Slashdot Mirror


ARM Hopes To Lure Microsoft Away From Intel

Steve Kerrison writes "With the explosion of netbooks now available, the line between PC and mobile phone is becoming much less distinct. ARM, one of the biggest companies behind CPU architectures for mobile phones (and other embedded systems), sees now as an opportunity to break out of mobiles and give Intel a run for its money. HEXUS.channel quizzes Bob Morris, ARM's director of mobile computing, on how it plans to achieve such a herculean task. Right now, ARM's pushing Android as the OS that's synonymous with the mobile Internet. But it's not simply going to ignore Microsoft: 'What if Microsoft offered a full version of Windows (as opposed to Windows Mobile or Windows CE) that used the ARM, rather than X86 (Intel and AMD) instruction set? Then it would be a straight hardware fight with Intel, in which ARM hopes its low power, low price processors will have an advantage.'"

333 comments

  1. ARM? x86? by Yvan256 · · Score: 4, Funny

    You will kneel before Z80!

    1. Re:ARM? x86? by davester666 · · Score: 1

      Didn't they see what happened with the PPC market?

      And does ARM actually make a desktop-class CPU (as compared to Intel/AMD's mid or high end cpu's)?

      What market are they going after with this, netbook's with ARM instead of Atom cpus?

      --
      Sleep your way to a whiter smile...date a dentist!
    2. Re:ARM? x86? by mdwh2 · · Score: 2, Insightful

      I'm not sure what you mean with your PPC comparison? ARM have shipped 10 billion CPUs. Intel have shipped between 1 and 2 billion. ( http://www.computerworld.com/s/article/9131098/ARM_Heretic_in_the_church_of_Intel_Moore_s_Law ) I'm not sure what total PPC sales, but they're not even remotely close to ARM.

      What market are they going after with this, netbook's with ARM instead of Atom cpus?

      Presumably. As TFS points out, the line between PCs and mobiles is becoming less distinct. I must admit, personally I'd have a preference for x86, because of compatability with PCs (which I will always prefer as a platform over locked down phones), but it's not like ARM are some niche player here.

    3. Re:ARM? x86? by BikeHelmet · · Score: 5, Informative

      And does ARM actually make a desktop-class CPU (as compared to Intel/AMD's mid or high end cpu's)?

      ARM CPUs are advancing faster than x86 CPUs.

      The Cortex A8 has roughly P3 performance (per clock), and clock speeds varying from 600-1000mhz. This is without Out of Order execution, 64bit support, or any other fancy stuff. The power envelope is about 50 milliwatts load. Most SoCs bundling GPU, DSP, LCD controller, wifi, etc. consume around or under a watt.

      The Cortex A9 should be significantly faster. If I recall correctly, it has OoOe and sports a 2-4 core multicore architecture, with increased clockspeeds, in the same power envelope. Look up TI's OMAP4 SoCs. When these are released in 2010, we'll have Pentium D/GeForce 6600 level performance using up a hundred or so milliwatts, and generating a completely negligible amount of heat.

      Now maybe you can see the implications of this?

    4. Re:ARM? x86? by larry+bagina · · Score: 2, Interesting

      Samsung (and maybe others by now) have 1ghz ARM chips. Dual core is expected next year.

      --
      Do you even lift?

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

    5. Re:ARM? x86? by radeon21 · · Score: 5, Informative

      ARM doesn't actually ship or make CPUs, they license IP cores. There are a whole shit ton of ARM cores out there, though.

    6. Re:ARM? x86? by davester666 · · Score: 3, Insightful

      I'm not sure what you mean with your PPC comparison? ARM have shipped 10 billion CPUs. Intel have shipped between 1 and 2 billion. ( http://www.computerworld.com/s/article/9131098/ARM_Heretic_in_the_church_of_Intel_Moore_s_Law ) I'm not sure what total PPC sales, but they're not even remotely close to ARM.

      What market are they going after with this, netbook's with ARM instead of Atom cpus?

      Presumably. As TFS points out, the line between PCs and mobiles is becoming less distinct. I must admit, personally I'd have a preference for x86, because of compatability with PCs (which I will always prefer as a platform over locked down phones), but it's not like ARM are some niche player here.

      First off, the install base counts for nothing. This is a from-scratch implementation, with an install base of zero cpu's and applications, just like Windows PPC. The number of existing systems with ARM embedded in them that can be "upgraded" to run this new OS is approximately zero. And given that Windows 7 is only slightly less cpu intensive than Windows Vista, which is what ARM wants for their CPU, and that "high-end" ARM cpu's seem to be comparable to Intel cpu's used in low-end netbooks, I don't see how people will like using it in this fashion. And it'll suffer the same problem as the PPC version of Windows did, no applications. When people read the specs and it says "Windows 7", they will expect to run Windows apps on it. Many will be disappointed when, AFTER they buy the netbook, they find out they can only run a few other applications besides whatever the system came with. And if people are just going to get stuck with using the pre-installed apps, why bother with the OEM fee to Microsoft?

      --
      Sleep your way to a whiter smile...date a dentist!
    7. Re:ARM? x86? by commodore64_love · · Score: 1

      >>>The Cortex A8 has roughly P3 performance (per clock), and clock speeds varying from 600-1000mhz

      How on earth is something that slow supposed to handle the behemoth that is Windows Vista? Even with a 3000 megahertz P4, my brother's machine runs like a snail. I don't see an ARM processor with about 1/6th the power working well with Vista, unless you enjoy watching your programs operate in slow motion.

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    8. Re:ARM? x86? by Hurricane78 · · Score: 2, Insightful

      Simple. I have already seen it working. You add an nVidia Tegra chip, any you still stay below 2 watt.

      But Vista/Win7 really is pointless. On *any* computer.

      On such a small system, Linux really can play its cards. Full HD + Flash in browser + 10 hours of battery life + nearly no heat = $100-$200. Out this fall.

      What do you think about that? :)

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    9. Re:ARM? x86? by Accursed · · Score: 1

      I think that maybe this might lead to the year of the linux desktop!

      ...Or you're building castles in the sand.

    10. Re:ARM? x86? by Mprx · · Score: 1

      It means Seymour Cray's metaphorical "1024 chickens" might now fit on a single chip, only this time they're the size of dogs and actually outplow the "two strong oxen" he favored.

      Amdahl's law still applies, but there's a lot of embarrassingly parallel problems out there.

    11. Re:ARM? x86? by coxymla · · Score: 1

      Good luck getting flash to work on a 600 MHz linux computer... Even Mac users with 2.4 GHz Core 2 Duos have issues with Youtube videos and flash ads randomly deciding to take 60% CPU.

    12. Re:ARM? x86? by happymellon · · Score: 3, Insightful

      I must admit, personally I'd have a preference for x86, because of compatability with PCs (which I will always prefer as a platform over locked down phones), but it's not like ARM are some niche player here.

      Compatability? I thought we used .net these days in Windows. Why are we using a VM if the code isn't portable?

    13. Re:ARM? x86? by Anonymous Coward · · Score: 0

      That's because Adobe can't code shit.

    14. Re:ARM? x86? by AnyoneEB · · Score: 5, Informative

      Flash is pretty inefficient, but it does run (admittedly not great) on the N810 which has a 400MHz ARM processor, which is a generation behind the Cortex A8s, so a Cortex A8 should have no real trouble with Flash.

      I hope some non-Adobe Flash implementation is ready for real use soon as the only possible reason for Flash to be as slow as it is is that Adobe must not care at all about its speed.

      --
      Centralization breaks the internet.
    15. Re:ARM? x86? by Anonymous Coward · · Score: 2, Funny

      That's because Adobe can't code shit.

      Hey, you take that back! My laptop is pretty bottom-of-the-line these days, and about the best it can do with open source software is scale 480p video up to ~1067x800 fullscreen; it can't even do 720p without dropping frames.

      But with Adobe Flash Player? It can play 320p video, as long as you don't dare to hit the fullscreen button. I'd say Adobe has proven that they're quite capable of coding shit.

    16. Re:ARM? x86? by BikeHelmet · · Score: 3, Interesting

      Mod parent up. He's the only guy in this whole tree of posts to understand mhz isn't everything.

      Many ARM SoCs have co-processors called DSPs, which can help decode video. Last-generation DSPs could manage 720p/1080p, so Youtube shouldn't cause it to break a sweat.

      Or if it does break a sweat, at least it won't stutter. ;)

    17. Re:ARM? x86? by BikeHelmet · · Score: 2, Interesting

      I don't know - Windows 7 feels pretty snappy on an old 3.0ghz P4 I have sitting next to me. Snappier than Vista on a Q6600, actually.

      Vista has a noticeable delay whenever doing anything. It's short, but it's many miliseconds slower than the P4, and many miliseconds slower than my old Athlon XP w/ Win2k.

      I'm talking about stuff like opening the start menu, clicking a systemtray icon and waiting for a menu to pop up, or opening a folder and waiting for the contents to display. (this last one is horrible on Vista)

      Want proof? Open your System32 folder (or equivalent, for 64bit Vista/Win7) and see how long it takes to display. After a reboot, my Win2k box takes approximately a quarter to a half second, to display in list format. The P4/Win7 box takes about a second. Vista takes about 3-4 seconds to pop up.

      Why? No clue. Logically, older computers with older HDDs would take longer. Clearly Microsoft mucked something up.

    18. Re:ARM? x86? by Minwee · · Score: 1

      How on earth is something that slow supposed to handle the behemoth that is Windows Vista?

      I don't know and I don't care. However, "a P-III at 600 MHz" is exactly what powers my old Thinkpad X21 which I still use almost every day. It handles a full version of Ubuntu quite well, runs Firefox, does movies and plays games well enough for me while drawing something in the neighourhood of 50 Watts. A CPU which drew 1% of that would be just fine with me.

      Even with a 3000 megahertz P4, my brother's machine runs like a snail.

      Perhaps your brother's machine just sucks. Is it possible that he is running Vista?

    19. Re:ARM? x86? by andymadigan · · Score: 3, Interesting

      To have managed memory. It takes a lot to track pointers, more than a hack on to existing x86 can manage (libgc tries, quite well, but it isn't perfect).

      Yes, I'm being completely serious.

      However, .NET is apparently portable across architectures, as Portable.NET supports several.

      However, as with Java, your application is only as portable as your libraries. Take web browsers, for instance, I don't know of any rendering engines in real use that are written in a managed language. A lot of good, difficult to replace code is written in languages that aren't easy to port.

      --
      The right to protest the State is more sacred than the State.
    20. Re:ARM? x86? by rve · · Score: 2, Interesting

      On such a small system, Linux really can play its cards. Full HD + Flash in browser + 10 hours of battery life + nearly no heat = $100-$200. Out this fall.

      That would be nice.

      The batteries of both my laptop and my netbook drain in much less time when booted into Linux, compared to booting them in XP. Especially the battery use while idle, in full powersaving mode, still seems disappointing. I'm not a noob, I've been using Linux as a server OS since the mid 90's, I'm just not entirely convinced by your claims of superiority on mobile hardware, as compared to gadgets running Windows or OSX.

    21. Re:ARM? x86? by Svartalf · · Score: 4, Informative

      Heh... In the case of your laptop and netbook, the odds are good you don't have the power management turned on or turned up much. Stock configs for Linux leave that turned off. Windows turns it on and you deal with it or turn it off after the fact. Without the power management, it eats batteries like candy.

      Now... To put this in a perspective you and others can clearly understand:

      The netbooks we're about to see from ARM licensees are roughly in the same ballpark of performance and capacity (depending on RAM included with the devices...) of the eeePC when it first came out to the 900 series devices.

      The Intel based devices for these models needed a 49 watt-hour battery to do 3 or so hours runtime, whether you're talking Linux or WindowsXP.

      The OMAP3 boards I've had the fortune of having in my possession at one point in time were able to go roughly 10 hours...on a 13.5 watt-hour battery. While I've not abused it as much as others, some were not letting it just set idle- it did these amazing runtimes with emulators running full-tilt. It'd probably get approximately 8-ish in the same configuration if you had the 3D accel running.

      Oh... By the way... That was without any power management- not that it'd been kicking in with what they did to it.

      This is using the Cortex-A8. The A9, is out-of-order plus SMP capable, and has a few other gems going for it. It's like having 1-4 of the pre-Core P4M devices at the same rated clock speed as the ARM based SoC- and consuming only slightly more juice per core than the A8. That's NEXT year's crop of fun from ARM.

      --
      I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
    22. Re:ARM? x86? by renoX · · Score: 1

      >The Cortex A8 has roughly P3 performance (per clock)[cut] This is without Out of Order execution, 64bit support, or any other fancy stuff.

      I don't understand why you're putting OoO execution and 64bit support on the same level: one is an internal implementation optimisation of the CPU (better performance but higher power usage), the other is a change of the CPU's ISA to allow simple usage of big memory: they are totally different.

    23. Re:ARM? x86? by Anonymous Coward · · Score: 0

      Good luck getting flash to work on a 600 MHz linux computer...

      Flash worked just fine on my previous PC - AMD Athlon 500Mhz + 256M RAM running Fedora.

    24. Re:ARM? x86? by AliasMarlowe · · Score: 4, Funny

      That's because Adobe can't code shit.

      But they can and they do!

      --
      Those who can make you believe absurdities can make you commit atrocities. - Voltaire
    25. Re:ARM? x86? by SlashWombat · · Score: 1

      Has ARM actually shipped any CPU's? I always believed ARM was a licensed architechture. Its makers are Sharp, Intel, Fairchild, The fred blogs IC company ...

      Personally, I don't expect M$ to target the ARM market until there are valid financial reasons to do so!

    26. Re:ARM? x86? by Bert64 · · Score: 1

      In the case of browsers tho, we have both gecko and webkit which are open and already capable of being built on many different architectures.

      Portable non sourcecode is primarily of interest to those who want to make closed source apps, for people willing to publish their source porting isn't terribly difficult and usually gets done.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    27. Re:ARM? x86? by Bert64 · · Score: 1

      I wouldn't say 1/6 of the power, the p4 is slower clock for clock than the p3 was, so your 3ghz p4 will be comparable to a 2-2.5ghz p3, making it about 2.5 times the performance of a 1ghz cortex-a8...
      But compare the power usage, your p4 will consume something like 100W of power, if you conservatively estimate the cortex a8 to consume 1W (i believe the actual processor part consumes considerably less, and its the whole package including gpu and such that consumes 1W), then you could build a machine using 64 of these chips including interconnect circuitry which would trounce your 3ghz p4 while using a similar amount of power.

      Also, vista is meant to be much slower than windows 7...

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    28. Re:ARM? x86? by Bert64 · · Score: 1

      How bottom of the line?
      Do you have proper video drivers?

      I was always able to play videos with mplayer which wouldn't play on windows running on the same hardware, going all the way back to 300mhz machines playing dvd video or early divx...

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    29. Re:ARM? x86? by Bert64 · · Score: 1

      OoO execution actually makes the cpu more efficient at executing less efficient code (or code which runs less efficiently by virtue of having been written for a different cpu)... If your willing to write/compile your code for a particular cpu then in-order execution works very well, thats why the ps3 and xbox 360 use in-order processors.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    30. Re:ARM? x86? by Phoghat · · Score: 1

      Didn't they see what happened with the PPC market?

      What market are they going after with this, netbook's with ARM instead of Atom cpus?

      Why yes, yes they are.

      As far as PPCs are concerned, you must not know about the WM Smartphones out there that are running ARM processors. Hell, I bought an old Dell Axim X51v for ~ $100 just to read books on. My first PPC had an ARM running about 200 mgh this one runs at 624. Not too much of a stretch to imagine 1.6!

      --
      Think of how stupid the average person is, and realize half of them are stupider than that.
    31. Re:ARM? x86? by commodore64_love · · Score: 1

      >>>Flash does run (admittedly not great) on a 400MHz ARM processor

      I have a 400 MHz PowerPC G4 that plays youtube/flash videos, but not in full screen. It slows down dramatically.

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    32. Re:ARM? x86? by bluie- · · Score: 1

      Processor speed isn't everything. There is also the concept of how much work a CPU can do per cycle. If you'll notice, ever since the first 3.x GHZ chips came out, SPEEDS haven't really increased very much (in many cases they've dropped!), but performance has kept getting better and better.
      What also bugs me is when people think that the amount of memory in a video card is the main indication of its performance. In my mind this is the same type of thing.

      --
      life is a tragedy to those who feel, and a comedy to those who think
    33. Re:ARM? x86? by paugq · · Score: 1

      The N810 is a 16-bit color device and Flash video is already slow there. Now try to play 24 bit video on such an underpowered device. The N810 is perfect for many things but "portable video player" is not one of them.

    34. Re:ARM? x86? by extrasolar · · Score: 1

      Gnash anyone? gnashdev.org

    35. Re:ARM? x86? by ncc74656 · · Score: 1

      Good luck getting flash to work on a 600 MHz linux computer... Even Mac users with 2.4 GHz Core 2 Duos have issues with Youtube videos and flash ads randomly deciding to take 60% CPU.

      Flash on Mac OS X sucks, to not put too fine a point on it. It's a rare occasion when some random YouTube video plays within the browser at its full framerate on my G4 mini. If I take the same downloaded YouTube video and play it with VLC, though, it runs like a champ. Even when scaled up to fullscreen (1680x1050), VLC is still faster than Flash playing the same video within a browser window.

      --
      20 January 2017: the End of an Error.
    36. Re:ARM? x86? by Anonymous Coward · · Score: 0

      What about Opera Mini?

      Even the C++ Opera Desktop version has a lot of ports.

      You should had bolded the text of the I don't know part.

    37. Re:ARM? x86? by Nicolay77 · · Score: 1

      In a dedicated Youtube app, sure.

      Using Adobe Flash would surely kill the CPU and show only a slide show.

      --
      We are Turing O-Machines. The Oracle is out there.
    38. Re:ARM? x86? by Nicolay77 · · Score: 1

      In a dedicated Youtube app, it would work.

      Flash is the culprit there, dude.

      --
      We are Turing O-Machines. The Oracle is out there.
    39. Re:ARM? x86? by AnyoneEB · · Score: 1

      Yes, the N810 is a horrible example of a good media player. I recently more or less gave on on trying to get mine to play media files straight as far too often it would have frame rates best quantified in seconds per frame instead of frames per second. I now run videos through tablet-encode first, which, even on its highest quality setting, sets the resolution of its output to 400x240 (for the N810's 800x480 screen) -- which actually ends up looking fine, but maybe I am just not that picky about video quality.

      Given how underpowered the N810 is as a media player -- especially since that is apparently partly due to some bad design decisions on some on the internal interconnects -- and that it is still able to play YouTube videos, any new device using more recent ARM chips that made any attempt to play videos should have no trouble displaying Flash videos full screen.

      --
      Centralization breaks the internet.
    40. Re:ARM? x86? by AnyoneEB · · Score: 1

      Gnash is not terribly compatible with Flash last I checked. They are working on it. Admittedly, I have not taken a close look at it in a while. Maybe I will install it again and see if it works well enough now for me to go without Adobe's Flash implementation.

