Slashdot Mirror


ARM Stealthily Rising As a Low-End Contender

snydeq writes "InfoWorld's Neil McAllister examines how the ongoing rise of netbooks, decline of desktops, and the smartphone explosion are reconfiguring the processor market, putting Intel's Atom processor on a clear collision course with ARM. And here, on the low end of computing, Intel may have finally met its match. Thanks to a unique licensing model, ARM will ship an estimated 90 chips per second this year, and the catalog of OSes and apps available for ARM has been growing for decades, including several complete Linux distributions such as Google's Android OS and Chrome OS when it ships. 'One thing ARM doesn't have, however, is Windows,' McAllister writes, something that could ultimately stymie ARM's plans to compete on the low end of the netbook market. And yet Intel's bet on Windows and its x86 compatibility appeal among developers could backfire, McAllister writes. In the end, it's all about performance. Thus far, Intel has yet to demonstrate a model with power characteristics comparable to those of the current generation of ARM chips, which are fast proving their ability to handle high-performance applications."

285 comments

  1. Competition by mhajicek · · Score: 5, Funny

    Still, competitors claim it's mostly 'armless.

    1. Re:Competition by Urza9814 · · Score: 1

      ...and it doesn't have a leg to stand on

    2. Re:Competition by Anonymous Coward · · Score: 0

      so, that makes it a torso?

  2. ARM/Linux in the Tesla Roadster by Rei · · Score: 5, Informative

    To tie in with an earlier article on the front page: the Tesla Roadster's battery pack management system is ARM-based. It's built around a Philips-LPC2294 with 32 megs of ram and a 1GB U3 Cruzer Micro USB flash drive, running Linux kernel 2.6.11.8-1.3.0.

    --
    Look at me, still talking while there's science to do.
    1. Re:ARM/Linux in the Tesla Roadster by mollog · · Score: 3, Interesting

      The article says that a port of Windows could be important to the future of ARM, and that Microsoft has no plans to do such a port. (Does anybody remember when Windows NT was supposed to be ported to DEC alpha, HP PA-RISC, and IBM PowerPC?). But why, exactly, does a consumer want Windows? For Excel? Word?

      Seems like Linux will fill the bill with a browser, maybe a PostScript app and a media player. Text editing isn't such an elaborate thing these days. And only a few people even know what to do with Excel.

      Sounds like ARM is to Intel the way that Linux is to Microsoft; a threat coming from the low-end.

      Speaking of apps, seems like iPhone and the like are coming up with apps that don't run on Windows. Do we really need, or even want, Windows any more?

      So, what we need is a netbook with ARM, running Linux, to serve as a model for future application development.

      --
      Best regards.
    2. Re:ARM/Linux in the Tesla Roadster by Korin43 · · Score: 2, Insightful
      The three biggest reasons I can think of for using Windows are:
      • Drivers - Presumably anyone selling a netbook with Linux on it would go to the trouble of writing drivers
      • Games - As if you could play games on a netbook..
      • Photshop - Same as above
    3. Re:ARM/Linux in the Tesla Roadster by Abreu · · Score: 1

      So, what we need is a netbook with ARM, running Linux, to serve as a model for future application development.

      Indeed. I have an Atom-based Netbook

      Wish I could buy an ARM-based one

      But none are available (at least none in my country)

      --
      No sig for the moment.
    4. Re:ARM/Linux in the Tesla Roadster by Anonymous Coward · · Score: 0

      I immediately understood from this that we should be running Windows on the Tesla Roadster battery packs!

      Advantages:
      - More familiary and ease of programming by developers of battery pack applications
      - A user friendly environment
      - Friendly environmental users
      - Environmentally user friendly
      - Comes with MS support hence increased reliability

    5. Re:ARM/Linux in the Tesla Roadster by Aliencow · · Score: 2, Informative

      Supposed to be ported to Alpha as 'Was sold for Alpha' ?

    6. Re:ARM/Linux in the Tesla Roadster by shutdown+-p+now · · Score: 4, Interesting

      The article says that a port of Windows could be important to the future of ARM, and that Microsoft has no plans to do such a port. (Does anybody remember when Windows NT was supposed to be ported to DEC alpha, HP PA-RISC, and IBM PowerPC?).

      Thing is, there may not be such public plans today, but don't think it would take all that long should MS change its mind. NT was designed from ground up to be portable; heck, its early builds ran on Alpha before they did on x86. And it wasn't "supposed" to be ported to MIPS and Alpha and PowerPC - it was ported to all those platforms, and successfully ran there, though that configuration was never popular, and so support was dropped in W2K.

      In fact, a version of NT running on PowerPC still exists today - it's the nameless OS inside Xbox 360...

      Software for a hypothetical Windows ARM port is a more interesting topic. Of course, you can be sure that most Microsoft software - most importantly, IE and Office - would be ported right away. For other stuff, it may not be as hard as it seems - it's not the 90s anymore, and you don't see many people hand-coding asm for performance, or using dirty architecture-specific tricks. Windows went through multi-architecture support pains when x64 and Itanium were introduced - and it was a lot of headache back then, because of all the bad code that assumed sizeof(void*)==sizeof(int) etc - so now the tools are there to handle a transition (C++ compiler will give warnings for nonportable constructs, for example), code for most products that are still being developed had been cleaned up, etc. It's still not quite just a recompile away, but it's close enough.

      Which means that pretty much every application that is actively developed for Windows today, you'd probably see ported to ARM in short time should there be demand: Flash, Quicken, new game releases...

    7. Re:ARM/Linux in the Tesla Roadster by Anonymous Coward · · Score: 1, Interesting

      ARM is the sort of thing that'll blindside Microsoft the way netbooks recently did. Cheap XP licenses for netbooks came about specifically because there were a bunch of popular linux netbooks, after which point MS decided they really needed to grab that new market and/or bump linux out of a market. That was the netbook panic point for MS, and if there end up being lots of cheap long-battery-life ARM netbooks running linux, that'll be the next panic point for MS. That'll be when we see an ARM windows.

      Intel's panic point comes after ARM windows, because if people get used to those ARM windows netbooks, we'll start seeing full fledged ARM windows laptops. If Intel gets totally asleep at the wheel we may even see full fledged ARM windows desktops.

      I would expect, though, that sometime before that Intel would try for a cross licensing deal with ARM - because once there's an ARM windows, it would be easier for intel to start building up on the existing ARM stuff than it would be for them to get x86 all the way down into ARM's stronghold. The atom isn't managing it, otherwise we wouldn't be having this conversation.

    8. Re:ARM/Linux in the Tesla Roadster by cbhacking · · Score: 4, Informative

      Between versions 3.5 and 5.0 (Windows 2000), NT was actually ported to several other architectures, including PowerPC and Alpha. None of them were particularly successful commercially, and from what I heard, the Alpha port was killed by in-fighting between Microsoft, DEC, and (IIRC) Compaq. The only non-x86-derived (and on RISC architecture) port of NT currently maintained is Itanium (ia64).

      There's no architectural reason why NT couldn't be ported to ARM, and I actually think it would be a good move to replace the WinCE kernel with a ported branch of the NT kernel optimized for smartphones. They could even keep backward compatibility with WinMo by using a WinMo subsystem (similar to the way that NT is compatible with both Win32 and POSIX by way of subsystem - the kernel doesn't directly handle Win32 or POSIX syscalls, they instead both get translated to NT syscalls which are designed to accommodate just about any API). This would also let Microsoft remain relevant on ARM-based netbooks, provided they port the Win32 subsystem (yes, applicaitons would need to be re-compiled, but for many apps that's all it would take).

      --
      There's no place I could be, since I've found Serenity...
    9. Re:ARM/Linux in the Tesla Roadster by ozmanjusri · · Score: 1
      Games - As if you could play games on a netbook..

      Right...

      And there's no games available for the iPhone either.

      Photshop - Same as above

      Gee, I guess there must be millions of businesses all over the world supplying their clerical staff with Windows/'Photshop'.
      And here's me thinking they were sticking to Microsoft because of document format lockin.

      --
      "I've got more toys than Teruhisa Kitahara."
    10. Re:ARM/Linux in the Tesla Roadster by jkrise · · Score: 3, Interesting

      While what you say is a valid point indeed, if Intel sees MS supporting ARM; it will immediately (and with much better success) come up with a much less power hungry Linux and make a separate processor for that. All the lock-ins such as ACPI etc which MS and Intel worked hand in glove will come crashing suddenly, when Intel's blood is running cold.

      --
      If you keep throwing chairs, one day you'll break windows....
    11. Re:ARM/Linux in the Tesla Roadster by CAIMLAS · · Score: 2, Funny

      running Linux kernel 2.6.11.8-1.3.0.

      Oh, THAT kernel version! Yes, I know exactly what it means.

      I mean, seriously folks. I've been using Linux regularly since '98, on servers since 2000, and almost exclusively for personal use since around 2001. WTF does that kernel version even mean?

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    12. Re:ARM/Linux in the Tesla Roadster by CAIMLAS · · Score: 1

      But why, exactly, does a consumer want Windows? For Excel? Word?

      For the same reason they need a Ford, Dremel, Dell, Whirlpool, Frigidaire, Coleman, and so on: because it's a known quantity (or so they think), or at least a quantity with a known name behind it which might have a reputation to uphold.

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    13. Re:ARM/Linux in the Tesla Roadster by npsimons · · Score: 1

      Do we really need, or even want, Windows any more?

      Some of us haven't needed Windows for years, and haven't *wanted* it for even longer. The only reason I even know that Windows even exists is that I have to support it for my users at work.

    14. Re:ARM/Linux in the Tesla Roadster by Anonymous Coward · · Score: 1, Insightful

      Half Life, Company of Heroes, World of Warcraft, etc. No games is a deal breaker for a lot of people.

      100% familiarity with the computer one uses all day at work is another deal breaker for a lot of people. If you have more money than time a few hours wages to mean your home computer is not ever going to deviate from what you know is money very well spent.

      The family tech support guy only knows Windows so buying anything else means figuring stuff out on ones own.

      There are plenty of reasons that may feel insignificant to you, but too many any one can be non-negotiable.

    15. Re:ARM/Linux in the Tesla Roadster by Meski · · Score: 1

      The article says that a port of Windows could be important to the future of ARM, and that Microsoft has no plans to do such a port. (Does anybody remember when Windows NT was supposed to be ported to DEC alpha, HP PA-RISC, and IBM PowerPC?). But why, exactly, does a consumer want Windows? For Excel? Word?

      As I recall, earlier versions of NT did run on MIPS, Alpha, PowerPC as well as Intel. They got dropped at about NT 4.

    16. Re:ARM/Linux in the Tesla Roadster by Cochonou · · Score: 1

      For "simple" games, I think the main point is flash support. If these ARM/Linux combo computer support flash with good performance, then it will cater to the gaming needs of most people on such a low-end machine.

    17. Re:ARM/Linux in the Tesla Roadster by dave87656 · · Score: 1

      Heh?

      Comes with MS support hence increased reliability

      Where did you get the increased reliability idea? We have about 10 Windows boxes in our shop and about 70 Linux boxes. We have no reliability problems with Linux and virtually no support costs once they are setup. We spend most of our time on the Windows boxes. Anyone who talks about "increased reliablity" on Windows is living on a different planet.

    18. Re:ARM/Linux in the Tesla Roadster by PitaBred · · Score: 1

      The most popular games in the world to play are Flash games and Solitaire type stuff. There are lots of games you can play without having a dedicated GPU, and they're the types of games that the non-techies flock to (Popcap, etc.)

    19. Re:ARM/Linux in the Tesla Roadster by JAlexoi · · Score: 1

      Do we really need, or even want, Windows any more?

      Yes, we still need windows doors and other holes in the walls to get into our houses :)

    20. Re:ARM/Linux in the Tesla Roadster by westlake · · Score: 1

      But why, exactly, does a consumer want Windows? For Excel? Word?

      For any one of the gazillion or so home and office apps released for the MSDOS and Windows platform since 1980?

      GOG.com

      And only a few people even know what to do with Excel.

      The reality is that training in MS Office is a marketable skill anywhere south of the Arctic Circle.

      I'd take the odds that MS Office lies at or near the core of any adult education program within your reach.

      That training will be free or generously subsidized for seniors, those on welfare or with disabilities.

      Seems like Linux will fill the bill with a browser, maybe a PostScript app and a media player

      The geek re-invents the net appliance every other year or so --- and gets his butt kicked the moment a more capable product enters the market.

      The iPhone on the Internet has a 0.35% share of the market. Operating System Market Share

      But it is an expensive commitment.

    21. Re:ARM/Linux in the Tesla Roadster by Mattsson · · Score: 2, Insightful

      Seems like Linux will fill the bill with a browser, maybe a PostScript app and a media player. Text editing isn't such an elaborate thing these days. And only a few people even know what to do with Excel.

      And most peoples "MS Office needs" can be met with Open Office. That people "require" MS Office has mostly to do with laziness (too much work learning a new program) and myths (you must have MS Office, otherwise you're not compatible).
      The funny thing is, going from MS Office 2003 to MS Office 2007 has a steeper learning curve than going MS Office 2003 to Open Office and has more or less the same compatibility issues.

      --
      /.Mattsson - My native language is not English, so please don't whine over linguistic errors. (That's lame anyway...)
    22. Re:ARM/Linux in the Tesla Roadster by Anonymous Coward · · Score: 0

      You obviously missed the joke.

    23. Re:ARM/Linux in the Tesla Roadster by HoppQ · · Score: 2

      The three biggest reasons I can think of for using Windows are:

      • Drivers - Presumably anyone selling a netbook with Linux on it would go to the trouble of writing drivers

      Well, they'd save some work by going with Linux, since Linux has more drivers for ARM than Windows (which has none).

      --
      My sig will be released in 2015 third quarter. Rating pending.
    24. Re:ARM/Linux in the Tesla Roadster by pseudonomous · · Score: 1

      I think it's safe to say that that one came somewhere after 2.6.10.something and before 2.6.11.something, and that it's not a vanilla kernel (because then it would be just 2.6.11.8) but rather a patched version of the kernel.

    25. Re:ARM/Linux in the Tesla Roadster by Serious+Callers+Only · · Score: 1

      For any one of the gazillion or so home and office apps released for the MSDOS and Windows platform since 1980?

      Which will not run on ARM.

      Also, most of them won't even run on Windows 7 without modification.

      I'd take the odds that MS Office lies at or near the core of any adult education program within your reach.

      Those skills are transferrable to any comparable program. Word processing et al are not fundamentally difficult or tied to using products from Microsoft, whatever Microsoft would have you believe. If you feel unable to transfer skills learned using one brand of word processor to another, then PEBCAK.

      The geek re-invents the net appliance every other year or so --- and gets his butt kicked the moment a more capable product enters the market.

      Windows doesn't even compete in this space currently, and it is debatable whether they ever will. Their current mobile effort (Windows Mobile or whatever they call it now) is very low quality, and certainly not more capable than competitors like Android or Maemo, which are also moving into the net appliance space with very capable offerings.

    26. Re:ARM/Linux in the Tesla Roadster by Korin43 · · Score: 1

      Yes, exactly the kind of games that run fine on Linux. When I said "games" I thought it was implied that I was talking about games that only work on Windows (because those are the games that would keep you stuck on Windows).

    27. Re:ARM/Linux in the Tesla Roadster by Korin43 · · Score: 1

      Games - As if you could play games on a netbook..
      Right...
      And there's no games available for the iPhone either.

      Apparently it's not obvious enough from the context, but when I say games are a reason for staying with Windows, I mean games for Windows don't work on Linux (for the most part). Sorry for not making that explicit. Yes you can write new games, but people want the games they have to work, and getting big budget games to work on Linux would require a massive shift. Luckily, the kind of games that people want to play but don't work on Linux tend to be the kind of games that wouldn't run on a netbook.

      Gee, I guess there must be millions of businesses all over the world supplying their clerical staff with Windows/'Photshop'.
      And here's me thinking they were sticking to Microsoft because of document format lockin.

      I assume you mean people who embed VB scripts in the excel documents? I suppose that's another use for Windows, but I seriously hope no one has to type up Excel documents all day on a netbook -- which is the situation I was talking about, so same response as Photoshop. For other uses of MS Office files, OpenOffice opens them fine. Impress/Powerpoint compatibility is pretty crappy too, but most people give their presentations from their own laptop, so you could just give the presentation in Impress.

      And I think format lock-in has very little to do with it. The reason businesses use Windows is because their systems administrators aren't familiar with Linux (and retraining everyone is more expensive than a Windows license), or because someone high up in the company has been drinking too much of the Microsoft Kool-Aid XP.

    28. Re:ARM/Linux in the Tesla Roadster by atilla+filiz · · Score: 1

      Even if there was an ARM port of WinXP, "Games for Windows" would not work on it because all of them are compiled for x86.

    29. Re:ARM/Linux in the Tesla Roadster by jonadab · · Score: 1

      > [Win NT] Supposed to be ported to Alpha as 'Was sold for Alpha' ?

      Theoretically was, but have you ever *seen* a copy of it?

      I've seen VMS, but I've never seen the Alpha port of NT. I think "offered for sale" might be a better description than "sold", because as near as I can tell, nobody actually bought it.

      --
      Cut that out, or I will ship you to Norilsk in a box.
    30. Re:ARM/Linux in the Tesla Roadster by marcosdumay · · Score: 1

      Well, Microsoft has a small windows of oportunity here, once Linux is stablished, they won't be able to take that market back. They won't be able to push a Cairo or Longhorn here, since several years of development will mean they'll lose that window. If history is any guide, MS should better already have a long ongoing work on porting their OS.

