Slashdot Mirror


Microsoft Signs License With ARM

G143 and several other readers let us know that Microsoft has signed a licensing deal with ARM. "Microsoft signed an agreement with the UK-based ARM, giving Microsoft access to some of the chip designer's intellectual property. The two companies have worked together since 1997, but Ian Drew, ARM's EVP of marketing, said this is the first time Microsoft has become a licensee of ARM's architecture, a move which will allow Microsoft to design their own microarchitecture. Other licensees include Qualcomm, Marvell, and Infineon. Neither company would reveal the cost of the license. Speculation about Microsoft's intentions includes wondering whether the company is taking aim at the iPad, or perhaps looking to produce a next-generation Xbox without the 360's heat problems."

148 comments

  1. Embrace... by tsa · · Score: 2, Funny

    Embrace, extend,... thrive! I guess.

    --

    -- Cheers!

    1. Re:Embrace... by Anonymous Coward · · Score: 0

      Personally I wish the best to Microsoft in this endeavor.

      If they want to make a supremely good cpu to run their own embedded platforms, well.. I won't be buying one because I'd want to install Linux on it. It just wouldn't make too much sense to actually change it in ways that would make it completely incompatible with their compilers, since that would just be extra costs. I'm sure they just want o make it run Windows CE better, and possibly sell chips to phone manufacturers.

      And as trends go, Microsoft seems to moving towards the good guy state, with their, slightly hopeless, attempts to improve their own platform design in ways that doesn't alienate the whole userbase of 'How do I start the computer?'.

  2. Even more worrisome by Anonymous Coward · · Score: 5, Funny

    Is the soon to be announced licensing with And A Leg Technologies.

    1. Re:Even more worrisome by Anonymous Coward · · Score: 0

      Nah, they are going to license hammers, and make a new code-cleanup appliance.

    2. Re:Even more worrisome by Monkeedude1212 · · Score: 0

      How else are they going to get a head of the competition?

    3. Re:Even more worrisome by myocardialinfarction · · Score: 1

      If they could somehow merge the knowledge-base of ARSE and ELBOW it would be a boon.

    4. Re:Even more worrisome by IorDMUX · · Score: 1

      My first-glance interpretation was quite a bit more unsettling: Microsoft Signs License With Amalgamated Regional Militia.

      What? Paranoid you say?

      --
      >> Standing on head makes smile of frown, but rest of face also upside down.
  3. The iPad market is about more than just the CPU. by Anonymous Coward · · Score: 0, Insightful

    The CPU is in fact quite a minor part of the iPad. It is an Apple device, so the consumer's main focus will be on the affixed logo, and nothing but the logo. Frankly, Microsoft just doesn't have the right logo to appeal to the hipster/trustfund baby/neckbeard market that Apple has taken control of. No matter what CPU Microsoft uses, their devices won't be adopted by the iPad crowd as long as the logo isn't an Apple logo.

  4. So I guess... by acnicklas · · Score: 1

    ... I shouldn't ask if it'll be running Linux?

    1. Re:So I guess... by fuzzyfuzzyfungus · · Score: 2, Funny

      They are licensing ARM so that they will be able to implement the 'halt_and_catch_fire" instruction specifically for that event...

    2. Re:So I guess... by Anonymous Coward · · Score: 0

      Undoubtedly that won't be the only event that causes it to do so. It's inevitable that some other noodle on the spaghetti plate will touch it.

    3. Re:So I guess... by NotBornYesterday · · Score: 1
      --
      I prefer rogues to imbeciles because they sometimes take a rest.
  5. XBox Portable? by Reilaos · · Score: 2, Insightful

    The first two things that come to mind when putting Microsoft and ARM together are Windows Phone 7 Phones and portable gaming systems, not slate tablets and full-on consoles.

    1. Re:XBox Portable? by SquarePixel · · Score: 1

      It also doesn't make much sense for Microsoft to change the xbox architecture that much, since it has always been basically a PC and it has all the same systems like DirectX, .NET and the usual compatibility with Windows.

      It would however make perfect sense for Windows Mobile.

    2. Re:XBox Portable? by Tom9729 · · Score: 4, Informative

      Most (all?) Windows Mobile devices already run on ARM. Windows CE has supported ARM since 1997.

    3. Re:XBox Portable? by MightyYar · · Score: 4, Informative

      It also doesn't make much sense for Microsoft to change the xbox architecture that much, since it has always been basically a PC and it has all the same systems like DirectX, .NET and the usual compatibility with Windows.

      I just had to check the calendar to make sure it wasn't 2001.

      They abandoned the PC-like architecture with the 360. It now runs a PowerPC hybrid chip.

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    4. Re:XBox Portable? by Anonymous Coward · · Score: 0

      You mean, like PSP? Oh, the fun of chips overheating to 90C in your hands waits up ahead!

    5. Re:XBox Portable? by Anonymous Coward · · Score: 0

      Xbox = x86
      Xbox 360 = PowerPC
      Xbox 720 = ARM

    6. Re:XBox Portable? by Narishma · · Score: 1

      ARM processors are nowhere near as powerful as PPC or x86.It doesn't make sense for Microsoft to use them in a console.

      --
      Mada mada dane.
    7. Re:XBox Portable? by eddy · · Score: 1

      It doesn't make sense to use them as the MAIN CPU, no.

      I could see ARM in a console, say for a low-power menu-mode, a bit like the 'instant on linux' found in some computers, or for having the console 'always on' downloading patches and what not.

      --
      Belief is the currency of delusion.
    8. Re:XBox Portable? by Anonymous Coward · · Score: 0

      It does if it supplements another processor in the console (or if their design is based on an array of ARM processors). It may not be as powerful, but it is highly efficient (in terms of energy consumption), and parallel processing negates almost all of the performance issues (when software is designed to take advantage of it, as a console's software would)

    9. Re:XBox Portable? by theheadlessrabbit · · Score: 1

      It also doesn't make much sense for Microsoft to change the xbox architecture that much, since it has always been basically a PC and it has all the same systems like DirectX, .NET and the usual compatibility with Windows.

      It would however make perfect sense for Windows Mobile.

      Maybe they are going for "x-box portable"

      although if they just shrunk down the existing x-box design to hand-held proportions, they could advertise themselves as having the world's first hand-held gaming system/hotplate.

      --
      -I only code in BASIC.-
    10. Re:XBox Portable? by sznupi · · Score: 1

      Unless it's a massively parallel array of ARM cores. An idea which some people are supposedly exploring. And for which ARM-like cores seem suited.

      With control of single manufacturer over hardware, OS, libraries and...developers it might be even workable (unlike quickly shifting PCs to many-core model)

      --
      One that hath name thou can not otter
    11. Re:XBox Portable? by ravyne · · Score: 2, Interesting

      Thats because ARM cores have always been targetted at the embedded and portable markets, where potential customers want "just enough" power with absolute minimum power draw -- Tha majority of ARM parts sold today draw peak power measured in milliwatts -- an order of magnitude or two lower than the most frugal X86 or PPC designs. Some of the higher-end ARM designs incorporate vector floating point, a DSP or two, hundreds of megabytes of on-chip RAM and quite capable 3D accelleration, and still manage to draw down less than a watt at peak power consumption.

      The fastest available ARM cores today are competitive with Intel's ATOM processors core-for-core, clock-for-clock. In practice, existing cores end up being slightly slower in actual use since none have a system bus wider than an anemic 32bits (and also not typically clocked very fast), but in terms of computational power, they already match some current x86 designs.

