Shifting Apps To ARM Chips Could Save Laptop Batteries 326
An anonymous reader writes "When is an Intel PC not an Intel PC? When it moves applications such as Internet browsing and email on to an ARM processor because it can get longer battery life. And according to a story at EE Times, this hybrid Intel-ARM processor approach is being taken by PC makers as prominent as Dell. The problem for Intel: Why would you switch out of 'all-day' mode and use the Intel processor? The problem for ARM: lacking support from Microsoft for Windows; the applications it runs for the PC have to do so under Linux."
Not a problem (Score:5, Interesting)
Not a problem for everyone. I've already got an ARM-based Linux running on a NSLU32 NAS head - 32Mb RAM, 32 Mb flash. If I could get a lightweight laptop with a modern ARM chip, I would be over the moon.
Re:Not a problem (Score:5, Interesting)
Re: (Score:2, Insightful)
It just begs a question, for WHOM REALLY is Windows and its software a limiting factor? It looks now as if the only people who just would die from not having access to Windows are those who put their whole commerce on it and people who sit and play the latest games. ALMOST everyone else has had choice for at least a year now, and that choice is rapidly improving. Heck, I did not know what Linux really was a year ago, and now I do not see which things is it that it cannot do. I have my text input app, a medi
Re: (Score:2)
Even games need not be a problem, the nintendo ds is arm based and probably wouldn't be terribly difficult to emulate on an arm based laptop. There are plenty of games for the ds, games which are suited to small low powered machines.
If you want to play big bloated games with fancy graphics then a netbook was never a choice anyway.
Re: (Score:2)
That were exactly my thoughts the other day as I was preparing a birthday gift for my mother. You can imagine the kind and multitude and last but not least, the kind of generics the applications she needs to run ;-) Even two years ago, I could not with a confidence in my heart propose a Linux based desktop to her. Today I feel I can, given I run my desktop completely hassle free, and I do quite a lot more things on it than she will ever imagine. Even Skype, albeit proprietary, something she uses, exists on
Re:Not a problem (Score:5, Informative)
WINE is just Win32 for POSIXy platforms. It's not able to rewrite x86 binary for ARM. You could perhaps take Windows software compiled for an ARM processor and run it, but that kind of defeats the point of using Linux for portability in the first place. KVM/Xen also do not rewrite binary for other architectures. QEMU could do it, but performance and battery life would drop dramatically.
Darwine already does this (Score:5, Informative)
WINE is just Win32 for POSIXy platforms. It's not able to rewrite x86 binary for ARM.
Indeed, *wine* doesn't do it itself. But nothing prevents you from running a separate layer to do the translation.
QEMU has a Linux-on-Linux mode, where it doesn't emulate a full blown virtual PC, it only runs the application targeting a foreign architectures inside the emulator and passes along the calls to the actual native OS and libraries.
Darwine has been doing exactly this to run x86 Win32 application on PPC Mac OS X using a combination of Wine and QEMU. It should be possible to build a similar stack to run x86 Win32 application on ARM Linux.
But don't expect much performance from it on an ARM netbook. It will probably OK to run a couple of simple tools. It won't probably work with games or other more resource intensive application.
But gamers aren't the machine's main audience anyway, the ARM netbooks are targetted at people who just want Web, Email & Chat, with the longest possible battery life.
Although, you probably could get better Win32 performance (at the cost of battery life) with dual-chip machine (like DELL Lattitude ON) or using accelerator boards if the ARM netbooks has some standard connector (like Xpress card).
Re: (Score:2)
Re:Not a problem (Score:5, Funny)
Re:Jack Bauer Option (Score:4, Funny)
"Have you used Windows Mobile? That's something I reserve for inflicting on only my worst enemies and only as a last resort. It's the Jack Bauer option of OSs."
That is an insult to Jack Bauer. He is competent and works 24 hours a day.