      --
      Centralization breaks the internet.
    41. Re:ARM? x86? by andymadigan · · Score: 1

      Opera Mini can hardly render pages the same way Opera (Desktop) does. C++ (aside from some strange Microsoft bastardization) is not a managed language.

      The point was that there are problems that thus far have only been solved in well in non-managed, not-entirely-portable ways. This means that many real applications written in Java/.NET depend on difficult to port code.

      --
      The right to protest the State is more sacred than the State.
    42. Re:ARM? x86? by bhtooefr · · Score: 2, Informative

      Opera desktop, however, has different binaries for each architecture it runs on. As Opera's closed source, that means Opera Software gets to decide what their program runs on.

      With managed code, the VM developer gets to decide what platforms the VM runs on, and the software developers just target the VM.

      As an example... there's a VNC app out there written for .NET. Now, normally, you'd need one VNC app for your PC, one VNC app for an ARM-based Windows CE device, so on, so on.

      With .NET, I can run the same binary on an x86 PC, an Itanium server, or two different variants of ARM-based Windows Mobile device. (Not that I'd want to, it's not as good as, say, UltraVNC on x86, but it's still an example of how it can work.)

      Anyway, there is also Java as an option, and a few real, useful apps out there are written in Java - I use a couple every day. And, the ARMs have Jazelle support, which basically means a subset of Java bytecode instructions that can be accelerated by running them directly are run directly on the CPU, so Sun would just have to release a JVM for Win32/ARM that used Jazelle, and Java performance would be excellent on ARM. (I think Jazelle's there because of ARM being used on cell phones, which almost always have JVMs of some sort, often.)

    43. Re:ARM? x86? by bhtooefr · · Score: 1

      ARM designs CPU cores and licenses the cores and architecture to other companies.

      Right now, off of the top of my head, there's the following architectures commonplace today:

      ARM7, an ARMv4T-based core that's not far removed from the original ARM1 (ARM2 = ARM1 with hardware multiply, ARM3 = ARM2 with cache and coprocessor support, ARM6 = ARM3 with 32-bit addressing and minor speed improvements, ARM7 = ARM6 with more cache, essentially.)
      ARM9, an ARMv4T-based core
      ARM11, an ARMv6-based core
      ARM Cortex-A8, an ARMv7-based core

      All of those were designed by ARM.

      XScale, an ARMv5T-compliant core designed by DEC (IIRC) and Intel, now marketed by Marvell
      Feroceon/Sheeva, an ARMv5T-compliant core designed by Marvell
      Snapdragon, an ARMv7-compliant core/SoC designed by Qualcomm

      The thing is, ARM is trying to push netbooks based on ARM CPUs, now, with TI and Freescale Cortex-A8-based chips and Qualcomm Snapdragon chips. This is why they're trying to get MS to pay attention to ARM.

    44. Re:ARM? x86? by bhtooefr · · Score: 1

      He meant PowerPC, not Pocket PC.

    45. Re:ARM? x86? by Nicolay77 · · Score: 1

      Don't you mean 240p video ?

      Ohh, you tilt your head!

      --
      We are Turing O-Machines. The Oracle is out there.
  2. Dream on by Anonymous Coward · · Score: 0

    Intel has Microsoft by the balls. [maybe not, but i just wanted to say that]

    1. Re:Dream on by MightyMartian · · Score: 2, Insightful

      NT was originally designed to be portable. Whether that has been retained since the abandonment of support for Alphas and PowerPCs is something I couldn't say. However, it wasn't an insurmountable effort to port other operating systems like Linux over to new infrastructures, so I doubt it would be that horrifying awful for Microsoft. In fact, I'd be damned surprised if Microsoft, like Apple before it, didn't have some resources quietly working on it.

      --
      The world's burning. Moped Jesus spotted on I50. Details at 11.
    2. Re:Dream on by Hadlock · · Score: 1

      Great! Let's just set the compile flag for NT 4.0 to "ARM" and.. waaaiiit a minute.

      --
      moox. for a new generation.
    3. Re:Dream on by jernejk · · Score: 3, Interesting

      Well, Microsoft can't just ignore the risk "if x86 goes down, we go down". For this reason some kind of even the lastest versions of windows portability is plausible, IMO.

    4. Re:Dream on by Anonymous Coward · · Score: 0

      Windows runs on Itanium. So, yes, Windows is still portable.

    5. Re:Dream on by Nursie · · Score: 2, Insightful

      Yes, so all the standard (rubbish) arguments people make about linux apply equally here.

      Oh but I can't run $software_2_people_use! It's useless!

    6. Re:Dream on by allaunjsilverfox2 · · Score: 3, Insightful

      They do have a port for power architecture , its called the xbox360. :p

      --
      Restore the madness of youth's lechery
    7. Re:Dream on by dhavleak · · Score: 1

      Actually it's kind of true. And that's only part of the reason that this is a good idea (for Microsoft).

      AFAIK (and I don't know much) - ARM chips don't require a translation layer that converts machine code to microcode - and this results in huge efficiency gains (compared to x86/x64 chips). If that's the case (second disclaimer - I don't know much about this so I could be wrong) - but if that's the case, the future of laptops/netbooks/mobile devices/perhaps even datacenters probably has ARM in it somewhere. After all, power efficiency is important in all these areas, and only getting more important with time.

      So in other words, MS themselves might want to think about building ARM versions of Windows irrespective of any persuasion from ARM.

      The reason Intel having MS by the balls comes into the picture -- Intel has been 'sleep around' a little over the last few years. For example Moblin. Or recall the Mac Book Air processor that debuted exclusively with Apple before an PC OEMs even knew it existed. So MS might want to keep Intel on their toes as well and let them know that they're not going to be the only game in town forever (with due apologies to AMD who are putting up a game fight).

    8. Re:Dream on by Hashi+Lebwohl · · Score: 1

      "Well, Microsoft can't just ignore the risk" Perhaps "risc" instead? Talk about laugh, I nearly did.

      --
      I'm in to sadism, bestiality and necrophilia. Am I flogging a dead horse?
    9. Re:Dream on by smash · · Score: 1

      Most of windows is probably written in C/C++ or C# by now, so I'd say its pretty portable that way anyway. All the major APIs have been recently re-written recently, and moving to a new architecture would allow them to drop a lot of legacy x86 shit... I'd hazard a guess that Microsoft has Windows running on various other platforms in some way internally already. They'd be stupid not to.

      --
      I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
    10. Re:Dream on by afidel · · Score: 1

      The opcode decoder stage in a modern x64 processor is about 5% of the active (non-cache) transistors, it's not a significant contributor to power use. The biggest problem is that modern x54 designs are very complex and so they don't scale down as far as a stripped down ARM core can.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    11. Re:Dream on by dhavleak · · Score: 1

      Thanks for the insight! Do you know if that complexity translate into a higher IPC for x64 designs? We already have 32-bit ARM processors clocking in the 1GHz region. If they've got low IPCs compared to x64 processors it might explain some of the performance difference (i.e. that ARM is following a true RISC style approach).

    12. Re:Dream on by drsmithy · · Score: 1

      NT was originally designed to be portable. Whether that has been retained since the abandonment of support for Alphas and PowerPCs is something I couldn't say.

      Given that it's still availabile on 3-4 (depending on how you want to count) different architectures, I'd say "yes, it has been retained" is a fairly safe bet.

      The problem is not the OS. The problem is the applications.

    13. Re:Dream on by Rockoon · · Score: 1

      At equal levels of microcode-per-clock, the RISC machine needs to fetch quite a bit more instructions-per-clock out of cache/ram, which is actualy problematic when the instruction fetching unit runs at the same speed as the CPU. The instruction fetcher is highly parallel, which in turn means that the pipeline must also be highly parallel to accomodate, and so on..

      Yes CISC machines have more complicated decoding logic, but its offset to a large extent by various RISC-punishing factors.

      --
      "His name was James Damore."
    14. Re:Dream on by Yvan256 · · Score: 1

      How about "When you're in the software business, there is always a risc."

    15. Re:Dream on by afidel · · Score: 1

      Yes, x64 has a much higher IPC than a non-superscaler design like most ARM cpu's (the A8 and A9 are the only superscalar ARM cpu's). ARM also get lower MIPS/watt despite what people claim, the A9 MP gets only 2,000 Drystone MIPS while consuming .64W whereas Atom 330 get 7,800 DMIPS from 2W (3,125 MIPS/W vs 3,900). If you need to fit into a sub Watt power envelope then Intel currently doesn't have a solution for you but for anything from a palmtop on up you are better off with the Intel solution because it gets better performance per Watt, scales to much higher performance, and is compatible with the 99.99+% of software that's available for the dominant ISA.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    16. Re:Dream on by Hal_Porter · · Score: 1

      The fact that NT has run on Risc architectures in the past an currently Windows on x86, x64, Itanium (and probably PPC for XBoxes) and Windows CE runs the GDI on ARM makes me think they could do it. The GDI code is probably quite portable, especially if it is shared between CE and the desktop.

      Still they'd have to port Office. Office is x86 only but coming soon to x64. But that's not really the point - people run Windows because they have a bunch of CDs with x86 Win32 binaries on them. Those will run like ass on an x86 emulator running on ARM.

      Even for native code I think that any shipping ARM is going to end up performing as fast or slower than an Atom. And desktop Windows, even XP or 7, is a bit slow on Atom for my tastes. Finally ARM is a cool chip with lots of clever addressing modes. Those clever addressing modes, if you believe Henessy and Patterson, have a cost in terms of maximum clock speed and building superscalar out of order chips, i.e. the sort of chips that get used even on notebooks these days. For a 500Mhz in order single chip in a cellphone that's no problem. For a 2+Ghz out of order dual issue chip, i.e. a Core2 class ARM I wonder if ARM is just a poor fit. Mind you you could get rid of the 32 bit instructions and run the MIPs like Thumb subset.

      Still, I'm skeptical that ARM will end up replacing x64. Come to think of it that's another thing ARM doesn't do - 64 bit address spaces. Don't get me wrong - ARM is great if you want a small in order core in some embedded widget, but it's even less suited for the current desktop world than x64.

      --
      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;
    17. Re:Dream on by Hal_Porter · · Score: 1

      I think x64 will dominate desktops and servers, but for code density the Thumb2 instruction set on ARM should be pretty good.

      --
      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;
    18. Re:Dream on by Hadlock · · Score: 1

      Office for mac is written in pretty portable code. It might take more than a week, but MS could throw a team at it for a month or two and probably have a working beta that would compile for ARM

      --
      moox. for a new generation.
    19. Re:Dream on by daw1234 · · Score: 1

      Office for Mac is really crappy though!

    20. Re:Dream on by Hal_Porter · · Score: 1

      Mac office is designed to run on a different OS though. It's also apparently a different code base from the Windows version. I think the fact that Windows office is being ported to x64 means that Office is being made more portable now anyway. Really there's not much of an excuse for modern Win32 application not being portable to other processors, the problem is that Office has been around for ages and probably has a few x86isms like inline assembly back when that was necessary for performance. Or something like that. Anyhow Office 2010 will have both 32 and 64 bit binaries -

      http://www.redmondpie.com/office-2010-x64-technical-preview-screenshots/

      --
      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;
    21. Re:Dream on by Bert64 · · Score: 1

      Old versions of office (97 i believe) were ported to Alpha back in the days.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    22. Re:Dream on by Anonymous Coward · · Score: 1, Interesting

      Oh but I can't run $software_2_people_use! It's useless!

      That's not insightful, that's a troll.

    23. Re:Dream on by Hadlock · · Score: 1

      Well that's good news. I use 97 at work and it seems to work flawlessly (and damn fast on a modern computer, at that)

      --
      moox. for a new generation.
    24. Re:Dream on by Nursie · · Score: 1

      How so, anonymous coward?

      It nearly always comes up here and elsewhere - Linux can't run application X, therefore it is useless. Windows on ARM would suffer from exactly the same.

    25. Re:Dream on by dhavleak · · Score: 1

      +5 Insightful, sir!

    26. Re:Dream on by Anonymous Coward · · Score: 0

      That's not Windows... ...it's a trap!

      But, no, seriously, it's not Windows, it was "grown from scratch", or so I've read earlier on Slashdot.

    27. Re:Dream on by badkarmadayaccount · · Score: 1

      Excuse me, I'm just a teenaged enthusiast, but isn't recompilation all that is needed to get some application from the type of an office suite running on another CPU?

      --
      I know tobacco is bad for you, so I smoke weed with crack.
    28. Re:Dream on by bhtooefr · · Score: 1

      This is a bit confusing, but ARM claims 250 mW. That may be for a 2000 DMIPS single core, or it might be for an 8000 DMIPS quad core. Either way, that's 1 W at most for a quad, or half of Atom's power consumption.

      If you're counting the SoC power, then please count the Atom's north and southbridges.

    29. Re:Dream on by bhtooefr · · Score: 1

      Oh, and I just noticed, you used an Atom 330. That's not a 2 watt CPU, that's 8 watts. If Intel made a low voltage (N-series) part, it'd be 5 W, and a ULV (Z-series) part would be 4 W.

    30. Re:Dream on by Hal_Porter · · Score: 1

      In an idea world, yes. I've written code and it builds fine for a couple of platforms. I've also worked with code that took ages to port - third party libraries needed to be replaced, inline assembler rewritten and loads of alignment, structure packing and timing issues needed to be fixed. And architecturally it's quite easy to end up with code that depends on some subtle detail which you only find out about once you port.

      --
      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. Re:Dream on by badkarmadayaccount · · Score: 1

      IOW, LLVM FTW.

      --
      I know tobacco is bad for you, so I smoke weed with crack.
  3. Some ARM twisting going on? by Anonymous+CowHardon · · Score: 3, Funny

    Employing strongARM tactics? Better keep them at ARM's length. (Don't worry, these horrible puns are quite ARMless.)

    1. Re:Some ARM twisting going on? by FishWithAHammer · · Score: 1

      Your lame-ass puns can suck my Dragonballs.

      --
      "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
    2. Re:Some ARM twisting going on? by bhtooefr · · Score: 1

      The strongARM pun is so beaten into the ground that DEC's implementation of ARM was even called StrongARM. ;)

    3. Re:Some ARM twisting going on? by schlouse · · Score: 1

      (Don't worry, these horrible puns are quite ARMless.)

      I lost my both of my arms in an armed robbery, you insensitive clod!

    4. Re:Some ARM twisting going on? by Anonymous+CowHardon · · Score: 0

      I think that story's really got legs! Let's run with it!

    5. Re:Some ARM twisting going on? by maxwell+demon · · Score: 1

      Just wait until they send the ARMy. And make sure to have your ARMour ready.

      --
      The Tao of math: The numbers you can count are not the real numbers.
  4. Good way to enter the market by OrangeMorange · · Score: 1

    Given a Microsoft OS, these processors could easily pierce the market as many people would not even notice the difference between an Intel netbook or an ARM netbook. This seems like the best way to enter the market.

    1. Re:Good way to enter the market by MightyYar · · Score: 1

      many people would not even notice the difference between an Intel netbook or an ARM netbook.

      They'd notice when none of Window's vaunted software library would run. I don't even want to know what ix86 emulation on ARM is like...

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    2. Re:Good way to enter the market by Orange+Crush · · Score: 1

      If they keep it to netbooks (most don't have optical drives), then they'd ostensibly create a windows market of sorts that contains only ARM-compiled apps. Get enough ARMbooks in the wild, and the vendors will just make fat binaries for both arches.

    3. Re:Good way to enter the market by porkThreeWays · · Score: 1

      Porting isn't THAT huge of a deal. Very low level libraries would need to be ported and compilers and the kernel, but everything above that usually isn't that huge of a deal. Modern OS's are pretty darn abstracted. Look at how quickly Apple ported Mac OS to Intel.

      --
      If an officer ever threatens to taze you, say you have a pacemaker.
    4. Re:Good way to enter the market by Orange+Crush · · Score: 4, Informative

      ^Apple didn't suddenly port Mac OSX to x86. Both versions had been in development since OSX's inception so Apple could keep its options open if the PPC roadmap didn't unfold to their liking. It didn't, so they exercized the option.

    5. Re:Good way to enter the market by itsdapead · · Score: 2, Interesting

      I don't even want to know what ix86 emulation on ARM is like...

      Well, it was ok for light use in 1988 (NB: PDF file, parent page is here). That was back in the day when ARM was pitched as a high-performance workstation chip rather than a low-power option.

      Seriously, though, the windows back-catalogue might not run on ARM, but the .NET framework is MS's preferred platform for new apps, and that is VM-based and supposed to be CPU independent, is it not?

      --
      In a survey of 100 programmers, 111111 thought that duck-typing was a good idea.
    6. Re:Good way to enter the market by Jeremy+Erwin · · Score: 5, Informative

      Look at how quickly Apple ported Mac OS to Intel.

      Apple maintained an internal cross platform port.

    7. Re:Good way to enter the market by Sponge+Bath · · Score: 1

      MS could use the transition to marginalize Windows application competitors unwilling or lacking resources to support the ARM version of Windows. For the most part that process was completed with the transition from DOS to Windows (bye WP and Lotus 123).

    8. Re:Good way to enter the market by johnsonav · · Score: 1

      Get enough ARMbooks in the wild, and the vendors will just make fat binaries for both arches.

      Yeah...

      Imagine, for a moment, that some people would buy a netbook with no third party software; they just use Microsoft products (assuming MS ports more than just the OS). Are those the people who are going to buy enough software to create a viable market? After all, if they wanted third party software, they probably would have gone with an x86 to begin with.

      --
      ... and that's when the C.H.U.D.'s came at me.
    9. Re:Good way to enter the market by Anonymous Coward · · Score: 0

      It's been done. My 1987 ARM2-based Archimedes A310 runs eighties DOS games in emulation at a good speed. But this was back when ARM performance was taking a giant dump on x86, so it probably won't work out so well now.

    10. Re:Good way to enter the market by mdwh2 · · Score: 2, Insightful

      Well they've been selling Linux netbooks. Remember that lots of people are buying these to access the Internet, and not to run general applications. An ARM Windows netbook won't have the disadvantages of unfamiliarity, or people who insist on Windows because that's all they know. It'll also be much easier to port apps to it from x86 Windows, than to Linux.

      Anyhow, Microsoft themselves could supply web browser, email client, IM program, complete office suite, media player, which covers most people's uses of netbooks.

    11. Re:Good way to enter the market by johnsonav · · Score: 1

      Anyhow, Microsoft themselves could supply web browser, email client, IM program, complete office suite, media player, which covers most people's uses of netbooks.

      This kind of proves my point. If the people who buy these netbooks have all their needs met by MS products, those people aren't really much of a market for third party developers.

      --
      ... and that's when the C.H.U.D.'s came at me.
    12. Re:Good way to enter the market by FishWithAHammer · · Score: 1

      The .NET Framework (at least, parts of it) have already been ported to ARM; the Compact Framework runs on it as I recall.

      I believe Mono has an ARM port too.

      --
      "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
    13. Re:Good way to enter the market by MightyYar · · Score: 1

      You mention Apple... there are relatively simple apps like Picasa that only work on the Intel architecture. I have a feeling there are a lot of Windows apps tied to x86.