      If someone took the chains of power-consumption off and said "We're going to get all we can out of, say, a 20 Watt power envelope" you'd end up with something quite powerful. For starters, with very little work on the core itself, you could double the core speed and simply allow greater power leakage, then toss 16 of those on a die with local and shared cache. 16 2Ghz ARM cores, each with a very capable vector-floating-point unit, would be every bit as powerful as even the fastest Intel quad-core i7. Then there's the other end of the spectrum -- reworking the core architecture from the ground up, optimizing for performance, rather than power consumption. You could reasonably attain competetive performance with fewer, more-powerful cores as well.

      All of that said, I'm skeptical that this is about Xbox. This is for sure about Zune, possibly about a Microsoft portable console, possibly for high-performance peripheral devices (Think Kinect 2.0 offloading most of the work to the kinect unit itself), and only just by the slimmest of chances about Xbox 3 (or 4, for that matter) -- The only thing that gives me pause that it might be about Xbox proper, is that all their other devices are well-served by the existing ARM ecosystem, too well served to enter the chip-design business anyhow. An upcoming Xbox is one compelling reason to liscense a new micro-architecture, and being able to respond to Apple's in-house ARM core is the other.

      Make no mistake that ARM is a very capable architecture though, and it's a delight to code for in Assembly Language. I've said many times that ARM is, in the coming years, going to be the most credible threat Intel and X86 has ever faced. It's going to be moving into Netbooks and STBs more this year, then laptops, some servers and higher-end embedded devices (I'm convinced Nintendo will consolidate all their systems behind ARM beginning with their next home console in order to leverage their 1st and 3rd party experience with ARM that is the result of their portables' popularity). In 10 years time, the question may not be Intel vs. AMD, but x86/x64 vs. ARM.

    12. Re:XBox Portable? by staalmannen · · Score: 1

      Sounds like the Tile64 idea http://www.tilera.com/products/processors/TILE64, which basically is a massively parallel design where each individual core is relatively low power. For a gaming system I think this might be quite suitable - it should be more GPU than CPU dependent anyway.

    13. Re:XBox Portable? by sznupi · · Score: 1

      Plus, something like this actually blurs the line between the CPU and GPU; yeah, something which Larabee was supposed to give and failed...but without all the baggage.

      --
      One that hath name thou can not otter
  6. foray into nothing by Anonymous Coward · · Score: 0

    this kin finally be a way for MS to kill the iphone ? no...

  7. Intel's reaction by bonch · · Score: 3, Insightful

    I wonder what Intel's response is, especially since Microsoft is such a long-time partner. Apple went with A4, and here Microsoft is licensing ARM too. The emerging market is mobile computing, so what's the future for Intel? Surely, they can't live on x86 forever, and Atom currently isn't competitive with ARM when it comes to battery life.

    1. Re:Intel's reaction by DeadboltX · · Score: 1

      Different processors for different applications.

      It is difficult to stick a full sized car engine into a scaled down remote control car. It is difficult to move a full sized car with a scaled down remote control car engine.

    2. Re:Intel's reaction by SquarePixel · · Score: 1

      Future for Intel will be Microsoft's largest business area, desktop computers, just like now. I very much doubt that Microsoft is planning to change to ARM with Windows.

    3. Re:Intel's reaction by doconnor · · Score: 1

      That wouldn't be true if remote control car engine where doubling in power every 18 months.

    4. Re:Intel's reaction by garyisabusyguy · · Score: 1

      Intel already licenses the ARM architecture and uses it in their xScale line of processors

      Currently Intel supplies compilers, but this Intel forum contains many complaints about performance under WinCE.

      http://software.intel.com/en-us/forums/showthread.php?t=67843

      Seems, like MicroSoft decided to take things into their own hands

      --
      Wherever You Go, There You Are
    5. Re:Intel's reaction by Anonymous Coward · · Score: 0

      Get back to us when it can do what my car engine can do today... in about 15 years. We'll try to keep the laughter to a minimum.

    6. Re:Intel's reaction by ADRA · · Score: 1

      *cough* Xscale was sold to Marvell 4 years ago...

      --
      Bye!
    7. Re:Intel's reaction by garyisabusyguy · · Score: 1

      Thanks for the info, however;
      "The acquisition was completed on November 9, 2006. Intel was expected to continue manufacturing XScale processors until Marvell secures other manufacturing facilities, and would continue manufacturing and selling the IXP and IOP processors, as they were not part of the deal.
      The XScale effort at Intel was initiated by the purchase of the StrongARM division from Digital Equipment Corporation in 1998. Intel still holds an ARM license even after the sale of XScale."
      http://en.wikipedia.org/wiki/XScale#Sale_of_PXA_processor_line

      It looks like Intel still owns intellectual property AND may even continue to manufacture them for Marvell.
      This seems even more like MicroSoft taking control over a technology because their partner is not giving them what they want

      --
      Wherever You Go, There You Are
    8. Re:Intel's reaction by sznupi · · Score: 1

      Intel probably still has something. Recent "Atom for smartphones" most likely includes an ARM core in its radio interface. And in the "southbridge" there's a part described as 32 bit host controller (or something like that) - would be surprising if not some ARM (why wouldn't it be one?)

      --
      One that hath name thou can not otter
    9. Re:Intel's reaction by UnknowingFool · · Score: 1

      Well, for the mobile market, the chip has been at the discretion of the WinMobile maker. Most of them use ARM based chips anyway. So it's not like Intel would lose any more business.

      --
      Well, there's spam egg sausage and spam, that's not got much spam in it.
    10. Re:Intel's reaction by renoX · · Score: 1

      > The emerging market is mobile computing, so what's the future for Intel?

      Well, the PC market is not going anywhere, so it means that Intel will still make *huge* benefits with x86 and have the best fabs.

      > Surely, they can't live on x86 forever, and Atom currently isn't competitive with ARM when it comes to battery life.

      For now.. But having the best fabs, it's quite possible that Intel will be able to make x86 competitive in battery life,
      but this may be also too late: now software compatibility for smartphone is in favor of ARM and against x86!

    11. Re:Intel's reaction by MemoryDragon · · Score: 1

      Intel is counting on their manufacturing to get up to ARM in a performance per watt ratio, the problem is that ARM is manufactured in so many fabs that some of them already are working on 20nm cortex A9s which means Intels master plan has failed again.

      It is particularily nasty becase most programs in the mobile world are compiled against native arm instructions and even if they use java lots of them have native code integrated. Intel faces the same problem in the mobile world as others do in the Desktop computing world, a huge stack of programs which are not compiled for your platform.
      So what is left is a worse offering with less programs which is also more expensive, not a good starting point. So far they only can leverage their desktop stronghold to force some companies (mostly companies which have their core business in producing pc hardware) to produce ATOM based phones or tablets, but I dont think those devices will sell well.

    12. Re:Intel's reaction by Blakey+Rat · · Score: 1

      Intel already got snubbed for the Xbox 360. Doesn't seem to have affected the relationship any.

      Honestly, Microsoft seems to be relatively CPU-agnostic anyway. For example, they picked AMD's 64-bit instruction set over Intel's. They didn't seem to hesitate when picking a PPC-based chip over an Intel chip in the Xbox 360, and they've never had any qualms about selling Windows to be installed on AMD computers.

    13. Re:Intel's reaction by exomondo · · Score: 1

      Honestly, Microsoft seems to be relatively CPU-agnostic anyway. For example, they picked AMD's 64-bit instruction set over Intel's.

      No they didn't, they supported IA-64, in fact they only very recently discontinued it.

    14. Re:Intel's reaction by Blakey+Rat · · Score: 1

      No they didn't, they supported IA-64, in fact they only very recently discontinued it.

      Only server OSes, and only a subset of them. x64 has enjoyed broad support.

    15. Re:Intel's reaction by exomondo · · Score: 1

      No they didn't, they supported IA-64, in fact they only very recently discontinued it.

