirements; (iv) greater reliability; and (v) total system cost reductions. With POET’s materials
    system based upon comprising direct bandgap III-V compounds, the active optical elements and high-performance electronic elements
    can achieve a device density similar to that of silicon, the market’s traditional integrated circuit material.
    The POET platform is relatively easy to implement utilizing industry standard tools and infrastructure. Utilizing industry standard
    circuit design tools and process flows enables low adoption cost for implementation of POET. The POET wafer fabrication process is
    similar to that of current industry standard silicon CMOS. POET manufacturing supports testing infrastructures, test-on-wafer
    techniques, and post-fabrication procedures comparable to existing silicon CMOS procedures. The primary additional requirement to
    convert silicon CMOS foundries to POET manufacturing would involve the acquisition of molecular beam epitaxy (“MBE”)
    capability for the pre-processed GaAs wafers, or outsourcing the purchase of such wafers.
    POET is differentiated from competing semiconductor processes such as silicon, silicon germanium or indium phosphide by its more
    comprehensive set of functional capabilities and its ability to integrate them. Unlike existing processes which require the use of
    multiple chips, circuit boards or sub-systems being linked together by either physical snap connections or multiple cable connections
    that (i) produce the potential for multiple points of failure, (ii) require more space, increasing the physical end product size and (iii)
    require greater power levels with the consequent production of excess heat, thus demanding additional space for cooling and
    ventilation, we anticipate that POET will enable lasers, modulators, photoreceivers and passive optics as well as high-speed, lowpower
    electronics on one monolithically-fabricated die. This would allow POET ICs, when fully developed, to demonstrate a lower
    cost structure, increased power savings and increased reliability. "
  • Kidster3001 - Friday, February 27, 2015 - link

    Much of the process to make current chips on Silicon is also poisonous. Ever heard of Silane or Hydroflouric Acid?
  • Khenglish - Monday, February 23, 2015 - link

    What's the deal with the 40Gb/s serializer? Is that good for CMOS? 80Gb/s is common for HBT with up to 160Gb/s at the high end so at 1/4th the speed of what's already been done this looks like nothing special at all to me.

    I suspect that Intel posted some pretty serializer eye pictures to make their 14nm look impressive hoping that no one looking at the data would have any idea what it meant.
  • Khato - Monday, February 23, 2015 - link

    It's not the highest speed out there by any means. But most of what shows up on a quick search is on much older process technologies. So this is a demonstration of a high-speed transmitter on their leading edge process tech in a very small die area - small even accounting for the node shrinking.
  • willis936 - Monday, February 23, 2015 - link

    Those 40Gbps eyes look like shit. Also they must have a $500k scope to be able to measure that.
  • extide - Monday, February 23, 2015 - link

    No, the eye's look fine. The bottom one is not a NRZ code so it isn't supposed to look like the top one. As you can see, the bottom one has 4 discreet levels, plenty good.
  • extide - Monday, February 23, 2015 - link

    And also, you can easily measure that with a much cheaper than $500k scope, closer to $100k or less.
  • willis936 - Monday, February 23, 2015 - link

    You're going to tell me an eye that is has almost as much edge as open is "fine". Also what sampling scope has 100 GHz bandwidth (40 Gbps / 2 = 20 GHz * 5 for characterization) for 100k? Sign me up.
  • danjw - Monday, February 23, 2015 - link

    I saw a story recently that Broadwell desktop and laptop parts were going to be skipped. I have just skimmed this article, but I didn't see anything to confirm or deny that. Have we heard any more on this?
  • extide - Monday, February 23, 2015 - link

    That is false, (or some incorrect speculation, that you mis-read as fact) -- current latest news is that broadwell mobile (>15w) parts, and desktop parts will be available, including a socketed version with crystalwell.
  • danjw - Monday, February 23, 2015 - link

    I think you are correct I was confusing Broadwell-H for Broadwell-K. But, it seems odd that If these CPUs will be hitting the market shortly, that many OEMs are updating laptops with updated Nvidia 900 series mobile parts. It seems it would make more sense to update the once they had updated CPUs.
  • sonicmerlin - Monday, February 23, 2015 - link

    > These kinds of configuration may appear in smartphones, tablets, or other devices that use highly-integrated chips where multiple types of fabrication would be necessary, and where manufacturers can charge the premium price necessary to cover the additional costs.

    Smartphone and tablet SOCs sell for literally 1/10 the price of Intel's Core M and desktop CPUs. Their "premium" rationale strikes me as illogical.
  • eanazag - Monday, February 23, 2015 - link

    So does this mean the chips based on this process should be better overclockers?

    Does this say we may not likely see a Crystal Well part? As the cache can hit 10.5 MB or higher. Embedded devices could be anything these days.

    I get that Intel is trying to push the message out that they'll be on time.
  • watersb - Tuesday, February 24, 2015 - link

    Excellent. This is what I look for at AnandTech. Looking forward to ISSC and MWC coverage. And you just got over the CES hangover...
  • BOMBOVA - Tuesday, February 24, 2015 - link

    The papers Intel is presenting should be available via the ISSCC website as the presentations take place, along with a few others that pique our interest " i am looking out for them " Low powered wireless, should be interesting.
  • AbelDD - Thursday, February 26, 2015 - link

    Does anyone know about POET Technologies?

    "POET is developing a proprietary semiconductor technology that incorporates novel functionality on a gallium arsenide (“GaAs”) substrate. We believe that our technology will enable semiconductor end-user device designers to design integrated circuits (“ICs”) that offer greater processing speeds, utilize less power and incorporate more functionality in a single chip than many integrated circuits currently available in the market. POET has been developed to include novel function architectures utilizing gallium arsenide GaAs wafers, which enable the production of ICs that can be manufactured with processing speeds substantially in excess of those currently obtained by ICs fabricated utilizing silicon wafers and complementary metal oxide semiconductor (“CMOS”) technology. In addition, the POET technology incorporates positive and negative heterostructure field effect transistors (“HFETs”) as well as positive and negative heterojunction bipolar transistors (“HBTs on a single GaAs wafer, thus substantially broadening the capabilities of GaAs device technology,”), allowing for much improved power efficiency and speed, in addition to the combination of analog and
    digital circuits in a single chip design"

    http://www.poet-technologies.com/docs/POET-Overvie...

Log in

Don't have an account? Sign up now