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    14. Re:Good way to enter the market by smash · · Score: 1

      Exactly. OS/X is just an updated (majorly, but still) variant of NextStep, which ran on Intel since 1991 or so.

      --
      I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
    15. Re:Good way to enter the market by rtb61 · · Score: 1

      The netbook market is a competitive market driven by price. Price of hardware and software. So low low cost. It is really hard to squeeze and thousand dollars worth of software, excluding entertainment on a $200 dollar PC. Right no arm on netbooks represents a huge price advantage because intel is burdened with windows after M$ market leveraged most intel netbooks to windows.

      So which do the public really want an ultra portable PC that runs like the phone or one that runs like a desktop, battery life they don't have to think about or battery life they have to conserve, one completely ready to go out of the box (just like their phone) or one where they have to buy more stuff in fact triple or more the price in order to do any work.

      Don't forget the netbook is in affect, the third pc after the desktop/notebook and smartphone, so on one course you pay triple software licence fees on the other course you pay none to get up and running. You can even image specials where you can buy all three in the one hit for a major discount excluding of course closed source proprietary software which you end up having to pay for three times.

      --
      Chaos - everything, everywhere, everywhen
    16. Re:Good way to enter the market by iJed · · Score: 1

      However they did port it to ARM for the iPhone and iPod touch.

    17. Re:Good way to enter the market by NCG_Mike · · Score: 1

      You might recall that NeXTSTEP and OpenStep ran on Intel based hardware. Before the switch to Intel, NeXTSTEP ran on Motorola 68K based CPUs. It's a pretty portable OS though the move from 68K to Intel took a long time as I recall.

      Apple took OpenStep and made it run (slowly) on PowerPC hardware with a replacement for display postscript so it was no great surprise when they switched to Intel.

      Their main effort, I feel, was really getting the legacy Carbon APIs ported across to Intel for large developers like Microsoft and Adobe/Macromedia as well as assisting them to move onto the GNU toolchain from CodeWarrior.

      I've seen code that worked on CodeWarrior and Visual Studio 6 that fell apart on g++ (v-table fun). Apple updated their g++ release to accomodate.

    18. Re:Good way to enter the market by QuantumRiff · · Score: 1

      And likewise, MS didn't only write windows for X86. I had it running on an Alpha CPU, there was also PPC, and MIPS, if I'm not mistaken. (why do you think all the important stuff for XP goes in a folder called i386 on the disk?, The disk used to have other directories too)

      --

      What are we going to do tonight Brain?
  5. An interesting idea. by jd · · Score: 2, Insightful

    But it wouldn't be a straight fight between ARM and Intel. It would be a fight between ARM, StrongARM, Asynchronous ARM (yes, there really is an asynchronous CPU based on the ARM core), and every other ARM variant out there.

    --
    It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    1. Re:An interesting idea. by MartinSchou · · Score: 1

      You say this as if it would be a bad thing?

      As long as the instruction sets are compatible in such a way that I can take all my programs from platform A and move it to platform Q, how can we not be the winners in this competition?

    2. Re:An interesting idea. by mschoolbus · · Score: 1

      Drivers barely work in windows as is, like adding ARM and variants to the mix will help at all.

      Not to mention getting software compiled to run on it, developers won't like it at all. Adding a compatibility layer for x86 apps would defeat the point.

    3. Re:An interesting idea. by MrMista_B · · Score: 1

      Not to mention AMD.

    4. Re:An interesting idea. by mdwh2 · · Score: 1

      And similarly, with Intel Core Duo, Pentium Dual Core, Celeron, and AMD Athlon 64.

    5. Re:An interesting idea. by Anonymous Coward · · Score: 0

      The difference between, say, Intel's celery processor and the Athlon 64 are much smaller than the differences between the standard ARM processor and the AMULET clockless ARM.

      In the case of the Core 2 Duo, Pentium "we can divide, honestly" processor, and the Celeron, they're all made by one company rather than several dozen.

      The last major Intel clone to be released, the Crusoe, failed to take off and the company folded. What is left is a strict duopoly, which works(ish) in the marketplace even if it doesn't produce high-quality products.

      If you look at the ARM and MIPS arenas, you see many, many companies. Nobody has a monopoly, or anything remotely resembling one. This makes for some superb innovation, and is certainly truer to a more co-operative concept of the market, but it isn't going to stand a chance in the supernova blast of destruction known as the ix86 architecture.

      (When was the last time you used a 680x0 series processor? That tried going against the Intel range as well. The Transputer isn't exactly an everyday item either, with modern clusters almost invariably being x86-based.)

    6. Re:An interesting idea. by badkarmadayaccount · · Score: 1

      You talk as if breaking Windows drivers is a bad thing.

      --
      I know tobacco is bad for you, so I smoke weed with crack.
    7. Re:An interesting idea. by bhtooefr · · Score: 1

      And the processors being targeted by a theoretical ARM netbook port use one of three (OK, four) cores.

      ARM Cortex-A8 (TI or Freescale SoCs)
      ARM Cortex-A9 (TI SoCs in the future)
      ARM11 (nVidia Tegra)
      Qualcomm Snapdragon

  6. Here's what I think would be funny... by Anonymous Coward · · Score: 4, Funny

    Mac users have had to endure 2 processor family changes and finally had to settle for the same one the PC uses. Could you imagine the irony if the PC switched to ARM and the Mac was left using the "outdated" x86 architecture?

    1. Re:Here's what I think would be funny... by CarpetShark · · Score: 2, Funny

      Apple would probably be quite happy to start over on a new arch with Windows. Competing head-to-head on a new platform would be a big catch-up compared to their current position of limited drivers.

    2. Re:Here's what I think would be funny... by TheRaven64 · · Score: 5, Insightful

      Apple already ships a huge number of OS X machines with ARM chips, they just brand them as iPhones and iPod Touches. OS X makes it easy to add another architecture for fat binaries and most OS X apps have already been ported from PowerPC to x86 so have no CPU dependencies; porting them to ARM would be relatively easy. That said, since Apple bought PA Semi, I wouldn't be entirely surprised if they released a PowerPC chip that competed in the same area as ARM.

      --
      I am TheRaven on Soylent News
    3. Re:Here's what I think would be funny... by szark · · Score: 1

      OS X already has a version running on ARM for the iPhone and iPod Touch. They could release a full MAC OS X ARM port quite quickly if Microsoft announced they were transitioning to ARM.

    4. Re:Here's what I think would be funny... by mdwh2 · · Score: 1

      No, Iphone OS is not OS X. Even if they did share some code. You might as well claim that Windows already runs on ARM and loads more (due to Windows CE).

    5. Re:Here's what I think would be funny... by TheRaven64 · · Score: 5, Informative

      It uses the same kernel. It uses the same CoreGraphics, Foundation, and CoreAnimation frameworks as well as countless others. About the only difference is that OS X on the iPhone does not have AppKit or Autozone.

      --
      I am TheRaven on Soylent News
    6. Re:Here's what I think would be funny... by recoiledsnake · · Score: 1

      most OS X apps have already been ported from PowerPC to x86 so have no CPU dependencies

      Huh what? Porting a app to another CPU means it has no CPU dependencies? What are you smoking? An RDF cigar?

      --
      This space for rent.
    7. Re:Here's what I think would be funny... by bhtooefr · · Score: 1

      Except PA Semi also does ARM cores, and the rumor mill says that that's what they're working on for Apple.

    8. Re:Here's what I think would be funny... by Anonymous Coward · · Score: 0

      lets place "spot the guy who's spouting shit while not knowing what the fuck he's on about"... oh look! it's you!

    9. Re:Here's what I think would be funny... by Anonymous Coward · · Score: 0

      have already been ported from PowerPC to x86

      so have no CPU dependencies

      These are two very different statements.

      In other news, NT used to run on other architectures, and Windows Server currently runs on Itanium. MSFT is, historically and in the present, not strictly linked to x86.

    10. Re:Here's what I think would be funny... by divisionbyzero · · Score: 1

      Yeah except Mac OS X already runs on ARM. Ever heard of the iPhone?

    11. Re:Here's what I think would be funny... by Anonymous Coward · · Score: 1, Funny

      About the only difference is that OS X on the iPhone does not have AppKit or Autozone.

      Great, where the hell am I gonna get auto parts then?

    12. Re:Here's what I think would be funny... by dfghjk · · Score: 1

      yes, of course, those are the only differences. That and an entirely different UI...

    13. Re:Here's what I think would be funny... by Anonymous Coward · · Score: 0

      Many of the PA Semi team originally worked on ARM.

    14. Re:Here's what I think would be funny... by Anonymous Coward · · Score: 0

      What are you, a moron?

      What the [expletive] has the UI got to do with anything? Hint: if all of the rest of OSX runs on the iPhone, how [expletive] hard would it be to bring over the UI?

      Even if they had to code up a completely new UI, it wouldn't be a bigger deal than creating the [expletive] iPhone UI was to begin with.

      Beyond that, OSX is a certified unix, and can be used (and considered to be usable) without any GUI whatsoever. You can hook it up to a teletype if that's what gets your rocks off, and it would be completely fair to say that OSX had been ported to the ARM architecture if that was the only functionality available.

      The UI is not the OS, any more than the file manager is. Both are trivially replaced.

    15. Re:Here's what I think would be funny... by iJed · · Score: 1

      No, Iphone OS is not OS X.

      Except that it is OS X. It has the same kernel, frameworks, driver model, graphics subsystem and so on. The only thing really different is the UI layer because a desktop UI is highly unsuited for use on a mobile phone.

      WinCE, on the other hand, shares little code in common with Windows XP/Vista/7 other than its APIs.

    16. Re:Here's what I think would be funny... by jgrahn · · Score: 1

      most OS X apps have already been ported from PowerPC to x86 so have no CPU dependencies

      Huh what? Porting a app to another CPU means it has no CPU dependencies? What are you smoking? An RDF cigar?

      I think he means "make portable", i.e. to remove the bugs which make the application only *accidentally* work on a on a certain CPU: unaligned memory accesses, endianness issues, assumptions about the size of integers and pointers, and so on.

      Changing a program which works on ppc but breaks on anything else, into working on x86 and breaking on anything else -- that would be stupid.

    17. Re:Here's what I think would be funny... by mdwh2 · · Score: 1

      Which is what I said with more explanation. A kernel is not an OS, even if they share some libraries. By that logic, OS X is Darwin, and Iphone OS is NEXT.

      Iphone OS is simply not the same OS as OS X that runs on desktops. Crying about how much in common is irrelevant - as long as there's some that's different, you're not running the same thing. (Not sure why this is such an issue - I imagine people want to go "Wow, Iphones can run the same OS as desktops", though this is misleading, they're not doing anything different to other phones.)

  7. That's pretty amazing... by Anonymous Coward · · Score: 0

    We've never been at a point where we could run a full OS in a mobile profile. Yet this could be the bridge we cross over to reach such an awesome concept.

    Only five years ago, people would have laughed at the idea of music and video on computers, but today we can use the power of the Internet to access this content with our televisions and stereo systems. It really makes you wonder, if with the decreasing cost and increasing capacity of Compact Flash (CF) technology, not to mention built-in WiFi, we're reaching the level of convergence where it is possible to run the same operating system everywhere.

    We can send e-mail with a cellphone, or place phone calls from a computer. Why not play DVDs on a handheld, or browse the Internet with your television? The future is now.

    1. Re:That's pretty amazing... by Anonymous Coward · · Score: 0

      Only five years ago, people would have laughed at the idea of music and video on computers

      False.

    2. Re:That's pretty amazing... by Anonymous Coward · · Score: 0

      Only five years ago, people would have laughed at the idea of music and video on computers

      WTF? I was doing multitrack recording on my Mac back in 1989!

    3. Re:That's pretty amazing... by Anonymous Coward · · Score: 0

      5 years ago was only 2003. What a crock of shit..

    4. Re:That's pretty amazing... by Anonymous Coward · · Score: 0

      Typo, 2004. Point still stands.

      I was downloading torrented movies before that.

    5. Re:That's pretty amazing... by Gerald · · Score: 1

      Only five years ago...

      Only five years ago, Twitter was still steam-powered!

    6. Re:That's pretty amazing... by True+Vox · · Score: 1

      Only five years ago, people would have laughed at the idea of music and video on computers

      Wait... I CLEARLY remember watching porn on my PC in the 90's... And that had crappy porno music.... So.... WELCOME TO THE 90's!

      --
      "Gratuitous complexity is akin to chaos" - True Vox
    7. Re:That's pretty amazing... by EvanED · · Score: 1

      I'm guessing the OP meant to say "on phones", not "on computers".

    8. Re:That's pretty amazing... by Guy+Harris · · Score: 1

      We've never been at a point where we could run a full OS in a mobile profile.

      What's your definition of "a full OS"? Presumably you're not counting iPhone OS, even though it's based on much of the same core OS code that Mac OS X is based on (heck, jailbreak it and you can even get a terminal emulator with a shell prompt). (I don't know whether the rumored Nokia N900 would be a phone or not, or whether it'll be Maemo-based.)

    9. Re:That's pretty amazing... by larry+bagina · · Score: 1

      2004 era phones (RAZR, for example) supported music and video.

      --
      Do you even lift?

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

    10. Re:That's pretty amazing... by Dogtanian · · Score: 2, Insightful

      Only five years ago, people would have laughed at the idea of music and video on computers

      I'm guessing the OP meant to say "on phones", not "on computers".

      Even on phones, I doubt people would have been laughed at the idea five years ago. Remember that the Motorola Rokr (the iTunes compatible phone) was out almost four years ago, and it's not like playing MP3s on your phone seemed such a big deal even then.

      Ten years ago, perhaps. It's almost exactly 10 years since Napster arrived, and most people at that time hadn't even heard of- let alone listened to- MP3s. The first style/youth-oriented phone, the Nokia 3210, had only just arrived as well, offering (*gasp*!) customisable ring tones- customisable monophonic beeps that is.

      So, ten years ago, the embryonic parts of today's market had literally just arrived on the scene, though perhaps it wasn't obvious at the time. However, five years ago, I doubt that (given the ever-increasing power of electronics) MP3 and video on phones in the near future would have seemed that far fetched.

      --
      "Slashdot - News and Chat Sites Deviant". (Click "homepage" link above for details).
    11. Re:That's pretty amazing... by mdwh2 · · Score: 2, Interesting

      He's still wrong - I'm pretty sure mp3 phones were around before 5 years ago, and it was also around 2004 that companies were hyping viewing video on then new 3G phones.

      Now 11 years ago, that's when we laughed at the idea of video on compuers :)

    12. Re:That's pretty amazing... by tepples · · Score: 1

      What's your definition of "a full OS"?

      An operating system whose user space comes jailbroken out of the box, like Linux or Mac OS X or Windows.

  8. The only important question is by Anonymous Coward · · Score: 0

    Will I be able to download and run J Random Application and have it execute on my ARM PC?
    If the answer is no, then it is simply not going to fly. .net might be heading that way, but there is still a hell of a lot of native x86 apps out there.

  9. Applications are the problem by jmorris42 · · Score: 3, Insightful

    Windows on ARM would be as pointless as every other port Microsoft has tried and eventually killed off. And for the same reason, lack of applications.

    Microsoft itself has never bothered porting any of their consumer apps such as Office. Remember DEC having to use FX!32 to get Office running via emulation at a fraction of native speed... leading customers to fail to see the advantage of the Alpha. Now we are to expect the hundreds of large and small shops making the Windows apps people associate with "Windows" to all port to a platform where there are no suitable developer workstations available and Windows development tools lack much in the way of cross compiler support.

    Compare to Linux on ARM where pretty much the entire Debian/Ubuntu collection is up and running and Adobe has ported the one key closed piece, Flash Player.

    --
    Democrat delenda est
    1. Re:Applications are the problem by Anonymous Coward · · Score: 2, Informative

      > Remember DEC having to use FX!32 to get Office running via emulation at a fraction of native speed

      I'm assuming by fraction you mean somewhere between .9 and 1.1. Yes, if you had some ancient, assed-out Multia running at 166MHz you weren't
      going to be happy compared to a then-smoking 450MHz P3. However, at the same time Intel was stuck around 450MHz, Digital was cranking their
      processors to much higher clock speeds.

      P.S. Word and Excel had native AXP ports. You were stuck using FX!32 to run Outlook, but be honest -- who really gave a shit about Outlook 97?
      That's like complaining that Schedule+ or Microsoft Bob didn't run on your PWS500

    2. Re:Applications are the problem by Giometrix · · Score: 1

      Windows on ARM would be as pointless as every other port Microsoft has tried and eventually killed off. And for the same reason, lack of applications.

      Microsoft itself has never bothered porting any of their consumer apps such as Office. Remember DEC having to use FX!32 to get Office running via emulation at a fraction of native speed... leading customers to fail to see the advantage of the Alpha. Now we are to expect the hundreds of large and small shops making the Windows apps people associate with "Windows" to all port to a platform where there are no suitable developer workstations available and Windows development tools lack much in the way of cross compiler support.

      Compare to Linux on ARM where pretty much the entire Debian/Ubuntu collection is up and running and Adobe has ported the one key closed piece, Flash Player.

      With .NET getting more popular, maybe now (or at least the near future) this will be less of an issue?

      --
      Download free e-books, lectures, and tutorials at bookgoldmine.com
    3. Re:Applications are the problem by BUL2294 · · Score: 1

      I'm assuming by fraction you mean somewhere between .9 and 1.1. Yes, if you had some ancient, assed-out Multia running at 166MHz you weren't going to be happy compared to a then-smoking 450MHz P3. However, at the same time Intel was stuck around 450MHz, Digital was cranking their processors to much higher clock speeds.

      Except the example you use is of a more powerful server or workstation-class behemoth trying to run x86 desktop/notebook class software. That's doable and probably quite useful. But here, we're talking about an underpowered ARM netbook trying to run x86 desktop/notebook class software. The user experience will suck. So why not just go with an x86 netbook and run everything natively?

      Give my Blackberry enough RAM and it could probably run MS-Office--but it would suck...

      --
      Windows 3.1x calc: 3.11 - 3.10 = 0.00
    4. Re:Applications are the problem by jmorris42 · · Score: 3, Interesting

      > With .NET getting more popular, maybe now (or at least the near future) this will be less of an issue?

      I'm old enough to remember when people said these silly things about Java. No it won't help much. As someone else in this topic has already noted most non-trivial .net apps use native .dlls to make up for the performance problem with .net. Just like Java did. Then there is the problem that while Microsoft has spent oddles optimizing the compiler and virtual machine to perform fairly well on x86 it is doubtful much effort will be expended on ARM. Again Java is the reference model except Sun did make Sparc a first class Java platform along with x86.

      But finally there is the bigger question, just how many application domains are even suitable for .net? Anyone expecting games (not counting little cellphone suitable stuff) to EVER be released as managed code will grow old and die waiting. Tier one applications will also be unlikely to forego the performance advantages of native code. Adobe won't be releasing Creative Suite on .net. And don't expect Microsoft to eat their own dogfood anytime soon with IE or Office.