      Only server OSes, and only a subset of them. x64 has enjoyed broad support.

      Obviously, you wouldn't put out a consumer OS for a chip that has no consumer version. Point is that MS supported IA-64 in its target market, and supported x86-64 in its target market - as did Intel.

  8. Innovate? Nah, this is a control maneuver. by Anonymous Coward · · Score: 0, Troll

    Microsoft just wants a relation$hip with ARM so they can influence them before a huge wave of low cost, linux friendly PC's, netbooks, you name it hits the market.

    I think it's interesting how the article speculates about innovation when to a large extent Microsoft M&A's are aimed at stifling competition. Seriously, when is the last time MS came up with a new idea?

    1. Re:Innovate? Nah, this is a control maneuver. by Anonymous Coward · · Score: 0

      Yup, this proves it!
      You can never fool a cynic!

    2. Re:Innovate? Nah, this is a control maneuver. by $RANDOMLUSER · · Score: 1

      That's the smartest thing I've read today. And it'd be a hell of a negotiating tool against Intel, too. Meanwhile, the idea of Microsoft trying to do their own phone isn't all that far-fetched.

      --
      No folly is more costly than the folly of intolerant idealism. - Winston Churchill
    3. Re:Innovate? Nah, this is a control maneuver. by westlake · · Score: 1

      Microsoft just wants a relation$hip with ARM so they can influence them before a huge wave of low cost, linux friendly PC's, netbooks, you name it hits the market.

      ----- and sink like a rock when they hit the shelves at Walmart.

      Apple has re-discovered an old truth about the high-tech gadget - it sell best to folks with serious money to spend - so you might as well take them for whatever they are worth.

    4. Re:Innovate? Nah, this is a control maneuver. by larry+bagina · · Score: 1

      Your ignorance of the Microsoft Kin is forgiven, but only because it was a miserable failure.

      --
      Do you even lift?

      These aren't the 'roids you're looking for.

    5. Re:Innovate? Nah, this is a control maneuver. by MightyYar · · Score: 1

      Seriously, when is the last time MS came up with a new idea?

      Some of their brutal business practices were pretty inspired.

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    6. Re:Innovate? Nah, this is a control maneuver. by ooshna · · Score: 1

      He said a phone not a social networking portable machine handed down from the gods for all the tweens. A machine crafted by Jesus and powered from the lightening bolts of Zeus himself. Didn't you pay attention to the commercials?

  9. Already done, thank you very much by garyisabusyguy · · Score: 3, Interesting

    The ARM core is so widely licensed that it would be hard to find a modern handheld device that does NOT contain one.

    "Many semiconductor or IC design firms hold ARM licenses; Analog Devices, Atmel, Broadcom, Cirrus Logic, Energy Micro, Faraday Technology, Freescale, Fujitsu, Intel (through its settlement with Digital Equipment Corporation), IBM, Infineon Technologies, Nintendo, NXP Semiconductors, OKI, Qualcomm, Samsung, Sharp, STMicroelectronics, Texas Instruments and VLSI are some of the many companies who have licensed the ARM in one form or another" http://en.wikipedia.org/wiki/ARM_architecture#ARM_licensees

    IMHO, this is a non-story.

    --
    Wherever You Go, There You Are
    1. Re:Already done, thank you very much by fuzzyfuzzyfungus · · Score: 5, Insightful

      It is something of a story, though: "Many semiconductor or IC design firms hold ARM licenses". Microsoft is, historically, neither of those things and; because of the number of existing ARM licensees, they can already get virtually any ARM based SoC configuration that you could reasonably desire, at highly competitive prices, off the shelf, without any sort of license.

      Microsoft using ARM cores would be a total non-story. I'm pretty sure that they already do, in a number of capacities. Becoming an ARM licensee, though, means that you have a plan that goes well beyond shoving some off-the-shelf chips into your product. Since MS doesn't seem like a logical entrant into the chip fab market, this development means that they have some kind of design demand up their sleeve that the market for commodity SoCs hasn't delivered....

    2. Re:Already done, thank you very much by tsa · · Score: 1, Informative

      But those are all hardware companies... oh, wait... But I did score a Funny! :)

      --

      -- Cheers!

    3. Re:Already done, thank you very much by garyisabusyguy · · Score: 3, Interesting

      I had a couple of 'why' questions and found a possible answer.

      This Intel forum:
      http://software.intel.com/en-us/forums/showthread.php?t=67843

      Contains many complaints about the performance of the Intel compiler under WinCE (as well as Intel selling it all off to Marvel).

      If you ask me, MS wants a chip that they can optimize for their OS. Seems liek this will lead it down a proprietary hole, not unlike Apple.

      So, is that the real story, "MicroSoft, now more like Apple!"

      --
      Wherever You Go, There You Are
    4. Re:Already done, thank you very much by Bill,+Shooter+of+Bul · · Score: 0

      Ah, Kin V2.

      --
      Well.. maybe. Or Maybe not. But Definitely not sort of.
    5. Re:Already done, thank you very much by Joce640k · · Score: 1

      Ummm...doesn't Microsoft have their own C++ compiler for Intel chips?

      --
      No sig today...
    6. Re:Already done, thank you very much by owlstead · · Score: 0

      Akin Kin.

    7. Re:Already done, thank you very much by Anonymous Coward · · Score: 0

      Maybe that's why the Kin V1 failed? Not propriatory enouhg?

    8. Re:Already done, thank you very much by garyisabusyguy · · Score: 1

      There is a big difference between writing a compiler for a chip that you do not manufacture, and writing a compiler for a chip that you can add extensions to in order to support faster performance.

      It reminds me of Suns attempt to create a picoJava compiler that did not have to perform jit compiling and could directly run bytecode

      --
      Wherever You Go, There You Are
    9. Re:Already done, thank you very much by mark72005 · · Score: 1

      Cool, a completely new way for them to make users want to shoot themselves in the face.

    10. Re:Already done, thank you very much by gbjbaanb · · Score: 1

      no, but Intel has a compiler for Intel chips :)

      It runs on Windows too.

    11. Re:Already done, thank you very much by mcgrew · · Score: 1

      Since MS doesn't seem like a logical entrant into the chip fab market, this development means that they have some kind of design demand up their sleeve that the market for commodity SoCs hasn't delivered....

      BSOD in silicone?

    12. Re:Already done, thank you very much by Anonymous Coward · · Score: 0

      No, you'd want need to visit a Japanese trade show, for that.

    13. Re:Already done, thank you very much by firewood · · Score: 1

      The ARM core is so widely licensed that it would be hard to find a modern handheld device that does NOT contain one.

      Not only handhelds. There's a good chance your Wintel laptop or desktop PC might have one hidden in its disk controller or wifi chipset as well.

    14. Re:Already done, thank you very much by marcosdumay · · Score: 1

      So, they'll write a Windows for the ARM? And where will they use that core?

      I'd bet they want it to their periferals, that just make a lot more sense. With that IP, they can design custom chips for them and reduce costs or increase functionality beyhond what their competitors are able to.

    15. Re:Already done, thank you very much by SnarfQuest · · Score: 1

      Microsoft, of course, will design one that is incapable of running any competators software.

      --
      Who would win this election: Andrew Weiner vs Andrew Weiner's weiner.
    16. Re:Already done, thank you very much by Anonymous Coward · · Score: 0

      maybe they should have licensed the ARM core that directly runs Java bytecode?

    17. Re:Already done, thank you very much by Jorophose · · Score: 1

      Could they be looking at an equivalent of Jazelle but for C#?

      I don't see microsoft having enough engineers willing to work on an ARM core unless MS has something they want to try and pull the industry with. The idea of an optimized core might make sense, but i'm not sure how much they could change it without running into problems.