    31. Re:ARM/Linux in the Tesla Roadster by Johnny+O · · Score: 1

      I installed NT on a DEC Alpha. So I can safely put that on my resume as my only Windows experience. Few days later I wiped it and installed OSF/1 so I could do something useful with the machine. But there definitely was a port for Alpha and it worked (as in installed). I'm not sure my company bought it. Maybe it was a demo. We were definitely just a OSF/1, SCO, Linux, OS/2, & VMS shop. No real use for NT.

    32. Re:ARM/Linux in the Tesla Roadster by b0bby · · Score: 1

      But why, exactly, does a consumer want Windows? For Excel? Word?

      Here's what I do with my netbook:
      Simple browsing - Linux works fine (but is ARM flash support as good? My kids request YouTube funny cats videos on a regular basis)
      Email - Linux works fine, using Outlook Web Access is much better with IE
      Watching movies while travelling - Linux works ok, with some issues with sound & volume levels
      Importing AVCHD files from camcorder while traveling - Could be done with Linux but more awkward
      Dreamweaver - I haven't found a WYSIWYG editor for Linux that is as easy to use as even a very old version of Dreamweaver.
      So I bought an XP EEE, and have Ubuntu on an SD card for when I want it. For most of what I want to do, XP is easier or the same; nothing I want to do regularly is actually easier in Linux. And most of the shell scripting stuff I ever do in Linux, I can do with Cygwin.

    33. Re:ARM/Linux in the Tesla Roadster by C0vardeAn0nim0 · · Score: 1

      (yes, applicaitons would need to be re-compiled, but for many apps that's all it would take).

      it's not that simple. this porting howto from handhelds.org have some good info on the subject:

      http://handhelds.org/minihowto/porting-software.html

      the most important issue there when porting from x86 to arm is the pointer alignement thing.

      --
      What ? Me, worry ?
    34. Re:ARM/Linux in the Tesla Roadster by snadrus · · Score: 1

      If you really don't know...

      o Drivers - Since Vista, Linux has supported more hardware than Windows. Specifically for Netbooks you have the all-Intel Atom which Intel has already written drivers 100% for, and you (may) have ARM which has had Linux as its target platform for years.
      o Games - Iphone games don't need Windows, Linux has 100s of open source games for the casual gamer. Oh, and don't forget Wii, PS3, DSi, etc that don't need Windows.
      o Photoshop - Image Editing isn't magic anymore and even if you haven't seen Gimp in a few years, there are many free & paid replacements.

      My concerns for Linux Netbooks are:
      o AutoCad (there are some replacements, but it has as much lockin as Word),
      o QuickBooks (no business that does taxes can escape the fact that it's the only way to work with an outside accountant. At-least individuals have online tax prep software. )

      --
      Science & open-source build trust from peer review. Learn systems you can trust.
    35. Re:ARM/Linux in the Tesla Roadster by bigngamer92 · · Score: 1

      o Interface - People don't want to learn a new "kiddie"/"simplistic" interface on a OS that doesn't run their normal software

    36. Re:ARM/Linux in the Tesla Roadster by someSnarkyBastard · · Score: 1

      Not to troll here but refutations are in order... Drivers - You are aware that most currently-available netbooks run on an Intel 950 GMA, which last I checked, has closed source binary drivers that break on recent kernels, right??? And don't even get me started on the state of wireless on Linux... Games - There are plenty of people who like playing peggle and bookworm, both of which would easily be supported by the hardware in a netbook. Photoshop - People don't know or care that their cute little netbook cannot properly run Photoshop, they will still want it anyways.

    37. Re:ARM/Linux in the Tesla Roadster by Anonymous Coward · · Score: 0

      There were never any plans to port Windows NT to PA-RISC. Windows NT did originally run on i386, Alpha, PowerPC, and MIPS chips. The PowerPC and MIPS ports were dumped after NT4, and Alpha after Windows 2000. And FWIW, I think that if ARM becomes a serious competitor to Atom, to the point where it's going to start costing Microsoft a significant loss in market share, Microsoft will make an ARM port of Windows. In fact, I wouldn't be surprised if they already have a project working on it. Companies like Microsoft (and Apple, IBM, etc.) start many projects as a hedge against changes in the marketplace. If those changes don't happen, the results of those projects never see the light of day. Occasionally they do, and Windows for ARM could be one that does.

    38. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      Windows itself may even be a questionably thing in today's market. If you're talking about WinCE, it's already on ARM, and not a leading applications platform, largely due to Microsoft not pushing that for a decade or so. On the desktop, there's no binary compatibility, and at least for the present, ARM could never compete except against low-end Netbooks.

      The simple fact is that ARM is everywhere else. Some years back, I designed a high-end digital radio controller using a single TI MSP430 microcontroller. It worked fine, but the memory capacity on the device (60K Flash) was a limiting factor. The replacement for that radio controller had not one but two NXP ARM microcontrollers (one 256K flash, one 32K flash)... it sold for $200 less (MSRP), and the total cost of a USB solution was less (and much faster) with the ARM. They have not entirely conquered embedded, but they're strong on everything between 8-bit and desktop-class, already.

      So while I think ARM could eventually move to the desktop, I think the real interesting thing here is that the desktop is more likely moving to the ARM. When personal computing began, everyone needed a personal computer, on the desktop... there was no other way. Today, there are already a class of people doing more traditional computer stuff on their "phones"... which aren't any just phones, anymore than a PC is just a wordprocessor. The latest generation of "phone" had 500-1000MHz CPU, with >VGA class screens, 3D video acceleration, etc.

      In the not too distant future (in the USA.. this is already happening in Japan), many users will consider the "pocket computer" as their primary computing device. When you get home, drop it into the charger/cradle, and it'll hook into a regular monitor, keyboard, mouse, etc. That device will be ARM based. Those who need more computation power than the "phone" can provide might easily tape the CPU power of their games console or Blu-Ray player.. no real need for that, usually, in a mobile situation. One the internet connections are fast enough, this could be done "in the cloud", too... just like the data storage the modern mobile systems (Android, Palm WebOS) are already tapping for mobile computing.

      This is an ideal time to keep Windows out of the way mainstream mobile computing is headed, and eventually, mainstream computing. No, it won't replace all desktop PCs, but really, there are only so many desktop users who really have any use for a quad-processor 3GHz PC anyway. And while I have one of these, I'm looking toward the mobile device becoming more of a central device for "regular" computing, and the PC for the workstation class stuff... NOW.

      --
      -Dave Haynie
    39. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      Indeed... Linux is starting to benefit from the long history of a consistent driver model.

      When a new version of Windows comes out, more often than not, the driver model has changed. Microsoft may have the occasional legit reason for changing the driver model, but unless the current model is seriously broken (and after a half dozen "this breaks" revisions, you would think they finally have it right.. only, it's changed again for Win7), they could simply add additional functions... old drivers still work, new ones offer new features.

      The problem here, from MS's point of view, is that drivers have been a magnificent lever in implementing MS's policies. When MS sells Windows to OEMs (Dell, Sony, HP, Toshiba, etc), they get a discounted price that'd dependent on every driver shipped in a new PC of any kind having passed MS's driver certification. This isn't really a test against buggy drivers (though that's how it's sold), but a test of toeing the line. The end result is that no one without current, certified drivers gets in any new PC. To a lesser effect, they also don't get that shiny "Made for Windows" sticker on the retail box. This is also the reason that pretty much all Windows hardware ships with old drivers.

      So, there might have been no problem in running XP drivers in Vista or Win7. But when XP came out, 64-bit support was optional. In Vista, it was mandatory... can't get certification without it. So, to get all that stuff written, they force everyone to revise every driver. With Win7, they didn't entirely break the model, but they added features to some drivers.. many things HAD to be rewritten. The hardware companies put up with this because [a] Microsoft is the 8,000lbs gorilla, and [b] in doing this, they're weeding out perfectly good older hardware, so at least some hardware vendors will benefit.

      But the bottom line is that supporting new versions of Linux is easy, once you get that knowledge in-house. There may be no reason to update drivers very often, and so they build a collection of good drivers. Given these don't need to be revised, the stuff that does need revision, and particularly the new stuff, can be released faster, even with fewer people on the job.

      I think we're also potentially poised on a "Great Awakening" about the advantages of Open Source. That's been understood, behind the scenes, among server people and embedded device companies, but Android, for one, is going to break this wide open -- Android will be the thing that knocks out Apple and RIM in the smart phone business... that business that is currently defining the major computing platform of the future. Netbook and even desktop companies will need to learn from this.. the successful ones will.

      --
      -Dave Haynie
    40. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      Actually, NT was on the MIPS first, thank to NEC championing the ARC initiative, which defined a MIPS-based platform as an x86 alternative. After that, there were x86, Alpha, and PowerPC ports in public, and a long rumored SPARC port.

      NT on the low-level did many things wright. They defined a HAL (Hardware Abstraction Layer) which, when used correctly, accounts for driver-level differences in machine architecture, even things like endian-ness.

      The big problem in the non-x86 market for NT was that Microsoft didn't write these, they just enabled them. So, for example, Motorola did the NT port to PowerPC. They had to pay Microsoft millions for the opportunity. Even the MIPS version, while started at Microsoft, was spun out to NEC's control. DEC did the Alpha port... one reason why DEC's was the only version that also ran some x86 32-bit binaries (they provided a dynamic code translation mechanism, no one else did).

      I would put MS's moving Windows to ARM as a self-preservation move... but maybe too late already. ARM is flourishing on open source software, and the only time anyone even mentions Windows is when ARMs are pushed up into competition with x86s. But they pretty much already own most of the rest of computing. The reason is simple: they're the IBM PC of the CPU world.

      The PC didn't succeed because it was a good design... it was initially a horrible design. It won early on through a few market factors (the IBM name, the math chip's effect on the use of spreadsheets as models), but it dominated because no single entity had control.. anyone could make a PC. Today, since Advanced RISC Machines has chosen to just remain a design center, not a manufacturer, anyone can make an ARM chip. After a decade+ of that, it's awfully hard to find a significant electronic device powered by something else. There are billion of ARMS sold per year.

      Windows might have a shot on ARM-based netbooks, and perhaps if ARM chips upscale to be even more into x86 territory. But it fails in all of the big market things ARM is doing well today, some of which, like pocket computers (eg, smartphones), even WinCE has largely failed. These are going to be the future of computing for many users, not PCs.

      --
      -Dave Haynie
    41. Re:ARM/Linux in the Tesla Roadster by shutdown+-p+now · · Score: 1

      Windows might have a shot on ARM-based netbooks, and perhaps if ARM chips upscale to be even more into x86 territory. But it fails in all of the big market things ARM is doing well today, some of which, like pocket computers (eg, smartphones), even WinCE has largely failed.

      I agree here. I was definitely speaking in "direct desktop competition" (i.e. netbooks, currently) context, not ARM in general.

      These are going to be the future of computing for many users, not PCs.

      And here I have to disagree. I don't believe that smartphones and their ilk will replace PC for the majority of tasks. Even for surfing, a PC (or netbook) is still way more convenient; and it also has the advantage of offering many more opportunities - e.g. you can actually view videos at decent size on a netbook. Of course, any kind of office work requires a bigger screen, too. So I don't think this market segment is going away, or even significantly shrinking, anytime soon.

    42. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      There is a great big potential for games on ARM machines. Not in direct competition with the PC, but as an alternative.

      Gaming is big... an estimated $57 billion in 2009. PC gaming is a big chunk, sure... about $11 billion. But that ought to tell you... PCs are not the dominant form of gaming anymore, even if they're the largest single platform, in terms of dollars.

      Witness the example of the Wii... it doesn't really compare to the X-Box 360, PS3, or a PC in gaming... yet it's been remarkably successful. Why? It changed the model, created a new sector of gaming that doesn't count so much on hardware power. Look at Wii Fit... that's doing about $20 million per week, internationally.. sold over 20 million units, about $2 billion in total sales. No one would have even considered that a reasonably risk in the PC gaming world. Same with the GameBoy (ARM-based, since the Gameboy Advance).

      The iPhone (ARM too) has done well... over $250 million in gaming sales from 2008-2009. Not PC big, but consider, these are $1-$5 games, largely. And this is more digital download revenue than any console platform to date. Current estimates put handheld gaming at about $12 billion by 2014... certainly on par with the PC of today... we'll bave to see if PC games sales drop or increase in the next five years. And "handheld" means nearly all ARM based. They also currently expect Apple to own about 25% of that gaming market.

      --
      -Dave Haynie
    43. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      MIPS was the first version of NT.. the x86 version was ported from that. Not much more than a historical footnote anyway, since they were both done by the time NT actually shipped to end users.

      Windows NT 4.0 was supported under active contracts in the day (mid 1990s). It was the move to Windows 2000 (NT 5) that caused the problems. Microsoft never did much if any of the porting work anyway, it was all done at other companies. By Win2K development time (late 1990s), they decided to ask for something in excess of $25 million from NEC (MIPS), DEC (Alpha), and Motorola (PowerPC) to allow these companies to do all the work needed to let Microsoft sell Windows 2000 on those various platforms.

      I was working closely with Motorola at the time. Windows NT represented less than 5% of their sales within the StarMax (PPC desktop PCs) lines, and even less from partner IBM. Plus, they were high on the crack Apple had been selling them about MacOS compatibility. So they nixed this, as did the others.

      I do recall rumors of both PA-RISC and SPARC ports. I don't know if any of those were real.

      --
      -Dave Haynie
    44. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      That people "require" MS Office has mostly to do with a lack of eduction... the vast majority of PC users don't know a thing about MS Office, or FOSS in general. Or, for that matter, anything that's not firmly entrenched in consumer product advertising. They know Coke and Pepsi, not so much Maine Root, Vignette, or Boylan's. They know Budweiser and Miller, not Flying Fish, Anchor, or Rogue.

      On computers, they haven't even been shown that the OS is a choice -- regular folks think "Windows" == PC, and their only alternative is a Mac... also just a PC these days, but that subtlety is even lost on most Mac users. Where will they even hear about Open Office, except maybe when one of us installs it for them. And once done, prepare to support it...

      --
      -Dave Haynie
    45. Re:ARM/Linux in the Tesla Roadster by hazydave · · Score: 1

      Whoops... should have read "don't know a thing about Open Office".. you figured that out, I'm sure.

      --
      -Dave Haynie
    46. Re:ARM/Linux in the Tesla Roadster by vadim_t · · Score: 1

      No, Linux is benefitting from Open Source drivers.

      The internal kernel API changes whenever needed, they just fix every driver as well, since they can. And Microsoft can't, so each new API obsoletes everything before it, unless the manufacturer does the work, and they rarely have any incentive.

    47. Re:ARM/Linux in the Tesla Roadster by Anonymous Coward · · Score: 0

      its an old ass kernel. today's kernel is at 2.6.30.foo (foo for I am not sure after that). I am guessing tesla managed to quash all the bugs and decided to not do anything else as it worked fine.

    48. Re:ARM/Linux in the Tesla Roadster by Mattsson · · Score: 1

      But when buying a ARM computer, you don't have to choose Linux as the OS. It is chosen for you when you select that product.
      The problem isn't those who doesn't know that they can choose to run Linux and/or Open Office on their Intel/AMD computers, the problem is those who buy a ARM computer and then goes back to the store complaining about how it can't run Office (MS Office) or Internet (Internet Explorer. MS did a really slick move when they managed to equal "Internet"=="Internet Explorer" in the minds of the masses).

      --
      /.Mattsson - My native language is not English, so please don't whine over linguistic errors. (That's lame anyway...)
  3. MAME by Anonymous Coward · · Score: 0

    Just release MAME for a popular ARM motherboard.

    1. Re:MAME by Nuno+Sa · · Score: 1

      I think we need PC-like motherboards. Mini-itx or even uATX. With slots for real RAM, PCI(e) and such.

      My previous comment on this very subject a few days ago.

  4. So, where are ARM netbooks? by should_be_linear · · Score: 3, Interesting

    I am yet to see any. If they only at least produced one for each article declaring ARM ubiquitous winner at low-end netbooks....

    --
    839*929
    1. Re:So, where are ARM netbooks? by jedidiah · · Score: 1

      This is from the "vaporware = product" crowd that get excited just because something has been announced or might be available in Akihabra.

      It may or may not be real in 6 months.

      --
      A Pirate and a Puritan look the same on a balance sheet.
    2. Re:So, where are ARM netbooks? by Anonymous Coward · · Score: 5, Informative

      http://www.alwaysinnovating.com/touchbook/

    3. Re:So, where are ARM netbooks? by RichMan · · Score: 0, Offtopic

      "I have yet to see any." Then you are not looking. It seems last year there were many. It seems there are fewer this year but still.

      An example -

      Go to www.dell.com
      Select "for home"
      select "laptop/notebook"
      select "OS Ubuntu"

      Tada :

      http://www1.ca.dell.com/ca/en/home/Laptops/laptop-inspiron-10/pd.aspx?refid=laptop-inspiron-10&s=dhs&cs=cadhs1&~oid=ca~en~70702~inspnnb_10vu_en_feat_1~~

    4. Re:So, where are ARM netbooks? by fuzzyfuzzyfungus · · Score: 4, Informative

      There are a few things; but mostly obscure or dubiously suitable. The Touchbook (not toughbook) still has a touch of beta about it; but you can actually order one. The Sharp PC-Z1 has a bad case of obscure and japanese; but otherwise exists. You can also get a number of super cheap ARM based netbooks from various random Chinese outfits. Trouble is, most of those are basically the WinCE PDAs of a couple of years back, stuck into a netbook shell. Truly dire specs are the order of the day.

      I'm frankly a bit surprised. You can get beagleboards and shivaplugs, with pretty credible ARM based specs, for not all that much even in small quantities, and ARM based smartphones are all over the place, so the field seems surprisingly thin on the netbook side.