      And since I'm posting a followup anyway I forgot one other point in my assertion that few 3rd party ISVs would bother with ARM. Windows is mostly a platform for commercial applications and shareware. This means they expect to have people actually pay money for applications, usually a pretty nice price. What market segment is ARM netbooks targeting? $300 will likely be the high water mark this Xmas, never to be seen again as by Xmas '10 the ever lowering price tags will have moved down again. How many copies of Creative Suite would Adobe expect to sell? Even Intuit would probably be dubious as to how many units of Quickbooks they would move to such price sensitive customers.

      Note, I believe the ARM advantage is more than price but doubt the market will realize that anytime soon and produce my dream machine. I want a replacement for my Thinkpad X31. Something with a 12" widescreen with at least 1280x720 resolution, 2 GB ram, 32 or 64GB of SSD and with the ARM enough staying power to run all day (12+ hours at least) while still being lighter than the X31.

      --
      Democrat delenda est
    5. Re:Applications are the problem by Hurricane78 · · Score: 1

      That's the really nice thing on Linux. You can recompile nearly all of your 13745 applications (current Gentoo Portage app count) for ARM, and do everything you want. Firefox, Amarok, VLC, OpenOffice, you name it...

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    6. Re:Applications are the problem by bhtooefr · · Score: 1

      To be fair, MS has worked on optimizing .NET for ARM. But, only a limited subset of it, the .NET Compact Framework. It's used in WinMo.

    7. Re:Applications are the problem by foo+fighter · · Score: 1

      Compare to OS X running on PPC or Intel: almost completely seamless to the end user.

      Look at the clusterfuck that Windows AND Linux have with 32-bit vs. 64-bit architectures. Again, Apple made it the 68K to PPC to Intel almost completely seamless to the end-user.

      Apple doesn't get enough credit for the amazing job they did engineering OS X.

      --
      obviously no deficiencies vs. no obvious deficiencies
    8. Re:Applications are the problem by hedwards · · Score: 1

      The only technical reason why we use the X86 and AMD64 platforms is because it maintains backwards compatibility better. Just look at the lack of success that Intel had when they tried to break that compatibility.

      It is somewhat unfortunate that we seem to be locked in like that since there isn't really much reason why we need to hold onto a lot of that old, used to be necessary, architectural cruft. Not to mention the fact that a significant number of the assumptions upon which the original architecture was built upon are no longer valid. And the sooner a switch like this is made the sooner emulation can handle the old stuff at proper full speed. Or I suppose you could just handle it the way that Apple did when they switched to Intel architecture.

    9. Re:Applications are the problem by Anonymous Coward · · Score: 0

      If you call it seamless, I call it a pain in the ass. The swap from PPC to Intel was a bitch.

      And it's not hard to mess up 64-bit when you don't offer it for how many years. Suddenly Apple comes out with 64-bit stuff and they're the savior of everything? No, thanks, fanboy.

    10. Re:Applications are the problem by drsmithy · · Score: 1

      Something with a 12" widescreen with at least 1280x720 resolution, 2 GB ram, 32 or 64GB of SSD and with the ARM enough staying power to run all day (12+ hours at least) while still being lighter than the X31.

      I must admit I have troubling understanding why anyone would want to spend any longer looking at a tiny 12" screen and working on a tiny keyboard, with only a trackpad or clitmouse, for any longer than they had to.

      Just thinking about working on a laptop all day gives me a head and back ache.

    11. Re:Applications are the problem by Anonymous Coward · · Score: 0

      Wouldn't it be possible to build an ARM/Atom computer which uses ARM for the OS and just uses the Atom for "compatibility mode" to support apps which aren't available in ARM versions, switching the Atom off when it isn't needed in order to save power.

      Well, I think it should be possible, since after it was rumoured that Amiga would follow Apple's footsteps in migrating from the 680x0 to the PPC, but there wasn't any actual development done, a couple of manufacturers made 680x0/PPC combo accelerator cards. Though perhaps that was different since the PPC apps were (presumably) written to launch from a 680x0 OS, and in the case I'm proposing the x86 apps won't be written to launch from an ARM OS.

  10. Good Luck With That by bruciferofbrm · · Score: 0

    Do you remember the last time they tried to introduce a new Windows platform on a non-Intel based architecture?

    Yes, it was Windows CE.

    The biggest stumbling block was that MS made it look to much like Windows and gave it a confusing name. Users who bought in wondered why none of their favorite apps would work.

    If MS went with an ARM architecture, the biggest issue would be everything else. All your apps would have to be specifically compiled to run on one architecture or the other. (Didn't Apple have this problem, and come up with FAT Bits and then carbon?) How many sales would be lost because WoW or game of the day doesn't run on that yet?

    Or ARM would have to implement an X86 compatibility layer.

    Hmmm. Windows 8 Ultimate Extreme Business Gamer ARM Edition Pro. Sounds like a winning SKU to me.

    But will in run on a Mac or in VMWare?

  11. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    Does it Freeze, lock up, blue screen, crash & reboot like a full windows OS too?

    Or more importantly... Can it run Linux?

    You're so cute. Who saw that coming?

  12. still not a straight fight by Anonymous Coward · · Score: 0

    If Windows runs on ARM, you still have to convince hardware manufacturers to make drivers for your platform. And don't forget you also need to get software houses to compile for your platform as well. good luck with that.

  13. Make MS come to you by alvinrod · · Score: 3, Insightful

    Don't even bother trying to make a deal with the devil. The rotting corpses of the scores of companies screwed over through their dealings with Microsoft line the landscape of the past decades tech industry. Instead, make them come to you and don't make any deals with them either. If ARM based netbooks start becoming a huge commodity, Microsoft is going to have to port a version of Windows to run on ARM processors or they'll end up missing out on sales.

    It would probably make a great deal of sense for Microsoft to work on this as well as it would most certainly help out their ailing phone technologies as well. They'd probably rather that ARM-based netbooks not take off in the market, but if they were to do so, Microsoft wouldn't be able to ignore them. I wouldn't bother making any plans with them at this point; they'd only find some way to fuck you over.

    1. Re:Make MS come to you by dhavleak · · Score: 2, Interesting

      Do you mean, like they fucked Intel over on IA32/IA64?
      Or the way they fucked Alpha over (when NT used to run on that arch.)?

      Oh that's right -- they didn't!

      And for that drivel you wrote to be ranked +3 Insightful just goes to show how worthless this site has become.

    2. Re:Make MS come to you by maugle · · Score: 1

      You're rebutting the statement "Microsoft has a long history of fucking companies over" by listing two companies Microsoft didn't fuck over? Bravo.

      "Don't try to talk to that kid over there. He's an asshole who just keeps kicking everyone in the nuts."
      "He's not an asshole! He hasn't kicked those two guys in the nuts yet!"

    3. Re:Make MS come to you by commodore64_love · · Score: 2, Informative

      Microsoft fucked-over IBM when they suddenly decided to develop Windows 3 as their main OS, instead of sticking with the original OS/2 agreement. For the rest of this post, I'll just quote wikipedia because it saves typing effort:

      "The majority of criticism has been for its business tactics, often described with the motto "embrace, extend and extinguish". Microsoft initially Embraces a competing standard or product, then Extends it to produce their own version which is incompatible, which in time Extinguishes competition that cannot use Microsoft's new protected version." [editors note - See Lotus 1-2-3 and WordPerfect as examples.] [Also DR-DOS = http://en.wikipedia.org/wiki/Windows_3.1#DR-DOS_compatibility ]

      "... vice president of Intel, Steven McGeady, testified that Microsoft vice president Paul Maritz used the phrase in a 1995 meeting to describe Microsoft's strategy toward Netscape, Java, and the Internet."

      - Browser incompatibilities: Added ActiveX to break compatibility with existing NSCA Mosaic and Netscape Navigator

      - Breaking Java's portability - Microsoft deliberately tied Java programs to its Windows platform, making them unusable on Linux, Mac, Amiga, or NeXT systems, rather than Java's original intent (platform-independence)

      - Networking: In 2000, an extension to the Kerberos networking protocol was included in Windows 2000, effectively denying all products access except those made by Microsoft

      - Instant Messaging: Microsoft put pressure on AOL to make its IM networks interoperable with competing instant messaging services, an outcome that eroded AOL's market leadership.

      - Adobe fears: Adobe Systems refused to let Microsoft implement built-in PDF support in Microsoft Office, citing fears of EEE.

      - More Browser Incompatibilities (CSS, data:, etc.): A decade after the original Netscape-related antitrust suit, the web browser company Opera Software filed an antitrust complaint against Microsoft with the European Union

      - Spreadsheet non-conformance with ODF standards

      "In 2004, to prevent a repeat of the "browser wars," and the resulting morass of conflicting standards, Apple Inc., Mozilla Foundation, and Opera Software formed the Web Hypertext Application Technology Working Group to create open standards. Microsoft has so far refused to join."

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    4. Re:Make MS come to you by dhavleak · · Score: 1

      Apply things in context -- we're talking CPU architechtures here. How exactly do you propose that MS might fuck ARM over?

    5. Re:Make MS come to you by dhavleak · · Score: 5, Insightful

      Take yourself a little less seriously for 5 minutes, and try to come up with a credible scenario in which MS can fuck ARM over. Remember for those 5 minutes that TFA refers to CPU architectures. Try to resist MS-bashing just long enough to stay on topic..

      In any case, let me address a bit of that garbage you spewed:

      1. Regarding your point about Lotus. Read here to be disabused of this myth/dogma: http://www.proudlyserving.com/archives/2005/08/dos_aint_done_t.html Or here if you prefer: http://slashdot.org/articles/05/08/02/2219208.shtml?tid=109&tid=1
      2. "Vice president of Intel, Steven McGeady..." -- whatever. It's just words..
      3. You don't think Active-X was simply a plugin architecture? Why do you suppose other browsers have plugin architectures? All of them are trying to break compatibility with each other???
      4. "Microsoft put pressure on AOL to make its IM networks ** interoperable ** with competing instant messaging services, an outcome that eroded AOL's market leadership." What exactly are you complaining about here???
      5. Adobe Systems refused to let Microsoft implement built-in PDF support in Microsoft Office, citing fears of EEE." And this is proof that MS is evil? Adobe disallowed something, therefore MS is evil??
      6. "A decade after the original Netscape-related antitrust suit, the web browser company Opera Software filed an antitrust complaint against Microsoft with the European Union" Find me a 100% standards-complaint browser, I'll show you a software maker who has a right to complain. Opera and Safari do a better job than most, but nobody is 100% compliant.
      7. Spreadsheet non-conformance with ODF standards" -- ODF 1.0 and 1.1 do not support formulas. The result? All ODF spreadsheet implementations are application dependant. See here for detials. Note MS's complete transparency in the implementation process.
      8. "Apple Inc., Mozilla Foundation, and Opera Software formed the Web Hypertext Application Technology Working Group to create open standards. Microsoft has so far refused to join." See here: (Chris Wilson of Microsoft was invited but did not join, citing the lack of a patent policy to ensure all specifications can be implemented on a royalty-free basis.) - What, again, was your objection?? Also note - WHATWG was formed to accelerate standards creation - not to avoid browser war incompatibilities as you claim.

      That leaves you with 2 out 10. It's still pretty damning, but it's even more damning that 8 out of 10 of your accusations have no basis. So I repeat, stop taking yourself so seriously. Try seeing past the dogma for 5 mins, so you can respond with something related to the article itself rather than this off-topic drivel.

    6. Re:Make MS come to you by alvinrod · · Score: 1

      I'm not just talking about hardware companies, but also software companies. I suppose my comment sounds like the regular anti-microsoft bile that passes for a quick up-mod on Slashdot and on a second read it does come off a bit harsh. I use Microsoft products on a daily basis and a lot of them are quite decent, but if I were in business there's no way I'd make a deal with that company. Hell sometimes you don't even need to make a deal with them, they'll just throw their weight around to crush you.

      Just because I think they tend towards the evil side of the spectrum doesn't mean I think that all of their products are somehow inferior or a complete waste. I just think it's sound business advice to stay the hell away from them as best as possible.

      If ARM netbooks start becoming the next big thing, eventually Microsoft will want to be in on it but no one will owe them any favors. If you try to make some deal with Microsoft, who knows what kind of terms or conditions they'll want which probably serve their own interests far more than anyone else's. I'm just stating that any company should be wary of Microsoft.

    7. Re:Make MS come to you by dhavleak · · Score: 1

      Your comment did indeed come across as the usual anti-MS-bashfest, hence my response, but this is much more measured - thanks!

      In terms of scales of evil - this stuff is just too subjective. If you frequent this particular site too often you'd think MS is the devil's spawn -- there's simply no balance here.

      So like I mentioned to other people so far, is there acutally a scenario in which you can imagine ARM getting screwed over by MS? Note that ARM processors run virtually 100% (if not exactly 100%) of the world's smartphones. This is a significantly larger market than the netbook sector, and expected to grow at alarming rates for the forseeable future. What's the worst MS can do? Make some promise to create an ARM windows, and then pull out at the last minute? What exactly will they achieve by doing that? What would their motive be??

    8. Re:Make MS come to you by commodore64_love · · Score: 2, Insightful

      Talking to someone who is in love with Microsoft, is like trying to convince a girl not to marry her abusive boyfriend. Nigh-impossible. You sir are an apologist trying to defend actions that are not defensible. (Similar to how the record companies' actiosn to fix CD prices at $12 were indefensible, and eventually led to a U.S. FTC lawsuit.)

      As for ARM -

      Microsoft could screw them the same way the screwed PowerPC Mac owners. Sign an agreement to develop the software, do it for five years and gradually win-over fans to the Microsoft way of doing things, and then just stop, leaving ARM/PowerPC users feeling abandoned. Yes ARM will make money during those give years, but eventually they will be stabbed in the back as Microsoft leverages their position to suck users away.

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    9. Re:Make MS come to you by commodore64_love · · Score: 1

      "Microsoft put pressure on AOL to make its IM networks ** interoperable ** with competing instant messaging services, an outcome that eroded AOL's market leadership." What exactly are you complaining about here???

      This is an obvious case of EEE

      - Embrace AOL's technology by becoming their partner. AOL wants to keep their technology locked-up because it's profitable, but MS doesn't want that, so they pressure them to open it. Normally that would be okay, but then.....

      - Extend - Microsoft secretly develops Window Messenger and since it's free with Windows XP, it becomes the dominant client. Next MS changes the protocol, patents the new design, and what was once open is closed again, but this time it's under MS' control not AOL's control.

      - Extinguish - AOL, once dominant, now barely has 10% of the messaging market, so they file bankruptcy. They re-emerge but are only a shadow of what they used to be.

      Please note AOL is not the only company to find itself destroyed by a partnership with MS.

      "Vice president of Intel, Steven McGeady..." -- whatever. It's just words..

      More like an admission of guilt. "Yeah we seek to kill companies by using EEE." Just like a criminal in those court dramas.

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    10. Re:Make MS come to you by Hierophant7 · · Score: 1

      I for one applaud Microsoft's successful implementation of EEE. Maybe Corel should have made WordPerfect better.

      Using words like "indefensible" don't mean you're right. It's not a black and white situation as you seem to be indicating here. "Indefensible" is a very closed-minded term on this topic, and I know I'm not going to convince you of anything other than your own viewpoint, but that won't stop me from sharing my two cents.

      Maybe I missed something, but how exactly did Microsoft screw over PowerPC users? Apple switched from PowerPC to Intel. Therefore, PowerPC macs are not getting any better. They're the same machines they were 4 years ago. Why would Microsoft continue developing Office for these under-powered machines? I mean, even if Apple stayed with PowerPC, the latest and greatest software would still not run on an iBook G3 with 512MB of RAM. You want to run new software, buy a new computer, it really doesn't matter if the Mac is PowerPC or x86. If it's old, it's old.

      As for ARM, I think trying to take over the desktop market is the worst idea they could have. They would deserve to be screwed over by M$. It's like all the Linux folk who complain that M$ is keeping them down. Well, Windows pretty much has the desktop market on lockdown. I'm not saying Windows should be the only desktop OS, but if linux has 1% market share, then your OSS OS is still being used, and be happy about it. People call Linux a failure because of this, but Linux seems to be a fair bit more successful in other areas. Cell phones, GPS devices, etc etc etc. M$ haters are starting to really bother me. Seriously, they're a company, and a successful one at that. I'm not saying everything they do is right, of course not. They fuck up plenty, as does Apple and Linux.

      I guess I'm just agreeing with dhavleak; stop taking yourself so seriously, especially when it comes to one of the dumbest news articles I've seen in a while.

    11. Re:Make MS come to you by Hierophant7 · · Score: 1

      Oh, and your signature's retarded. WTF is Vista 6? 0.1 more bugfixes? What does that even mean? The taskbar received the biggest overhaul I've seen since Windows 95. Up until Windows 7 came out, I was a die-hard OSX fan, but now I have to say I'm jumping ship; Windows 7 is the best OS I've ever used.

    12. Re:Make MS come to you by dhavleak · · Score: 1

      "Talking to someone who is in love with Microsoft...."

      Whatever dude. Try using logic/facts instead of psychobabble..

      "Microsoft could screw them the same way the screwed PowerPC Mac owners."

      See what I mean about logic? You think Microsoft screwed PowerPC Mac owners?? Unfuckingbelievable! The platform had enough issues that Apple themselves moved away from it. You need to build a stronger case than the nonsense you just posted. Same thing for ARM. You're simply missing a motive/advantage for these silly actions you propose.

    13. Re:Make MS come to you by dhavleak · · Score: 1

      "This is an obvious case of EEE"

      Look - your entire AOL rebuttal lacks facts, and so does the OP's original point regarding AOL. It's all just baseless accusation so far and the burden of proof is upon you to make a better case than these random accusations you're coming up with. I suggest researching this a bit more before you respond.

      "Vice president of Intel, Steven McGeady..." -- whatever. It's just words..

      More like an admission of guilt. "Yeah we seek to kill companies by using EEE." Just like a criminal in those court dramas.

      In the middle of some random conversation, with some Intel dude, who later claims that this is what was said? Try "clutching at straws".

    14. Re:Make MS come to you by bhtooefr · · Score: 1

      And the entire reason that ARM is trying to make deals with MS is because they want ARM netbooks to be the next big thing, and x86 Linux netbooks quickly got replaced by x86 Windows netbooks, so they obviously see ARM Linux netbooks as weak against x86 Windows netbooks.

  14. It's not gonna happen! by synoniem · · Score: 1

    Intel and Microsoft do have the same interests and earn a lot of money because of their relationship. What has ARM to offer against that? Mobile phones? Who wants Windows on his phone anyway? Or Linux? Nokia with Symbian still do have lead there simply because they deliver what the customer wants.

    1. Re:It's not gonna happen! by Darkness404 · · Score: 1

      It depends, except for the stupidity of app "approvals" the iPhone is pretty much a perfect phone and runs a pretty high level OS which is basically Mac OS X ported for ARM minus the GUI. The difference is the applications. If I have Linux on my phone I can run a -ton- of applications even with almost no commercial support (see the GP2x) because most apps are OSS. On the other hand Windows will fail because of the fact that it relies so much on proprietary software. ARM CPUs aren't fast enough for emulation of x86 at a decent speed, so you end up with Windows that is effectively useless.