Re:Jack Bauer Option (Score:4, Funny)
"Have you used Windows Mobile? That's something I reserve for inflicting on only my worst enemies and only as a last resort. It's the Jack Bauer option of OSs."
That is an insult to Jack Bauer. He is competent and works 24 hours a day.
But only one day a year.
Re:Jack Bauer Option (Score:4, Funny)
Yeah, but he spends the rest of the year describing everything he did on that one day to ad-nauseam, and he always makes it sound like he saved the world.
Re: (Score:2)
It doesn't run the same apps, it is only partially source compatible and 99% of windows apps don't come with source code anyway.
Compare that to arm linux, on which 99% of linux apps can simply be recompiled, the source is available for anyone to do the compile and most apps are already available precompiled for arm, look at the debian/arm packages...
Binary closed source software is the millstone, if you have the source then porting to a new superior architecture is easy, and you don't have to do it because
Pocket PC (Score:2)
Windows CE, maybe, but that has far less capabilities (and applications) than Linux on ARM does.
Citation needed that popular Pocket PC applications [google.com] are few and far between.
And WINE doesn't support Windows CE anyway.
Yet.
Re: (Score:2, Interesting)
I just ordered one of these. [openpandora.org] 256MB RAM, 512MB flash, ARM Cortex-A8.
Re: (Score:3, Funny)
Can someone send a crate of these NSLU32 to NASA?
Re: (Score:3, Funny)
Sure... now, how many bushels in a crate [cnn.com]?
Re:Not a problem (Score:4, Insightful)
Not really even a problem for Windows, at least a long term one.
There have been some instances (PPC Mac I think?) where they ran a lightweight QEMU + Wine to get wine working on a non-Intel platform.
They may start a standard application layer that will determine if the binary is x86 or ARM, and shuffle it to the correct processor, they applications will only need to make ARM based variants. Either that or use something related to dynamic recompiling to put stuff on the ARM processor on the fly.
Now, the question is, do they want to spend the effort.
Re: (Score:2)
...But really you have to talk to Microsoft about when they want to support ARM architectures. It's not up to us," answered East. "We're seeing a lot of activity in the Linux space so I don't think it's a serious brake on our progress into that new application area, right now," he concluded.
ARM notebook (Score:4, Insightful)
Funny...I read the story and was going to ask on this thread, "Where could I get an ARM-based laptop to run Linux on?" All day on a battery would be fantastic.
Re: (Score:3, Insightful)
I don't know about laptops, but there's a PDA-like device called the Pandora [openpandora.org].
It meets your "all day" requirement - according to the devs, it has a ~10hr battery life when doing stuff like browsing the net. It can also drop into and out of standby very quickly, to save even more power when not in use.
It has a touchscreen, mini keyboard, and gaming controls, so it does a bit of everything. Good for note-taking, good for surfing, good for emulators.
The biggest negative is right now they aren't in mass producti
Would you settle for a MIPS-based netbook? (Score:2)
I think I'd get one of these Alpha 400 MIPS netbooks [elanso.com] although I'd prefer more memory.
Confusing name (Score:2)
I think I'd get one of these Alpha 400 MIPS netbooks
That looks like similar CPU specs and price to Sony's PSP. But from the name only, is it a MIPS CPU or an Alpha CPU? I wonder if HP (owner of Digital) isn't already having its legal department draft a cease-and-desist for the maker of these netbooks.
Re:Not a problem (Score:5, Interesting)
About 10 years ago I had an IBM z-50. It was about the size of one of the larger Eee's and sported a MIPS processor. At that time (with late 90s battery and display technology) it offered a decent computer (I made it run NetBSD later in its life) with a 10 hour battery life.
A decent laptop built around one of these low-power processors could last a week on a single charge and a big enough battery.
As for desktops, how many ARM cores, FPUs, vector units and cache can be put on a Core i7 die?
Re: (Score:2)
Not a problem for everyone.