    5. Re:So, where are ARM netbooks? by royallthefourth · · Score: 1

      I went to that link. It has an Intel Atom CPU.

      WTF are you talking about?

    6. Re:So, where are ARM netbooks? by Anonymous Coward · · Score: 0

      A4, 1992. Newfag.

    7. Re:So, where are ARM netbooks? by Nadaka · · Score: 1

      You can roll your own with with a beagle board or gumstix plus a lot of hard hacking. Unfortunately the economies of scale mean you won't save any money, you would end up spending something like $500 to $700 plus a few weekends of research and work to put something together that would have about half the power of a standard netbook (possibly with the exception of hardware accelerated video thanks to the secondary features of the OMAP 3530 system on a chip).

      The next year or so should see more powerful ARM chips on the market.

    8. Re:So, where are ARM netbooks? by Anonymous Coward · · Score: 0

      So which will we see first: ARM netbooks or the year of Linux on the desktop? My prediction: neither.

    9. Re:So, where are ARM netbooks? by phantomcircuit · · Score: 1

      Where can I buy that? oh right I cant.

    10. Re:So, where are ARM netbooks? by tchuladdiass · · Score: 3, Interesting

      I've been thinking about this. What I've got planned so far:
      Beagle board -- $150
      800x480 - 1024x??? 7" - 10" LCD -- ???
      Battery pack with charger -- $20 to $40
      Small USB keyboard -- $20 to $80
      Trapper Keeper to use as a housing -- $10

      I'm not sure where to get an appropriate LCD. I'd like to find one that can use 5 volt and DVI input, otherwise I'd have to run a ribbon cable and bypass the DVI controller on the Beagle Board. They shouldn't cost too much, as I see 800x480 Photo Frames going for $80. I've also seen several "cell phone extenders" that output 5v and have an a/c charger. There's also the rechargeable USB hub from CyberPower. For a keyboard I could either use one that is meant for a data center 19" rack, or get one of the many other mini keyboards that are available. And finally if I house everything in a zippered 8x11 binder then I'd have a built-in carrying case.

      Of course for $300 I could get the Touch book without a keyboard, add my own mini keyboard & carry it in the same zippered binder.

    11. Re:So, where are ARM netbooks? by ingsocsoc · · Score: 1

      Unfortunately, it's still very beta. They're shipping out a bracket that will stop it falling over due to being top heavy. It blows my mind to think how this got through testing! The software isn't very good and I wish they would just ship it with Ubuntu instead of trying to roll their own.

    12. Re:So, where are ARM netbooks? by MichaelSmith · · Score: 3, Interesting

      so the field seems surprisingly thin on the netbook side.

      ...because windows doesn't run on it.

    13. Re:So, where are ARM netbooks? by musicalwoods · · Score: 1

      Huh, there is this funny little button that says "Buy" on the site.

    14. Re:So, where are ARM netbooks? by Anonymous Coward · · Score: 0

      I am yet to see any. If they only at least produced one for each article declaring ARM ubiquitous winner at low-end netbooks....

      http://www.pcworld.com/businesscenter/article/171560/foxconn_developing_inexpensive_armbased_smartbooks.html

      http://www.reghardware.co.uk/2009/09/08/foxconn_cheap_arm_netbooks/

    15. Re:So, where are ARM netbooks? by CAIMLAS · · Score: 1

      Wait for it, wait for it... $399 for one with a keyboard (twice the Mini-9), and I'm stuck with a "red backcover". And the Mini-9 appears to be getting phased out in preference for a Mini-10, at that.

      Sorry, that's about $100 too expensive, even with a touchscreen. It's got a 1024x600 8.9" display (which is smaller than most netbooks now). What happened to "ARM processors are cheap"? (Oh, and 3lb?)

      The only thing it really seems to offer is 10 hours of battery life. That's nice, but it's only marginally higher than most netbooks these days.

      Don't get me wrong: I'm waiting with baited breath for one of these devices which is actually within the "I can justify" price range ($200 sounds about right, or even a little steep). They need an economy of scale to make these things go anywhere, and unfortunately there simply isn't enough large industry support to push them to the point of acceptance.

      Put a user-friendly Linux distro on them and sell them at Best Buy for $189 as a portable multimedia internet device and they'll fly off the shelves.

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    16. Re:So, where are ARM netbooks? by JAlexoi · · Score: 3, Insightful

      No. Because the manufacturers still think that "It will run Windows" is the best advertising and marketing strategy. Yet, iPhone and Chinese derivatives are fine without it. All of them should rethink their market research. Most people need nothing more than a browser, email reader and flash on their netbooks. I can name a lot of people that are IT professionals and people that are IT unaware, that use nothing more. Those that need windows software, should just go for another device.

    17. Re:So, where are ARM netbooks? by risom · · Score: 1

      I've been thinking about this. What I've got planned so far: Beagle board -- $150 800x480 - 1024x??? 7" - 10" LCD -- ??? Battery pack with charger -- $20 to $40 Small USB keyboard -- $20 to $80 Trapper Keeper to use as a housing -- $10

      Check out the SmartQ 7 - it does everything you want (minus the keyboard) and is cheaper than your parts cost. Comes with Ubuntu, but the Maemo Community is porting Maemo to this device.

    18. Re:So, where are ARM netbooks? by Nadaka · · Score: 1

      Revision C beagle boards have a TFT connector available, allowing you to wire directly into some LCD panels. This is probably the most expensive part of a portable beagle system. Most 7 to 10 inch screens I saw were around $200 for single units. Though you could get something like a PSP screen for about $30-40.

    19. Re:So, where are ARM netbooks? by Jesus_666 · · Score: 1

      If you're cool with dropping the 300 USD you could also get a Pandora (essentially what you described plus game controls, touchscreen, WLAN and Bluetooth in a clamshell roughly the size of a first-gen Nintendo DS). They're currently preparing for the first mass-production run and preorders for the second batch should start somewhere within the next to or three months.

      If you're interested, check out http://openpandora.org/. If you're not, you could try to get in touch with the OP devs and find out where they source their screens - however, their source might not work for you as they might only sell in bulk.

      Disclaimer: I'm not directly affiliated with OpenPandora but I did preorder a Pandora.

      --
      USE HOT GRITS WITH STATUE OF NATALIE PORTMAN (NAKED AND PETRIFIED)
    20. Re:So, where are ARM netbooks? by Anonymous Coward · · Score: 0

      Or grab yourself an Openpandora, openpandora.org. Mini computer with Omap3 ARM powered CPU and lots of other goodies...You know it makes sense.

  5. Fast is not always best by RichMan · · Score: 3, Interesting

    The fastest processor is not always the best for all applications. Certainly most desktops these days have more than enough power for those that browse the web. So why not save the cost of the big overpowered processor (and the big overpowered OS) where possible.

    And in embedded designs the fastest processor is almost always an overdesign. All those kiosks for cash machines, ticket sales and cash registers do not need the latest fast processors. The do fine with a slower processors.

    There is certainly a big market for an OS that does not tax the processor and is able to provide the minimal OS functionality dedicate application devices need.

    1. Re:Fast is not always best by MightyYar · · Score: 3, Insightful

      I have a feeling the processor itself is not all that expensive in most "browse the web" computers. If ARM or some other processor is to make inroads it will have to be in the power department. A more efficient processor means a cheaper, lighter laptops with smaller batteries.

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    2. Re:Fast is not always best by A+beautiful+mind · · Score: 1

      Oh I disagree. I want the fastest processor I can get...with a 1W thermal envelope.

      --
      It takes a man to suffer ignorance and smile
      Be yourself no matter what they say
    3. Re:Fast is not always best by gedrin · · Score: 2, Insightful

      I'd agree with this. Processors only have to be fast enough that human beings don't notice the time it takes for the processor to do its work.

      --
      Moderation : -1 Conservative Viewpoint
    4. Re:Fast is not always best by BrentH · · Score: 1

      Thermal Envelope? Isn't an anti-static envelope enough? Geez....

    5. Re:Fast is not always best by FrankieBaby1986 · · Score: 2, Insightful

      A more efficient processor means the same laptop, with massively better longevity

      Well, that's what I'm looking for anyway...

      --
      ERROR: SIG NOT FOUND (A)bort, (R)etry, (F)ail?:
    6. Re:Fast is not always best by jointm1k · · Score: 1

      Unfortunately, the processing time that humans are able to discern is divided by two, approximately every two years. So you will need the speed of faster processors -anyway- at one point in the future.

      --
      You know it makes sense, a little reminder from jointm1k.
    7. Re:Fast is not always best by walshy007 · · Score: 1

      don't know about you, but for me VI on a p3 450 from 1999 goes faster than the blink of an eye when editing text, no waiting for it at all.

      For a given usage people don't need faster computers.. (ok except 3d rendering and other infinite processing time things) it's just the usage patterns change and developers misusing abundant resources (flash web pages that make core2duos crawl anyone?)

    8. Re:Fast is not always best by MightyYar · · Score: 1

      A more efficient processor means the same laptop, with massively better longevity

      That too :)

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    9. Re:Fast is not always best by mccrew · · Score: 1

      Actually, it's the screen that is the biggest drain on the battery. A more efficient processor will help with battery longevity, I'm just skeptical about the use of the word "massively."

      --
      Hey, Windows users, there is no such thing as "forward" slash, there is only slash and backslash.
    10. Re:Fast is not always best by KillerBob · · Score: 2, Interesting

      You're right that the screen is the biggest drain on power... on my laptop, it accounts for about 40-50% of the juice that the system uses. Most of that comes from the backlight... in fact, battery life goes up by almost an hour by turning the backlight down to respectable levels. The system in question gets very good battery life, though... it's a 15.4" display @ 1680x1050, with a GeForce 8600M GT 256MB. 4GB of RAM, T5450 processor, 120GB 7200rpm hard drive, running Windows 7 (RTM version, from MSDN). I was able to stay online for 3h during a power failure while raiding in WoW... ventrilo, wireless network (UPS to keep home server up), and all. (it's a Dell Inspiron 1520 with the 9-cell "high capacity" battery)

      But if I can get that kind of battery life out of a system that's drawing its maximum, what do you suppose would happen to the battery life if I were to swap out the 25W Centrino processor with a 2W ARM? Ok, it probably wouldn't be powerful enough to run WoW, but for something like word processing/web surfing, and a few other power efficiency changes (video card, display resolution/brightness, hard drive for SSD), we could be building laptops with a full size keyboard and screen that's big enough to do actual *work* on that can pull off 8h on a charge.

      --
      If you believe everything you read, you'd better not read. - Japanese proverb
    11. Re:Fast is not always best by mikael · · Score: 1

      Going by the cost of replacement components for a laptop, buying a replacement LCD screen from some companies is more expensive than buying a new laptop with equivalent capabilities.

      --
      Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
    12. Re:Fast is not always best by Missing_dc · · Score: 1

      Slow may work, but I would really like it if the ATM (and cashier/register) were quite a bit faster.

      --
      How amazed would you be to suddenly find that you just forgot what I wrote and you needed to reread my post.... again.
    13. Re:Fast is not always best by BikeHelmet · · Score: 3, Interesting

      Don't forget that processor cost isn't just the price of the CPU.

      ARM-based SoCs integrate many peripheral controllers right into the SoC. What might require a $30 atom and $100 board for x86 could require a $45 ARM SoC and $30 board, plus consumes 1/5th the power and is 1/4th the size. That's a big impact for power and space efficient devices.

      Intel has been trying to do the same thing for their new Atoms - but driver support isn't there yet, and power consumption is still many magnitudes higher. (500mw, vs ~8 watts?)

    14. Re:Fast is not always best by MichaelSmith · · Score: 2, Insightful

      When waiting for windows to open its start menu it is fun to estimate the number of clock cycles which have elapsed. Two billion clock cycles? What was it doing?

    15. Re:Fast is not always best by tinkerghost · · Score: 1

      Up until 2 months ago, my main development box was an AMD Athalon 1700+. My Java work was through Eclipse, my web work was in vim over an SSH connection to my server, and both were capable of running faster than I could type.

      I've given away faster systems because I didn't need anything faster for what the box was. I finally upgraded because the MB melted down in a thunder storm. The need to wave around the biggest E-penis is counter productive for most people.

    16. Re:Fast is not always best by MartinSchou · · Score: 3, Informative

      Waiting for disk access.

    17. Re:Fast is not always best by mgblst · · Score: 1

      Make sure you don't store that stuff in memory. There must be gigabyes of information needs for a shitty start menu.

    18. Re:Fast is not always best by ToasterMonkey · · Score: 1

      It's not that slow twice in a row... so what's your point?

    19. Re:Fast is not always best by Anonymous Coward · · Score: 0

      I don't know if color LCD without backlight is even possible, but everyone was playing the GameBoy for months without changing the 2 AA batteries back when I was a kid, and the backlight didn't seem to be needed. Whatever happened to that tech.

    20. Re:Fast is not always best by bsdaemonaut · · Score: 1

      Though it seems hard to find clear power specs for arm processors, ARM11 looks to be 0.6mw/mhz. If your going to compare an ARM11 processor to a dual-core 1.6ghz atom (which is what you seem to be doing) its going to be more like ~2 watts vs 8 watts. ARM is still a clear winner, but with laptop developers coming out with 7+ hour batteries for much more power hungry processors one has to wonder whether the difference is enough to really effect the market.

      BTW, you can get an atom+mb for much less than that -- unless you insist on getting the nvidia board, which is admittedly a good idea considering power consumption.

    21. Re:Fast is not always best by Joey+Vegetables · · Score: 1

      Serving kiddie porn maybe? (No, I'm serious . . . a Windows system that's slower than when you first bought it has a significant chance of being infected, and at that point, you have no idea what it is actually doing unless you inspect the network traffic from another system that you know not to be compromised itself.)

    22. Re:Fast is not always best by Jesus_666 · · Score: 1

      Think of a device with a 16-hour uptime. Under load. With uptimes like that we're approaching the same kind of "needs to be recharged once a week" territory non-smart mobile phones reside in. In short: Netbooks actually become mobile devices instead of computers that happen to have a very good USP built in.

      --
      USE HOT GRITS WITH STATUE OF NATALIE PORTMAN (NAKED AND PETRIFIED)
    23. Re:Fast is not always best by bsdaemonaut · · Score: 1

      Yeah I don't deny that. If Asus can supposedly get 11 hours out of an atom then they should be able to get some amazing things out of an ARM. The problem comes in outside of the processor. If the ARM doesn't have similarly amazing power specs for its MB and peripherals then its impact will be largely mitigated. What if the end difference ends up being something like 42 watts vs 48? It's hard to judge without a real world example.

    24. Re:Fast is not always best by Jesus_666 · · Score: 1

      It's not out yet, but the Pandora (which runs on a TI OMAP 3530) mentions in its tech specs that the battery life is expected to be 10+ hours with a 4000 mAh battery. Given that the Pandora is mainly used for games, emulation and multimedia (so it's likely to be under heavy load much of the time), that sounds great. And at least the devs think that the figure they give is likely.

      Netbooks are likely to have a bigger screen (the Pandora's is 4.3") but they also have more space for a battery and casual users aren't likely to constantly put them under load. So yeah, 12+ hours do appear realistic at the moment - at least for a device without an HDD that mostly sees casual use.

      --
      USE HOT GRITS WITH STATUE OF NATALIE PORTMAN (NAKED AND PETRIFIED)
    25. Re:Fast is not always best by BikeHelmet · · Score: 1

      The Pandora devs posted power consumption of individual parts on the gp32x forums. I've lost most of the links, but someone devoted could find them.

      I recall that the LED backlit LCD and CPU running an emulator full throttle was under 700mw.

      The Pandora battery is also at a lower voltage - 3.7v, I think, instead of whatever most laptops run at.

  6. Re:I Must be Getting Old by fuzzyfuzzyfungus · · Score: 1, Funny

    As it happens, that would have been a perfectly cogent headline a few years back, had we been bothering to pay attention.

  7. Windows missing ARM by hansamurai · · Score: 5, Insightful

    'One thing ARM doesn't have, however, is Windows,' McAllister writes, something that could ultimately stymie ARM's plans to compete on the low end of the netbook market.

    In my opinion, it's the opposite. One thing Windows doesn't have is ARM support (besides Windows CE). Manufacturers are already seeing the advantage of ARM, and the lack of Windows support isn't a deal breaker in every segment. I have a SheevaPlug which is an ARM device, and while most major Linux distributions have support for the architecture, Microsoft just has the one, and it isn't even a consideration for most users of the device.

    1. Re:Windows missing ARM by mrmeval · · Score: 1

      What is your opinion of the SheevaPlug?

      --
      I'd go on a Vegan diet but the delivery time from Vega is too long. --brownkitty
    2. Re:Windows missing ARM by jkrise · · Score: 1

      Well said. This means Microsoft cannot employ the Strong-Arm tactics it used with Asus to compel the vendor to drop Linux based Netbooks.

      I'm already evaluating a SmartQ5 and a SmartQ7 MID from a Chinese vendor SmartDevices, as a data entry terminal and doctors' PC at a hospital where I consult. Since our HMIS and PACS systems are both web-based, we don't need Windows on the client side, just a decent sized screen and a simple windowing environment, which Linux provides on the ARM processors.

      --
      If you keep throwing chairs, one day you'll break windows....
    3. Re:Windows missing ARM by ToasterMonkey · · Score: 1

      Just read every third post on every third article for Christ's sake. Please, no more fucking plug plugs, we get it already.

    4. Re:Windows missing ARM by Anonymous Coward · · Score: 0

      I particularly loved the bassackwards "The chip already supports multiple flavors of the Linux OS, but does not support Windows 7."