  10. Pocket XBox, anyone? by FreonTrip · · Score: 3, Funny
    Any number of potential reasons exist for this license, but that's the one which bubbles to mind most readily.

    In before the "What's that giant thing in your pocket?" "That's what she said!" engine gets warm.

    1. Re:Pocket XBox, anyone? by kg8484 · · Score: 1

      Doesn't seem likely to me. From what I can tell, the PSP was profitable for Sony, but it is being sorely beaten by the Nintendo DS series and now standalone portable video game sales are being cannibalized by smartphones. I would say that this is more likely to end up in a Zune phone and will be Microsoft's in-house alternative to nVidia's Tegra processors. I will chuckle if they contract AMD/ATI to do the graphics again, kind of like how they switched to ATI graphics when building the XBox 360 processor.

    2. Re:Pocket XBox, anyone? by Yvan256 · · Score: 2, Funny

      Is that a fire in your pants or are you just happy to see me?

    3. Re:Pocket XBox, anyone? by FreonTrip · · Score: 1

      "OW, OW! OH GOD, IT'S BOTH!"

  11. Hmm... by fuzzyfuzzyfungus · · Score: 1

    I wonder what MS has in mind. You don't have to be an ARM licensee to use ARM chips in your designs. For large enough orders, there are already a number of outfits that will implement customized ARM SoCs with your choice of functional blocks, and either fab them or farm the design out to somebody else, on a variety of processes. For smaller orders, there are even more outfits who have ARM SoCs, in a variety of common configurations, in stock and ready to go. Lead times pretty much limited by Fedex for small orders, some weeks for big ones. Buying an actual license seems to indicate Serious Business of some sort.

    Without any particular background in chip design, what does MS want to do that they couldn't do at off-the-shelf prices just by calling one of the existing ARM licensees and asking for a quote? For the sake of my faith in their executive team, they couldn't be doing this just because Apple is, could they?

    What will it be? Massive arrays of power optimized ARMs supporting a CLR environment as the future of Windows Server technologies? Xbox720 is going to be ARM based with some sort of secret sauce?

    1. Re:Hmm... by wowbagger · · Score: 5, Insightful

      "... ARMs supporting a CLR environment...."

      Actually, that would be my guess: Microsoft wants to make an ARM chip that implements the Common Language Runtime in the microarchitecture, just as some ARM chips now implement the Java runtime in the microarchitecture. They may also want to add instructions to bring even more Trusted Platform Computing Model down into the ARM core.

      They may also want to make an ARM core that implements a graphics accelerator more friendly to the Direct3D model (and less friendly to OpenGL ES) than is currently available.

    2. Re:Hmm... by MightyYar · · Score: 3, Insightful

      Microsoft wants to make an ARM chip that implements the Common Language Runtime in the microarchitecture

      The thought of Microsoft shipping code that they cannot patch later is at least somewhat amusing to me.

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    3. Re:Hmm... by Amouth · · Score: 2, Interesting

      i'm betting on 5 things - 1-5 most likely to doubt

      #1) and and most likely (as it has the highest chance to fail) - MS tries to make it's own hardware for it's Win7 phone OS so that they don't get the bad rap they did with windows mobile on phones that didn't have the hardware to run them

      #2) they might be looking into using it for the next xBox - and at that point doing it in-house so they don't have to rely on IBM as they have in the past (them supporting IBM who is also being supported by Sony can make it seem like they are supporting the competition)

      #3) they might be looking into using them for their next HPC platform - it is at least 3-5 years out which is a good lead time for them to design and refine a new way of using exiting ARM cores.

      4#) maybe they want to design and test extensions to the ARM archt that they don't want to trust a partner with - once they refine them submit them back to ARM (think of it as custom extensions for either Win7/8 Phone OS or xbox OS or HPC OS)

      #5) maybe they are rethinking their canning of the courier - and are rather going to embrace it and actually make it with a competitive chance.

      I find it odd that in my mind the list 1-5 of most likely to doubt is inverse of what i think would work out best for them.. and would be happy to see them do. Maybe its All of the above and a slice of pie?

      --
      '...if only "Jumping to a Conclusion" was an event in the Olympics.'
    4. Re:Hmm... by Microlith · · Score: 2, Informative

      Fundamentally altering the ARM core logic at the level required to add CLR support (similar to the Java implementations) requires a license on a level that ARM does not give out. Only a handful of companies, Apple being one of them, hold the necessary license to do so (mostly the founding companies.)

    5. Re:Hmm... by ADRA · · Score: 1

      I think that the CLR thing has more credence than some of the other suspicions. That type of chip is really something that only Microsoft would spearhead, and the fact is that I don't think MS would make a better chip than what it would cost to license it from others.

      That said, a Desktop level performance ARM chip is something that hasn't been done yet, so maybe this is just an Xbox play.. It couldn't hurt their 'runs on all devices' initiative having two of their platforms sharing the same CPU architecture.

      --
      Bye!
    6. Re:Hmm... by MasterOfMagic · · Score: 1

      You do realize that ever since the Intel Pentium FDIV fiasco that their processors allow you to patch the microcode, right? It would be silly to think that you couldn't do the same with an ARM chip, especially when it's tracking a moving target like the CLR.

    7. Re:Hmm... by hackerjoe · · Score: 1

      Interesting speculation but unlikely. The Java-specific mode (Jazelle) is deprecated; ARM's for a few years already been moving instead to a mode that supports CLR and JVM managed runtimes equally well, called ThumbEE, which is already in the newer Cortex A8-based smartphone chipsets:

      ThumbEE in Jazelle article on Wikipedia
      Information on ThumbEE from the ARM tech docs

      It's a much more elegant approach -- do all the easy transformations via JIT compilation to the existing native ARM instructions, and add a handful of extra instructions to speed up the expensive things you do all the time, like null pointer checks and array bounds tests.

    8. Re:Hmm... by joe_bruin · · Score: 1

      They may also want to make an ARM core that implements a graphics accelerator more friendly to the Direct3D model (and less friendly to OpenGL ES) than is currently available.

      The ARM core has nothing to do with graphics. The graphics accelerator is a discrete logic unit chosen by the SOC maker to integrate into the chip. This part uses the standard AHB/AXI (ARM Host Bus) interface. A major architecture license is not required to do this.

      CLR acceleration, on the other hand, seems like a possibility. They could replace the Jazelle (Java) mode. More likely, though, they will extend the ARMv7 ThumbEE mode, which is designed for this sort of thing. Here's the synopsis of ThumbEE from the Cortex reference manual:

      Thumb Execution Environment (ThumbEE) is a variant of the Thumb instruction set designed as a target for dynamically generated code. This is code that is compiled on the device, from a portable bytecode or other intermediate or native representation, either shortly before or during execution. ThumbEE provides support for Just-In-Time (JIT), Dynamic Adaptive Compilation (DAC) and Ahead-Of-Time (AOT) compilers, but cannot interwork freely with the ARM and Thumb instruction sets.

      ThumbEE is particularly suited to languages that feature managed pointers and array types.

    9. Re:Hmm... by Brit_in_the_USA · · Score: 3, Informative

      That said, a Desktop level performance ARM chip is something that hasn't been done yet,

      It has been done. I used to own a RISC PC desktop with 200Mhz StrongARM CPU at the time x86 PC's were maxing out with 90MHz Pentium. Other than in FP applications it ran laps around the Intel chips of the time.
      It is also worth noting the StrongARM was in a plastic package with no heatsink as it dispated so little heat.

      Ultimately the platform stalled at this CPU achievement and Intel eventually caught up and surpassed (on the speed front anyway). I often wonder if (the lack of speed bumps to StrongARM for a very long time) had anything to do with Intel taking over the design/manufacture.