Indeed. That's why the article says "The problem for ARM", not "the problem for everyone".
Happy though you are running Linux, ARM themselves would love for the other 99% of the market to be able to run their OS of choice on an ARM processor.
You could argue that it would be nice if this could be achieved by moving people to Linux. ARM, however, just want people to buy their chips in large quantities, and don't particularly care why they're doing it.
Re: (Score:2)
I'd actually argue otherwise. I'd suspect the vast majority
Re: (Score:3, Insightful)
Not a problem for everyone. I've already got an ARM-based Linux running on a NSLU32 NAS head - 32Mb RAM, 32 Mb flash. If I could get a lightweight laptop with a modern ARM chip, I would be over the moon.
Exactly, my first thought is that it sounds like a feature!
Re:Not a problem (Score:4, Informative)
yep, Pandora fills this niche. 0.3kg, ARM, 10h battery, runs ubuntu just normally. But it's very small, only a 4.3" screen 800x480. About the size of DS. http://openpandora.org/ [openpandora.org]
It's just a startup now, people did preorders (by preordering it means that you are trusting them ;) and it will be delivered about March or April. I expect that by the end of the year they will be selling it in online shops in a usual way.
It's a perfect UMPC for me, a really "mobile" PC, smaller than my wallet, actually.
Re: (Score:3, Funny)
It's a perfect UMPC for me, a really "mobile" PC, smaller than my wallet, actually.
You must have a george constanza wallet. I'll be impressed when they get a really "mobile" PC smaller than my wallet [all-ett.com].
Re: (Score:2)
I don't see it a problem for windows. You use the ARM processor as an external device. When you Run an ARM app it will just switch to that processor for the bulk of the processing. It would be something like a MasPar setup where you have your Main Platform and OS then it uses additional processors as an other device.
Re: (Score:2)
Second that. A tiny laptop that's as powerful as an iPhone would be fine with me.
Re: (Score:2)
If I could get a lightweight laptop with a modern ARM chip, I would be over the moon.
Try waiting for Pandora orders to open up again.
Re: (Score:2)
Re: (Score:3, Insightful)
The reason Teh Lunix fails when sold at retail is primarily due to returns. If you sell out all your computers, and 80% of them get returned because people don't want Teh Lunix... how are you supposed to make a profit? The profit margin on computers is very low, and if a company has to sell at a steep discount for "open box"... they've just lost money.
I don't know why this guy got modded down except for the typical mindless pro-Linux bias here. The above is realistic. I don't know if it's 80%, but Linux desktops see FAR more returns than Windows desktops. MacOS desktops see more returns too, that's part of the reason for the high costs. Compatibility is a major factor. In practice, this completely negates any cost advantage Linux might have. You add in support costs and selling Linux is basically a loser for most PC vendors. It makes a LOT more sense for
And this is how Linux will win. (Score:5, Insightful)
And this is how Linux will win. Not with a bang but a whimper. Embedded appliances, dedicated purpose applications, and multi-platform compatibility.
Firefox, Thunderbird, and (hopefully) soon KDE.
MS users who don't know any better, will win this for us.
Geeks like us have already dominated the server-side of the Linux equation, now fools will win the desktop for us.
Re: (Score:2)
Re: (Score:2)
And this is how Linux will win. Not with a bang but a whimper. Embedded appliances, dedicated purpose applications, and multi-platform compatibility.
Firefox, Thunderbird, and (hopefully) soon KDE.
MS users who don't know any better, will win this for us.
Geeks like us have already dominated the server-side of the Linux equation, now fools will win the desktop for us.
Given the differences between the two markets (server and desktop) I wouldn't write off MS so quickly.
A different scenario - Intel uses it's Atom as the pathway to a combo setup - develop the Atom to run a low power mode and switch to another processor as needed. Intel's advantage is that they can build the bridge into the design - and work with MS to adapt Windows to use the design.