      I mean seriously, WTF? This is InfoWorld, a supposedly half-decent publication. A chip does not support operating systems. An operating system may support the use of a particular chip.

  8. Windows on low-end? by WarJolt · · Score: 1

    'One thing ARM doesn't have, however, is Windows,'

    Who wants windows running on low-end computers anyway? You'd be waiting minutes for your web-pages to load.

    Ubuntu has the arm stuff working now, so I want a laptop to install it on. It would keep me from lugging around a big notebook.

    It's interesting they don't talk about the palm pre with armel-linux.

    I've rooted my pre and I can run stuff like ssh or telnet from it, but it would be cool to have something with a larger screen and a keyboard.

    1. Re:Windows on low-end? by Anonymous Coward · · Score: 0

      I think the idea is that Windows on Atom in Netbooks is already popular. A more powerful, efficient processor exists, but Windows cannot be used on ARM (currently).

      Who wants windows running on low-end computers anyway? You'd be waiting minutes for your web-pages to load.

      If thats the case, you'd be waiting even longer on the slower Atom. Whats wrong with people wanting more power?

    2. Re:Windows on low-end? by AaronW · · Score: 1, Informative

      I actually upgraded from XP Home to Windows 7 Ultimate on my HP Mini Netbook (using an Atom N270). I was very pleasantly surprised at how well it runs. It actually feels smoother than XP and is generally quite usable, even with the slow 60GB hard drive. Then again, I also have 2GB of RAM installed, but the memory usage only went up maybe 100MB. Note that I am a Linux junkie and all of my other computers run Linux.

      --
      This post is encrypted twice with ROT-13. Documenting or attempting to crack this encryption is illegal.
    3. Re:Windows on low-end? by yurtinus · · Score: 1

      Hah! You thought we'd buy into your trolling post! Er... wait... That wasn't a troll. Somebody with mod points fix that... Maybe very slightly offtopic but definitely not a troll.

      Do you suppose it was netbooks that helped force Microsoft's hand on the system requirements for windows 7? I don't know of anybody who's tried running Vista on an Atom, but it is nice to see a rollback in OS bloat.

      Now, as a linux junkie, any particular reason you went with Windows on your netbook? I had issues with flash video on my aspire one running ubuntu 8.10, but dealt with it. I was suprised at the performance of 9.10 (and despite initial reservations, am loving netbook remix).

      --
      +1 Disagree
    4. Re:Windows on low-end? by MichaelSmith · · Score: 1

      Who wants windows running on low-end computers anyway?

      Windows users. There's a lot of them around, unfortunately.

    5. Re:Windows on low-end? by AaronW · · Score: 1

      I think Netbooks and low-end notebooks really forced Microsoft to go back and optimize things since they can no longer assume people will have the latest and greatest hardware. I can't compare it with Vista since I've never used Vista but it is definitely an improvement over XP. I was surprised that the memory usage didn't increase all that much over XP. Besides the task bar, hibernate is vastly improved and it feels a lot more responsive. The wireless issues with XP vanished and things just seem to work. The UI is also improved in many small ways but they add up to make a more usable desktop.

      I basically left it running Windows since once in a while it is useful to have a Windows system since sometimes there's software I need to use that isn't available on Linux. I also don't have to mess around trying to get everything to work properly like wireless, bluetooth, VPN, etc. which can be problematic depending on the hardware.

      If I want to work on Linux on my netbook I have the NX client installed so I can access my Linux box any time I feel like it, almost as if it were running locally. This way I basically have a fast Linux system available to me anywhere I have a net connection. It's like having a 12GB quad core I7 monster at my fingertips in a netbook form factor. And NX makes remote access a dream, much better than VNC or remote X, even on slow connections. For when I do drop to the CLI, I have Cygwin installed.

      Since I haven't used Windows much I figured I'd play with it. I'd set it to dual boot but the 60GB hard drive is too small for that.

      It came with Windows XP Home which worked (except for hibernate issues) and I got the Windows 7 Ultimate RC for free and decided to play with it.

      I may try installing Linux on it later. I'd love to get a 120GB or larger SSD for it but it's too expensive to justify right now and there's few manufacturers of hard drives for my netbook (it takes a 1.8" ZIF drive).

      For my general needs on my netbook, Windows is fine. I need it for web, email, viewing photos and VPN access. For web access, I use Chrome which is snappier than Firefox and better using screen real-estate at the low resolution (1024x600) than Firefox is. My netbook is mostly just to play with and not for serious work.

      For my desktop, it's Linux, and most of my time is spent with my desktop.

      --
      This post is encrypted twice with ROT-13. Documenting or attempting to crack this encryption is illegal.
  9. Gadgets not laptops by Darkness404 · · Score: 0, Redundant

    The problem with ARM is that it will perpetually be in the "gadget" category until it can run some "real" OSes. Yes, there is Linux but on popular Linux distros aimed for the general public (such as Ubuntu) ARM is only slightly supported and is still very much a "second class" port compared to the x86 and x86-64 versions. But really what will kill it is more "innovative" UIs for lower-end laptops don't look like "real" computers in the eyes of the consumer. If it looks like http://en.wikipedia.org/wiki/File:Ubuntu_netbook_remix_9.04.png it is a gadget, compared to if it looks likehttp://en.wikipedia.org/wiki/File:Windows_XP_SP3.png , http://en.wikipedia.org/wiki/File:Snow_Leopard_Desktop.png or even http://en.wikipedia.org/wiki/File:Gnome-2.28.png

    --
    Taxation is legalized theft, no more, no less.
    1. Re:Gadgets not laptops by yurtinus · · Score: 1

      Except that a netbook really *is* a gadget. The screen is too small for most general purpose computing. It only does a few tasks, but does them well. As for real OSes, once there is a device you'll see the development. It happened with Linux for the Atom networks, and it will happen if ARM netbooks come out. As for your analysis on UIs... eh, that's subjective. I'm loving netbook remix, but I'm also not trying to use it as my regular computer. The thing I love about it is in a pinch, yes-- it will do whatever my main computer will do-- but as I typically use it, it is very quick to navigate.

      Also-- your signature versus the current moderation (redundant) on your post his hilarious!

      --
      +1 Disagree
    2. Re:Gadgets not laptops by petermgreen · · Score: 1

      The screen is too small for most general purpose computing.
      On the very early netbooks and the bottom end ones today I'd agree with you.

      But 1024x600 (the most common on netbooks at the moment) while a little annoying sometimes (mainly due to app developers who assumed 1024x786 as a minimum) is sufficiant for most stuff and 1366x768 (rare on netbooks at the moment but looks like it going to become more common) is marginally better than the 1280x800 of most low end regular notebooks.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    3. Re:Gadgets not laptops by yurtinus · · Score: 1

      Certainly sufficient to do just about any task, but when you get used to having dual 1600x1200 displays for work, the lack of real estate definitely effects your productivity. It *can* be done, it takes getting used to, and it may cost you some time managing windows or workspaces. I wouldn't choose to do all of my work on a small screen, but like I said-- it's awesome that it will do the trick in a pinch.

      Of course, just about all of us started on computers at 640x480 or less, so I suppose you could argue what all the hoopla is about!

      --
      +1 Disagree
  10. I'll take three, thanks by Anonymous Coward · · Score: 5, Funny

    " 'One thing ARM doesn't have, however, is Windows,' McAllister writes"

    I'm sold.

  11. Almost 3 billion chips this year? by Anonymous Coward · · Score: 1, Interesting

    90*60*60*24*365= about 2.8 billion
    Is that for real or is it a typo?

    1. Re:Almost 3 billion chips this year? by Volante3192 · · Score: 4, Informative

      Had you read the article, you'd see where all the chips come from, because it's summarized right below that line on the first page.

      Hint: if you have an electronic device that is NOT a desktop or laptop computer, the odds are somewhere around 99 out of 100 that it's using one or more ARM chips. This includes, but is not limited to, cell phones, GPSes, home routers, calculators, and portable gaming devices like the DS.

    2. Re:Almost 3 billion chips this year? by lordtoran · · Score: 1

      I'd like to add to your thoughts that nowadays nearly all "devices" are computers too. They have general purpose CPUs (nearly always ARM- or MIPS-based) and more or less powerful I/O. In most cases it's only the software that confines them to specific gadget-typical tasks.

      --
      Want to hear the voice of GOD? cat /boot/vmlinuz > /dev/dsp
    3. Re:Almost 3 billion chips this year? by marcansoft · · Score: 1

      Desktops and laptops have plenty of ARM chips in them. Lots of drives use ARM chips for the drive controller, for example. Just about everything that needs more than an 8-bit micro has a very good chance of having an ARM chip these days (not 99%, but still a pretty high number). It's almost scary. And now, with Cortex-M0, ARM is heading straight for the 8-bit and 16-bit market (though it isn't here yet: so far, low end devices like computer input devices, simple appliances like microwave ovens, etc. don't use ARMs).

  12. looks like Slashdot really wants this by Trepidity · · Score: 2, Interesting

    February: Shifting Apps To ARM Chips Could Save Laptop Batteries

    September: ARM Attacks Intel's Netbook Stranglehold

    3 days ago: ARM Launches Cortex-A5 Processor, To Take On Atom

    Doesn't mean it won't happen, of course, but still unclear if it will, either...

    1. Re:looks like Slashdot really wants this by JSBiff · · Score: 1

      Slashdot articles are essentially just links to 'real' articles by other authors/publishers. So, if there are a number of Slashdot articles about a topic, wouldn't that tend to indicate that someone (possibly multiple someones) in "The Industry" are writing about this? Granted, there's always the possibility of Cherry Picking - that is, if the /. Eds. *are* biased, they can 'overrepresent' the articles, but honestly, 4 articles in a year doesn't strike me exactly as cherry picking - just covering what various IT journalists are writing.

    2. Re:looks like Slashdot really wants this by bhtooefr · · Score: 1

      It's a possibly credible threat to x86, which quite a few people have wanted to see die since before x86 was called "IA-32."

      In addition, it can't run full Windows, so to work, it's Linux or bust (let's face it, even if you like WinCE, it's totally unsuited to this application,) and this is a Linux-biased site.

      That's why Slashdot would want to see this.

  13. Windows CE and Windows Mobile by Blakey+Rat · · Score: 3, Informative

    Windows CE and Windows Mobile both support ARM.

    There might not be "full-featured Windows" on ARM, but saying there's no Windows at all on ARM is just ignorance.

    1. Re:Windows CE and Windows Mobile by Compholio · · Score: 1

      Windows CE and Windows Mobile both support ARM.

      There might not be "full-featured Windows" on ARM, but saying there's no Windows at all on ARM is just ignorance.

      They're probably subscribing to the argument that if it does not support Win32 then it does not "run Windows programs" and is therefore "not Windows." While this is technically incorrect, it is true from a practical sense for most people.

    2. Re:Windows CE and Windows Mobile by Bert64 · · Score: 3, Insightful

      It cannot run the same applications as windows, therefore it's not windows...

      It is partially source compatible, but not enough to make any but the simplest of apps a direct compile... Linux/arm on the other hand, makes it possible to simply recompile the vast majority of applications so that they work (i have a sheevaplug running gentoo and i have done exactly that).

      People buy windows because it runs the applications they have or are familiar with, the versions of windows which run on arm don't provide this.. Linux has a greater chance of running apps users will find familiar, since there are ports of things like firefox to arm.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    3. Re:Windows CE and Windows Mobile by Anonymous Coward · · Score: 5, Insightful

      Windows CE and Windows Mobile both support ARM.

      There might not be "full-featured Windows" on ARM, but saying there's no Windows at all on ARM is just ignorance.

      Except that with Linux, BSD, and even OS X, the code that runs on x86 is the same code that runs on ARM (and PowerPC).

      With "Windows", the code that runs on x86 is not the same as runs on the embedded stuff: there's no "scaled down" version like the Unix-based systems. It's a completely separate OS. The only multi-platform stuff that Microsoft has is Windows for Itanium.

      Just because the Microsoft marketing folks call it "Windows" CE or Mobile does not make it the same as the desktop / server OS. With the Unix-y systems, it is the code and OS (though perhaps cut down to the bare essentials). And that's what we're talking about here: taking the same code and simply doing a recompile. It's not going to happen with Vista or W7, but it can happen with other OSes (heck, even OpenSolaris is being ported as-is to ARM and PowerPC).

    4. Re:Windows CE and Windows Mobile by Anonymous Coward · · Score: 0

      No, that's actually a huge difference between "no Windows support" and "Windows Mobile support". It has many similar applications and features; that's why it's called Windows.

    5. Re:Windows CE and Windows Mobile by tepples · · Score: 1

      It is partially source compatible, but not enough to make any but the simplest of apps a direct compile... Linux/arm on the other hand, makes it possible to simply recompile the vast majority of applications so that they work

      How? Is it really that much easier to port an application for Windows to one of the common GNU/Linux app frameworks than to Windows CE? It might be if the app currently runs on Qt, or if you treat Winelib as a framework.

    6. Re:Windows CE and Windows Mobile by cbhacking · · Score: 1

      First, Windows Mobile is just a wrapper around the Windows CE core. There's no particularly great need to mention them separately.

      More importantly, there's no reason that the Win32 API couldn't be brought to ARM. There are a few possible ways to do this:
        * Hacking it into WinCE somehow (the brute-force approach)
        * Port NT and the Win32 subsystem to ARM (certainly possible, but if you do that then you probably need to port the WinMo API to an NT subsystem for backward compatibility. On the plus side this is one less kernel to maintain)
        * Use a POSIX system (possibly the POSIX subsystem for NT, but more likely something *BSD) with Wine on top (Wine is already working on an ARM port, although I'm not really sure why)

      There's no reason that most Win32 apps couldn't be re-compiled for ARM, it's just that there isn't currently a Win32 API on ARM. Fix that, release a handful of first-party ARM ports, make the SDK a free download (it already is for x86-based apps) along with a free update to Visual Studio that uses the cross-compiler and checks for architecture-specific compatibility issues, and watch ISVs fall all over themselves releasing ports of their software for the new platform.

      --
      There's no place I could be, since I've found Serenity...
    7. Re:Windows CE and Windows Mobile by Hurricane78 · · Score: 1

      It cannot run the same applications as windows, therefore it's not windows...

      Actually, it can. All the developer needs to do, is recompile for ARM, and link to different libraries. (The WinCE ones.)

      But the more important thing is: What are the main holdbacks that lets people use Windows.
      1. Games: Don't run on these small systems anyway. I've seen enough people, meaning "Flash games" when they say "games". And those work on Linux.
      2. "My very specific app": = lack of being informed about Wine, and the great alternatives that exist for Linux
      3. Being used to what you always used: With KDE and Gnome imitating every single shitty aspect of Windows, most people you ask on the street (there was a video about that) won't know KDE4 from Win7 anyway. Re-label the items in the "start" menu (eg "OOo Writer" to "Microsoft Word"), and they won't have any trouble switching.

      It's mostly not being used to how you get support anyway. If the average Luser knows about e.g. the Gentoo Forums, IRC and Bugzilla, he gets through without problems. Besides: What are friends for? ^^

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    8. Re:Windows CE and Windows Mobile by Anonymous Coward · · Score: 0

      Yeah, and you don't even have to compile the apps, they already are there. That's one reason why free software rules, it's a lot easier to change architecture. Ubuntu already has ARM port.

    9. Re:Windows CE and Windows Mobile by petermgreen · · Score: 1

      1. Games: Don't run on these small systems anyway.
      The latest and greatest don't but there are a lot of older games that run just fine on netbooks and are a lot better than most flash crap.

      2. "My very specific app": = lack of being informed about Wine,
      Wine works sometimes but it's a hit and miss thing (some stuff works fine, some stuff sorta works,) either way this won't be helpful for arm linux devices anyway unless someone integrates wine with an emulator (and even if they do I expect it to be dog slow)

      and the great alternatives that exist for Linux
      Sometimes there are great alternatives, sometimes there are alternatives but they are much crappier, sometimes there isn't really any alternative.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    10. Re:Windows CE and Windows Mobile by Bert64 · · Score: 1

      All the "developer" needs to do..
      What if the developers have no interest in an ARM port? most windows software only comes as binaries, and some is abandonware...

      And it's more than just a straight recompile, the API is similar but different, and the underlying kernel is totally different. Unlike Linux, where the kernel and APIs are the same, most apps are a recompile away (and have often already been compiled for arm by distro maintainers) and most apps come with source code enabling third parties (including those with vested interests like the hardware makers) to compile the apps if the developers won't.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
  14. Stealthily?! by QX-Mat · · Score: 3, Insightful

    Oh please!

    It's not a stealth thing at all. The low power SoC market has always been ARMs. It's AMD (Geode... and then Intel's Atom) who decided to bring x86 to the low power market. If anything the article should focus on the troubles ARM is likely to face in the near future: unless RISC can continue to compete for price (aggressively), I doubt that adding more pipelines will make the general purpose platform developers happy - RISC bottlenecks will always be bottlenecks; x86 can simply gun for greater clock speed.

    IMO Transmeta had it right: very long instruction words (which ultimately do 'everything'). Unfortunately it came 10 years too soon and no-one was ready because we didn't know "what" we wanted from a clock (or half clock etc if you're talking ARM...).

    VLIW will be back soon enough, but I worry that it wont be the right place for ARM.

    (nb: I am an ARM fanboy, having 'matured' in an ARM sponsored undergrad lab. it upsets me as much as anyone that ARM haven't tried to reinvent the wheel using the cash from their recent market dominance)

    Matt

    1. Re:Stealthily?! by rolfwind · · Score: 1

      It's not a stealth thing at all. The low power SoC market has always been ARMs. It's AMD (Geode... and then Intel's Atom) who decided to bring x86 to the low power market.