      --
      Taxation is legalized theft, no more, no less.
    2. Re:It's not gonna happen! by bhtooefr · · Score: 1

      Lower power consumption, smaller die size, smaller PCB area.

      And, they're working on the performance.

      This isn't ARM trying to get Windows on mobile phones, this is ARM trying to get into the netbook space.

    3. Re:It's not gonna happen! by tepples · · Score: 1

      If I have Linux on my phone I can run a -ton- of applications even with almost no commercial support (see the GP2x) because most apps are OSS.

      But sometimes I want to play a game on my phone. How many of these games for Linux phones are original games, not emulators that run copies of generally dubious legality of game programs designed for obsolete video game consoles?

    4. Re:It's not gonna happen! by Darkness404 · · Score: 1

      There are actually a lot of Linux games, especially for the Gp2x. While most development is naturally focused into making emulators, there are a few other games. And Windows ported to ARM wouldn't really be any better than Linux for games.

      --
      Taxation is legalized theft, no more, no less.
    5. Re:It's not gonna happen! by tepples · · Score: 1

      Windows ported to ARM wouldn't really be any better than Linux for games.

      It'd probably be able to run Windows CE games (like Pocket PC PDAs and Windows Mobile smartphones) and XNA games (like Zune and Xbox 360). And with Microsoft's name on the platform, it would probably attract major labels.

  15. vaporware by quantic_oscillation7 · · Score: 0

    why wait for vaporware when you got already available today linux on systems like, android, moblin, ubuntu remix, maemo etc? not to mention the future googleOS, which is based...right...linux!

  16. Not quite what people expect by downix · · Score: 1

    ARM can't run x86 software, so would be nothing other than a GUI and name recognition, due to the lack of app support. Same issue Windows NT on MIPS and PowerPC had back in the day.

    --
    Karma Whoring for Fun and Profit.
  17. Please stop with these by fat_mike · · Score: 4, Insightful

    The article is nothing but FUD. They base the relationship of Microsoft and Intel cooling on a comment an Intel employee made at a trade show that some Microsoft employees in the next booth overheard and said "Hey, we're listening."

    This is just another crappy article that is spread over a bazillion pages when one when would do so they can push their advertisers.

    "What if Microsoft switched to ARM?"

    "What if Count Chocula and the Cookie Monster teamed up kidnapped the Keibler Elves? What if monkey's flew out of Cowboy Neil's butt? What is Megan Fox showed up naked at my front door with Natalie Portman covered in grits?"

    Its about the same comparison.

    1. Re:Please stop with these by bryonak · · Score: 2, Funny

      "What if Count Chocula and the Cookie Monster teamed up kidnapped the Keibler Elves? What if monkey's flew out of Cowboy Neil's butt? What is Megan Fox showed up naked at my front door with Natalie Portman covered in grits?"

      I find your thoughts intriguing and wish to subscribe to your newsletter!

    2. Re:Please stop with these by Anonymous Coward · · Score: 0

      hot grits?

    3. Re:Please stop with these by Anonymous Coward · · Score: 0

      "What if Count Chocula and the Cookie Monster teamed up kidnapped the Keibler Elves?"

      One wonders.

  18. Watts by hyperion2010 · · Score: 1

    I honestly hope this works, ARM always seems to use a more stable and generally applicable architecture, besides, at this point it the game we can get speed and cores and performance no problem, but in the long run it will always boil down to performance/watt. This might apply more to servers, but I think it is still a good idea for all tiers of computing. Might finally get people to accept a reasonable standard so we can stop splitting the compiler developer community. *pieinthesky*

  19. It's all about the apps by overshoot · · Score: 1
    And the only reason to use Microsoft is the huge supply of binary-only applications distributed for it.

    Which means that an ARM market gets into the same chicken/egg problem that a shift to Linux does.

    --
    Lacking <sarcasm> tags, /. substitutes moderation as "Troll."
    1. Re:It's all about the apps by et764 · · Score: 1

      It's probably a lot easier to convince application makers to port their application from Windows (x86) to Windows (ARM) than from Windows (x86) to Linux (x86). There's a pretty good chance that switching architectures for most applications just requires a recompile, like porting from x86 to amd64. It's not always that simple, but in this case you'll still have all your Win32 APIs available, whereas porting to Linux will often times mean rewriting the whole thing in GTK or QT.

      ARM processors still aren't being targeted at desktop machines either, but mostly Netbooks. I could see application makers being convinced that writing a netbook edition would be worth porting architectures, but maybe not being worth the full cost of porting to Linux.

    2. Re:It's all about the apps by badkarmadayaccount · · Score: 1

      One acronym:
      WINE.

      --
      I know tobacco is bad for you, so I smoke weed with crack.
  20. Gag me with a spoon. by Joseph_Daniel_Zukige · · Score: 0, Troll

    nt;

    1. Re:Gag me with a spoon. by Anonymous Coward · · Score: 0

      You can choke on my 8" uncut cock, if you want.

  21. Smart move to cut loose with Mac OS X by cyrilc · · Score: 1

    Microsoft was once king on the Intel platform and then came Linux which was much less expensive, followed by Mac OS X which was more user friendly.

    So that would mean they would have to fight 2 fronts to survive and try to keep their supremacy.

    Now, with notebooks being the new eldorado, Microsoft could benefit a lot more if they try to gain momentum on ARM which Apple cannot afford to follow (yet) because of another big CPU switch.

    1. Re:Smart move to cut loose with Mac OS X by Anonymous Coward · · Score: 0

      Microsoft was once king on the Intel platform and then came Linux which was much less expensive, followed by Mac OS X which was more user friendly.

      So that would mean they would have to fight 2 fronts to survive and try to keep their supremacy.

      Now, with notebooks being the new eldorado, Microsoft could benefit a lot more if they try to gain momentum on ARM which Apple cannot afford to follow (yet) because of another big CPU switch.

      I think the iphone osx runs on ARM, correct me if im wrong?

      Apple is already investing heavily on the field, even more if the tablet rumor is true.

    2. Re:Smart move to cut loose with Mac OS X by kinabrew · · Score: 1

      OS X already runs on ARM processors. If you have an iPhone, you already have a copy of OS X running on an ARM processor.

    3. Re:Smart move to cut loose with Mac OS X by mdwh2 · · Score: 1, Insightful

      OS X only runs on Macs, and as good as Linux is, it doesn't (sadly) seem to be gaining market share.

      I can just see them quaking.

      There are obvious reasons for them wanting to expand there share on netbooks and other mobile devices, but I don't think there worried about competition on the desktop.

      And OS X more user friendly?

    4. Re:Smart move to cut loose with Mac OS X by Hierophant7 · · Score: 1

      I know Apple calls it "OS X," but it's clearly not the same operating system. If that's your argument, then Windows also runs on ARM processors, and you've nullified the entire article. (IMO the article should never have been posted anyway, what a waste of time.)

    5. Re:Smart move to cut loose with Mac OS X by WaltFrench · · Score: 1

      Microsoft could ... gain momentum on ARM which Apple cannot afford to follow (yet) because of another big CPU switch.

      Arguably, nobody would be better off than Apple from a massive shift to ARM architectures (except, of course, ARM itself).

      ALMOST ALL apps for both Mac OSX and iPhone and iPod/Touch are written in the exact identical developer environment, and share a huge fraction (not 100%) of frameworks. I.e., the internal tools to support multiple code bases are in great shape for such a change. Go ahead, ask a developer who writes for both Mac OSX and iPhone: the ones I've seen quoted say that writing for iPhone actually helps them re-code better for Mac OSX, not that they had to relearn everything as FUD would suggest.

      The crossover functionality is so great that I, for example, expect that a LOT of Snow Leopard functionality shows up in iPhones within less than 12 months, as the CPUs go multi-core, graphics switch between CPU and GPU, and Apple goes berserk about surmounting Pre's edge in multi-tasking. Why not? Or rather, why is this not inevitable? Apple doesn't talk a lot about its roadmaps, but these are connect-the-dot obvious, no?

      This is not like trying to get Java to work acceptably on 16 different architectures. There are some major apps not written using Apple's current frameworks, but the whole beauty of netbooks is that you aren't expecting (yet, anyhow) to run massive CS4, Office or other huge apps barely able to carry around their own weight. So MacOSX/Arm has thousands of everyday iPhone and Mac OSX apps ready to burnish for ARM books, with a streamlined app store for mass consumer distribution.

      Finally, Microsoft makes its money off (a) Corporate Desktop Windows and (b) Corporate Desktop Office, plus those of us unlucky enough to need to take work home. Neither of these share any resemblance to the burgeoning netbook ethos, which is small, flexible, almost throwaway. The last thing MS wants to do is undercut its only source of profitability by declaring their current game over, and starting another where they have no monopoly power. (Nota bene: Zune, XBox, Bing, ... they're all money-losers.)

      If I were Apple, I'd be drooling if I thought the original premise were much more than a wet dream.

      --
      "Inquiring Minds Want to Know!"
    6. Re:Smart move to cut loose with Mac OS X by bhtooefr · · Score: 1

      Except Windows CE has nothing in common with the NT branch other than part of an API. The iPhone OS runs the Darwin kernel, and has subsystems very similar to those on desktop OS X.

  22. CORE by d4nowar · · Score: 1

    Wherever there are ARM, the CORE will come to destroy. Long live CORE!

    1. Re:CORE by codecore · · Score: 1

      CORE forces have gone to a better place.

  23. JVM/CLR by CarpetShark · · Score: 2, Interesting

    The problem isn't the OS, it's the software for the OS. On Linux, you port the kernel, and then simply rebuild your distro (fixing portability bugs in the process relatively rarely). Job done. On Windows, you need mom & pop go to the car boot sale, buy Knitting Extravaganza 4.0, and still have it install/run successfully.

    I think this is the whole reason why microsoft is pushing dot-net and higher-level languages -- not because they care about the languages so much, but because they care about abstracting the windows platform away from PCs until a virtual machine, like Java has been doing for years. Whether Windows, OS X, Linux, or something else wins the desktop wars, Java will survive. Microsoft wants to survive that loss too.

    1. Re:JVM/CLR by TheRaven64 · · Score: 5, Insightful

      Exactly. A few people want to run Windows, but most don't care. What they do want is to run Windows apps. A port of Windows wouldn't be a straight hardware fight with Intel. Windows NT ran on Alpha and was a lot faster (and not much more expensive) than anything Intel had to offer, but all of the apps were emulated x86 apps, which ran slower than native apps on Intel chips.

      The CLR helps a lot here. A .NET app isn't a native app anywhere, so it's a level playing field. Except that there are very few real .NET apps; they all include a load of native DLLs and unfortunately these are very often in performance-critical code.

      --
      I am TheRaven on Soylent News
    2. Re:JVM/CLR by MightyMartian · · Score: 1

      If Microsoft does again decide to start pushing portable multi-platform versions of Windows, then I guess Microsoft developers are just going to have to learn what folks who develop for other operating systems have done for decades; and that is how to construct directives and a proper makefile, or move to .Net or Java. Microsoft has obviously wanted to push developers away from native compilation for a few years now, but let's face it, there's still a helluva lot of Windows software being pumped out that's natively compiled. Intel, of course, has made that very damned easy.

      --
      The world's burning. Moped Jesus spotted on I50. Details at 11.
    3. Re:JVM/CLR by Zixaphir · · Score: 1

      Which is why Open Source is a problem for Microsoft. Everything is innately portable by anyone who wants to sit there and take the time to make it work. A lot of the time, that's as easy as a recompile, and since the source code is just right there....

      --
      "Now I am become Death, the destroyer of worlds"
    4. Re:JVM/CLR by FourthAge · · Score: 1

      A binary translator would be used to dynamically recompile x86 code as ARM code, taking care of "legacy" x86 applications. Only the OS kernel would need to be native. Eventually, software makers would produce Mac-style "fat binaries" with support for both architectures, but the binary translator would be used in the meantime.

      In the *best* case, you could expect performance on your ARM netbook similar to running PPC code on an Intel Mac. However, if you could run your desktop apps on an ARM, natively or with perfect translation, you would discover that there is a big performance difference between ARM CPUs and Intel CPUs.

      This is my personal theory about why ARM hasn't already come up with an x86 instruction frontend for their CPUs, like the Jazelle decoder for Java bytecodes. It would invite direct comparison between Intel designs and ARM designs, and that comparison would not be favourable because Intel would emphasise the performance difference. There's nothing magical about the ARM ISA that gives them both "low power" and "high performance". The ISA is only slightly cleaner than x86. Currently, the ARM mystique is maintained by the fact that only embedded systems engineers and iPhone hackers really use ARM properly. If you invite every Windows luser to the party as x86 support would, then you can expect a lot of "ARM sux!" chatter on teh intarwebs.

      --
      The tao of democracy: the government you can vote for is not the real government.
    5. Re:JVM/CLR by bhtooefr · · Score: 2, Interesting

      To be fair, IIRC, Alpha's x86 emulation could actually run about as fast as the fastest x86 machines back then...

      But, Alpha ran at literally DOUBLE (or more) the clock speed, and had roughly equal integer IPC and better floating point IPC.

      ARM has a clock speed deficit and somewhere in the same IPC ballpark as Atom, the weakest of the current x86s.

      They are working on that, though. And, ARM did start out as a couple engineers at Acorn designing a custom CPU for a desktop machine, and they had one of the fastest desktop chips by a LOT when it came out. (They were gunning for the Amiga and the like, and an 8 MHz ARM2 just SLAUGHTERED the 7 MHz 68000. Yes, the 386 was about as fast at 25 MHz or so. But in 1987, a comparable 386-based machine was several times more expensive.)

      I'd like to see ARM be a viable alternative to x86, but I don't think it's happening for a while. Windows is necessary, and that won't happen until ARM is fast enough to emulate x86 at near-Atom speeds. Good news is, an ARM in the Atom power envelope could probably do that.

    6. Re:JVM/CLR by afidel · · Score: 1

      Digital made the best binary translator ever made (FX!32), it didn't help the adoption of NT/Alpha despite the fact that Alpha was about twice as fast as the fastest PPro available at the time. Now you think that people are going to run an alternative processor that's several times slower just to get somewhat better battery life? You have got to be joking.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    7. Re:JVM/CLR by Anonymous Coward · · Score: 0

      WinCE/Mobile ran on ARM, MIPS and x86 officially. And there were some ports to microSPARC and PowerPC as well. Microsoft has dealt with cross-platform before.

    8. Re:JVM/CLR by Miamicanes · · Score: 3, Interesting

      > A .NET app isn't a native app anywhere, so it's a level playing field.

      At least, until Intel, AMD, or somebody else adds native .CLR acceleration, kind of like ARM did with Jazelle. ;-)

      ARM had a bigger problem holding it back from Windows than raw speed -- RAM. It's dirt cheap on a PC, but hideously expensive on microcontrollers -- the universe where ARM dominates -- and the moment you decide to add a single byte of external RAM (SRAM, PSRAM, or otherwise) to a MCU design, you've just doubled to quadrupled the system's cost. That, more than anything, is what's killing embedded Java -- the CPU and its speed are the least of anyone's problems. You can buy a cheap ARM with enough onboard SRAM to run most embedded tasks written in C(++) or assembly for under $20 in single quantities, and slap it on a board with minimal external parts & due something useful with it.

      The last time I checked, the most sinfully ram-laden ARM was made by Atmel, and had a whopping 256kB of it. That's *almost* enough memory to do something trivial in Java... except if you were doing something THAT trivial, you'd do it in C and build the hardware for $20 instead of $100. I think it's safe to say that implementing hardware CLR acceleration won't be much harder/easier OR more/less resource-demanding than hardware Java acceleration... and with Java, nothing determines the system's ultimate performance and cost more than the amount of RAM it has.

      I'm sure ARM will fight a hard, valiant battle, but I think they're going to have a hard enough time fighting off x86-on-a-chip microcontrollers. I think there's already a German or Israeli company that's been showing off what's essentially a single-chip 386SX PC with a meg of RAM, VGA-ish graphics, and a reference BIOS that can make SD cards look like floppies and hard drives. Trust me... THAT more than anything scares the bejesus out of ARM, even MORESO because it's not even Intel that's pushing the embedded x86 envelope the hardest (Intel's earliest x86 patents are already expiring, and Intel ALSO happens to be one of the biggest manufacturers of ARM chips.

      ARM didn't become pervasive because it was the cheapest or best... it became pervasive because it was good enough, cheap enough, and available in roughly equivalent form from multiple companies. If Atmel's factory in Singapore goes up in flames, there are dozens of other foundries making ARM chips that are roughly similar. Probably not identical, but nothing like the difference between x86 and M68k, or x86 and ARM. Multiple sources means you can get away with Just-in-Time supply-chain management, instead of having to order and stockpile chips months before you're ready to start using them.

    9. Re:JVM/CLR by shutdown+-p+now · · Score: 1

      Exactly. A few people want to run Windows, but most don't care. What they do want is to run Windows apps.

      If Microsoft releases Visual C++ targeting desktop ARM, with all exact same APIs, and if ARM-based netbooks become popular, you'll see plenty Windows applications for ARM in no time.

      And I don't see why this would be impossible. There are already VC++ versions targetting ARM (WinCE one, for example).

    10. Re:JVM/CLR by i.of.the.storm · · Score: 1

      This whole thread is hilarious, because I was actually thinking about this last night and I hadn't seen this. I think ARM has a better chance than you think though- Cortex A8 has similar IPC to Atom, sure, but Cortex A9 brings out of order execution and dual cores to ARM, so I think it could really give Atom a run for its money. And the best part is that it'll probably use an order of magnitude less power than Atom. I can't wait for ARM to become a viable desktop platform, and I guess at least with Linux it already is. Once ARM gets fast enough and Microsoft gets some sense and ports Windows to ARM, with perhaps some x86 emulation for "legacy" applications (I want to play Starcraft on ARM, silly, I know) it will be awesome.

      --
      All your base are belong to Wii.
    11. Re:JVM/CLR by i.of.the.storm · · Score: 1

      Err, I'm not sure if you were aware, but ARM is on tons of smartphones and PDA type devices and some of them have 288MB of RAM. ARM isn't just for microcontrollers.

      --
      All your base are belong to Wii.
    12. Re:JVM/CLR by Anonymous Coward · · Score: 0

      Most if not all top-of-the line SoC's containing ARM cores also have external memory interfaces so that makes the point about on-chip memory unnecessary for anything else than early booting.

    13. Re:JVM/CLR by Anonymous Coward · · Score: 1, Interesting

      What else is a netbook besides a computer based around a processor that is "several times slower just to get somewhat better battery life"? On my netbook, the most cpu-hungry thing I do is to watch YouTube videos, and frankly, I could easily do without YouTube entirely.

      I love my netbook; it runs Fedora and occasionally Moblin, and goes everywhere I do. I'd trade it in a heartbeat for something that got the same battery life as a Kindle. If you make a small, cheap computer that will run for days on a single charge, of course people will buy it. You can even market it as a green alternative.

      Take a look at the market for netbooks. Take a look at the demand for aftermarket netbook batteries with increased capacity. You have people paying as much as the rest of the hardware to have a four-hour battery instead of a three-hour battery. Battery life is a much bigger deal than processor speed.