Do not underestimate Wintel's ability to take on challengers and adopt good ideas to their own ends.
Re:And this is how Linux will win. (Score:4, Interesting)
windows CE is not windows. If the advantage of using windows CE is getting to use your old, familiar windows programs, good luck, because you're going to need at least a recompile if not a gigantic refactoring to get it to run on CE. If you're going to refactor anyway, then you don't necessarily have to choose CE.
Re:And this is how Linux will win. (Score:5, Interesting)
Honestly, an appropriately skinned version of Linux would probably be more familiar to most users than would WinCE.
Re: (Score:2)
WindowsCE runs on ARM and x86.
Well I'm sure we could care less about x86 ATM because we have enough operating systems that run on it, and also the article is talking about ARM, not x86. Also, WinCE != Windows, the underlying system is vastly different (they do, after all, release the source code under the "shared source" license, don't they?) and therefore the system calls are bound to be different unless an application is specifically designed (embedded Visual C++) to be run in that embedded environment.
So unless your favorite games
Re: (Score:2)
Options (Score:2, Funny)
Or... you could just switch to linux.
Nah, too easy.
Re: (Score:2, Insightful)
Hasn't been easy for me in my dozens of attempts over the past couple of years.
Re:Options (Score:4, Insightful)
Out of curiousity, not hostility, can I ask why?
I work as a systems architect/administrator (whatever you want to call it) for UNIX/Linux-based large datacenters, but also use Linux personally and for non-technical tasks (e.g. Word, Excel, and assorted other files), without any difficulty. And I've been using Linux for almost 10 years now - back when things were difficult for users that weren't highly technical.
The only things I ever find myself using Windows for is to run Visio (if someone could recommend a F/OSS replacement for it, it would be greatly appreciated, but I have yet to find one as full-featured - or even close) or to play games (which I do rarely, I prefer other forms of entertainment). And Flash rarely works to my satisfaction, but I don't really consider that a great loss either.
I just don't understand it when people say that they can't switch over to Linux. Or at least dual-boot. Not to insult your intelligence, but most modern distributions are simple to install and productively work in. Maybe it's my background, maybe it's your choice of distributions, but I fail to see what the fuss is about. Especially when there are distributions (Ubuntu, for example) that are specifically geared towards non-technical users. While I personally find Ubuntu to be over-simplified and (as of my last use, about 3 years ago) not secure enough, I don't see why it wouldn't be easy to use as well as a vast improvement over Windows.
Re: (Score:3, Informative)
Of the operating systems I've used and administrated (Windows, Linux, FreeBSD, MacOS), I've had to spend more time administrating Linux than the others (FreeBSD might take more administration time, but short of mergebastard 'administrating' it involves me typing a make or portupgrade command, and leaving it along for a couple hours, or at least not performing a relatively small set of tasks).
Starting in 02 or whenever I first tried it, I had to deal with the usual dependency hell. I found out about yum late
Re: (Score:2)
Addendum, I can complain about windows lack of a decent command line. For file browsing and management, I prefer bash+cp+mv+ls to most gui utilities any day...
Re: (Score:2)
Well, I can't speak to your experiences, but I've installed Ubuntu on at least a half dozen machines, and have been using it continuously for about 3 years now (I was using XP before that). It's never taken me more than 2 hours to get a complete working install, I've never had a problem with the package manager, and in general I've had to spend almost no time to keep my machine working (certainly far less than when I used Windows).
There will always be problems with any OS, but in my experience Ubuntu is mo
Hybrid machine just like Acorn Computers (Score:4, Interesting)
Reminds me of the days when Acorn Computers were around with their RISCPC - A machine that was ARM powered, but you could also attach an x86 processor.
This is so 1990's!
I once looked to port Linux to the Archimedes (Score:2, Interesting)
While browsing comp.sys.os I found a post from some bloke called Linus who was offering a *nix kernel that could be compiled for x86 and we started having an email chat with him about how I'd go about porting it to the ARM hardware. I took it know further when all
Re: (Score:2)
Or an Apple II with a CPM card. Quite a lot of people used those...