      Yeah, but they're still not really low power and neither are their boards. They're not competing with Arm yet, in that sense.

      I'll say they might be in trouble when I see first see a decent cell phone running intel.

    2. Re:Stealthily?! by maczealot · · Score: 1
    3. Re:Stealthily?! by walshy007 · · Score: 1

      Intel once thought VLIW was the future also, thusly making the Itanium IA64 architecture.. and I'm sure you'd know how that turned out for them.

      For VLIW to be properly used compilers would have to significantly improved for the scheduling of out of order instructions at compile time.

      that being said I still need to pick up an IA64 system, it's one of the last remaining on my to get list (have superhitachi, 68k, arm, ppc, sparc, mips, etc etc)

    4. Re:Stealthily?! by confused+one · · Score: 1

      It's only stealthy to someone who has not been paying attention and/or did not know that embedded processors outsell desktop and server processors by more than 10 to 1.

    5. Re:Stealthily?! by Erich · · Score: 1

      VLIW will be back soon enough

      Sooner than you know.

      --

      -- Erich

      Slashdot reader since 1997

    6. Re:Stealthily?! by couchslug · · Score: 1

      "IMO Transmeta had it right: very long instruction words (which ultimately do 'everything'). Unfortunately it came 10 years too soon and no-one was ready because we didn't know "what" we wanted from a clock (or half clock etc if you're talking ARM...)."

      Unfortunately Transmeta didn't release any (consumer) DESKTOP MOTHERBOARDS with processors so enthusiasts could try them out by building systems around them and their product could get market traction.

      Do you have a recommendation for an ARM CPU/mobo combo?

      --
      "This post is an artistic work of fiction and falsehood. Only a fool would take anything posted here as fact."
    7. Re:Stealthily?! by Anonymous Coward · · Score: 0

      "RISC bottlenecks will always be bottlenecks" Huh? I think you mean CISC bottlenecks.
      Clock speed is an implementation feature, not a ISA feature. RISC has higher clock speed right now too.

      All things equal an x86 chip would lose significantly to ARM/POWER/Sparc. Fortunately for Intel/AMD all things aren't equal and the non ISA issues compensate for x86's problems. AMD's 64bit extension is very good. But if Intel was making an RISC mainstream chip and ARM was trying to sell an x86 CISC chip you can be certain that CISC would actually have died.

      Don't believe the hype, VLIW will be here when we have rotary engines displace piston engines and commercial airlines switch to Flying Wing aircraft instead of tube+wing design. Great theory to overcome one engineering problem, but introduces enough small ones that it isn't practical.

    8. Re:Stealthily?! by JAlexoi · · Score: 1

      Beagleboard and derivatives? I can get a beagleboard based device with WiFi, DVI and sound in eurpoe for Eur150.

    9. Re:Stealthily?! by hitmark · · Score: 1
      --
      comment first, facts later. http://chem.tufts.edu/AnswersInScience/RelativityofWrong.htm
    10. Re:Stealthily?! by Guy+Harris · · Score: 1

      RISC bottlenecks will always be bottlenecks;

      What "RISC bottlenecks" (other than "RISC chip developers don't have the money that Intel does") are there that aren't also bottlenecks for x86?

      x86 can simply gun for greater clock speed.

      ...and the RISC vendors can't? (Not that Intel is exactly "simply [gunning] for greater clock speed" - I don't think they've yet come out with a post-NetBurst processor that has a clock speed as fast as the fastest NetBurst had. That suggests that clock speed isn't everything....)

      IMO Transmeta had it right: very long instruction words (which ultimately do 'everything').

      ...devoted to implementing x86, so that you never actually saw the native instruction sets ("sets", plural, as I think their first processor and second processor had different underlying instruction sets).

    11. Re:Stealthily?! by bhtooefr · · Score: 1

      There's actually been quite a few enthusiast-oriented ARM development boards as of late. In addition to the BeagleBoard and Gumstix...

      Marvell OpenRD Client: http://www.globalscaletechnologies.com/t-openrdcdetails.aspx (much more desktop-oriented, albeit barely able to keep up with Beagle and Gumstix in integer, and lagging WAY behind in floating point (no FPU.))
      Genesi EFIKA MX Open Client: http://www.genesi-usa.com/products/efika

      Of course, there's always the Acorn Archimedes 305, which is a complete ARM-based desktop, and is very much aimed at consumers, not just enthusiasts. 8 MHz ARM2 (there were some ARM1s that made it into the public, but they were aimed at developers, not consumers,) 512 kiB RAM, one 800 kiB floppy drive, no hard drive. And for 1987, it was ridiculously fast - IIRC, the only thing that wasn't a *nix workstation that could come within striking distance was a 25 MHz 386, and those cost quite a few times more money for an equivalent spec (and, there was a version of the A440 (same thing with a hard drive interface and 4 MiB RAM) called the R140, which was actually a *nix workstation running a 4.3BSD variant.) ;)

    12. Re:Stealthily?! by Anonymous Coward · · Score: 0

      Because x86 allows for greater clock speeds than RISC processors because of "RISC bottlenecks", right?
      VLIW is really nice if you believe all the academics working on compiler technology and tell how a wonderful work a compiler can do on your code. In the real world I don't really believe in VLIW, but that's a personal opinion.
      With the many-cores I do believe that RISC processors will make a small-comeback. Probably in the form of the ARM. They may integrate some form of "SLIW" (somewhat long instruction word ;) ) and also some form of SIMD capabilities.

      Oh! and in the SoC market size of the core really matters, and you also have many companies competing in the ARM market, instead of the virtual duo-poly in x86, and with a huge and growing market supporting them (phones). I think this is a battle that Intel may actually lose.

    13. Re:Stealthily?! by sketerpot · · Score: 1

      Modern x86 processors translate instructions into a sequence of RISCy operations (which takes quite a bit of silicon), and then operate like any other high-speed processor internally.

  15. Details are Wrong by mpapet · · Score: 1

    Is this the End of Intel AND Microsoft?

    Intel doesn't care what OS runs on their chip. I think their Linux distro is Moblin? As long as they have orders, they don't care what the consumer uses.

    Microsoft doesn't care because this is still a niche and they can string along the OEM's with XP forever. When it starts blowing up into a category all its own, I think they'll do something to encourage OEM's to use Intel chips and keep XP out there. Microsoft relies on the fact Linux still doesn't have anything overtly special on XP that the average Dell buyer wants.

    Please don't flame me bro. I say these things as a long-time Debian user who gets the differences.

    --
    http://www.maxineudall.com/2010/02/should-economists-be-sued-for-malpractice.html
    1. Re:Details are Wrong by koiransuklaa · · Score: 1

      Intel doesn't care what OS runs on their chip. I think their Linux distro is Moblin? As long as they have orders, they don't care what the consumer uses.

      Yeah, that part about Intel betting on Windows is just bogus nowadays. Intel is one of the 4 largest contributors to the linux kernel, has moblin as their own mobile "base" distro and mostly provides good linux support for their hardware.

      Of course their investment in Windows is even larger (makes sense when you look at the market shares) but saying that Intel is somehow "betting on Windows" is just idiotic.

  16. Low power FTW by Sporkinum · · Score: 3, Informative

    I just purchased a Wikireader, which uses a low power Epson S1C33E07 60 mhz RISC processor, not unlike an ARM. It will run for 90 hours on 2 aaa batteries. And that includes a 240 * 208 capacitive touch screen.

    --
    "He's lost in a 'floyd hole"
    1. Re:Low power FTW by NevarMore · · Score: 1

      Yes but all it does is surf wikipedia from an SD card.

      It's a neat device, but hardly a netbook call me when it can play a movie, view slashdot, check my email, view slashdot, update a few trouble tickets for work, view slashdot, submit an order to Jimmy Johns for lunch, view slashdot, run an SSH client, view slashdot AND load wikipedia.

    2. Re:Low power FTW by supersloshy · · Score: 1

      Yes but all it does is surf wikipedia from an SD card.

      It's a neat device, but hardly a netbook call me when it can play a movie, view slashdot, check my email, view slashdot, update a few trouble tickets for work, view slashdot, submit an order to Jimmy Johns for lunch, view slashdot, run an SSH client, view slashdot AND load wikipedia.

      I think you forgot "view slashdot". I thought it would have been obvious; guess I was wrong =\

      --
      "Our country is not nearly so overrun with the bigoted as it is overrun with the broadminded." -Archbishop Fulton Sheen
    3. Re:Low power FTW by Anonymous Coward · · Score: 0

      My N900 can do all that stuff plus it has a 5 MP camera and can record h264 video at roughly DV quality. Oh yeah, and it's a phone too.

    4. Re:Low power FTW by VoltageX · · Score: 1

      *and* contains a fairly complete Forth interpreter.

      Source code + bootloader at http://github.com/wikireader

      --
      "Anonymous could not immediately be reached for further comment." - International Business Times
    5. Re:Low power FTW by yurtinus · · Score: 1

      I sleep in a racecar bed. Do *you* sleep in a racecar bed?!

      --
      +1 Disagree
    6. Re:Low power FTW by BikeHelmet · · Score: 1

      view slashdot

      Unless I'm mistaken, this requires a 2.0ghz quadcore, so you're not likely to see it in a handheld any time soon!

    7. Re:Low power FTW by Anonymous Coward · · Score: 0

      Yes but all it does is surf wikipedia from an SD card.

      It's a neat device, but hardly a netbook call me when it can play a movie, view slashdot, check my email, view slashdot, update a few trouble tickets for work, view slashdot, submit an order to Jimmy Johns for lunch, view slashdot, run an SSH client, view slashdot AND load wikipedia.

      No porn?

    8. Re:Low power FTW by Anonymous Coward · · Score: 0

      I just purchased a Wikireader, which uses a low power Epson S1C33E07 60 mhz RISC processor, not unlike an ARM. It will run for 90 hours on 2 aaa batteries. And that includes a 240 * 208 capacitive touch screen.

      Yes, the Wikireader is a nice compact gadget, and the power efficiency is superb. Too bad it has no network connectivity at all. It could gain a lot of useful features--graphing calculator + PDA/organizer + etext reader + handheld game console comes to mind--but it's no netbook

    9. Re:Low power FTW by Sporkinum · · Score: 1

      I wasn't clear in what I was trying to get across. Yes I know it isn't a netbook, but it shows the extreme levels of low power use that can be achieved. It

      • is

      a computer though.
      I'd bet in a couple of years there will be chips with comparable power use levels that will be able to do netbook level tasks.

      --
      "He's lost in a 'floyd hole"
    10. Re:Low power FTW by NevarMore · · Score: 1

      No porn?

      What do you think the SSH client is for?

    11. Re:Low power FTW by lactose99 · · Score: 1

      My Android phone does all these, and is ARM-based.

      --
      Fully licensed blockchain psychiatrist
    12. Re:Low power FTW by Anonymous Coward · · Score: 0

      It's also very expensive, at least if you want it without a contract. I was looking at the UK prices and it was ~£450 (not that it has been released here yet AFAIK), though I really want one, I don't want to pay that sort of money for it.

    13. Re:Low power FTW by Anonymous Coward · · Score: 0

      Yes, it is amazing how little power a processor can use when it has negligible processing power (by modern standards). Though the power usage is impressive, it doesn't seem terribly relevant, for example my watch lasts years on a single button cell battery, so it lasts a lot longer than that wikireader using a smaller battery, but it also does a lot less.

  17. stealthily? by Anonymous Coward · · Score: 0

    Far too stealthily for my taste! Let's get lots of netbooks/notebooks with ARM so we have some choice!

    1. Re:stealthily? by Nefarious+Wheel · · Score: 1

      Far too stealthily for my taste! Let's get lots of netbooks/notebooks with ARM so we have some choice!

      Yes, a processor architecture guaranteed by the second amendment to the US constitution. You can't take my netbook away from me, no sir, you can pry it away from my cold dead hands.

      (Uh, can I get a rez please?)

      --
      Do not mock my vision of impractical footwear
  18. Re: was wrong thats Atom not Arm by RichMan · · Score: 1

    Ok I was wrong there that was an Atom not an ARM notebook.

    This is ARM
    http://armnews.wordpress.com/2009/09/29/dell-announce-notebook-with-arm-processor/

  19. Re:MAME on ARM in Debian by mpapet · · Score: 3, Informative

    http://packages.debian.org/lenny/arm/xmame-sdl/download

    I've run Debian ARM distro on an NSLU2. Works great.

    --
    http://www.maxineudall.com/2010/02/should-economists-be-sued-for-malpractice.html
  20. Re:It's JVC's VHS-C versus Sony's Video8 again by LWATCDR · · Score: 2, Interesting

    That really depends I think on how netbooks mature.
    Is a netbook a small weak notebook or a big iPod Touch?
    Take a look as the WindowsMobile vs iPhone battle.
    WIndowsMobile had years of time in the market before the iPhone and it had a lot more applications than the iPhone. The iPhone blew it out of the water in just a few short years.
    If the ARM baised netbook folks get their act together then yes Arm could move up into the netbook area. From there it could move up into the Notebook and even Desktop space.
    You may think that could never happen but the X86 went from a toy to push up into the workstation and server market. You even have some X86 style systems pushing well into the Mini/Mainframe area.
    Windows and X86 has done so well because it is cheap and fast enough.
    Now ARM is heading into cheap and fast enough.

    --
    See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
  21. Re:It's JVC's VHS-C versus Sony's Video8 again by 91degrees · · Score: 1

    It didn't monopolise the market though, and may not have done so well had it not had other advantages (i.e. it was cheap). Camcorders had phono composite connectors so it wasn't that hard to convert other formats to VHS.

    Similarly, all people really want is to be able to transfer documents seamlessly. They don't care so much if different applications run on different machines. You can already get Windows CE on ARM, and MS would have no objection to producing a Word compatible word processor for CE if demand was sufficient.

  22. I'm running Windows on ARM *right now* by argent · · Score: 3, Interesting

    As far as the application is concerned, the only difference between Windows CE and Windows NT is the APIs exposed. The calling sequence is the same, the library structure is the same, the IDE is the same, the Pocket PC emulator on Windows works by recompiling the same source to x86 instead of ARM code and linking to a different set of libraries.

    Given the variety of APIs exposed to applications running under Linux on ARM (two different Java runtimes, as well as the native UNIX APIs and X11), the differences to the application between Windows CE on my iPaq and Windows on my desktop are less than the difference between Android and Familiar.

    1. Re:I'm running Windows on ARM *right now* by slimjim8094 · · Score: 1

      Wait, the only difference between Windows CE and Windows NT is the APIs exposed, and the instruction set? That's true between Mac System 7 and Linux.

      I think what you meant was that the APIs are very similar, or perhaps that CE is a subset of NT. Most of an OS (as far as an application is concerned) is the API.

      --
      I have developed a truly marvelous proof of this comment, which this signature is too narrow to contain.
    2. Re:I'm running Windows on ARM *right now* by Com2Kid · · Score: 1

      the Pocket PC emulator on Windows works by recompiling the same source to x86 instead of ARM code and linking to a different set of libraries.

      To be clear about this, Microsoft Device Emulator is a bog standards dynamic recompilation emulator for the ARM instrution set.

      Applications are compiled as ARM code and linked to the ARM compiled Windows Mobile or Windows CE versions of libraries which are loaded by the Windows Mobile OS which is ARM code running fully emulated within Device Emulator.

      When writing code for mobile devices, please keep power usage in mind at all times (please please please don't auto wake a thread on a timer....) as well as screen size and usability. Although (IIRC) WinCE can support USB mice, they aren't exactly common for that user segment. :)

    3. Re:I'm running Windows on ARM *right now* by Anonymous Coward · · Score: 0

      But you're missing the point. Windows CE is just a lousy, broken, piece-of-shit toy. What the article is saying is that Microsoft does not have an _operating system_ for ARM.

    4. Re:I'm running Windows on ARM *right now* by Anonymous Coward · · Score: 0

      The other difference to the application, of course, is that the app isn't compiled for ARM instructions, they're compiled for x86 instructions. As the main reason Windows people stick with Windows is the applications that are available for it, and given that the majority of those applications are compiled for x86, this is a big sticking point.

      Of course, developers could "just" recompile targeting ARM, but the problem is that they don't. It's just one more thing to have to test and debug before getting the product stamped with a new version number and punted out the door.

    5. Re:I'm running Windows on ARM *right now* by argent · · Score: 1

      Wait, the only difference between Windows CE and Windows NT is the APIs exposed, and the instruction set? That's true between Mac System 7 and Linux.

      The low level API on Windows CE and Windows NT... the process you go through to make a call, the overall structure of the program, the library format, the shared library interface, these things are all the same. It's more like OS X vs Linux than Mac OS vs Linux.

    6. Re:I'm running Windows on ARM *right now* by argent · · Score: 1

      To be clear about this, Microsoft Device Emulator is a bog standards dynamic recompilation emulator for the ARM instrution set.

      That's new then. When I was doing this you compiled for ARM, SH3, MIPS, or x86... for the three supported Pocket PC CPUs or for the emulator. You couldn't run an ARM or SH3 binary directly.

    7. Re:I'm running Windows on ARM *right now* by Com2Kid · · Score: 1

      That might have been the old (really old) "emulator" that actually just linked to x86 versions of the libraries and ran the OS in a mini window. That is rather ancient. x86 code is different enough other platforms that you can get better results compiling to ARM code directly and running it.

  23. Windows is too expensive for ARM by Cro+Magnon · · Score: 2, Funny

    Everyone knows it costs an ARM and a LEG.