    14. Re:JVM/CLR by Anonymous Coward · · Score: 4, Interesting

      ARM had a bigger problem holding it back from Windows than raw speed -- RAM. It's dirt cheap on a PC, but hideously expensive on microcontrollers -- the universe where ARM dominates --

      Is a ARM11 based Freescale i.MX31 with all its stuff onboard a microcontroller? Is a PIC16F88 a microcontroller? What do these two devices have in common. Really, almost nothing at all.

      It really sounds like you're not considering the application space for ARMs at all. Except for some ARM7 stuff, an ARM core is much more capable of running software with a 256KB working set. The applications being discussed (netbooks, PDAs) couldn't do anything useful with 256KB no matter what the architecture.

      Almost all modern ARM cores are implemented along with an SDRAM controller, which in many cases will support DDR2. This is the exact same RAM used in many PCs and since this is a commodity its trading price will be exactly the same. Obviously the unit cost for raw DRAM chips will be lower than that for a DIMM stick from Newegg. So really, no, there is no reason why RAM is any more costly for these "microcontrollers" as you call them.

      Also realize that onboard memory for these devices is typically SRAM and in some ways acts like an L2 cache for these devices. The per-bit cost is many times that of DRAM. Since, DRAM is cheap and the controller is builtin, the cost of memory for these ARM "microcontrollers" is just as cheap as PC RAM, because it is PC RAM. You are simply wrong.

      Even in a number of somewhat embedded applications, the cost issue in an ARM based platform will generally not be constrained by RAM prices, but by Flash prices. In most applications that require the horsepower of a ARM9, the use of a non upgradeable components is very limited, so these systems WILL have Flash. It is quite common to design a system with 16MB of RAM and 1MB of Flash with a total unit cost of sales of $20. (The ARM MCUs are in the $4-6 range in modest ~1000 quantities)

      Probably not identical, but nothing like the difference between x86 and M68k, or x86 and ARM. Multiple sources means you can get away with Just-in-Time supply-chain management,

      I really question your background in this area. This is just not true. In fact it is quite wrong. Despite all the problems with PCs, there is more standardization with ACPI, PCI, and x86 then there is with anything ARM based.

      How many sources are there for a Samsung S3C2442: 1
      i.MX31: 1
      Marvell PXA320: 1

      If you had a complete custom embedded system based on the peripherals of one of these and you had to create a new driver set from scratch, how long would it take? Let me tell you from first hand experience that it is not a weekend project.
      The only thing that those three examples have in common is *some* of the instruction set architecture (not even the cores are the same--in fact, actually the ISA diverges in a number of non-fundamental ways). And even if they had identical cores, that is not a complete system. Merely an important part.

      If you really think if you have a hardware and software design with say a Freescale ARM based device and you can just drop-in a PXA320 and be done in a couple weeks, you are smoking something, or really don't know how much has to be accomplished in that couple weeks.

      The reason that we get away with these single sourced components is because we are relatively certain that if Motorola or Intel decides to get out of the business, the product is still enough of a cash machine that other companies will spin-off or buy it (eg Freescale and Marvell) and in reality there are usually contractual agreements and last-time-buys and a number of economic considerations that a major manufacturer goes through. It has nothing to do with any (nonexistent) technical uniformity in the ARM core based MPU/MCU industry. Nothing at all.

      Trust me, I do low-cost embedded systems design for a living, and most of what you say just doesn't make sense.

      Having developed 386SX based industrial systems in the early 90s, if you think some SoC with 386SX hardware has anything to do with ARM's roadmap, you really don't know a thing about either.

    15. Re:JVM/CLR by FourthAge · · Score: 1

      Isn't that what I said? But the comparison with FX!32 is very interesting, and next time I hear of this "Windows for ARM" business, I will mention that as a counterexample.

      --
      The tao of democracy: the government you can vote for is not the real government.
    16. Re:JVM/CLR by Bert64 · · Score: 1

      Alpha was so much faster that for a while at least, the emulated apps ran faster than anything intel could offer and native apps just made intel look like a joke.

      But it was more expensive, and only ran apps designed for NT, while most people were still running win16 and dos apps which the alpha couldn't emulate.

      Alpha boxes running linux were great tho, the only thing that couldn't be recompiled was netscape, and you could run the native alpha version of netscape designed for digital unix, which always seemed far more stable than other versions of netscape.

      Linux also had the ability to emulate x86 apps on the alpha, but it was slower than the version windows used.. I never really used it beyond testing because i didn't have any apps that were only available for x86 linux.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    17. Re:JVM/CLR by TheRaven64 · · Score: 1

      Microsoft is not a single person. Their OS team has been dealing with multiple platforms since the Dave Cutler era. Their applications teams have, for the most part, not had to deal with anything other than x86.

      --
      I am TheRaven on Soylent News
    18. Re:JVM/CLR by TheRaven64 · · Score: 1

      Even the A8 has a lot of advantages over the Atom. Clock for clock, it gets similar performance (better on a lot of branch-heavy workloads due to the predicated instruction set on ARM). At this speed, however, it uses a lot less power which is very important for a portable. The CPU speed doesn't tell the whole story though, because a typical ARM SoC comes with a DSP and a few other specialised coprocessors on-die. These can offload some of the most processor-intensive workloads and use even less power. An OMAP3 can play back an MP3 on the DSP in a fraction of the power that an Atom consumes at idle.

      --
      I am TheRaven on Soylent News
    19. Re:JVM/CLR by Anonymous Coward · · Score: 0

      What if MS released Midori (a managed OS incubator project they're working on) on desktops, mobiles and the XBOX720 for a mix of Intel, ARM and PPC systems?

      It's a very risky move to be sure since it opens a huge window of opportunity for other operating systems to get in the game during the transition.

      But it might encourage the development of "pure" CLR apps that could run on both Midori and the legacy Windows versions.

      These might have a better chance than historical Java long term because the OS underlying the VM would also end up being the same across machines.

      If say, Adobe didn't port their Creative Suite, MS could back fill the niche with their own apps. Yes, they'd be behind in capability but it would give them the chance to break into Adobe's market. I see this echoing the way Word stole Word Perfect's lunch money during the transition from DOS to Windows.

      I know, crazy talk.

    20. Re:JVM/CLR by Anonymous Coward · · Score: 0

      Exactly. A few people want to run Windows, but most don't care. What they do want is to run Windows apps.

      With all the negative publicity that has flown Microsoft's way about Vista, we're seeing a stronger push to alternative OS's that people previously didn't know existed. There's still the Mac fans, but those people that "don't care" are starting to see cheaper alternatives to get their work done. This is where Ubuntu is starting to come in and fill the gaps. Those that "don't care" could be swayed away from the MS beast and make the choice among a Vista powerhouse laptop that lasts 2-3 hours and weighs 10 pounds, an XP ultra-portable that lasts a few hours (don't feel like doing research), or an Ubuntu portable that lasts all damn day.
       
      As a college student, I personally wouldn't care much about what the underlying hardware was as long as I could take notes, write papers, check email, browse the web, and write some code (CS student, hence the /. reading...). I don't care what OS it runs, as long as I can do what I need to do. During undergrad, to have a cheap machine that could last all day without me having to recharge it 3-4 times would have been more than ideal. If we can get some ARM netbooks that are usable, cheap, and last for a good portion of the day, I'd say there is certainly a market for them. The gamer in me may disagree with the low-power machine, but I generally try not to play starcraft/WoW in class.

    21. Re:JVM/CLR by Bert64 · · Score: 1

      Again, closed source software hampers development...

      Despite Digital's best efforts, FX!32 still ran a lot slower than native Alpha code... Alpha was a lot more expensive than x86, and when running FX!32 not much faster.

      With native Alpha code, the performance difference was more than enough to cover the price difference (a multi processor x86 box that, when running appropriately threaded code, could keep up with a single cpu Alpha cost a lot more).. Alpha boxes running Linux were really great for those of us who had them, they ran rings around people using x86...
      I still have 5 Alpha boxes in the attic ranging from a 166mhz EV4 to a dual 750mhz EV67.

      The same thing happened to IA64, running native code IA64 was much faster than x86, but it was too expensive and too slow when emulating x86 code...

      Expect the same thing to happen with ARM, although ARM processors will still be around because of the phone/pda market, their use in laptops and desktops is likely to only take off among Linux users where closed source apps are few and far between.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    22. Re:JVM/CLR by afidel · · Score: 1

      Even in the Linux world there is a huge subset of apps that are only compiled or tested on x86/x64.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    23. Re:JVM/CLR by 0ld_d0g · · Score: 0

      A lot of the time, that's as easy as a recompile, and since the source code is just right there....

      Sorry, this is bullshit. "Just Recompile" only works if the original source code was written with portability in mind. If you think that "most" of the applications are written with portability in mind, you're sadly deluded.

      But that's not even the main issue. If you are not the original programmer of the application, Porting a moderately big application, like say OpenOffice (or any part of it) would require a huge team of programmers to fix portability bugs and run regression tests.

      What you say might work for tiny 1-2 man projects.

    24. Re:JVM/CLR by bhtooefr · · Score: 1

      However, an Atom SoC could get a DSP of its own, and be competitive still. The other points still stand, though.

    25. Re:JVM/CLR by badkarmadayaccount · · Score: 1

      You don't know about the three way Intel/Microsoft/HP Alphcide, do you?

      --
      I know tobacco is bad for you, so I smoke weed with crack.
    26. Re:JVM/CLR by Zixaphir · · Score: 1

      For the sake of argument, yes, I made it sound easier than it is... But compared to porting a closed source application?

      --
      "Now I am become Death, the destroyer of worlds"
  24. Re:Full Windows on a phone? by CannonballHead · · Score: 1

    Does it Freeze, lock up, blue screen, crash & reboot like a full windows OS too?

    Where is this freezing, locking, BSODing, crashing, and rebooting Windows OS that you speak of? Aside from a few driver conflict issues, I haven't had many problems since Win2k (and XP). I have yet to have a Windows issue on Vista x64 and Windows 7, actually... although I still really didn't like Vista at all.

    Disclaimer: No, I am not a Windows fanboy. Yes, I run Linux. I work with AIX, HPUX, Solaris, Windows, and Linux as my day job. I don't like Macs out of principle.

  25. X86 Compatibility by linuxguy · · Score: 1

    Someone here is ignoring one of the biggest draw of Windows. People can run *their programs* on Windows. They wont be able to do that with Windows on ARM. Then they might as well be running Chrome OS or some other variant of Linux. At least with most variants of Linux they'll have huge selection of software that runs on ARM.

    1. Re:X86 Compatibility by Anonymous Coward · · Score: 0

      This is the "mac" or OS/2 problem all over again. You can't run existing software (good or at all). You can get some of the same behavior on an x86 based linux machine with WINE. It won't work. The people who hated the linux eee pc will hate an ARM box. Remember the PPC based windows systems sold around 1996? History repeats itself.

  26. Re:Full Windows on a phone? by Monkeedude1212 · · Score: 1

    XP was pretty good. After patching it a few times. Windows Vista Home 32 bit still crashes while trying to play Oblivion, and somehow manages to freeze up when playing Pre-Win2K games in "compatibility mode". Windows 7 on the other hand, I haven't had much opportunity to really fiddle around.

  27. Re:Full Windows on a phone? by TheRaven64 · · Score: 0, Flamebait

    Where is this freezing, locking, BSODing, crashing, and rebooting Windows OS that you speak of?

    It's called Windows Mobile (formerly Wince) and it already runs on phones.

    --
    I am TheRaven on Soylent News
  28. Re:Full Windows on a phone? by DrLang21 · · Score: 3, Interesting

    Was it Linus who said that Microsoft hating was a disease? I am a Linux user at home. I'm not much of a fan for Windows XP and I loath the Vista user interface. Windows 7 actually has me a little excited. And all of these are stable systems. The benefit to Windows XP being around for so long is that Microsoft had a long time to make it stable. I haven't had a blue screen of death on Windows in years. It's time for people to move on from knocking Windows for instability. It just makes them look like lackeys.

    --
    I see the glass as full with a FoS of 2.
  29. Re:Full Windows on a phone? by CannonballHead · · Score: 1

    I used Vista x64. No problems with Oblivion, one of th few games I do play. Maybe it was a hrdware or driver issue, I don't know. Hooray for two conflicting anecdotal evidences! ... hehe.

    Windows 7 seems much smoother, so far, than Vista - even though I just said I didn't have too many issues with Vista, hehe. I've run some pretty old programs on it with no problems. If you do use Windows, I'd actually recommend it. Oblivion "has issues," according to MS - which I think is an alt-tab issue - but it handles it fine otherwise. It switches the desktop to 'classic' mode before running and switches it back afterwards. NWN2, Sid Meier's Pirates!, Sibelius (music notation software), Age of Empires III ... all working fine so far.

  30. Re:Full Windows on a phone? by Monkeedude1212 · · Score: 1

    I haven't had a blue screen of death on Windows in years.

    Then that means you're doing it wrong!

    I'm just kidding, I only ever have them when I'm pushing the limits, IE, running something slightly below the Minimum Requirements.

    (Damn you AutoCAD!)

  31. Re:Full Windows on a phone? by sortius_nod · · Score: 3, Informative

    Actually, the first BSOD I had in a number of years was when I installed Vista recently (fully SPed too). I quickly went back to XP until 7 RTM came out.

    Yes, I will admit 7 has been quite smooth, apart from the odd lock up/crash when playing TF2. Still, there's your lock up.

    Whether you're a fanboy or not, you seem to be ill informed about windows issues. They still exist and are still a thorn in Microsoft's side.

  32. Applications? by Phroggy · · Score: 4, Interesting

    When Apple switched from Motorola 680x0 to PowerPC processors in 1994, they built an emulator into the operating system to allow m68k code to run transparently on the new platform. In fact, they didn't even port the entire operating system itself; bits and pieces of it ran under emulation for years as Apple gradually finished porting it all.

    In addition, they created an easy way for applications to be compiled natively for BOTH architectures at the same time, and encouraged application developers to release fat binary versions of their apps. This worked so well that the majority of users weren't even aware that the PowerPC was a completely new incompatible architecture, as opposed to simply a new faster version of what they'd always had.

    When Apple switched CPU architectures again, they mostly duplicated this success. Some applications and drivers aren't compatible with Rosetta (the PowerPC emulator), and it's not possible to use a plugin compiled for one processor in an application compiled for another, but Apple's own developer tools offered a simple checkbox to recompile an app as a Universal Binary, and most developers have moved away from third-party compilers.

    Microsoft does have x86 emulation technology that they bought from Connectix a few years ago, but they have no experience getting applications to work transparently across dissimilar architectures, and moving from a faster Intel CPU to a slower ARM CPU makes emulation pretty unappealing anyway. Look at what a pain in the ass it is just to get everything to work on a 64-bit version of Windows!

    Mac developers are accustomed to following Apple's spontaneous whims, because users consistently reward them with big piles of cash, but Windows developers have a lot less incentive to play ball by releasing native applications for a platform that doesn't exist yet, has no users, and seems unlikely to get users because there is no native software. If they can make the emulation work perfectly, then they might get some users, and if they have users, some developers will start porting their apps. You'll never get all of them, of course, but the ones most people use every day will probably have ARM-native versions introduced. Also, pure .Net applications should work perfectly out-of-the-box. Microsoft wouldn't use a universal binary architecture like Mac OS X; since virtually all Windows applications require an installer and you can't easily move an app from one computer to another without reinstalling it from scratch, there's no reason to do that.

    In contrast, Apple could announce a new ARM-based Mac netbook tomorrow, and a majority of developers would have native applications ready to go in six months.

    --
    $x='S24;r)>63/* h@<5+oZ)32"5cz';$me='phroggy'x$];
    $x=~y+ -xz+\0-Tx+;print$_^chop$me for split'',$x;
    1. Re:Applications? by et764 · · Score: 2, Interesting

      Microsoft does have x86 emulation technology that they bought from Connectix a few years ago, but they have no experience getting applications to work transparently across dissimilar architectures, and moving from a faster Intel CPU to a slower ARM CPU makes emulation pretty unappealing anyway.

      Microsoft actually does have some experience with this. The XBox 360 is PowerPC-based, but it's able to run games from the original XBox, which was x64-based. I'm not sure, but this is quite possibly done using the very software you mentioned from Connectix.

      At any rate, if Microsoft were to release an ARM port of Windows, it'd very likely be some kind of Windows Netbook Edition, and application providers would release versions of their apps for the netbook edition. It seems like the trend is largely towards smaller computers, and software companies would be stupid not to make sure they support this space too.

    2. Re:Applications? by twosat · · Score: 1

      When Apple was moving away from the Motorola chips several prototype boards were created around the ARM (which Apple owned in part) but did not adopt. One of my computer science tutors at the University of Canterbury wrote an ARM emulator in the late eighties for his thesis; he now works for ARM in Texas, presumably in a similar line of work.

    3. Re:Applications? by the+linux+geek · · Score: 1

      I'm pretty sure x86 applications run transparently on Itanium. Or somehow Doom Legacy uses some sort of magic to run on both my Thinkpad and my ZX6000 on work, which I doubt.

    4. Re:Applications? by raftpeople · · Score: 2, Informative

      Hardware x86 was dropped from Itanium when Itanium 2 came out, from then on it's a software emulator. So if your ZX6000 has an older Itanium processor then it probably has the x86 hardware on the chip.

    5. Re:Applications? by heffrey · · Score: 1

      What's so hard about 64 bit on windows. You can single source 32 and 64 bit versions without any ifdefs with no trouble. The interface on 64 bit is called win32 and is identical. What's your problem?

    6. Re:Applications? by avandesande · · Score: 1

      The trick with emulation is easy to do when you have control over a small set of hardware drivers.

      --
      love is just extroverted narcissism
    7. Re:Applications? by Phroggy · · Score: 1

      Thanks, I'd forgotten about that.

      --
      $x='S24;r)>63/* h@<5+oZ)32"5cz';$me='phroggy'x$];
      $x=~y+ -xz+\0-Tx+;print$_^chop$me for split'',$x;
  33. There's already something like this. by Anonymous Coward · · Score: 0

    There is a HTC Shift, a 7" mobile running Vista Business, 800MHz CPU, 1GB RAM and GMA 900.

    1. Re:There's already something like this. by bhtooefr · · Score: 1

      That has two CPUs, one x86 and one ARM, and Windows runs on the x86.

      This is about running Windows on an ARM.

  34. Remember that.. by Paracelcus · · Score: 1

    NT came in Alpha and MIPS once too, you can see how well that went.

    --
    I killed da wabbit -Elmer Fudd
    1. Re:Remember that.. by the+linux+geek · · Score: 1

      It went pretty well. NT for Alpha kicked ass.

  35. Re:Full Windows on a phone? by mdwh2 · · Score: 1

    The benefit to Windows XP being around for so long is that Microsoft had a long time to make it stable.

    Before that even - Windows 2000 is rock solid. The important point is that they're all derived from the much more stable NT line, as opposed to the shoddy Windows 9x that everyone remembers, and still seems to give Windows a bad name, even though it was a completely different OS (it would be like criticising OS X for the flaws in the joke that was classic MacOS).