Acorns (BBC Micros) with co-processors date from 1984-ish, CPM Apple IIs from earlier still. Someone below has already mentioned the DEC Rainbow from a similar timeframe.
The were probably other hybrids too - especially in the minicomputer area.
Re:Hybrid machine just like Acorn Computers (Score:4, Interesting)
Acorns (BBC Micros) with co-processors date from 1984-ish...
Don't forget that the A in ARM used to stand for Acorn. The first ARM1 was developed as a coprocessor for one of those BBC Micros.
I sometimes wonder what the modern computing world would look like if Acorn had had anyone who actually knew how to run a business. Their hardware was so much better than IBMs (or Apple's!) that it's not funny...
Good but.. (Score:5, Interesting)
Frankly I would love an ARM based notebook except for just a few issues.
1. Flash. Like it or not Flash is everywhere and I have not seen a Linux ARM version.
2. Java. I need it and JavaFX could be a nice alternative to Silverlight/Moonlight.
I see Flash as the big issue for most people. I would love to see ARM back on the "desktop" even if it is on the laptop. A ARM with a good GPU really would be a nice netbook system.
Re: (Score:2)
I'd like to see the x86 chip just sort of sit there unused most of the time... fire it up when a Windows app gets started. Windows could run like the old OS9 compatibility layer in OSX before the switch to Intel. It had a nice mix of usability, but being *just* irritating enough that you wish you didn't have to do it. Paired with a "battery" warning of some kind, it could be usable.
Re:Good but.. (Score:5, Informative)
Re: (Score:2)
(if you look, Adobe is quite clear on the fact that desktop/laptop flash is free as in beer; but embedded flash very much isn't)
...which is all the more reason to hurry up with the efforts to get SVG + SMIL + XForms + JavaScript + other W3C technologies working together, so that we can kill off Flash.
I call BS (Score:2)
The N810 has GPS, but the N800 doesn't.
Re:Good but.. (Score:5, Informative)
Then put your name down for one of these [engadget.com].
ARM licensed Java from Sun years ago, and include hardware acceleration for Java apps via Jazelle. In addition, Adobe have said they will have a version Flash 10 for ARM sometime this year. So get your wallet out.
At $199, these netbooks won't cost you and arm and a leg...
Re: (Score:2)
At $199, these netbooks won't cost you and arm and a leg...
Just two hands damaged from having to use that keyboard :)
Re: (Score:2)
Well we will see if flash 10 ships. Flash 7 just isn't good enough anymore. Now if we can get Java 6 sdk as well for ARM I would be a happy customer. Now if we can get inexpensive ARM mother boards with on board GPUs and SATA drives then we can really start moving away from X86 for things like NAS and MediaPCs.
Re: (Score:2, Informative)
Java works on ARM, kind of. Sun and ARM both seem to want to charge for ARM-based Java implementations.
Sun's KVM (used on many phones, can only handle J2ME, very slow) is proprietary, and only available for large-scale embedded use. Some ARM CPUs can actually execute Java bytecode directly, but they won't disclose any information about how to actually write a JVM that uses it. JVMs that use this feature cost an arm and a leg. Sun had a full J2SE JVM for ARM at some point, but again it was targetted at embed
ARM Cortex A8 netbooks Real Soon Now (Score:3, Informative)
Freescale and Pegatron showed a prototype at CES:
http://jkkmobile.blogspot.com/2009/01/meet-pegatron-199-arm-based-netbook.html [blogspot.com]
Re: (Score:2)
Frankly I would love an ARM based notebook except for just a few issues.
1. Flash. Like it or not Flash is everywhere and I have not seen a Linux ARM version.
2. Java. I need it and JavaFX could be a nice alternative to Silverlight/Moonlight.
Both Gnash [gnashdev.org] and OpenJDK are available for ARM.