    --
    Slow down, cowboy! It has been 4 hours since you last posted. You must wait another few hours.
  24. The Debian Distro Says Otherwise by mpapet · · Score: 4, Informative

    http://www.debian.org/ports/arm/

    I've run it on an NSLU2. Worked perfectly. They've got desktop packages for it an everything.

    Ubuntu is has been standing on the shoulders of giants (Debian) for a long time. It's time for you to go straight to the source.

    --
    http://www.maxineudall.com/2010/02/should-economists-be-sued-for-malpractice.html
    1. Re:The Debian Distro Says Otherwise by petermgreen · · Score: 1

      The question remains though as to when and if they will deal with the floating point issue.

      Different arm chips have different (incompatible) FPUs. The old arm port was compiled for an old FPU that is virtually nonexistant nowadays leaving it using very slow FPU emulation.

      Armel improves the situation by allowing binary compatibility between code compiled with different FPU settings. The debian armel port builds for softfloat, there was talk of making special versions of floating point critical packages for various fpus but I don't think anything much came of it.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  25. Windows is fading into the background by Kupfernigk · · Score: 4, Interesting
    It's possible that the desktop dominance of Windows will keep Arm out of the small computer market. But a lot will depend on developments with Oleds and e-ink. Currently the display is the power hog of all-in-one computers, which means that changing the cpu energy consumption makes relatively little difference. But once Oled and e-ink displays reduce the power consumption needed for the display, the cpu becomes more significant. As screen sizes on convergent devices fall - I personally suspect that the 5.5 to 7 inch diagonal screen will come to dominate in truly portable devices - the resulting limit on battery size will be the difference between an all-day device and one that cannot get through a working day. This is where the new generation of Linux distributions like Maemo and Android running on Arm will deliver a visible benefit, and the end user - who doesn't really care whether he has to run "word" or "floop" so long as the document opens correctly and edits - will be more interested in whether he can go from 7 a.m. to 7p.m without a charge.

    I'm writing this on a netbook running Ubuntu Netbook Remix 9.10 and it just works (TM). It would work just as well on an Arm processor.

    In the real world, I'm sure that Microsoft will be able to roll out Windows Mobile on Arm one microsecond after Dell tell them that their new 7 inch communications centre and ebook reader will have to run an OS supplied by Canonical.

    --
    From scarped cliff or quarried stone she cries "A thousand types are gone, I care for nothing, no not one."
    1. Re:Windows is fading into the background by afidel · · Score: 1

      I would say WAY more people care about if their apps will run then care about if they can work for 12 hours on battery. Seriously, I've never been away from a plug more than about 4 hours except when in the backwoods camping. Even on transatlantic flights I can get a power plug to keep my laptop running.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    2. Re:Windows is fading into the background by JAlexoi · · Score: 2

      And as all other people, who bitch about their apps, you need a laptop. I bought my netbook with the same attitude - "I need to run special software".
      After 6 months I can say, that I do not run anything other than Firefox, Thunderbird, IM clients and occasionally some document editing and ssh sessions. Nothing, and I mean nothing is irreplaceable when moving from windows. My sister, who is your stock anti-nerd, will run same stuff as me, except for SSH.

    3. Re:Windows is fading into the background by afidel · · Score: 1

      It's the document editing that's the key there, alternative document editing programs just haven't taken off in business because the marginal gains from going away from Office haven't justified all the downsides. I don't see netbooks with 12 hour battery lives chancing that.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  26. OS/X? by hemp · · Score: 1

    ARM lacks OS/X in addition to Windows.

    --
    Skip ------ See the latest from http://www.anArchyFortWorth.com
    1. Re:OS/X? by Anonymous Coward · · Score: 0

      Sort of. The iPhone is a trimmed down OS/X, and it runs ARM.

    2. Re:OS/X? by kamochan · · Score: 4, Informative

      Apple's iGadgets are ARM-based and run a variant of OS/X. Of course, ARM also has WinCE, so that kind of balances the karma.

    3. Re:OS/X? by jdgeorge · · Score: 1

      ARM lacks OS/X in addition to Windows.

      Perhaps, but the iPhone and iPod Touch use ARM. Lacking OS/X isn't likely to damage the prospects for ARM. At all.

    4. Re:OS/X? by Anonymous Coward · · Score: 3, Informative

      Apple's iGadgets are ARM-based and run a variant of OS/X [sic]. Of course, ARM also has WinCE, so that kind of balances the karma.

      It's not a variant. It is the same code that runs on an iMac or MacBook, just trimmed back (e.g., no FireWire or SATA drivers).

      The Windows CE has barely any relation to Windows Vista or 7. It's two different code bases, whereas with OS X it's the same code base.

      This doesn't really make much of a difference to the end user in most cases, but keeping one code base bug free and thoroughly tested is generally less of a hassle than keep more than one code base the same.

    5. Re:OS/X? by Guy+Harris · · Score: 1

      It's not a variant. It is the same code that runs on an iMac or MacBook, just trimmed back (e.g., no FireWire or SATA drivers).

      ...and no AppKit (or Carbon; AppKit is replaced by UIKit, and Carbon is replaced by nothing). Perhaps you don't consider the GUI toolkit as part of "the code" to which you're referring, but it's certainly relevant to application developers (you can't just recompile a Mac OS X app for iPhone OS, and you can't just recompile an iPhone OS app for Mac OS X - and I'm not sure you should, given that a UI design for a computer with a 13"+ screen, full keyboard, and mouse/trackpad might not be very good for a computer with a 6" touchscreen with the keyboard popping up on the touchscreen - and vice versa).

  27. The problem for AMD is... by El+Cabri · · Score: 1

    Nobody gives a hoot about how " high performance applications " do on netbooks.

    1. Re:The problem for AMD is... by Anonymous Coward · · Score: 0

      What the flux does AMD have to do with ARM?

    2. Re:The problem for AMD is... by Anonymous Coward · · Score: 0

      I'd guess that, since AMD is a competitor to ARM, and since they don't have any real low-power offerings, ARM's success on netbooks would be a problem for them.

  28. But why do you want a laptop? by Kupfernigk · · Score: 2, Interesting

    But really what will kill it is more "innovative" UIs for lower-end laptops don't look like "real" computers in the eyes of the consumer.

    No, they look like smartphones on steroids. And as these lower-end units will basically be just that - with 3 and 3.5G, phone connectivity, GPS, Bluetooth and wireless, and connecting seamlessly to the back at the ranch desktop - they will be seen as a step up from phones, not down from laptops.

    --
    From scarped cliff or quarried stone she cries "A thousand types are gone, I care for nothing, no not one."
    1. Re:But why do you want a laptop? by petermgreen · · Score: 1

      Maybe but the longer wintel netbooks remain the main type of netbook on the market the more the "netbook as a cut down laptop" perception rather than the "netbook as a souped up smartphone" perception will become seated in the minds of netbook users.

      Which isn't to say that there is no market for "smartphones on steriods" I just think that marketing them as netbooks will lead to dissapointed customers.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  29. Re: was wrong thats Atom not Arm by Narishma · · Score: 1

    That's not a netbook and it has both an ARM and an Intel CPU.

    --
    Mada mada dane.
  30. Re:It's JVC's VHS-C versus Sony's Video8 again by FrankieBaby1986 · · Score: 1

    docs especially, but even apps don't have to be difficult to move back and forth. JPEGs, .doc/docx/odf are architecture independent. Java/.Net and fat binaries exist for apps, as well as cross compilation. Any good OS would provide all of this.

    --
    ERROR: SIG NOT FOUND (A)bort, (R)etry, (F)ail?:
  31. 90 Chips/Second? by StrixVariaXIX · · Score: 1

    That's 7,776,000 chips/day. I find that more than hard to believe.

    1. Re:90 Chips/Second? by KillerBob · · Score: 1

      That's 7,776,000 chips/day. I find that more than hard to believe.

      They're not building the chips themselves. ARM licenses their chip designs out to other fabricators. When you consider that most of the cell phones in the world have an ARM chip in them, as well as many embedded devices (ATMs, fridges, programmable coffee makers, DVD players, car stereos, iPods/portable MP3 players, programmable remote controls, telephones, etc.), it's really not hard to conceive that they're shipping 2 billion units a year. Actually, I'm a little surprised the number is so low.

      --
      If you believe everything you read, you'd better not read. - Japanese proverb
    2. Re:90 Chips/Second? by Zerth · · Score: 1

      I just got an oven that has more oomph than my first computer. Possibly more than my second, although much less disk.

    3. Re:90 Chips/Second? by Rewind · · Score: 1

      I dunno LOTS of things use ARMs. Two huge sellers that come to mind are Nintendo DSs and iPhones/iPod touches

      --
      ?
  32. Radeon by Anonymous Coward · · Score: 0

    ATI has used VLIW in its GPU for a few years now. It is beating nVidia quite readily.

    1. Re:Radeon by ShadowRangerRIT · · Score: 1

      Everything I've seen lately indicates that for GPGPU purposes (one of the somewhat useful ways to compare GPUs), nVidia is winning. There are strengths and weaknesses in each design, but the overall performance favors nVidia. Now I'm not saying this is necessarily because nVidia has better hardware; much of their advantage seems to be down to better compilers. But it's not as cut and dry for ATI as you think, and if they can't write a decent optimizing compiler, any hardware advantage they may have is moot.

      --
      $_ = "wftedskaebjgdpjgidbsmnjgcdwatb"; tr/a-z/oh, turtleneck Phrase Jar!/; print
  33. They are mostly in GSM SIM cards by Anonymous Coward · · Score: 0

    Yes, 2 billion units a year. Most of the mobile phones in the world have at least one ARM core in them, which adds up to an awful lot.

    1. Re:They are mostly in GSM SIM cards by appleguru · · Score: 1

      [citation needed]

      Last I checked sim cards just had embedded "smart cards" which are just fancy contacts to a relatively "dumb" small thin embedded security chip and some flash memory.

  34. Correcting myself by Kupfernigk · · Score: 1

    I meant "roll out the latest Windows Mobile on Arm..."

    --
    From scarped cliff or quarried stone she cries "A thousand types are gone, I care for nothing, no not one."
  35. Re:MAME on ARM in Debian by 0100010001010011 · · Score: 5, Interesting

    My SheevaPlug arrives via Fedex in about 30 minutes :).

    It's going to be like Christmas in a few hours. The Fedex box will be ripped apart strewn across the living room as will be the product packaging. I'll plug it straight into the wall and Ethernet, realize it doesn't do much. Break out the 8GB SD card and not sleep tonight.

  36. Who cares about Windows? by cheesybagel · · Score: 5, Interesting

    Even if there was a Windows port, if you cannot run the vast set of Windows applications a port is useless. You would be better off running a Linux distro since it effortlessly comes with most categories of apps people need, because said apps are open source and usually can be recompiled fairly easily. If most Windows applications were targeted at .NET by now I could see a point, but they are not.

    1. Re:Who cares about Windows? by Hurricane78 · · Score: 1

      As one user above said, the libraries for WinCE and WinNT are the same. Except for which parts are exposed. And porting consists of re-compiling and linking to different libraries. I don't think any software developer will have much trouble doing this.

      But nonetheless, as I said, it looks like, to predict the future, one could combine the "Year of Linux on the Desktop" meme and the "In Soviet Russia ..." meme into one, saying that it will soon be the year of the Desktop on (mobile) Linux. Meaning that Linux won't need to come to the desktop. Because the desktop will be an outdated concept, and Linux will run on everything that replaced it. :D

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    2. Re:Who cares about Windows? by Karellen · · Score: 1

      And porting consists of re-compiling and linking to different libraries. I don't think any software developer will have much trouble doing this.

      Except that Windows developers have a *really* bad habit of assuming that everything is a little-endian x86-32, because that's all they've ever had.

      Heck, it even catches some experienced *nix developers out every now and then, that apps will have strange bugs on platforms the developer doesn't own, even if they *try* to make their code architecture neutral. Most of the Windows software I've seen doesn't even try to make itself portable. Even "porting" to something as similar as x86-64 has exposed plenty of bugs in a fair amount of Windows software. And you think recompiling on ARM is going to "just work"?

      --
      Why doesn't the gene pool have a life guard?
  37. Re:It's JVC's VHS-C versus Sony's Video8 again by FrankieBaby1986 · · Score: 4, Insightful

    WIndowsMobile had years of time in the market before the iPhone and it had a lot more applications than the iPhone. The iPhone blew it out of the water in just a few short years.

    Let me preface this with a disclaimer. I never really liked WinMo, and I can't wait till I can buy a cheap, fast ARM netbook to run linux on!

    However, WinMo did not come about in the era of ubiquitous high-speed internet and wifi, large hosted storage and applications ('cloud' crap). I used to own an HP Jornada 320lx (precursor to netbook- a palmtop)

    WinMo however sucked because of poor app compatibility. The portable versions of word and excel were pretty useless. Nobody uses these types of apps regularly on an iPhone. The iPhone is largely (but not solely) a toy used for music, video playback (youtube) and web browsing. When WinMo was relevant, processing power and internet availability were not up to it, and so the only people buying it were using it primarily for Calendaring, Portable Office, and the like, and it wasn't all that great at it, as I mentioned before. As such, the usability, simplicity and broad appeal of the iPhone is simply not there.

    The scene is very different, it is hard to say just what will happen.

    --
    ERROR: SIG NOT FOUND (A)bort, (R)etry, (F)ail?:
  38. Re:MAME on ARM in Debian by walshy007 · · Score: 1

    how much did it cost you? been looking at getting one myself.

  39. Does such a thing exist? by Dimwit · · Score: 1

    I would love a full-size laptop (13" screen or better) with an ARM chip. Long battery life, full size keyboard and display. It'd be great.

    The only things I can find with ARM chips these days are tiny netbooks. The largest I've found is only 10".

    Anyone know any "big" ARM laptops?

    --
    ...but it's being eaten...by some...Linux or something...
    1. Re:Does such a thing exist? by Bert64 · · Score: 1

      Where did you find the 10" one?
      Only ones i've seen were smaller than this, and typically had very lowend previous gen arm chips and tiny non upgradeable amounts of memory.. Something around the spec of a sheevaplug, but in a laptop with multiple battery options (light 3-4 hour, heavier 1- hour) would be nice.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
  40. Re:MAME on ARM in Debian by 0100010001010011 · · Score: 3, Informative

    $99 + $17 shipping, no tax. There's only 1 supplier in the US at the moment.

    And for slashdotters, the devkit is MUCH better than PogoPlug or other 'final' products.

    USB -> JTAG adapter. If you fubar it, you should be able to unfubar it.
    SD Slot: 8GB card will act as the boot drive. Saving wear on the internal 512MB memory and allowing me to add a ton of other stuff.

    I plan on it being my IRC, AIM, Torrent, Usenet, XBMC Serving, HVAC Controlling, 1-Wire Weather Sensing, 5W (max) box.

    For kicks I'll probably do some mencoder benchmarks.

    FYI: http://computingplugs.com/ is hosted on a Plug. It survived the last Slashdotting. The guy was using it to stream a TV show and it was still only using 40% CPU. He only unplugged it when he didn't know he was getting slashdotted and thought it was acting weird.

  41. Re:MAME on ARM in Debian by The+Archon+V2.0 · · Score: 3, Funny

    My SheevaPlug arrives via Fedex in about 30 minutes :).

    how much did it cost you? been looking at getting one myself.

    Well, if he doesn't answer in the next 17 minutes, we know we're not gonna hear anything for a few days....

  42. That's a lot of chips by iliketrash · · Score: 0, Redundant

    "ARM will ship an estimated 90 chips per second this year"

    Really? Is this some kind of government math? That's 2.84 billion chips shipped in 2009.

  43. Re:MAME on ARM in Debian by walshy007 · · Score: 1

    decent price, nice bonus with the jtag adapter too, I still have a ghetto one I made for parallel port when I was playing with cpld's.

  44. Re:It's JVC's VHS-C versus Sony's Video8 again by CarpetShark · · Score: 2, Insightful

    VHS-C was compatible with people's home machines, so you could use your camcorder to tape family or vacations, and then just pop it into your VHS VCR to watch it on the big screen TV. With Sony's Video8 that wasn't possible, so VHS-C quickly dominated the camcorder market.

    Be careful about assuming causation here. It might have easily been that VHS-C sounded familiar to people who had VHS, and they went with what they knew. Video8 might have been just as successful if the names had simply been reversed.

  45. The monopoly was always Wintel by Britz · · Score: 1

    Neither Microsoft nor Intel had it. The perfect monopoly was always the duo. Both of them. Hence it was called Wintel by many in the industry. And AFAIR Intel was really up there with Microsoft when it came to playing hardball with the competition.

  46. So AMD is squezed from both ends now by xiando · · Score: 1

    The Intel has a monopoly on high-end CPUs right now while AMD is pretty much alone in delivering band-for-the-buck budget CPUs. Now ARM is trying to take on the really cheap budget segment? That is bad news for AMD, far worse news for them than it is for the Intel empire.

    1. Re:So AMD is squezed from both ends now by shutdown+-p+now · · Score: 1

      The Intel has a monopoly on high-end CPUs right now while AMD is pretty much alone in delivering band-for-the-buck budget CPUs. Now ARM is trying to take on the really cheap budget segment?

      Cheap budget != best bang-for-the-buck. AMD still makes fast CPUs, just not as fast as Intel top of the line (but cheaper in proportion). ARM is coming from the low-power, low-perf angle here, which is a different thing altogether; think netbooks etc.

  47. Re:It's JVC's VHS-C versus Sony's Video8 again by LWATCDR · · Score: 1

    But WinMo is still with us. The Treo and other WinMo smartphones did have internet data before the iPhone.
    What I think was the big advance was the App store. It made it easy to find, buy and sell software for your device. I do agree that it is hard to say what will happen but I hope that we get something more innovative than just little Windows machines running on Intel Atoms.