    10. Re:Hmm... by hhedeshian · · Score: 1

      You do realize that ARM is RISC and doesn't need/use microcode. "To keep the design clean, simple and fast, the original ARM implementation was hardwired without microcode" (Wikipedia) and to my knowledge it still is. It would up the power requirements considerably because you would have to have additional translation logic. It would defeat the purpose of ARM.

      (someone correct me if I'm wrong, though)

    11. Re:Hmm... by WagonWheelsRX8 · · Score: 1

      Actually, I think what is REALLY going on is MS doesn't actually have a plan for the ARM architecture. Instead, they figured they'd generate some buzz and a lot of speculation by licensing it. Then they'd cherry pick the best of the speculative ideas, and use them as their plans for ARM...

    12. Re:Hmm... by Anonymous Coward · · Score: 0

      Microsoft wants to make a better compiler and/or operating system for ARM. This requires detailed knowledge of the architecture.

    13. Re:Hmm... by svirre · · Score: 1

      There are no patching capabilities in any ARM core I am familiar with. (OK they have ROM patch capabilities, but that was not what you was suggesting)

    14. Re:Hmm... by Anonymous Coward · · Score: 0

      Hey! Microsoft has an /entirely clean/ record of designing CPU instructions...

    15. Re:Hmm... by dfghjk · · Score: 1

      "That said, a Desktop level performance ARM chip is something that hasn't been done yet,..."

      The very first ARM processor was for a desktop.

    16. Re:Hmm... by ooshna · · Score: 1

      Probably meant modern Desktop level performance.

    17. Re:Hmm... by JAlexoi · · Score: 1

      FYI: The Jazelle in ARM's is the JVM "accelerator", not H/W level JVM.

    18. Re:Hmm... by MasterOfMagic · · Score: 1

      I do realize this, but there are myriad of ways you can design a processor and you can implement the ARM instruction set in microcode if you so choose.

      I'm more responding to the belief that processors in general cannot have bugs fixed in the field, not that ARM itself can be fixed with a microcode update.

  12. Re:The iPad market is about more than just the CPU by Anonymous Coward · · Score: 2, Insightful
    I have seen the ipad in the wild, and the bottom line is the damn things work and work well. I personally do not want one because of the software stranglehold. The fact that there are a large number of people who love their Apple i%DEVICE% is very telling. I meet damn few people who feel that way about MS products. Most people who use MS tolerate it and choose it because they think it is an "MS world." I love my linux system, but that is for mostly intangible reasons that make it worth the frustrations.

    The folks at Apple understand what people want and understand how people work. They are also unscrupulous. It is dangerous to underestimate the power of this combination. It is easy to ridicule them, but it is to our detriment if we do recognize it and confront it.

  13. Microprocessors and Marvel? by Parker+Lewis · · Score: 1

    They'll try to built a Ironman suit.

    1. Re:Microprocessors and Marvel? by oodaloop · · Score: 1

      That's Marvell.

      --
      Tic-Tac-Toe, Global Thermonuclear War, and relationships all have the same winning move.
    2. Re:Microprocessors and Marvel? by Parker+Lewis · · Score: 1

      Oh, really? You can note that I forget one letter, but you can't understand irony.

    3. Re:Microprocessors and Marvel? by oodaloop · · Score: 1

      I actually posted a self-reply whoosh just to be funny, and slashdot of course lost it. Dammit. Yes, I know you were being ironic. Sigh.

      --
      Tic-Tac-Toe, Global Thermonuclear War, and relationships all have the same winning move.
  14. Re:The iPad market is about more than just the CPU by SquarePixel · · Score: 1

    The fact that there are a large number of people who love their Apple i%DEVICE% is very telling. I meet damn few people who feel that way about MS products.

    Obviously, because Apple is targeting niche market and also labels themselves to the hardware (and pay Intel etc so they can remove their logos).

    In the normal PC world the cpu is from different manufacturer, the memory is, everything in the hardware is. People most likely just remembers something along the lines of their computer being a Dell-computer, because that's what the combination is sold at. Why would casual people be so interested about the single parts that make it? They just want to do their thing, that's it.

  15. Innovation? They do it all the time! by Anonymous Coward · · Score: 0

    Seriously, when is the last time MS came up with a new idea?

    I went out to lunch with an MS software engineer a couple of weeks ago. He said that he wanted the ham sandwich. I said that I was considering the grilled cheese. He said it sounded good but had his heart set on the ham sandwich. After a brief pause he slammed his menu down and proudly blurted out, "Fuck it! I want a ham sandwich with cheese and grill the whole god-damned thing."

    It took a short time for me to catch my breath, but I quickly saw the brilliance. Surely, it was the best idea to come out of Redmond since the quick turn around on the Vista service pack called "Windows 7."

    1. Re:Innovation? They do it all the time! by ooshna · · Score: 1

      That be funny if Vista wasn't a service pack for Windows ME.

  16. Re:The iPad market is about more than just the CPU by Black-Man · · Score: 1

    Microsoft is still lost since their tactic of "give the people something that kinda looks the same but cheaper" didn't work for the Zune.

  17. Yes, but... by Dancindan84 · · Score: 1

    Was it the right or the left?

    --
    "Always forgive your enemies; nothing annoys them so much." - Oscar Wilde
  18. Windows phone by Local+ID10T · · Score: 2, Interesting

    Speculation about Microsoft's intentions includes wondering whether the company is taking aim at the iPad, or perhaps looking to produce a next-generation Xbox without the 360's heat problems.

    Seriously? Microsoft has been chasing the smartphone market for a while now, but keeps having performance issues. They want a custom designed chip for their next gen smartphone.

    --
    "You want to know how to help your kids? Leave them the fuck alone." -George Carlin
  19. The reason is the PRICE by stanlyb · · Score: 0

    It is pretty simple, if you wanna to sell 100-200 devices, then you just buy the ARM-CPU from another manufacturer. But if you wanna to sell 1-2 millions, then you will save a lot of money by simply buying the right to make the hardware and if you are good enough, even the right to change/modify it. From what i remember, the starting price for this scenario is $200k, which explains why there are so few companies willing to have this kind of agreement.

  20. Microsoft is going to build their own machines now by mrjatsun · · Score: 1

    It's not surprising... A lot of things have been pointing to Microsoft building their own H/W in this space. HP canceling Slate and buying Palm. Dell going with Android. It makes a lot of sense for Microsoft to build their own ipod, ipad, and ARM based "netbook" like machines. If true, in the long run, I think this puts more pressure on Dell and HP.

  21. ARM and HAND by Theaetetus · · Score: 1

    And possibly even a PEN.

    1. Re:ARM and HAND by cynyr · · Score: 1

      no no, thats ARM and LEG...

      --
      All of the above was encrypted with a Quad ROT-13 method. Unauthorized decryption is in violation of the DMCA.
  22. ARM is going to end up in servers by alen · · Score: 1, Troll

    there is some company selling Atom CPU based servers and a lot of customers like them. Atom is just a Xeon with almost everything disabled due to manufacturing issues. Apple did a nice job with the A4 in terms of battery life and power consumption. MS will probably port Windows Server and other products to the architecture to keep VmWare and Linux at bay.

    and with tech demos of Apache running on the iPhone any idiot will say that ARM will end up in servers soon with the big plus being you can customize it to your needs. just like Apple and Qualcomm did. with Intel you get a Xeon at $1500 each on average or a Xeon reject at $150. ARM CPU's cost a fraction of that even after R&D. and when you calculate the electricity savings it gets even better.

    1. Re:ARM is going to end up in servers by alen · · Score: 1

      P.S. same story as Nokia. they sold dumb phones at cost and smart phones to drive profits. apple is killing that model.