Re: (Score:2)
Not sure how up to date it is now, but there was definitely a java version for linux/arm a few years ago, and with the jdk being open source now I'm sure there will be an updated version before long.
Flash is available for some arm based linuxes, such as the nokia n800, not sure if you could reuse the plugin on another linux/arm system, but considering a plugin already exists it shouldn't be too hard to convince adobe to write one.
Also, the flash spec was opened up recently so open source plugins will be pro
A complex solution ... (Score:2, Insightful)
So what we're talking about here is a Linux running on a decent ARM SoC most of the time... which I agree with, it's enough for the common case.
If we need performance for any reason we switch on an attached x86 and run that performance application (which of course is an x86 binary).
Or we run a VM on the x86 into which we put Windows, for compatibility.
Or we create a Mac OS X like fat binary system for Linux that includes both ARM and x86 variants, but imagine the pain in switching between the two! I think i
Snapdragon (Score:2)
But would it actually run Linux?? (Score:3, Interesting)
Would such a system actually use ARM Linux? The reason I ask is that the ARM processor is commonly used PDAs and therefore has Windows CE (or whatever they call it now).
So I wouldn't be surprised if M$ just renamed it Windows 7 Green Edition and rolled it out for such netbooks. Joe Public would be all oooh it runs powerpoint and word and IE and they'd be happy.
Does it matter still ? (Score:5, Interesting)
I'm wondering if, the the overall scheme of things, the price we pay for the x86-ness of Intel and AMD's CPUs is that high. All their CPUs are basically RISC things, with a very optimized x86 compatibility layer running on top. Is that layer that expensive performance-wise ?
Re: (Score:2)
Is that layer that expensive performance-wise ?
That was the bet IBM and others made with RISC. It still seems like the way to go, but Intel and CISC is still here...
Re: (Score:2)
Re: (Score:3, Interesting)
ARM kicks the crap out of Intel/AMD when it comes to performance per Watt. That makes it great for embedded work (10bn, yes 10e9 CPUs shipped) and looks like it might be starting to migrate into netbooks.
Re: (Score:3, Interesting)
Are you sure? Have you compared a 33Mhz ARM to a 33Mhz x86 chip? Is the performance that different?
There is no way to do an apples-to-apples comparison here, because I don't think anyone makes x86 chips that are as slow as ARM chips. The instruction set doesn't have that much bearing on performance. But power use goes up according to the square of the voltage, and voltage increases when clock speed increases -- so it is all about the megahertz.
Re: (Score:2)
IANAEE but I'm pretty sure that power usage goes up with transistor count as well. Last time we looked at boards, we'd have been quite happy with an x86 CPU but there were simply no solutions which didn't need a case fan. Since we didn't want moving parts, that meant no x86 - which I feel kind of implies the x86 parts use more power.
I could have phrased it better - there don't seem to be any equivalent x86 solutions to ARM in the low power arena. Yes, I know about Atom, but I've had a whole ARM board that d
Re: (Score:2)
The instruction set has an awful lot of bearing performance. The RISC ARM instruction set has only instructions that take exactly 1 cycle (last time I looked). This makes both efficiency and optimisation such as pipelining very effective. The CISC x86 instruction set has instructions that can last varying amounts of time. This makes things such as branch prediction misses expensive. To compensate for this x86 chips use a translator [pcguide.com] which turns the x86 into VLIW pseudo-RISC internally. Unfortunately this tra
Re: (Score:3, Informative)
Unfortunately this translator takes up most of the power and silicon real estate on the chip.
That is false. It actually takes up a few percentage points of power and silicon real estate. If it took up most of the power and silicon real estate, then they would not do it.