    --
    See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
  48. Re:MAME on ARM in Debian by Anonymous Coward · · Score: 0

    Yes. 100% support from some random dude on the internet. Try running mythtv on it including commflag... post your results somewhere. Others have.
    http://www.google.com/search?q=mythtv+sheevaplug&ie=utf-8&oe=utf-8&aq=t&rls=org.mozilla:en-US:official&client=firefox-a

  49. No mention of Acorn? by QJimbo · · Score: 2, Interesting

    Surprising nobody's mentioned Acorn Computers, the British company that actually gave us ARM. At the time Acorn simply used ARM to compete with Intel chips, in 1995 when the StrongARM Risc PC came out it was 233MHz, where as the latest Intel Pentium was 200Mhz or so. The advantages of the RISC architecture were also clearly present, with a higher MIPS rate. But of course the Windows beast could not be slain, and ARM went into portable devices, and became the most successful legacy of the Acorn era.

    Acorn is still around today in the form of Castle, Advantage Six and others, but it lives only really through enthusiast support. With ARM changing their focus to low power consumption (the reason they were able to step into the portable market in the first place), speed became less of an issue. The fastest ARM processors today are only 806mhz (in the form of the XScale), and so building an Acorn today that was realistically comparable to a modern PC is simply impossible.

    I'm just here hoping somebody ports Risc OS Open to x86, Apple managed it after all.

    1. Re:No mention of Acorn? by Haxamanish · · Score: 1

      I bought an Archimedes 305 right after its launch in 1987, so I share your nostalgia. But RISC OS has one major problem as an operating system these days: multitasking is co-operative, meaning that any non-co-operative program can hijack the complete OS.

    2. Re:No mention of Acorn? by Hurricane78 · · Score: 2, Interesting

      and so building an Acorn today that was realistically comparable to a modern PC is simply impossible.

      Oh boy are you wrong. :)
      With ARM's price and power ratio, one could slap 16 to 32 ARMs together, resulting in a more powerful, and still less energy consuming and cheaper "multicore" chip than the best one from Intel. :)
      I wait for mainboards with stackable ARM sockets. So that you can just put them on top of each other, with a thin heat-pipe layer in-between, leading to a cooler on the back wall of the case.

      Would look impressively cool (big win with the loud-voiced modders), and I'd be the first one to buy one. I run Linux anyway.

      Hey, think about it: Imagine you can just buy a couple of additional cores every few months, for little money, and over the course of 1-2 years, get a real powerful monster of a computer.

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    3. Re:No mention of Acorn? by footnmouth · · Score: 1

      >But RISC OS has one major problem as an operating system these days: multitasking is co-operative, meaning that any non-co-operative program can hijack the complete OS.
      Just like the iPhone. grrrrr

      --
      -- For evil to triumph it is enough that good men do nothing.
    4. Re:No mention of Acorn? by Alioth · · Score: 1

      ARM was *always* about low power consumption, right from the very first test article.

      I went to a talk by Steve Furber in September, where he discussed the BBC Micro, the development of the ARM, and the massively parallel ARM based system (thousands of cores) that he is now working on.

      They needed low power to make the chip inexpensive - they wanted the chip to be in plastic packaging which cost perhaps $1 per chip, rather than ceramic, which would cost around $10 per chip. (By then, Intel were already having to use ceramic packages due to the inefficiency of their designs). Not having any way to forecast accurately the power consumption of the chip they were designing, they did everything they could think of to keep power requirements low, desperately hoping it'd meet the 1W maximum they needed to make the chip inexpensive.

      When they got the test article back, they were astonished. They had *massively* overachieved - the original ARM had a power consumption of 0.1W.

      The original ARM was also specified in 808 lines of BBC BASIC.

      If you get the opportunity to see Steve Furber or Sophie Wilson talk about the ARM, take it.

      Intel have a huge ball and chain around them regarding the x86 architecture - the bit that just figures out how long the instruction is so it knows where to fetch the next one is the size of an entire ARM core. That is a huge opportunity cost they have to bear with low power designs, especially as even low power designs start to become multicore.

    5. Re:No mention of Acorn? by david.given · · Score: 1

      At the time Acorn simply used ARM to compete with Intel chips, in 1995 when the StrongARM Risc PC came out it was 233MHz, where as the latest Intel Pentium was 200Mhz or so.

      Actually...

      The ARM largely predates the Intel hegemony. Acorn designed it in about 1984 as a successor to the 6502 for the simple reason that they couldn't find any other processor that was fast enough to compete with the 6502! State of the art for 16 or 32 bit processors then were chips like the 68000, which had lousy interrupt performance.

      The first actual ARM computer was the Archimedes, which shipped in 1987. (Prior to that it had existed only as a second processor addon for the 6502-based BBC Micro.) It used a 16MHz ARM2. At the time the only Intel 32-bit processor was the iAPX; the 286 ruled the desktop market. The 386 would come out in 1988.

      As you say, the RISC PC came out in the mid-90s with a StrongARM, but by then Intel was working on the early Pentiums, and had pretty much won the desktop market.

      The fastest ARM processors today are only 806mhz...

      I have a SheevaPlug running at 1.2GHz; actual speed for integer stuff appears to roughly equivalent to a 500MHz Pentium. (Benchmarks here.)

      I'm just here hoping somebody ports Risc OS Open to x86, Apple managed it after all.

      Impossible, alas. RISC OS is a huge pile of undocumented hand-written ARM machine code. You'd need to rewrite it from scratch, from the ground up, to change architecture. Even just cleaning up the worst bugs (friends don't let friends allocate memory inside interrupt handlers) looks to be infeasible.

      OTOH if you want bug-for-bug compatibility, someone has it working on the BeagleBoard...

    6. Re:No mention of Acorn? by Skal+Tura · · Score: 1

      I would be running to get one, just like you ;)

      I've always wanted a computer on which when i want more number crunching power, i just could add a CPU or some ram.

      I wish someday i will see computers which is so modular that you could upgrade with a small addition at a time.

      Currently if i wanted to get any more number crunching power out of my computer it would be atleast 700euro trip to store... (Jumping to Core i7, DDR3 and a decent mobo as am already running top end of last gen.)

    7. Re:No mention of Acorn? by Anonymous Coward · · Score: 0

      cortex a9 is quad superscalar processor that goes up to 2ghz on each core with a respectable graphics dsp and io controller on die that at load uses 2 watts. atoms are inline single and dual core processors that currently have to have all of their chipset components outside the chip, they use five watts of power at load(which doesn't include chipset), and intel's current graphics offerings were anemic four years ago. A9 in terms of real world and MIPS performance spank the atom in every code performance category. also, arm chips cost half as much as intel chips to manufacture and do not need extremely advanced manufacturing techniques to stay competitive. the final nail in the atom coffin is that intel (in colusion with microsoft) insists on power plays with oems with such inane limitations such as mandating screen size limits, ram limits, and not allowing pcie, as well as making life as difficult as possible for chipset manufacturers (NVIDIA ION anyone?) Arm manufacturers, on the other hand, will sell chips to anybody and don't deal in this sort of market manipulation

      in short, the sooner ARM can kick intel where it hurts, their market domination, the better

      hell, if AMD could find a way to modify amd64 to use the ARM instruction set as a base, intel would be in deep trouble (EM64 is nothing but intel saving face by using amd technology and if they lost their licence to use it, say goodbye to the I7/I5 and core2 series)

  50. Atom by Anonymous Coward · · Score: 0

    There is an AI Touchbook review on the net somewhere in which the reviewer measured the draw from the wall. With the battery fully charged, it draws ~4 watts, and ~8 or 10 watts while charging. The omap3 consumes less electricity than the atom alone, both under full load. And the omap is on a 65nm process. All the fab technology Intel has isn't going to help them compete on power consumption or cost of manufacturing.

  51. ARM == Hype by Erich · · Score: 4, Insightful

    Yes, ARM marketing (notoriously overoptimistic) says they will have a 2GHz A9 in 28nm, relatively high performance process.

    But A9, in terms of efficiency, is not substantially better than where Atom will be. That shouldn't be surprising. They're both scalar architectures. They both have a little less than 15 useful registers. They both have similarly deep pipelines. They both rely on branch prediction for performance. Neither company has magic, it's not surprising that they're similar on the curve of performance / efficiency.

    Put another way, your instruction encoding doesn't really buy you all that much.

    Now ARM has some lower-end cores (ARM9, ARM11, Sparrow/CoretexA5) that are much more energy efficient than Atom. But they're also much lower performance.

    But this is how ARM's marketing plays it out: we have super-efficient cores (ARM9)! We have higher-performance cores (Theoretically, A9)! You think that ARM cores are somehow both high performance and much more efficient than Atom will be in the same technology... but this will probably turn out to be false.

    Put another way... are MIPS or PowerPC cores dramatically more efficient than x86 at similar performance levels? No. They have most of the same architecture benefits that ARM does... more, in many ways, because they have about double the number of useful registers. But they're on basically the same efficiency/performance curve as everyone else.

    You could probably do an x86 implementation that was similar to ARM11/A5... no floating point, no SSE, just the basic 386 instruction set. Give it a short pipeline and turn down the frequency, and it will probably compete relatively well on energy efficiency with those low-end ARMs.

    The thing I DON'T understand... why does ARM marketing get an article on slashdot every week or so?

    --

    -- Erich

    Slashdot reader since 1997

    1. Re:ARM == Hype by thaig · · Score: 1

      ....but one has a lot more baggage to carry around than the other. One doesn't have thumb and one doesn't have a very clever and compact instruction set. So it's dumb 386-mode would not make such good use of it's cache etc etc. Otherwise why didn't VIA or cyrix do what you're suggesting? Every company hypes it's products, Intel too, so what? At least ARM have actually been highly successful. PowerPC and MIPS - they aren't the embedded champions so why bring them up?

      Perhaps the reason why ARM did well is because it really did have a clever idea or two and everyone else was too arrogant to have considered the market that they all now want to enter.

      --
      This is all just my personal opinion.
    2. Re:ARM == Hype by Erich · · Score: 3, Informative
      Let me illustrate.

      ARM has ARM mode, Thumb Mode, Jazelle Mode, and ThumbEE mode. FOUR instruction sets. Multiple different floating point unit specs that are incompatible with each other. Crazy page table formats. The architecture spec is over 2000 pages long, for pete's sake!

      ARM has a more uniform encoding, but actually has a large number of instructions, and does crazy things like put a rotating shifter in the load address path. Not good from a modern pipeline perspective. You can get around it by breaking up the operation, but then you're getting into complex instruction decode like x86.

      I'm not saying ARM is bad. I'm just saying they have no magic. You're right, Intel doesn't either (though they do have manufacturing and an army of engineers to do hand-layout). Nor does MIPS or PPC. But MIPS does make energy efficient cores, roughly as good as ARM. They haven't been as popular as ARM, but they're around.

      And I'm certainly not saying x86 is great -- it's certainly not. I don't think it's quite as bad as people make it out to be...

      Look, I wish the architecture made a difference. For one, we'd all probably be using Alpha. That was a great, elegant, beautiful processor architecture. For another, I'd have much better job prospects. But it doesn't matter that much. Scalar architectures are scalar architectures. Instruction set makes some difference, but not very much.

      --

      -- Erich

      Slashdot reader since 1997

    3. Re:ARM == Hype by Hurricane78 · · Score: 1

      Uuum, sorry, but by specifically not mentioning, that a Atom only runs with a north-bridge that pulls a multiple of the power of the Atom itself, thereby hiding its real power usage, you fail, and I will ignore the rest of your comment, for lack of competence.

      Oh, and I have seen ARM Smartbook prototypes that take 1-2 watt TOTAL (including the Tegra GPU), and run pretty close to the 2 GHz already, with my own eyes. So don't tell me, something I have seen myself, can not possibly exist.

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    4. Re:ARM == Hype by evilviper · · Score: 1

      Oh, and I have seen ARM Smartbook prototypes that take 1-2 watt TOTAL (including the Tegra GPU), and run pretty close to the 2 GHz already, with my own eyes. So don't tell me, something I have seen myself, can not possibly exist.

      100% MHz-myth idiocy.

      Your 2GHz ARM Smartbook would probably compare decently to a 200MHz PentiumII, but a 2GHz Core2 would make your 2GHz ARM CPU look like it's standing still. Just look-up the DMIPS rating of the ARM chip, and an x86 chip...

      Better yet, ask yourself: "Why aren't there any supercomputers on the TOP500 which are based on ARM CPUs? Why are they all x86 or POWER?"

      The performance of ARM is all smoke and mirrors. They're designed to be impressively low-power, and compete well with slower microcontrolers, but don't hold a candle to real CPUs.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    5. Re:ARM == Hype by evilviper · · Score: 2, Informative

      At least ARM have actually been highly successful. PowerPC and MIPS - they aren't the embedded champions so why bring them up?

      MIPS has been a lot more successful in this space than ARM ever has. Cheap PCs all over China are using MIPS CPUs which rival 1GHz x86 CPUs. <$150 Netbooks have been available for a couple years now, using MIPS chips, a market ARM has been making a lot of noise about, but has only just now entered, and not even near the price point...

      Perhaps the reason why ARM did well is because it really did have a clever idea or two and everyone else was too arrogant to have considered the market that they all now want to enter.

      See above. ARM has been making a hell of a lot of PR noise, but that's the only thing they've done with any success.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    6. Re:ARM == Hype by Anonymous Coward · · Score: 0

      ARM is certainly a good amount less powerful per clock than modern x86 chips, but modern ARM smartphones are able to run a web browser (with fancy HTML5 features) and other real applications at a reasonable speed with far lower power usage (=longer battery life) than an x86 processor. x86 isn't going anywhere, but ARM processors can be very useful in that they are fast enough (or getting there) for a lot of people's everyday usage and they use far less power than x86 processors.

    7. Re:ARM == Hype by thaig · · Score: 1

      ARM has a lot of processors out there, in a lot of devices that are quite powerful (frankly those Chinese netbooks are probably less powerful than an iPhone with it's ARM). MIPS could have been the standard mobile CPU but it never was. Why? Someone just didn't think that was important? They missed out in other words but I think that's because they didn't see it coming.

      --
      This is all just my personal opinion.
    8. Re:ARM == Hype by thaig · · Score: 2, Informative

      Thumb is just a subset of ARM - so not another instruction set :-) and you haven't really said how a mini-i386 will get that code density. Jazelle etc just let you implement very fast Java apps on a very low power CPU - so what's wrong with that?

      There is no such thing as magic - it's all design at some point. ARM had the freedom to invent a better instruction set and they did. It allowed them to make very cheap CPUs at a time when that was needed. Now that processes have improved we can consider x86 but only when wearing very pink spectacles.

      So there were problems with floating point but it doesn't seem to have stopped anyone.

      I think that you're a bit fixated on CPUs that fit into machines with power cords or heavy batteries and what makes them good - which isn't what makes mobile CPUs good. I think that ARM deserve credit for seeing how important it would become and having exactly what was needed at the right time. They have salespeople (cough) now like any successful company but I have never thought that they benefit from more hype than anyone else.

      --
      This is all just my personal opinion.
    9. Re:ARM == Hype by JackDW · · Score: 1

      Actually the core parts of ARM's ISA were designed for maximising performance, not minimising energy. None of the 16-bit CISC designs circa 1982 could run Acorn's BBC BASIC runtime as efficiently as the 8-bit 6502. So Acorn's technical staff designed a new CPU; a fully-pipelined design based on the new idea of "RISC". It would go into desktop machines, like the Archimedes. Performance per watt was of no importance at this stage; this was the early 1980s, after all. It was only in the 90s that ARM started to focus on low power as a selling point, and by then (like Intel) they were stuck with an unchangeable core ISA...

      --
      You're an immobile computer, remember?
    10. Re:ARM == Hype by Anonymous Coward · · Score: 0

      Cortex A9 is not only superscalar like its A8 sibling, it also have out-of-order processing which I assure you the Intel Atom haven't.
      As of the instruction encoding any ARM is theoretically more efficient than x86 instructions as they support conditional execution, three operands and for some a "free" shift/rotate on data before execution the ALU operation.
      It's not unusual that hand optimized ARM inner loops have 1/2 or less instructions than the x86 equivalent, at least in the area I'm familiar with.

    11. Re:ARM == Hype by makomk · · Score: 1

      Your 2GHz ARM Smartbook would probably compare decently to a 200MHz PentiumII, but a 2GHz Core2 would make your 2GHz ARM CPU look like it's standing still. Just look-up the DMIPS rating of the ARM chip, and an x86 chip...

      A 2GHz Core2 would also use 10 times the power, cost 10 to 20 times more, and be 10 to 20 times bigger. The real comparison is with chips like Atom - obviously even Intel doesn't consider a Core2 chip a suitable substitute for Atom, or they wouldn't have created it in the first place.

    12. Re:ARM == Hype by Anonymous Coward · · Score: 0

      "The thing I DON'T understand... why does ARM marketing get an article on slashdot every week or so?"

      because x86IsDying(TM), and that will bring the YearOfLinuxDesktop(TM). Somehow.

    13. Re:ARM == Hype by Halo1 · · Score: 1

      Thumb is just a subset of ARM - so not another instruction set :-)

      ARM instructions are encoded as 32 bits per instruction. Thumb instructions are 16 bits per instruction. You have to explicitly switch to Thumb mode before you can execute any Thumb instructions (and back to ARM mode if you want to execute ARM instructions again). So they most definitely are two different instruction sets. The fact that they have similar mnemonics is irrelevant.

      Jazelle etc just let you implement very fast Java apps on a very low power CPU - so what's wrong with that?