      Intel sells i Core CPU's for branding and the profits are in the Xeons. All CPU's are manufactured as XEON's and binned when they are tested. ARM is about to demolish that model since it's dirt cheap to design and manufacture their CPU's.

    2. Re:ARM is going to end up in servers by TeknoHog · · Score: 1

      There are already supercomputers and servers based on POWER, MIPS and many other architectures. Broadly speaking, you can run open source operating systems on any architecture you like, or you can run closed systems on x86. Microsoft has a lot of catching up to do in this sense, but due to closed 3rd party applications, such versatility will never fly. Unless all the closed stuff is released as architecture-independent bytecode.

      Atom is just a Xeon with almost everything disabled due to manufacturing issues.

      I don't think this the case, they are probably completely different microarchitectures. For starters, Xeon has out-of-order execution while Atom is in-order only.

      --
      Escher was the first MC and Giger invented the HR department.
    3. Re:ARM is going to end up in servers by BLToday · · Score: 1

      Wait. Let's think about it for a second. If MS starts to optimize Windows Server for their own ARM processor, they're going to compete with their top customers (Dell, HP, etc.) Unless they start selling MS ARM to other computer makers, but now they're competing with Intel. They can probably win in a niche market fight (Xbox portable) but not going up against Intel, HP, and any real hardware guys. Plus, even if you have WinServer on ARM, the applications are still written for x86.

    4. Re:ARM is going to end up in servers by 0123456 · · Score: 1

      Atom is just a Xeon with almost everything disabled due to manufacturing issues.

      Uh, no it's not.

      However, I agree that ARMs probably have a place in low-powered servers in the not too distant future.

    5. Re:ARM is going to end up in servers by alen · · Score: 1

      Dell and HP started by supporting Linux, Android and Palm OS. Either Windows Server ends up running on ARM or Android/Palm server versions will. Wintel is starting to die

    6. Re:ARM is going to end up in servers by amliebsch · · Score: 1

      Good point. If only Microsoft had spent the last decade investing major resources on a platform for developing architecture-independent bytecode.

      --
      If you don't know where you are going, you will wind up somewhere else.
    7. Re:ARM is going to end up in servers by TeknoHog · · Score: 1

      Good point. If only Microsoft had spent the last decade investing major resources on a platform for developing architecture-independent bytecode.

      Then we only have to wait for all major 3rd party applications to be (re-)released in this form. Including games and other performance-sensitive applications.

      Or, get stuck in another closed ecosystem, when Windows transitions from x86 to Microsoft's implementation of ARM ;)

      --
      Escher was the first MC and Giger invented the HR department.
    8. Re:ARM is going to end up in servers by Anonymous Coward · · Score: 0

      Atom isn't even close to being "Xeon with almost everything disabled due to manufacturing issues" it's completely separate design, different core, different logic chipsets, it just happens to run the same x86 instruction set.

    9. Re:ARM is going to end up in servers by ovu · · Score: 2, Informative

      Atom is a Xeon with things disabled due to manufacturing issues?? Dude you are out of your element.

      Atoms are manufactured in different facilities, designed by different teams, in a completely separate division of the company! Also, Xeons consume an order of magnitude more power than Atom.

      And remember that the reason Intel dominates is due to manufacturing capability. Nobody can touch them. They do not have massive batches of defective chips being packaged and sold.

    10. Re:ARM is going to end up in servers by sznupi · · Score: 1

      ...the reason Intel dominates is due to manufacturing capability. Nobody can touch them...

      Except in low power scenarios, it seems.

      --
      One that hath name thou can not otter
    11. Re:ARM is going to end up in servers by MemoryDragon · · Score: 1

      Actually there was a news post a while ago that Microsoft has started to investigate into ARM for server usage. Google is doing currently the same. If you look at the performance numbers of the Cortex A9 compared to the ATOM you can see why, 2-3 times the performance compared to the ATOM with a fraction of the power drain ATOM causes. Intel has a serious problem there which they cannot resolve unless they drop x86 entirely in their low power cores, but they cannot do that because their userbase screams Windows ...
      Once one of the big ones has moved towards ARM in a serious manner others will follow and then it is goodbye ATOM unless you need Windows on the low power server side.

    12. Re:ARM is going to end up in servers by MemoryDragon · · Score: 1

      Actually in Low Power scenarios Intel is playing catch up and seriously you can license a single arm core (not a full license) for a few cents, so the bottom price line can be very low.
      Lower than what Intel can charge without losing money.

        Add to that that Intel seriously has to drop the x86 instruction set to come even close to ARMs performance per watt numbers and that ARM has started to outrun the Atom cores in its latest designs which will become visible in end user devices by the end of the year (Cortex A9, basically most consumer high end devices still use A8 which is seriously slower than the A9 core which is 2-3x times as fast as the current Atom gen), then you can see that Intel is scared, and seriously scared. For the first time in years they have serious competition which can hurt their core business and there is not too much they can do about it, because they cannot leverage their junk over the Windows monopoly this time.

    13. Re:ARM is going to end up in servers by drinkypoo · · Score: 1

      Atom is just a Xeon with almost everything disabled due to manufacturing issues.

      No, Atom is a third-generation Pentium III with some bits from the Core series. You can think of it as a Pentium 3 with a more advanced memory controller and hyperthreading.

      with tech demos of Apache running on the iPhone any idiot will say that ARM will end up in servers soon with the big plus being you can customize it to your needs.

      It takes too much glue logic to pull that off. x86 processors get better at power-saving all the time. By the time ARM servers became commonplace, x86 would probably get competitive power consumption, and it would only lead to fragmentation of the market.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    14. Re:ARM is going to end up in servers by O+Blimey · · Score: 1

      The rain in Spain falls mainly...
      I think he's got it.
      I think he's got it.

  23. More vertically integrated? by AmazinglySmooth · · Score: 1

    MS doesn't make PC's as far as I know. Maybe they have watched Apple be successful with their integrated hardware and software and want to duplicate their success.

    1. Re:More vertically integrated? by snadrus · · Score: 1

      Same thought from the negative side: ARM will soon outpace X86. Then noone wants to run a slow Windows (Desktop, Laptop, Server).
      WinCE is useless. They can't fix x86, so either modify arm to get Windows(x86 compatible) on it, or get a great arm implementation of something (CLR).
      For ref, their dual 1.2s outperform Intel's dual 1.6 in a power & size range so small that they already beat the biggest Intel servers at price-per-watt and rack space. And they're getting better, even rivaling gaming 3D which has limited uses in processing as well.

      --
      Science & open-source build trust from peer review. Learn systems you can trust.
    2. Re:More vertically integrated? by Anne+Thwacks · · Score: 1

      Blue Hardware of Death might not sell very well!

      --
      Sent from my ASR33 using ASCII
  24. Apple business copycat? by Anonymous Coward · · Score: 0

    Looks like they are copying the Apple's way of doing business. Can't live on Windows and the Office Suite alone!

  25. If Apple has it... by zunipus · · Score: 1

    Clone Apple. They have ARM. Microsoft must have ARM. Same old shite.

  26. The NINTENDO DS by DeanCubed · · Score: 2, Insightful

    Both the Game Boy Advance and the Nintendo DS used ARM7 and ARM9 chips. Now that Nintendo is using a different company from Japan to produce the architecture for the upcoming 3DS, perhaps Microsoft has decided to get into the handheld console race. I don't think this has anything to do with Apple or PC-related plans. This is the beginnings of X-Boy

    --
    Born to Play
    1. Re:The NINTENDO DS by Microlith · · Score: 1

      The company from Japan they're using is for the graphics chip. As far as most people can see, they're still using ARM for the CPU.

      Doesn't make any sense not to considering how well understood the architecture is for them.