  36. Re:Full Windows on a phone? by binarylarry · · Score: 1

    I bought a new laptop preloaded with Vista, which blue screened as soon as a USB mouse was plugged in.

    You can imagine how impressed I was with my first Vista machine. This was with Vista SP2 out of the box a few months ago.

    --
    Mod me down, my New Earth Global Warmingist friends!
  37. Vista? by Moof123 · · Score: 2, Insightful

    If M$ can shove Vista down consumers throats (admittedly their success rate has been low), why can't folks imagine something just as preposterous on the hardware front?

  38. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    It's pretty hard to blame the OS for a game lockup. In most cases it's the graphics driver getting woefully confused and eating it, resulting in a hard lock, or the game just wedging (if you could get the processor time to switch out you could kill the process, but often you can't--this happens in Linux gaming, what little there is of it, too).

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  39. Re:Full Windows on a phone? by commodore64_love · · Score: 1

    (sigh). I miss my Commodore Amiga. So easy-to-use and once an MMU was nstalled, as stable as a rock.

    >>>haven't had many problems since Win2k (and XP).

    Me neither... on my desktop. The Pentium 4 PC has no problems with XP, but my AMD K6(?) laptop does bluescreen at least once a week. So Windows ain't perfect yet.

    And as for Vista, ugh. Last time I turned-on my Vista machine, it claimed I had an invalid serial number. I copied it directly from the CD install disc - don't know why it's giving me hassles. (And of course even when it's working properly, that "Are you sure you want to watch video XYZ?" pop-up is damned annoying.)

    --
    "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
  40. Re:Full Windows on a phone? by commodore64_love · · Score: 1

    XP is simply Windows 2000 with a new coat of paint, so that's why they are so similar. Also these are not just "derived" from NT - they are all still part of that line:

    NT 3.1 (first release)
    NT 3.5
    NT 4.0
    2000 = NT 5.0
    XP == NT 5.1
    Vista == NT 6.0
    Windows7 = NT 6.1

    --
    "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
  41. "nothing other" by zogger · · Score: 2, Interesting

    When the first decent mass produced netbook -running ARM- hits the status of "blisterpack computer hanging near the checkout @ $99.95".. right next to the prepaid cellphones..I think the sales will be a lot better than "nothing other" and there will be browsers and media players and chat clients and wifi and so on, on it. Who knows, I could see a combo package, the netbook AND a cellphone in the same blisterpack.

    And people will not care if it isn't microsoft, or x86, just like they don't care much today with cheaper phones. If it does some basic expected things, that's all it needs. They will sell millions of those machines. Browse, watch vids or listen to tunes, do some email, do some messaging...they'll sell. Nailing that C note is a huge marketing psychological advantage, first company there with something that doesn't suck and is "good enough" will get "*rich*. At 3-5 hundred bucks like they are today, nope, just little laptops with no DVD drive, they sell good enough, but... when netbooks crack $100...license to print money almost. More apps and developer interest will follow shortly.

    1. Re:"nothing other" by bhtooefr · · Score: 1

      Also, MS could always make their compilers slip in an ARM binary automatically. Call it .exea. And make ARM DLLs .dlla or something.

      Then, have a stub at the very beginning of the .exe/.dll, in x86 code. This would be small, and it would basically detect an ARM, if ARM, replace image with the ARM image, drop out of x86 emulation, and continue execution natively. That would create an effective fat binary format, without actually needing to change the Windows executable format at all.

  42. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0
    Why is it Windows trolls always have to impress upon your readers how you couldn't possibly be a shill, after all:

    Yes, I run Linux. I work with AIX, HPUX, Solaris, Windows, and Linux as my day job.

    You make broken records sound fresh and new. Let me guess, you have some black friends too.

  43. This whole concept is nauseating. Others have explained why above -- no software, the only reason to do it is to emulate the UI, and we can do that with Linux, and why would we?

    (That's what makes me gag.)

    Okay, the other reason is marketing, to go with the crowd, to be "in" because Bill Gates is "in".

    (And that also makes me gag.)

    Sure, it's my opinion, but why mod me down for saying so in a crude way?

  44. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    -this happens in Linux gaming

    Bullshit! You fucking piece of shit troll. In all the years I have used Linux, the kernel has never not once locked up. If something, like a game, freezes X, it is braindead trivial to just ssh into the box from another machine and
    $ ps aux | grep $OFFENDING_APP
    $ kill -9 $OFFENDING_APP_PID
    Your lies aren't fooling anyone so go scuttle back under your bridge and get some new ones fucking shill bastard.

  45. Re:Full Windows on a phone? by smash · · Score: 1
    If you feed any OS shit hardware and/or shit drivers, it will die.

    I've stuck with Intel motherboards, intel CPUs and Nvidia video for the past 6 years, and the only blue screen i have seen in that time (on my desktop, don't get me started on the BIOS and driver issues on my P.O.S. Dell E6400 under Vista) was due to faulty RAM.

    But again, blue screens on the E6400 are Dell's fault. As proven by them coming and going with various BIOS and driver updates.

    --
    I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
  46. Re:Full Windows on a phone? by aztracker1 · · Score: 1

    Sorry, but I *HAVE* had shitty drivers in Linux cause lockups when playing a graphically intense game. Hard-lock, wouldn't even panic. I've also seen kernel panics from drivers with nearly-correct hardware. Linux isn't immune from faulty drivers/hardware locking up the OS.

    --
    Michael J. Ryan - tracker1.info
  47. Compatibility layer for CE just like for 3.1 by tepples · · Score: 1

    it'll suffer the same problem as the PPC version of Windows did, no applications.

    All versions of Windows NT for x86 have a compatibility environment for running DOS apps and Windows 3.1 apps. All versions of Windows NT for x86-64 have a compatibility environment for running Win32 apps. Why can't Windows NT for ARM have a compatibility environment for running Windows CE apps?

    When people read the specs and it says "Windows 7", they will expect to run Windows apps on it.

    Not if it says "Windows Mobile 7".

    1. Re:Compatibility layer for CE just like for 3.1 by davester666 · · Score: 1

      it'll suffer the same problem as the PPC version of Windows did, no applications.

      All versions of Windows NT for x86 have a compatibility environment for running DOS apps and Windows 3.1 apps. All versions of Windows NT for x86-64 have a compatibility environment for running Win32 apps. Why can't Windows NT for ARM have a compatibility environment for running Windows CE apps?

      Sure you could shoehorn this together. It's only add another couple hundred Mb's to the install footprint for this. And this compatibility layer is a new ball of wax to implement on top of porting Win7. And once it's done, you've a way to run apps typically designed for a cell phone screen, with cell-phone buttons, on what is essentially a small laptop. And WinCE apps generally look and work like crap (UI wise), only now their low-res graphics will be blown up on a much larger display. And this would only be used to be able to claim "there are X apps available right now you can use", because nobody in their right mind would use it to write new apps for this platform, except perhaps to rework an existing wince app to work/look better on this new OS.

      When people read the specs and it says "Windows 7", they will expect to run Windows apps on it.

      Not if it says "Windows Mobile 7".

      Maybe they would have to go with Windows ARM 7, because reusing WinMo would be really confusing.

      But still, assuming all this work is done by Microsoft and their driver partners (as you need to also port all those drivers to the platform as well), I don't see a huge win for anybody other than the cpu manufacturer.

      I'm sure a lot of MBA's are asking, vs an Intel system of the same CPU speed (say a slow Atom cpu), how much cheaper will an ARM system be (so the main difference in price will be price difference between Atom and ARM chipsets along with a smaller battery for the ARM system). From Googling, the cheapest Atom chipsets are in the $20 range for mass quantities, so there's not a huge amount of room for savings.

      And remember Microsoft is still pushing their newly rebranded Windows Phone OS for actual cell phones, with all new not-copying-the-iPhone touch interface (arrange icons using hexagons instead of square grid! different is better! Not copying Apple at all! We've been working on this all along).

      --
      Sleep your way to a whiter smile...date a dentist!
    2. Re:Compatibility layer for CE just like for 3.1 by Korin43 · · Score: 2, Informative

      Compatibility layers are much different than emulation. To run a DOS/Windows 3.1/Win 95/etc. program in Windows 7 all you need is the old libraries. I assume the x86-64 instruction set includes stuff to make x86 emulation faster. My guess is that emulation x86 on an ARM processor is nowhere near fast (otherwise they'd just always run them in emulation mode and compete with the Intel Atom and Via Nano).

    3. Re:Compatibility layer for CE just like for 3.1 by tepples · · Score: 1

      To run a DOS/Windows 3.1/Win 95/etc. program in Windows 7 all you need is the old libraries.

      Likewise, to run a program designed for Windows CE for ARM architecture on a port of Windows NT to ARM architecture, all you need is the old libraries.

      emulation x86

      Who said anything about x86? Windows CE has run on ARM for years.

    4. Re:Compatibility layer for CE just like for 3.1 by Bert64 · · Score: 1

      Windows CE has got a rather poor application base compared to windows/x86, you would end up with a decidedly sub par experience...

      If you marketed it as being windows, and let customers assume compatibility with the x86 windows they're familiar with, users will be disappointed and you will get a bad reputation...
      If you advertise it as something else, it has to compete on a more level playing field with linux which is cheaper, has a much larger application base, is more mature on the arm architecture and is much easier to use...

      Linux would also have much better compatibility with external peripherals like printers because most of the drivers are open and easily recompiled on arm, yet the windows drivers are typically shipped as binaries for x86 by the peripheral manufacturer who may be unwilling to produce arm drivers. I don't think many peripheral vendors produce drivers for windows ce...

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    5. Re:Compatibility layer for CE just like for 3.1 by Korin43 · · Score: 1

      The main reason people use Windows over Linux is so they can run their Windows programs. I'm guessing anything you could find ARM libraries for would also run on Linux anyway..

    6. Re:Compatibility layer for CE just like for 3.1 by tepples · · Score: 1

      I'm guessing anything you could find ARM libraries for would also run on Linux anyway

      Anything? I'd beg to differ. Numerous video games, such as an authentic Tetris game, are available for Windows Mobile but not Linux.

    7. Re:Compatibility layer for CE just like for 3.1 by Korin43 · · Score: 1

      You're really using Tetris as your example? I don't think people are going to be too worried that Linux's Tetris rip off isn't exactly the same considering that that's not really what most people use their computers for (solitaire maybe, but not Tetris).

    8. Re:Compatibility layer for CE just like for 3.1 by tepples · · Score: 1

      You're really using Tetris as your example?

      It's one of many.

      I don't think people are going to be too worried that Linux's Tetris rip off isn't exactly the same

      I'm more concerned about fallout from Tetris v. BioSocia. If Tetris wins the lawsuit, Canonical Ltd is in trouble because it distributes Gnometris, a Free alternative to Tetris, as part of its "Ubuntu" operating system distribution.

  48. Re:Full Windows on a phone? by Rycross · · Score: 0, Flamebait

    Because anything positive said about Windows usually prompts responses shrilly claiming that the parent poster must be a paid shill. Without any proof, of course.

  49. Code signing requirements per architecture by tepples · · Score: 1

    Apple already ships a huge number of OS X machines with ARM chips, they just brand them as iPhones and iPod Touches. OS X makes it easy to add another architecture for fat binaries

    Currently, if I compile an app as a fat binary for x86 and ARM, it won't actually run on a computer with an ARM CPU unless I pay Apple $99 to join the iPhone Creators Club. If Apple were to introduce "Mac" brand computers with ARM CPUs, how would the "fat binary" system handle different code signing requirements per instruction set?

    1. Re:Code signing requirements per architecture by TheRaven64 · · Score: 1
      Why do you imagine this is a nontrivial problem? OS X, since 10.5, has had the capability to refuse to load non-signed binaries via the security frameworks. They can easily ship one ARM-based machine with a version of OS X that will only run signed binaries, and one ARM-based machine that will run anything. It's just a few line difference in the system configuration files.

      The fat binary system just provides a set of ISA-specific sections in the binary. Code signatures, I believe, are stored in the .app bundle but outside the binary. Whether the loader checks the signature before loading is entirely up to the loader, and is not dependent on the binary format or the instruction set.

      --
      I am TheRaven on Soylent News
    2. Re:Code signing requirements per architecture by tepples · · Score: 1

      OS X, since 10.5, has had the capability to refuse to load non-signed binaries via the security frameworks.

      As I understand it, Mac OS X ordinarily lets the user sudo to change the system configuration files, but the version on an iPod Touch doesn't.

    3. Re:Code signing requirements per architecture by TheRaven64 · · Score: 1

      That's not due to an alteration in the operating system or loader, it's just that the iPod Touch doesn't include sudo and the user isn't told the root password.

      --
      I am TheRaven on Soylent News
    4. Re:Code signing requirements per architecture by tepples · · Score: 1

      the user isn't told the root password.

      In that case, I guess the real question is the following: Would Mac OS X on ARM-based subnotebook hardware tell the user the root password?

  50. Heard of XNA? by tepples · · Score: 1

    Anyone expecting games (not counting little cellphone suitable stuff) to EVER be released as managed code will grow old and die waiting.

    Games on .NET? Let me Bing that for you.

  51. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    So, what you're telling me is that it does wedge the system for any normal user?

    Awesome. Thanks for the corroboration.

    Unless you're trolling to demonstrate how braindead-fucked-up the Linux-on-the-desktop people tend to be, in which case I applaud heartily.

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  52. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    Erm. Freezing X and freezing the kernel are totally different. Bluescreens and driver crashes in windows are in the kernel, and they'd cause the same problems in linux, you just don't see them as often because you generally don't get production-rushed, crappy games there :p

    Yes, I've worked for nvidia on their kernel driver, on windows and linux.

  53. Good opportunity by hotfireball · · Score: 1

    It is good opportunity to make another Apple-like machines, e.g. running really damn polished Ubuntu or something like that.

  54. Re:JVM/CLR (It works). by Anonymous Coward · · Score: 0

    The JVM concept works. Right now I develop on an Intel/Linux[1] desktop and deploy the exact same jar files to an ARM system and a PowerPC system. Saves me a HUGE amount of effort. The user interface is via the web, so it all looks the same no matter where it runs. Luckily the JIT compilers make things fast enough so the app can be a pure java app, no dll/so required.

    [1] The rest of the developers use Intel/Windows. Makes very little difference
    for what we do except for video rendering.

  55. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    No, troll, but thanks for playing and winning the stoopie prize. On Linux, you log into the machine from another machine and unfreeze the user interface by killing whatever poorly coded app that caused the problem as a worse case scenario. Only thing you lose is the data in the app that froze X.

    Contrast this to Winduhs where you lose everything right about the time you press the power button as that is the only to unlock a frozen Winblows box.

    But you knew that. Hence, your OS of choice is shit and you are a troll.

  56. Get Apple to go ARM by Joelfabulous · · Score: 1

    Then Microsoft will be happy to follow suit!

    Seriously though, an Apple "netbook" tablet style PC with a reasonable size screen (10" maybe?) with gestureriffic stuff and some nice note taking software would be awesome. I'd probably even preorder one... and I've never owned an Apple PC before. :-)

    --
    Sometimes I wonder if I think too much.
  57. Handheld PC by tepples · · Score: 1

    And once it's done, you've a way to run apps typically designed for a cell phone screen, with cell-phone buttons, on what is essentially a small laptop.

    Every Windows Mobile device I've used has been a Pocket PC with a touch screen. And there even used to be Windows CE subnotebooks.

  58. Get rid of backward compatibility by kabloom · · Score: 1

    This would be a great time for Microsoft to get rid of 1001 compatibility fixes for applications that still rely on misfeatures DOS for x86 and will never be recompiled for ARM anyway. Maybe Windows will be able to become stable and secure in this iteration.

  59. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    How do you prove whether a particular poster is a paid shill or not? Who knows? How do you prove anything? I'll spare you the philosophical implications of that questions as you aren't intellectually equipped to appreciate them anyway. However, it is a known and verifiable fact that Microsoft does indeed pay people to troll internet forums like slashdot and spout vague shill bullshit. In memos released during a certain trial against Microsoft, it said precisely that and one of the tactics discussed in the document to give the professional propagandist "credibility" was to pretend to be a Linux user that "is willing to give Windows its due"

    Don't insult your inteligence by pretending this isn't so. And, if you are so oblivious or stupid to not already be aware of this fact, look it up. Typically, I don't do trolls' research for them but, this time, I'll at least point you to a couple of good places to get started.

    You obviously have some studying up to do, so I'll bid a good day sir.

  60. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    Yeah, because I really keep another computer around just in case X wedges when I'm playing the (very few) games that exist on Linux.

    Oh, wait. I don't, because my other machines (which do run Linux) are all headless and keyboardless.

    You're a fucking retard.

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  61. Re:Full Windows on a phone? by the_womble · · Score: 1

    [quote]Aside from a few driver conflict issues, I haven't had many problems since Win2k (and XP).[/quote]

    Aside from a few recurring issues that the average user would not have a clue how to fix, would probably just live with?

  62. Wate of time by the_womble · · Score: 1

    There is no evidence that MS is interested in porting Windows to ARM, the only thing anyone from ARM has said is that they would like WIndows to be available from ARM. They have not said that they will make any particular effort to get it ported.. This is all pure speculation.

  63. Re:Full Windows on a phone? by jparker · · Score: 1

    I've been writing PC/console games for 10 years now, and these days if your system locks (at least while playing something like TF2, especially fullscreen) there's a 90% chance it's a driver issue, most likely video drivers.
    I've been a mac user since 1984, run ubuntu on my netbook, and have refused to install any MS software on my macs (mostly as a test). I also have to run windows at work (xbox dev sort of requires it), and it almost never crashes. It hurts me to say it, but it's true.
    There are still countless horrible design flaws all over windows, but frequent OS instability in the absence of buggy driver-level code is now rare.

  64. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    Wow, you proprie-tards just don't know when to shut the fuck up. You think I give a shit how many computers you don't have? Go buy a fucking netbook or something. Or, shit, get an ssh client for your cellphone. You have one of those right, you unimagininitave prick? I'm just saying that you can unfreeze a stuck Linux machine by logging in. Something you singularly can't do with your precious Windows. Of course, you won't acknowledge that I am just right and move on. No, you have to pull the classic professional propaganist dick move of just dancing around a point when you are cornered on it. You make me want to vomit. But back to the point, for anyone else that may be reading this, as a matter of fact, with putty, you can even use the Windows box to do the logging in with.

    And, something else, you keep throwing the bait out there about Linux not having many games. Last I checked, there were plenty of first tier games that work on Linux. Are they Linux games in the truest sense of the word? No. But, who gives a fuck? FarCry 2, Fallout 3, Oblivion, Morrowind, Half-Life 2, etc. seem to work well on my box. So, suck it, bitch. This is Linux on the desktop. And I hope you don't like it. Sucks to be you because we will be here long after the last BSOD has faded into ancient history.

  65. Shit tons? by Anonymous Coward · · Score: 2, Funny

    Is that a regular ton + the weight of the approximate animal that shit that much for a whole year?