The Pentium Pro was the first Intel chip to have a translator, and to run RISC instructions internally. At the time, several techie magazines (Byte?) had articles on the architecture. Intel claimed something like 5% overhead from doing that. They even posited that they might be able to create a Pentium that could run any arbitra
Re: (Score:2, Informative)
Are you sure? Have you compared a 33Mhz ARM to a 33Mhz x86 chip? Is the performance that different?
Clock frequency is a horrible comparison statistic. Note that AMD chips for years have had similar performance with increased clock cycle lengths. It's not so much about MHz, it's about what you actually get done during that cycle.
There is no way to do an apples-to-apples comparison here, because I don't think anyone makes x86 chips that are as slow as ARM chips. The instruction set doesn't have that much bearing on performance.
I don't want to be rude, but you're obviously just an arm-chair commentator on the subject. While it's true, the fastest ARM based processor doesn't run any faster than 1 GHz (Cortex based ARMs, or the ARM being used in Qualcomm's SnapDragon platform) you can make direct compariso
Re: (Score:3, Interesting)
Are you sure? Have you compared a 33Mhz ARM to a 33Mhz x86 chip? Is the performance that different? There is no way to do an apples-to-apples comparison here, because I don't think anyone makes x86 chips that are as slow as ARM chips.
Well, you can if you have old Intel hardware to compare with. If you do, then you can make at least a "spartan to red-delicious" comparison.
I still have an operational 500MHz Celeron equipped with 256MB of RAM and integrated Intel graphics and sound, manufactured about 10 years ago. The BeagleBoard has awfully similar specs (similar clock speed, rev C will have the same amount of RAM, integrated graphics...). I can already tell you the graphics on the BeagleBoard wins hands down based on demo videos I've
Re: (Score:2)
looks like it might be starting to migrate into netbooks.
Look up the recent announcement of ARM and Canonical throwing their weight behind a fully supported ARM Ubuntu version for MID-like devices.
They were supposedly launching something in march or so.
I Approve.
Re: (Score:2)
If you look at the brazillions of transistors they throw at caches, execution units and now multiple cores, it's pretty clear that the designers don't really know what to do with all those transistors. The x86-to-micro-ops translation unit is just a very small part of the CPU. I see it as a real time decompression engine, with x86 code somewhat more compact than RISC. Given that RAM bandwidth is always a major limitation, this even makes sense.
Re: (Score:2)
Sounds familiar. What you're looking for is microcode and a writable control store. Pretty common in minis back in the day. And to some degree we have it in today's CISC CPUs if you look at the microcode patches that BIOSes load into certain CPUs although it's probably only used to fix bugs, er, errata.
Re: (Score:2)
Since the layer is implemented in hardware its performance impact isn't much, just a pipeline that's a bit longer resulting in a higher penalty for a missed branch prediction. The fact that they've decoupled the instructions they use inside their chips from the instructions people put their programs in is actually a big advantage in one sense: they get to mess with their internal instructions whenever they can gain some advantage by doing so and not worry about the compatibility implications.
I'm sure the i
Re: (Score:2)
On the other side of things, I'm wondering if, in the overall scheme of things, the value of x86-ness is all that high. I've been hearing that it's somewhat inferior for years, and the main reason that sort of architecture is still in use is mainly for compatibility reasons. OSX and Linux seem to be agile enough to switch between architectures with relative ease, so is the only hold-up Windows?
The CPU is not the biggest consumer (Score:5, Interesting)
The display uses far more power than the CPU, so the benefit of adding a second low-power CPU will only be realized with a different display technology that has much lower power consumption for a static image.
Re: (Score:2)
Screen technologies. (Score:4, Interesting)
What's the current state of OLED?
OLED display have been spotted in the wild (sony, available since 2007 [wikipedia.org]). They are ultra thin, size 11".
But they still cost an arm and a leg. And OLED currently still has a shorter life time.
But as production ramps up, price will probably fall down. After a couple of year, OLED will probably cheap enough for netbooks.
Electronic paper?
Still suffers from really slow refresh rate. Good for e-book. Bad for anything which needs higher refresh rate.