    2. Re:The NINTENDO DS by sznupi · · Score: 2, Funny

      "X-Boy" seems to be quite...scary name. And one that they could go with.

      --
      One that hath name thou can not otter
    3. Re:The NINTENDO DS by Thing+1 · · Score: 1

      Nice! Reminds me of the reason Winamp went from 3 to 5; they didn't want any "Winamp 4 skins".

      --
      I feel fantastic, and I'm still alive.
  27. Xbox 3? by Brit_in_the_USA · · Score: 1

    Since the have licensed the arcitecture and the instruction set they are in the position of starting grouond up on ARM isntruction set compatible design and/or (heavily) modifying the exiciting core design. As the poster above pointed out they must have a need that is not serviced by the exisiting SOC comunity.

    The prime candidate (IMO) is something in the Xbox3. After being burned by not controlling the CPU and GPU designs chipset parts for the Xbox1 they had tighter control on the Xbox2 (360) with thier own 3 core Power PC design.

    With Sony continuing to leaverage the cell co-processors maybe MS wants something similar. It is not too far fetched that the next gen xbox could be a 3+core power pc with ARM derived co-processors (like CELL).
    The advantage is that compiler support is mature and developers are very familiar with ARM architecture so getting the most out of the cores would not be the steep learning curve that cell has had.
    ARM cores take up very little space compared to modern Intel/AMD x86 chip designs and typically have small levels of cache. Could easily fit a 4-6 core power PC and 20+(?) ARM cores on a modern process comparable in size to existing Xbox2 CPU die.
    Disclaimer : I own some ARM shares.

    1. Re:Xbox 3? by tlhIngan · · Score: 1

      The prime candidate (IMO) is something in the Xbox3. After being burned by not controlling the CPU and GPU designs chipset parts for the Xbox1 they had tighter control on the Xbox2 (360) with thier own 3 core Power PC design.

      I don't see it as a core processing element, but maybe as an IO controller or something. But that would be awful since it's a lot of extra coding, especially multi-architecture coding.

      However, it's also possible that Microsoft is considering some sort of portable Xbox system. ARMs just don't to the crazy speeds that the current gen consoles are at (Cortex A8/A9 only go to 1.something GHz, those PowerPC cores are pushing 3GHz). A portable system however, doesn't need too much power, and power-optimizing ARM has a lot of knowledge already from cellphones and the like.

      It's unlikely to be a tablet (Microsoft wants Windows 7 for tablets), so I guess a handheld Xbox would be it.

    2. Re:Xbox 3? by fuzzyfuzzyfungus · · Score: 1

      As it happens, there is (at least) one ARM processor in many xbox 360 systems:

      The Microsoft xbox360 wifi adapter is based on the Marvell Libertas 8388, which has an embedded ARM946 onboard. (In a curious twist, the OLPC XO-1 uses the same chipset, in order to have a core to handle mesh networking duties when the main CPU is off.)

  28. Why do they have to have anything in mind? by XDirtypunkX · · Score: 1

    They don't really need a particular project in mind, they have the cash at hand. Maybe they just want the option in their back pocket so they aren't backed into a corner.

  29. Extension of Xbox 360 IP Ownership Strategy by Anonymous Coward · · Score: 0

    I believe that this is probably an Xbox 360 successor play by Microsoft. The original Xbox used a stock Celeron 733mhz CPU from Intel and a licensed Geforce 2 MX variant from Nvidia. MS learned from the original Xbox that it is not cost effective to license technology and continuously pay royalties on that tech per unit of hardware sold, particularly for graphics. For this reason, Nvidia was cut out of the design process for the Xbox 360.
    http://en.wikipedia.org/wiki/Xbox

    When Microsoft developed the 360, they opted to custom design both the CPU and GPU. For the CPU (Xenon), Microsoft used technology from the IBM/Sony Cell project, which IBM was more than happy to sell them (lol at Sony). They chose to place 3 of the Cell PPC cores on a die, giving each their own VMX vector processing unit to make up for architectural deficiencies related to not having attached Cell-like DSP units. This is the only CPU of it's kind, Xenon is a Microsoft designed chip to which they own the IP.
    http://en.wikipedia.org/wiki/Xenon_%28processor%29

    The ATI GPU (Xenos) was also completely custom, being neither a R500 or an R600 part but something of a cross between the two architectural designs. It employed unified shaders well before the R600 architecture and featured a unique daughter die consisting of 10mb of DRAM used as a (very) fast intelligent framebuffer capable of performing 4x anti-aliasing on a per frame basis. This design allowed Microsoft to get "free" anti-aliasing, freeing up more graphics resources for other operations. Microsoft also owns the IP for the Xenos chip.
    http://en.wikipedia.org/wiki/Xenos_%28graphics_chip%29

    As much as everyone here enjoys ripping on Microsoft, (I am also guilty as charged) I believe the 360 is a far more elegant design chip-wise than the PS3 and better suited to actual gaming applications. Microsoft would not have purchased an ARM license if it were not worth the cost. As I don't see them stepping up to revolutionize the world of cellular phones, I can only assume that they are designing something completely new. It is likely a design far in excess of the capabilities of the ARM chips that other vendors are providing. If it's really true, if I'm right, then Microsoft could be developing a high-powered multi-core ARM chip for the next Xbox in order to eliminate all out-of-house CPU design expenses. I'm pretty excited to see what they come up with, since current low-power designs by other vendors are beginning to reach clocks of 2ghz with ease, a simple redesign could produce chips in the 3.5 - 4.5ghz range without much effort at all. (Comparative to starting from scratch, of course)

    The question is really, how well would a high-clock multi-core (likely 4 or more) ARM chip perform? If the cost to performance ratio is even close to what can be seen from an Intel or AMD solution, I think my suspicions will have been validated.

  30. What about netbooks? by yuna49 · · Score: 1

    Back when netbooks first appeared on the market, many of them ran Linux for cost and performance reasons. At the time the only shipping version of Windows was Vista which was ill-suited for machines running early Atom processors. Microsoft actually extended the life of XP so it could be used on netbooks, but protected the notebook market by adding irrelevant licensing requirements on XP sales like limits on screen sizes and maximum memory.

    Then we started hearing about a brand-new generation of ARM netbooks with much longer battery lives than Atom's can offer. Linux enthusiasts exulted that since there was no shipping version of Windows that ran on ARM processors other than the hoary CE, this gave Linux another window of opportunity in the netbook market. I don't know if MS now has a Windows 7 build that runs on ARM, or whether they needed this deal to release one, but if this means we'll be seeing netbooks with Windows 7 on ARM chips, it will block Linux from advancing in this space. For evidence, it took only a few months after the extension of the end-of-life for XP to enable Windows to dominate the netbook market in the US.

    The netbook market is flourishing, by the way. Recent studies suggest that netbook revenues in 2010 will run into the $10-15 billion neighborhood and growing fast.

    http://www.abiresearch.com/press/1697-As+Market+Shares+Shift,+Annual+Netbook+Shipments+Will+More+than+Double+by+2013?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+AbiresearchPressReleasesFeed+(ABIResearch+Press+Releases+Feed)

    http://techcrunch.com/2009/12/22/netbook-shipments-2009/

    1. Re:What about netbooks? by 0123456 · · Score: 1

      I don't know if MS now has a Windows 7 build that runs on ARM, or whether they needed this deal to release one, but if this means we'll be seeing netbooks with Windows 7 on ARM chips, it will block Linux from advancing in this space.

      Why? People don't buy PCs to run Windows, they buy PCs to run their Windows applications... few of which will run on ARM.