      The GP didn't say there was anything wrong with that. He said that this was an example of another instruction set supported by ARM CPUs.

      There is no such thing as magic - it's all design at some point.

      Yes, that's what the GP said.

      I think that you're a bit fixated on CPUs that fit into machines with power cords or heavy batteries and what makes them good - which isn't what makes mobile CPUs good.

      I think that you're a bit fixated on straw man arguments.

      --
      Donate free food here
    14. Re:ARM == Hype by tslettebo · · Score: 1

      Crazy page table formats. [...] ARM has a more uniform encoding, but actually has a large number of instructions, and does crazy things like put a rotating shifter in the load address path.

      Could you have expanded on these two statements? What's "crazy" about its page table format?

      As for the ability to shift the address offset of a load/store, what's the problem with that? x86 has the same, except that their shifts are limited to a few places (at least it used to be that way).

      Look, I wish the architecture made a difference. For one, we'd all probably be using Alpha. That was a great, elegant, beautiful processor architecture.

      I don't know much about the Alpha, as it's been hard to find an assembly reference online, but some of what I think makes the ARM design elegant is:

      - Three-register architecture, where you may operate on two registers, and store the result in a third.
      - Conditional execution of all instructions (not for some of the new classes of instructions, such as the SIMD instructions, though).
      - Optional PSR updating.
      - Optional shifting of one of the operands by a constant, or a fourth register.

      The combination of features like this makes for very elegant, powerful, and compact code.

      The question is, can the Alpha do things like this?

      I think you'll find that what is considered the most "elegant" and "best" processor tends to be highly subjective...

      Furthermore, describing design choices as "crazy" doesn't sound very objective or balanced...

      Regards,

      Terje

    15. Re:ARM == Hype by Erich · · Score: 2, Informative
      Look, I'm not saying x86 isn't crazy. It doesn't have just shifting addressing modes, but ones with multiplies. That really forces you to have (A) an architecture that uses multicycle instructions, (B) a really horrid pipeline, or (C) splitting up instructions into multiple components that flow through a normal pipeline.

      Having shifts in the address calculation is fine for ARM7 where you're trying to squeeze every possible functionality out of a tiny number of gates, and don't really care about performance. But for even a reasonably high-performance design, you need to have a consistent pipeline.

      Probably the most important pipeline is the Decode->RegRead->AddressFormation->Dcache->Writeback pipeline. The latency of this pipeline is critical for performance. ARM has some advantages here: uniform (or, somewhat less so, semi-uniform, a la Thumb2) is easier to decode than variable-length at the byte level x86. Most architectures have an adder in the AddressFormation part (though notably not ia64). If you add two registers (which you can't in MIPS) you probably want to be able to shift by the access size because you're doing something like indexing into an array. So a small left shifter before the adder isn't uncommon, and it's usually about a 4:1 mux in terms of delay.

      But ARM allows you to do full rotations in front of the adder. This means you need more levels of logic in front of the address calculation adder, which hurts your memory latency. You can make it a multicycle instruction or split it up into multiple instructions (and many implementations do), but that of course adds significant complexity.

      The page table formats are kind of kooky. Most 32 bit architectures choose 4K pages as the minimal page size. 4K L1 translation and 4K L2 translation translates all 20 bits you need. The page tables are a multiple of the page size, which is handy. It's so clean, it's pretty obviously the "right" thing to do.

      ARM has a 16KB l1 translation, because they used to support 1KB pages, but no longer do. They have strange attributes that move around the format, which makes it more difficult to manipulate the page table entries. They also have no free bits, which makes it a pain in Linux to keep information like how new or clean the page is.

      I will say that the page tables are getting cleaner as they deprecate things like 1KB pages, but they're still pretty painful compared with other architectures.

      The Alpha Architecture Handbook is a good read, and Alpha is my very favorite RISC. Not that it's magical, either, but it's a lot cleaner than ARM. And it's less than half the length of the ARM Architecture Reference Manual (ARM ARM, which I must admit is a clever acronym).

      --

      -- Erich

      Slashdot reader since 1997

    16. Re:ARM == Hype by Anonymous Coward · · Score: 0

      "The architecture spec is over 2000 pages long, for pete's sake! "

      Is that much? Ooxml has over 7000 pages currently. 2000 is just peanuts. :P

    17. Re:ARM == Hype by tslettebo · · Score: 1

      Thanks for your substantial reply, as well as the link to the Alpha Architecture Handbook. I'll look into it.

      Although I'm not a hardware designer, myself, I've co-authored the extASM ARM assembler, currently being updated to ARMv7. The assembler is itself written in ARM assembly, about 20,000 lines of it, so I've got quite a bit of experience with writing ARM code. :)

      I understand what you mean about the shifter and the page tables, now.

      As you allude to, the designers of the ARM weren't stupid when they made this design, but as it often is, what may have been an advantage (or an efficient design) at one time, may turn into a disadvantage (or contributing to less efficiency) later, as the field evolves.

      One such thing I was recently made aware of is the SWI (system call) instruction. At the time, it was a reasonable design: Encode the system call number in the instruction (thereby saving a move instruction before the call). At the time, there were no instruction/data caches. However, with today's separate instruction/data caches, using the SWI instruction leads to "polluting" the data cache, as it needs to read the instruction (thus fill a data cache line) to find out the system call number.

      Also, historical reasons and market factors may contribute to making a design that was once simple and clean/elegant, become rather more complex and loose some of its elegance. In the ARM's case, it has become rather a lot more complex (I know that all too well, having to implement all of its instructions in extASM... :) ), but that has also made it more powerful (such as the addition of long multiply, SIMD, and floating point support).

      Regards,

      Terje

    18. Re:ARM == Hype by evilviper · · Score: 1

      modern ARM smartphones are able to run a web browser (with fancy HTML5 features) and other real applications at a reasonable speed with far lower power usage (=longer battery life) than an x86 processor

      Software development priorities have INFINITELY more to do with it than the CPU. Firefox is a dog. It should be 100X faster.

      ARM processors can be very useful in that they are fast enough (or getting there) for a lot of people's everyday usage and they use far less power than x86 processors.

      Yes, but you're talking about saving a couple watts, in a device which uses 20+. You wouldn't much notice if the CPU was completely eliminated.

      And besides, I was simply refuting the parent's ridiculous assertion.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    19. Re:ARM == Hype by evilviper · · Score: 1

      ARM has a lot of processors out there

      Irrelevant. Zilog has a lot of processors out there, too... They're not competing in the same market. ARM is working on breaking-in, MIPS is already there, as is x86 (Geode and ULV Pentiums more than Atom just yet).

      (frankly those Chinese netbooks are probably less powerful than an iPhone with it's ARM).

      Yes, the several-years-old, absolutely dirt cheap, 400MHz MIPS CPU used in cheap Chinese-made netbooks is likely slightly less powerful than the nice new and expensive ARM CPU found in the similarly expensive iPhone... So what?

      Take a look at the 3rd generation Dragon Chip if you want power. Super-scalar, competing with desktop chips, still in a minuscule power envelope. Much faster than anything ARM has to offer.

      Though, PowerPC chips tend to put them both to shame, while in the same ultra-low-power category.

      MIPS could have been the standard mobile CPU but it never was. Why?

      A very good question... considering that MIPS WAS in fact the standard mobile CPU for YEARS.

      "Through the 1990s, the MIPS architecture was widely adopted by the embedded market"
      "it was estimated that one in three RISC microprocessors produced were MIPS"

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    20. Re:ARM == Hype by thaig · · Score: 1

      The GGp did complain - he said "for pete's sake".
      Which I assumed to be a complaint although it's not clear exactly what it was about. Perhaps at there being too many instruction sets. What is too many?

      Thumb is a compression scheme for the existing instruction set implemented with 16-bit opcodes. It does not add anything new. To quote the ARM description:

      'A "Thumb-aware" core is a standard ARM processor fitted with a Thumb decompressor in the instruction pipeline. The designer therefore gets all the underlying power of the 32-bit ARM architecture as well as excellent code density from Thumb, all at 8-bit system code density.'

      So I can point to one thing which it is a bit misleading to complain about.

      The points made about there being no magic in ARM were in response to an implication that an i386 design could be made that did what ARM does. I'm trying to say that there may not be magic but you can't make the instruction sets the same and that *is* important since the instruction set is part of the design.

      --
      This is all just my personal opinion.
    21. Re:ARM == Hype by thaig · · Score: 1

      "part of the design" should read "an important part of the success of the overall design"

      --
      This is all just my personal opinion.
  52. Total Annihilation by Anonymous Coward · · Score: 0

    You know, that's what's going to happen when this whole ARM vs. Core rivalry thing gets taken just a step too far. But don't say you weren't warned.

  53. just don't call it a computer by Jessta · · Score: 1

    If you sell people a 'computer' they'll expect it to run windows or at least run all their 'PC' software, but if you sell it as a PDA or a smartphone, or a netgadget thingy then they won't expect it to run 'PC' software and so won't mind that it doesn't.
    eg. the iPhone is widely populate.

    --
    ...and that is all I have to say about that.
    http://jessta.id.au
  54. You can bet... by CAIMLAS · · Score: 1

    Dollars to doughnuts, you can bet that Microsoft is working on porting Windows 7 and Office, as well as their various other software packages, to ARM processors. With ARM breeching the 1GHz mark and fully capable 3d acceleration, they're at least on par with an Intel chipseted Atom, and in many ways vastly superior. With most people preferring "as cheap as possible" computers - because they'll do the job just fine - things are sure to move towards ARM.

    --
    ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    1. Re:You can bet... by nxtw · · Score: 1

      With ARM breeching the 1GHz mark and fully capable 3d acceleration, they're at least on par with an Intel chipseted Atom

      Or so ARM claims. Have you seen an ARM-based system that is comparable to the 945GSE + N270? Will Intel have anything better than the N270 by the time comparable ARM systems are mass produced, if ARM-based systems are as great as some claim?

    2. Re:You can bet... by Anonymous Coward · · Score: 0

      It's not ARM claiming it. It's half a dozen+ companies building SoCs based on ARM processors. ARM isn't like Intel; they license their chip tech, which is how they're able to hit such a high production number. Notable companies are Qualcomm (Snapdragon) and Nvidia (Tegra), but there are also others.

      And yes, we'll see those devices a long time before Intel comes even close.

    3. Re:You can bet... by nxtw · · Score: 1

      And yes, we'll see those devices a long time before Intel comes even close.

      I have yet to see any substantial comparison between an actual ARM-based netbook and an Atom-based one. Not even a prototype. I have yet to see any evidence showing that an ARM CPU can compete with an Atom N270 performance-wise.

    4. Re:You can bet... by Anonymous Coward · · Score: 0

      I did it in the shop:
      Acer Whatever - Sharp Netwalker
      Windows - Ubuntu
      Slow as molasses - Slow as molasses
      Battery hog - ~8 hours of real battery time
      Small - Smaller
      Really the performance is the part that is most similar and Atom is running on more hertz.
      I got the ARM device, but to be fair I wanted to hack it. Else I would have bought neither.
      The only part where it needs help is video decoding. An on demand coprocessor would rock there.

    5. Re:You can bet... by nxtw · · Score: 1

      I've used an Atom N270 netbook for the past six months, and it's hardly slow as molasses.

      I've read that the NetWalker takes 37 seconds to load OpenOffice... I've never counted how long it takes to load an Office 2007 application on my Atom netbook, but it's certainly less than 10 seconds. It's able to decode 480p H.264 video streams using only the CPU, and I've been able to play some 720p H.264 streams as well.

  55. Re:MAME on ARM in Debian by mirix · · Score: 1

    JTAG adaptor is included?

    That's great, most outfits charge $99+ for that alone.

    --
    Sent from my PDP-11
  56. You misunderstand by Anonymous Coward · · Score: 0

    He said "oh right I can't", which is accurate. YOU can buy one, but HE can't. Not until he cleans that basement, that is. It looks like a bomb went off in there! Once it's nice and tidy, then mom will let him.

    But for the moment it's a true statement. Until he gets the pizza boxes out to the curb anyways.

  57. Poor fellow with his Sheevaplug by yooy · · Score: 1

    Should have bought a Fritzbox instead...

  58. Re:It's JVC's VHS-C versus Sony's Video8 again by pseudonomous · · Score: 1

    One thing is sure; whatever platform ends up dominating the netbook space really needs some work done in terms of optimizing the user interface for smaller screens, becuase, as it stands, some software is completely unusable (without plugging in an external monitor) due to windows being designed to be too tall. I think this is one space where Microsoft could potentially have done a lot more than they have; linux is also a mixed bag, but at least Intel and Canonical are working on the problem.

  59. The ARM is an incredibly good chip... by PhunkySchtuff · · Score: 2, Interesting

    I've been a fan of the ARM for years, ever since I encountered them in high school in Acorn Archimedes computers. The instruction set was so elegant compared to the i486 and Motorola 68k series chips that it was up against at the time. Flat memory model, none of this segment:offset stuff on the intel platform and a really well-thought-out streamlined set of core instructions.

    I've recently got my hands on an ARM platform, and compared to what I was playing with in school, this thing is light-years ahead. 600HMz ARM, 256MB RAM, 256MB NAND Flash, GPU with ~10M polys/sec, SD Card Interface, High-speed USB 2.0 etc etc. It's all on a board that's 3" square, draws something like 1.75W at full tilt (it is powered from one of it's USB ports) and costs $150USD. No moving parts, not even a fan. 100% solid state.

    I'm currently running Ubuntu on it, but there are other systems like Angstrom and QNX that will happily boot on it as well. Boot the OS off SD card, swap them out to switch operating environments and it's all good.

    http://automatica.com.au/blog/2009/10/the-beagleboard/

    http://beagleboard.org/

    I've got no affiliation with Texas Instruments or anything like that, I'm just a happy customer who is amazed at the power of this platform, it's low cost, low power usage and flexibility opens the doors to doing so many things with it...

  60. The instruction set isn't that big a deal by argent · · Score: 1

    The other difference to the application, of course, is that the app isn't compiled for ARM instructions, they're compiled for x86 instructions.

    So? The RPMs you download from Fedora aren't compiled for ARM either, and packages that are have had to be pretty extensively modified to be usable on a handheld screen. When I ran Familiar on my iPaq there was very little software other than command line stuff that was really usable... that's why I flashed it back to Windows CE.

  61. Re:It's JVC's VHS-C versus Sony's Video8 again by LWATCDR · · Score: 1

    Don't forget Chrome OS from Google. I have high hopes for Chrome OS if for no other reason than it drops X windows. Yes that will mean that some software will not work but I wonder how many will be left out if they port GTK and QT to the new video system? If needed I am sure that it would be possible to add an X-Windows layer to the system similar to what Apple does on the Mac.

    --
    See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
  62. Re:MAME on ARM in Debian by petermgreen · · Score: 1

    It's internal, there is a mini-usb connector on the side which has a USB to serial and JTAG converter chip behind it.

    --
    note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  63. Unique Licensing Model? by eison · · Score: 1

    What is this unique licensing model, how is it different from standard chip licensing models, and why is Arm's success due to it?
    Don't manufacturers just pay some fee for every chip? Where does this license come into play?

    --
    is competition good, or is duplication of effort bad?
  64. Re:It's JVC's VHS-C versus Sony's Video8 again by petermgreen · · Score: 1

    XP itself is perfectly usable on 1024x600 (the most common netbook resoloution afaict), heck with the classic theme it's interface is much the same as windows 9x and I ran that at 640x480 for a while until I could afford a new monitor.

    The problem is app vendors became used to the minimum common screen resoloution being 1024x768 and developed apps based on that assumption, a couple of offenders that immediately spring to mind are iTunes and the lego mindstorms nxt software. There isn't really a whole lot MS can do about this.

    This was one of the reasons I waited and splashed out the extra cash to get a HP mini 5101 with a 10 inch 1366x768 screen.

    --
    note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  65. ReactOS on ARM by Anonymous Coward · · Score: 0

    ReactOS is a Windows clone currently being ported to ARM

    http://www.reactos.org/en/newsletter_37.html

    So what does ARM need?

  66. I forgive them, they are Infoworld by Anonymous Coward · · Score: 0

    'One thing ARM doesn't have, however, is Windows,' McAllister writes, something that could ultimately stymie ARM's plans to compete on the low end of the netbook market.

    What a bunch of tripe! Microsoft bullied all the laptop manufacturers into upping their harware specs and offering XP. They shot themselves in the foot doing this as it needlessly inflates the price of the 'netbook'.

    This is likely an opportunity for ARM to flood the market with supper cheap linux netbooks.

  67. Re:It's JVC's VHS-C versus Sony's Video8 again by DRACO- · · Score: 1

    He's not assuming. When I worked retail, the first question out of a customer's mouth was, 'Will this work in my vcr?" or "Is there an adapter for my VHS-C/Sony 8/hi8/digital8?" I had several that had Sony 8/hi8/digital8 cameras swear up and down that there had to be a vcr cassette adapter for their camera's tapes--For them I showed them the VHC-C adapter and told them "It wont work, but you can buy it anyways if you dont belive me."

    Not a one of the customers knew the difference between the formats. They knew SONY as a brand name and often wanted SONY. I had some ask for SONY cameras with VHS-C after explaining the differences. We often steered joe customers to VHS-C in herds because we knew they wanted simplicity. Throw some batteries in the adapter (or not if it is geared), shove the VHS-C in and shove in the vcr.. done. Any other format required cabling the camera to the tv, or vcr or dvd burner or pc and fat finger mashing the tiny buttons on the camera to play the video back.

    --
    Consider yourself blessed if you are sneezed on by a dragon and only get wet, it could have been a fireball.