    So, the average 180lb man would excrete 1 shit ton or equivalent of 2 English pounds of solid waiste for 365 days to meet the expectancy of his shit ton?

    I know a full-size mare would reach a man's shit ton every 2 months easily, so that would make a man about 1/6 mare shit ton, and if a man were to sire a creature to be half-horse then that offspring would be 1/3 mare shit ton.

    I know I kinda eluded onto a metric that might differentiate from yours, so I'll wait for your enlightenment O-ring King.

    1. Re:Shit tons? by dotgain · · Score: 1

      European swallows are non-migratory.

    2. Re:Shit tons? by SkipFrehly · · Score: 1

      Wow, if I keep recycling these jokes...

      She turned me into a newt! ...I got better.

      --
      So long, thanks for all the fish.
    3. Re:Shit tons? by Gilmoure · · Score: 2, Funny

      What's the conversion equation between shit-ton and metric butt-load?

      --
      I drank what? -- Socrates
  66. Re:Full Windows on a phone? by i.of.the.storm · · Score: 1

    On a related note, I've had kernel panics while installing Arch Linux. Not a knock against Arch at all, I'm really interested in getting it on my machine but the fact is that bad/broken drivers will lock up any OS, and a BSOD is always a hardware issue by design. The only time I've seen a BSOD in the past 8 years or so was recently when I was undervolting my laptop to reduce the heat, but I expected it to happen anyway.

    --
    All your base are belong to Wii.
  67. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    Clearly you've never had a driver wedge the kernel, you maggot-fucked brain-dead freetard. I have. It happens. And no, you can't just magically SSH into it when it panics because the graphics driver shits itself.

    And WINE doesn't count for games when I have a perfectly good Windows machine right here. You can't help but fail, can you?

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  68. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0
  69. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    You imbecile! Pull Ballmer's cock from your mouth long enough to think for a second. I never said anything about sshing into a box that has a kernel lock. Dumbshit, I was talking about X freezing up. You can even refer to my original post in this thread where I quite specifically said I had never had a kernel lock up. Again, in proprietard-land, sometimes, explorer freezes. When this happens, it's over. You reboot. When X freezes, you do what I've already said like three times. Since you are obviously so slow or just blinded by your hatred of freedom and open source, I'll spell it out. Your monopoly fueled Wintendo bullshit is fucking buggy bloated slow trash. Stick it up your ass.

    As far as Wine not counting, just hold on a minute. Oftentimes, Wine works better than your [sic]"perfectly good Windows". I had almost given up on FarCry as there was a weird graphical glitch that made everything black around my character everywhere I went back when I used to be shackled to the Winduhs teet like you are. Then, when I moved on to Linux, I decided to try FarCry in Wine to see what would happen. And wouldn't you know it, the black shit was gone. And furthermore, the game was considerably smoother. When new enemies jumped out, they didn't jerk at all. It was all perfectly smooth. Unlike Windows where there would always be the slightest momentary freeze when something new would hit the screen. So, yes, Wine is a credible alternative. I wouldn't go back to gaming on Windows if Ballmer open sourced the whole thing tomorrow. The only thing failing is you and your bullshit.

    Now, go back to your magnificent Vista *snicker*, fire up Internet Exploiter and jack off to some Win7 press releases. And while you're at it, don't forget to reboot the next time you update your precious fucking graphics driver that you seem to love so much.

  70. "True" Windows on Arm != backwards compatible by Anonymous Coward · · Score: 0

    It doesn't matter if MS creates a full Windows OS for ARM, x86 has a different instruction set. Existing Windows software still wont work on it. For backwards compatability, a newer Windows version that either emulates, or requires applications have two sets of instructions would be a nightmare for developers and probably support in general. Imagine the transition from one windows OS to the next, multiplied by 100 times as much pain.

    Because of Linux, a soup'd-up ARM processor already has a full OS. There's no lack of one.

    There's also no mention of AMD in the article...? The (stronger) ARM would be competing with two companies, with a product that isn't directly compatible. No way they'll coexist, and Windows isn't going to ditch Intel for ARM, like Mac ditched Motorola for Intel.

    1. Re:"True" Windows on Arm != backwards compatible by bhtooefr · · Score: 1

      But ARM knows that consumers want Windows, not Linux. Hence all this.

      Yes, applications are the problem, but if ARM sticks with it, eventually apps will migrate. I'll note that the various ports of NT to other architectures (other than MIPS) weren't paid for by Microsoft.

      DEC paid MS to do the Alpha port (which is why Windows 2000 wasn't released for Alpha - Compaq decided to chase Itanium, and stopped paying Microsoft to develop the Alpha port,) and I'm fairly sure someone in the AIM alliance paid MS to do the PowerPC port, and fairly sure HP/Intel paid MS to do the Itanium port.

      So, ARM would just have to pay MS to keep the port maintained. Keep doing it, and my guess is, given proper developer support (for example, Visual Studio compiling both x86 and ARM binaries by default,) within two Windows version generations, you'll have decent application support for ARM.

  71. Re:Full Windows on a phone? by Hal_Porter · · Score: 1

    A quick Google for "Oblivion crash vista" gives things like this

    http://www.howtogeek.com/forum/topic/trying-to-get-oblivion-to-work-on-vista#post-53749

    --
    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;
  72. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    Again, in proprietard-land, sometimes, explorer freezes. When this happens, it's over.

    1998 much?

    You seem very angry. I guess being a perpetual virgin does that to you.

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  73. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    I never said anything about sshing into a box that has a kernel lock.

    Yeah, but I did. Read my first post: in most cases it's the graphics driver getting woefully confused and eating it, resulting in a hard lock. That's a kernel issue. I've been talking about a kernel issue the entire time, except where I bothered to laugh at you for your "well yeah but if X freezes" inanity (where you very well illustrated why I, despite having three headless Linux servers locally and running a number of VMs on Rackspace's cloud services, don't use Linux on my desktop, and how out-of-touch you are with how people actually use their computers). I'm friends with a guy who worked at nVidia on their Linux driver code; even pointed him at this thread. He agreed with me and did so in tones that suggested he found it incredible that you would even contest it.

    You seem to be unable to stay on point, though. Ah well. It's okay. Really, Linux appreciates how vitriolic you get about it. Your behavior truly makes other people more interested in Linux. You're awesome.

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  74. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    Since I'm feeling charitable, and I know you won't be capable of understanding what I mean by "1998 much," let me explain: the explorer process can be killed, just like any other process. If explorer wedges, you hit Ctrl-Shift-Escape (or Ctrl-Alt-Delete and click "Task Manager"). This gives you a little thing called a "task manager"--it's like your little Linux "top" command, only it's actually useful for things. Still following with me? Now, you use that mouse thing attached to your computer and you click "explorer.exe". I know it's hard, but stay with me: now click "End Process." Wow! It goes away! But now you need to restart it. Don't be scared, man, it's easy: go to "File", click "New Task", type "explorer" into the friendly wittle box that pops up, and click "OK."

    Ain't that amazing? Not rebooting to address a wedged shell! (And, to forestall your tired wrong horseshit, under Vista you can even just kill the desktop manager if it runs amok.)

    Just because you don't know how to use Windows and are hostile to things that confuse and upset you doesn't mean the rest of us are as incapable of normal human function as you are. I use Linux, OS X, Solaris, and Windows every day. The best tools for the best jobs. And, no, Linux is not the best tool for the job on the desktop for me. Sorry, but no amount of sad basement vitriol changes that.

    I'd say "go home," but it's an open question when the last time you left your basement was. :-)

  75. AMD logo on an ARM newsitem? by sgarg · · Score: 1

    AMD logo on an ARM newsitem?

    Slashdot is getting old ...

  76. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0
    I can't believe I actually have to be this specific. I also can't believe I'm spending this much time on such a hopeless case. But, hell, it's only 3:30 in the morning. What the hell? I have personally had Explorer lock up to the point that task manager would not come up. The definition of explorer.exe being locked up is nothing works. When that happens, you reboot. Period. With GNU/Linux, on the other hand, there are several things you can do to quickly get back up if X freezes. Which is extremely rare. I've already mentioned one. There is also the sysrq key combinations, switching to a virtual terminal and killing the app. You can't do any of these things with Windows. So, I don't know what you are trying to prove. Whatever it is, you're wrong.

    hit Ctrl-Shift-Escape (or Ctrl-Alt-Delete and click "Task Manager"). This gives you a little thing called a "task manager"--it's like your little Linux "top" command, only it's actually useful for things. Still following with me? Now, you use that mouse thing attached to your computer and you click "explorer.exe". I know it's hard, but stay with me: now click "End Process." Wow! It goes away!

    Damn, and to think I go through all the trouble of hitting ctrl+alt+backspace to do the exact thing in one quick step. Boy, Windows sure does have me beat there.

    And task manager is real useful. Let's see. click process, click end process. Nothing happens for something like 10 seconds. Little box pops up, would you like to end this process (or whatever). /facepalm. When I want to end a stubborn app, I click a certain little icon on my taskbar, my mouse cursor turns into a little skull and crossbones. I click on what I want to die and it goes away. Instantly. Funny how that works. You know, without the interminable delay and all you get with Windows with every little thing.

    Linux isn't ready for your desktop. Fair enough. But making up stories to try to make Windows look better is just plain ugly. I've used Windows. I use Linux now. Linux does everything Windows did for me including play games, run windows only crapps like Quicken (Wine is better than you think), and tons more that Windows is not capable of at all and it does it faster with less drama. Face it, you got sucked into the Windows mindset and now your subconscious is doing everything it can to try to continue justifying it.

    As for your basement wisecrack, you'd be surprised. I'm a business owner and it one of the reasons I kick my competitors squarely in their asses is technical savvy and running an open source stack. I can't do anything but laugh when people extol the supposed virtues of closed source software. That's just a joke. Some proprietary software is more featureful but where you're lacking is flexibility. I'll spare you the details but, I couldn't be happier. This has been fun. Bedtime.

  77. Re:Full Windows on a phone? by maxwell+demon · · Score: 1

    Of course that only works if your computer is on a network, you have access to another computer on that network, and ssh access from that other computer to the frozen-X one is enabled.

    And BTW, before doing the kill -9, it's a good idea to first try kill -15 (note: -15 is the default for the kill command), kill -2 and kill -1. Unlike kill -9, those give the misbehaving application a chance to clean up. Most applications still react to a regular kill, and an astonishing number of those who don't react on -15 do so on -2 or -1. It's a very rare case that you have to resort to the "nuclear option" -9.

    --
    The Tao of math: The numbers you can count are not the real numbers.
  78. What is the point? by Bert64 · · Score: 1

    Assuming windows was ported to arm, what about applications?

    In the linux world, most apps come with sourcecode and are relatively easy to recompile for arm, you can use an existing distribution like debian which has thousands of applications already compiled for the arm processor, or if you are making such hardware it's not a huge effort to compile appropriate applications yourself.
    Most linux applications are coded fairly cleanly, those badly written ones which don't are likely to have been fixed already since linux runs on so many different platforms.

    On windows however, most apps come without sourcecode, and only come with binaries for x86, the vast majority of apps don't even come with x86-64 versions.
    Only the original app vendor has the capability to port the application to arm, which brings up lots of problems...

    Most windows app vendors are for-profit companies, they won't port to an architecture which doesn't have an existing user base. (conversely, a user base wont bulid around an architecture which has no apps)
    It's impossible to tell how portable their code is, for some it may be possible to just recompile, but my experience of commercial development is that the build environment is often quite fragile and would need quite a lot of work to target a new platform.
    Many people continue to run apps that aren't supported anymore by their original vendors, so no chance of porting.

    The only thing windows really has going for it, is the existing base of applications... if you port it to arm, you take all that away so you end up with an immature expensive os with very few applications and very few users which compares very poorly to linux/arm.
    the only thing that would help it sell is the windows name, but it would earn itself a very bad reputation when the customers realized they had effectively been tricked.

    --
    http://spamdecoy.net - free throwaway anonymous email - avoid spam!
  79. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    Tourette much?

  80. Open source 3D acceleration by coder111 · · Score: 2, Interesting

    I've looked at BeagleBoard and some other TI OMAP3 board specs. They all have PowerVR video/3D accelerator, which does not have any open-source drivers. And I'm not even sure about closed source ones. These boards lose 90% of their cool without them.

    Reading these specs felt like kissing a girlfriend and then getting kicked in the groin... Especially at a time when it is becoming possible to have a 100% open-source supported hardware in desktop machines (ATI drivers started supporting new cards, lots of opensource wifi drivers are mature, etc).

    --Coder

    1. Re:Open source 3D acceleration by Svartalf · · Score: 1

      There's been efforts on several fronts to get Imagination to relent on either FOSS drivers or release of the technical info. Unfortunately, every one of the SoC's on the table right at the moment have GPU hardware with no technical data available (not even Snapdragon- while they bought the mobile GPU division from AMD, those chips aren't the same as the R-series parts we've got info for...). I'm hoping Imagination will realize it's to their advantage or Qualcomm will at this point- I'm not holding my breath for NVidia for a while yet to come.

      --
      I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
    2. Re:Open source 3D acceleration by Svartalf · · Score: 1

      Oh, they DO have closed source ones, though. Wouldn't have Q3:A running on the Beagle otherwise (Or have something like Caster in development for it... ;-) )

      --
      I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
  81. Re:Full Windows on a phone? by binarylarry · · Score: 1

    This was a fairly expensive Toshiba and Vista's default drivers... it was a fucking Microsoft mouse.

    --
    Mod me down, my New Earth Global Warmingist friends!
  82. ARM 64-bit is nowhere in sight by DrDitto · · Score: 1

    All current ARM processors are 32-bit. There is nothing imminent on the roadmap for a 64-bit ARM processor.

  83. Re:Full Windows on a phone? by Bert64 · · Score: 1

    You can kill an X11 application too, using xkill, or terminal and a top...
    Both of these examples assume the GUI is functional, which it might not be (some programs, eg vmware, can hijack all input, and if such a program crashes you often find yourself unable to interact with the gui even if technically it hasn't crashed)...

    On Linux the gui is not an inherent part of the system, and the entire gui system (X11) can be killed and restarted... Explorer is not the equivalent of X11, it's not even the equivalent of a window manager, it's closer to nautilus.

    --
    http://spamdecoy.net - free throwaway anonymous email - avoid spam!
  84. Bedfellows by DarthVain · · Score: 1

    Good luck with that. Never gonna happen.

  85. Re:Full Windows on a phone? by Rycross · · Score: 1

    The point I was pointing out, and that you missed (as you apparently aren't intellectually equipped to appreciate this) is that just because Microsoft pays shills doesn't mean that a given person with a positive opinion of a Microsoft product is necessarily a Microsoft shill.

    And the reality is that it doesn't matter. In one case, the person is conveying their opinion, which can be simply countered with yours, and really doesn't matter in any debate (an opinion isn't proof of anything). In the other case, they're conveying facts, which can be verified or discounted. Claiming that a person is a shill is an anti-intellectual appeal to emotion. Its intellectual dishonesty, unless you have any proof to back up the claim (which they never do). In case you missed it with your staggering intellect, proof here means proof that the person in question is a shill, not proof that Microsoft in general pays for shills.

    But then again, you're linking to boycottnovel and twitter's journal, so you know all about intellectual dishonesty (Hell I'm giving it a 50/50 that you are twitter. Hi twitter!) But go ahead, have fun labeling me a troll. Easier to dodge the point that way, isn't it?

  86. Re:Full Windows on a phone? by GodfatherofSoul · · Score: 1

    Can I keep knocking them for their lousy documentation, unsupported libraries, Dilbert-driven technical decisions, and unethical conduct? I used to never knock Microsoft when I was a Java developer. Now that I'm a native coder, I understand.

    --
    I swear to God...I swear to God! That is NOT how you treat your human!
  87. Re:Full Windows on a phone? by DrLang21 · · Score: 1

    Yes

    --
    I see the glass as full with a FoS of 2.
  88. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    Ctrl-Alt-Delete is handled below the explorer.exe level, and so still responds even if explorer.exe does not, but my point was that explorer hanging, as the angry little AC insisted, did not mean you had to reboot.

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  89. Re:Full Windows on a phone? by FishWithAHammer · · Score: 1

    The funniest bit about this whole thing is that my business's products run on LAMP, because it's the best environment for it. I use Windows on the desktop because it works best for me. I don't call it the best one out there (as far as I'm concerned, OS X has that, I just don't feel like paying for a Mac), but all my business applications run on open-source.

    You're a very angry person.

    --
    "You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
  90. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    You seem to be very much in love with your argument and, as such, are unlikely to be swayed by me. However, in true Quixotian fashion...

    I'll try to break this down as simply as possibly so as not to overwhelm you. If someone makes an assertion that cannot be proven one way or another, such as, "in my experience, blah blah blah", you have no choice but to consider the character, hence the trustworthiness of the person making the assertion. Especially on an internet forum where you have practically squat to go on. This is doubly so when that person is making a seemingly dubious claim that flies in the face of your own experience. In this regard, judging whether a person fits the classic pattern of a shill, and if so, pointing this out as conspicuously as possible, is not only being intellectually honest but one would be completely remiss not doing so as early as it becomes apparent. I guess in your world, every opinion is taken completely at face value and the concept of "reading between the lines" doesn't even exist. Your wide-eyed innocence almost touches me.

    I've been around this stuff long enough and have enough common sense and street smarts to know when someone is feeding me a line of bullshit. Anyone that tries to argue against that is either a fool or is in on the deceit himself. Draw your own conclusion from that.

  91. Am I the only one who thought... by Anonymous Coward · · Score: 0

    Amalgamated Regional Militia?

    (Its from the Known Space universe)

  92. Re:Full Windows on a phone? by bhtooefr · · Score: 1

    You're playing a game on your ARM-based netbook away from home - remember, that's what we're talking about here. Not sure what you're playing, Tux Racer, maybe, because that's about all it could handle that runs on Linux. Oh, wait, maybe LBreakout. Anyway, something crashes and you need to SSH into it. Wait, you're on your netbook that you suggested someone buy for the purpose of SSHing into other computers. And you can't set up an ad hoc connection between your cell phone and your netbook because you'd have to SSH in to do that, and last I checked, phones didn't have ethernet or (lately, anyway - yes, I know, Palm OS stuff has them, but you're a Linux beardo that probably has a Freerunner, forget a G1 or a Pre) RS232 ports.

    But this is purely a hypothetical that you wouldn't understand, because you'd have to actually venture out of your mom's basement to encounter such a situation.

  93. Linux vs Windows netbook return rate by Anonymous Coward · · Score: 0

    This article says Linux netbook return rates were high. We keep seeing this. But that doesn't square with what the CEO of Asus reports:

    http://ostatic.com/blog/asus-ceo-says-linux-netbook-returns-on-par-with-windows

    "He says ASUS has found the return rates for the Linux and Windows models are similar. He also said that Linux has been quite popular in the European market."

  94. Re:Full Windows on a phone? by Anonymous Coward · · Score: 0

    You shouldn't be having to confirm to watch a video. If it's a UAC dialog, then you should check to make sure that the viewer you're using isn't writing data out to Program Files or anything, and if it is either swap to a program which is more multiuser friendly or increase your permissions to the location in question.