    2. Re:What about netbooks? by Hal_Porter · · Score: 2, Insightful

      Maybe they'll do ARM core that can run x86 instructions, Jazelle style. I.e. the most common 90% would map to ARM instructions via an extra pipeline stage, the rest would fault into an emulator.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    3. Re:What about netbooks? by MemoryDragon · · Score: 1

      Would not make sense from a performance point of view, jacelle is possible but it has been dropped in later designs because it was slower than JIT solutions. But even then the Java VM is a rather lean stack based vm which easily can be mapped, if you look at the hilarious dreadful bloat the x86 instruction set in reality is, you can see that an emulation on a totally different platform would mean a significant performance loss.
      Thats also the issue why no other architecture so far has replaced x86, you simply cannot emulate it faster on another architecture than the current generation of processors do (in their own hardware based emus)

      Arm is fine where it is and I personally think that there will be a split in the forseeable future. x86 in pc like devices ARM in everything else, often even outrunning the low end pc offerings in speed.
      I cannot see ARM making any huge inroads in the Windows PC crowd however. Also add to the fact that there is no hardware baseline like a Bios for ARM which makes a pc like design even more difficult.

    4. Re:What about netbooks? by Hal_Porter · · Score: 1

      Would not make sense from a performance point of view, jacelle is possible but it has been dropped in later designs because it was slower than JIT solutions

      If you read why that is it's not clear that it would apply to x86

      http://weblogs.java.net/blog/2007/02/13/when-software-faster-hardware

      He mentions that a JIT has an advantage over Jazelle (equivalent to his JPU case)

      To be fair to the JPU, to get around the stack architecture problem, a JPU would probably implement a stack caching scheme where some registers will mirror some top N values on the Java operand stack. It will also have some registers mirror some locals. This effectively allows the JPU to avoid memory accesses just like the ideal JIT case, thereby allowing it to theoretically attain speeds approaching the ideal JIT case. However, register pressure also limits the JPU just as it limits the JIT.

      In addition, the JPU can only mirror the top most operands on the stack, and maybe the first few locals. Which stack operand and/or locals get mirrored in registers usually isn't configurable at runtime. The JIT however can deal with this dynamically, and can arbitrarily choose which arguments and/or locals to keep in registers. Hence, the JIT has a higher probability of reducing memory accesses than the JPU.

      Complex Bytecodes

      But wait, that isn't the whole story. I said earlier that the above simple example was chosen because it shows off the JPU's best performance. Note that even when the JPU is best at its game, the JIT will still tend to beat its performance. Now consider the complex bytecodes in the VM instruction set (click here for a glossary of the VM bytecodes).

      The VM instruction set also consists of bytecodes like new (for allocating objects), newarray (for allocating arrays), monitorenter (for locking an object), monitorexit (for unlocking an object), and field accessors like getfield, getstatic, putfield, putstatic, and many other complex bytecodes.

      I call these bytecodes "complex" because their execution cannot be done in hardware. For example, new needs to work correctly in harmony with the VM's garbage collector; monitorenter needs to work in harmony with the VM's synchronization and threading mechanisms, etc. In the case of the field accessors, there bytecodes have to interface with the class' constant pool table which can be implemented differently depending on the software VM implementation. The constant pool entries will also need to be resolved (amongst other things) before the fields can be accessed.

      Now it seems like an ARM has enough registers to mirror the x86 ones, so no extra loads. And x86 code doesn't have things like new which can't be implemented in hardware because it's an assembly language that is designed to run on hardware, not a byte code that is designed to run in a VM.

      Most modern x86s actually map x86 instructions into Risc like uops before executing them, so it does seem like this technique is viable. Of course you need a lot of logic to do this. It's not clear what would happen performance-wise if you built an x86 instruction decoder as a front end for an ARM pipeline. There are probably legal issues too - there are still patents on x86. On the other hand, the patents on the core architecture will run out sooner or later.

      Actually I don't think Microsoft will do this - A JIT or JPU for executing x86 code on ARM doesn't really appeal at all unless you have ARM cores that are faster than the fastest x86 to run it on. Right now the fastest shipping ARM cores probably have less performance than the slowest x86 - the Intel Atom. The fundamental problem is that ARM has aimed at the mobile market where power consumption is important. x86 has aimed at servers and desktops where power consumption is much less important than computational ability. Of course ARM has improved in performance and x86 has got thriftier but I be

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    5. Re:What about netbooks? by MemoryDragon · · Score: 1

      fastest x86 to run it on. Right now the fastest shipping ARM cores probably have less performance than the slowest x86 - the Intel Atom. The

      Actually not really true the current cortex A9 is about 2-3 times as fast as the Atom, you can google the performance numbers. Which would probably make an extremely well optimized x86 emulation on such a thing slightly slower or about half as fast as an Atom processor.

    6. Re:What about netbooks? by Hal_Porter · · Score: 1

      Actually not really true the current cortex A9 is about 2-3 times as fast as the Atom, you can google the performance numbers.

      I'm highly sceptical of this

      http://www.anandtech.com/show/3696/intel-unveils-moorestown-and-the-atom-z600-series-the-fastest-smartphone-processor/14

      ARM does a bit better on CoreMark (5.7 vs 3.6 for a single threaded app, for dual threaded an N280 does 5.6. Most CPU intensive stuff is probably dual thread friendly these days, even the horrid flash)

      http://blog.linleygroup.com/2010/04/arm-outmuscles-atom-on-benchmark.html

      Still CoreMark is small enough to fit in the L1 cache. The Achilles heel of ARM systems has been slow memory controllers. Admittedly that's because ARM is aimed at phones where power consumption is a much more serious issue than netbooks, but still.

      On something like SpecInt which is large enough to exercise the DRAM interface I'd expect Atom to blow away an ARM from a similar generation. And Intel already have things like Core2 which can be migrated down to low power as you can see with ULV. I'm not convinced Arm can migrate up.

      Emulation would likely make things worse - CPU core performance will drop and if a JIT is used it will stress the memory subsystem more because you need to access both the native code and the translated code. An Jazelle like solution implies a greater memory subsystem hit too - you need to keep the code that emulates the instructions you don't handle in hardware in the cache. That's cache memory an Atom could use on the code its actually executing.

      In fact Anandtech reckons that Apple should switch from ARM to Moorestown

      http://www.anandtech.com/show/3640/apples-ipad-the-anandtech-review/17

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
    7. Re:What about netbooks? by MemoryDragon · · Score: 1

      Problem with Moorestone again is the power consumption while it is better than stock Atom there is a reason why Intel just gives the idle/sleep mode battery consumption numbers, because as soon as Moorestown has anything to do the power consumption goes way up an is worse than ARM. Even if the A9 is only as fast as Moorestown (I personally think in reality it is somewhat faster than a plain ATOM) why would you switch to Moorestown, same or worse performance higher power consumption than anything ARM has to offer.

    8. Re:What about netbooks? by Hal_Porter · · Score: 1

      I think Atom has more performance and needs more power. The efficiency of an ARM is better but I'm yet to convinced it is scalable to the same performance x86 is.

      --
      echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
  31. Next move... by igadget78 · · Score: 1
    Few things ...

    1. Microsoft has opened up a few Brick and Morter Stores designed for strictly Microsoft Technologies

    2. Microsoft is realeasing a new Mobile Phone OS shortly which will allow XBOX Live integration in combination with their "hopefully" intuitive UI and NetFlix video streaming.

    3. Microsoft already tried to cut in to the market with the Zune. Why not some other device that they themselves built.

    4. Microsoft now has an in with the ARM chipset

    5. The XBOX 360 will be hitting the 5 years old mark this November

    I guarantee (and by guarantee; I am fairly certain; and by fairly certain, I am completely speculating) that Microsoft is hedging their bets in order to enter the Hardware market in a more agressive fashion. And with their own brick and mortor store, they can guarantee "local" educated and informed support for their newest products.