The good thing, with eink is that, when not refreshing, it costs exactly 0 W. (Under sunlight. Otherwise, you still have to light it up somehow).
Maybe that display from the XO?
The first gen XO uses a normal LCD screen, but with a LED backlight that doesn't use coloured filters, but prism that split the light to generate the colours.
Thus having a better efficiency. Also works in B&W under sun light.
Currently, XO-type display are the best compromise in quality and price.
OLEDs are going to be the next-big-thing once 11" displays stop costing prices in the thousand dollar range.
Beside, given the power consumption of ATOM's chipset, a whole Intel-based solution still has a much more higher power drain than an ARM based one (which has everything into a single SoC - and can even embed RAM in the same CPU package).
So even if ATOM vs. ARM differences aren't big, Intel netbook vs. ARM netbook still makes a difference.
Re: (Score:2)
I'm serious. The portability of a computer really helps for (A) sitations where you don't have the infrastructure to support a computer, (B) places where you don't have a computer permanently, (C) tasks that occur intermittently or concurrent with non-computer tasks.
In all three cases, lower power and greater autonomy are what you want. But (C) is where the ARM CPU really shines, and yeah, it s
I like it (Score:4, Interesting)
When traveling, most of the time, I really do want a long battery life and don't need much compute power. But when I arrive at my destination, give a presentation, and demo some software, then I want compute power.
So, as far as I'm concerned, having a high power and a low power CPU sharing the same keyboard, screen, drive, and power supply is actually very much what I want. I hope it becomes standard.
Re: (Score:2, Funny)
Why can't you give your presentation in Vi?
Re: (Score:2)
How about 8 ARM cores with FPU and vector capabilities (that can be used for 3D acceleration), along with hefty caches, on a single chip? Now, imagine all parts can downclock themselves to a full halt when idling or even power down when the OS asks them. IIRC the hotplug stuff in the Linux kernel can already deal with that kind of stuff.
The tech is all around. All we need is someone who is willing to do it.
Re: (Score:2)
Re: (Score:2, Informative)
The trouble with most modern laptops, is that even when completely unattended, doing no work that the user expects any results of anytime, just by being 'on', these seldom consume below 5 Watts of power, and in their factory config about usually 15 (nobody bothers with configuring power management). I am talking about a laptop that is lid-closed, radios (wifi, bluetooth) off, not doing ANYTHING for you.
Windows-proof computing (Score:2)
It's actually great. An ARM-based PC would not only be Windows-free, it would be Windows-proof.
Not really. There is still Windows CE, but one can dream...
Re: (Score:2)
Shifting to paper could save laptop batteries (Score:2, Funny)
An anonymous reader writes:
"When is an Intel PC not an Intel PC? When it moves applications such as word processing on to a piece of paper because it can get longer battery life. And according to a story at EE Times, this hybrid Intel-Paper approach is being taken by PC makers as prominent as Dell. The problem for Intel: Why would you switch out of 'all-day' mode and use the Intel processor? The problem for paper: lacking support from Microsoft for Windows; the applications it runs for the PC have t
Apple / BSD (Score:4, Interesting)
Don't ARMs also run BSD ? It would seem that Apple might have a solution for their laptops, if they decided to go that way.
Re:Apple / BSD (Score:4, Informative)
Re: (Score:2)
Re: (Score:2)
He was making a joke. Apple gave up their efficient PowerPC to move to box-shifter x86 machines like Dell. Apple then copied the touch-screen Prada phone to make their iPhone. And he is being sarcastic in that he is suggesting the iPhone is a low volume device. Hence he is predicting in a round-about way that Apple will release a sweet ARM-based Netbook. Which we know already as Apple have already licensed the technology. Apple have had experience with the ARM ever since the Newton so they shouldn't have an
Sounds like a job for Windows NT 3.51 (Score:2)
It is just a stop-gap measure (Score:2)
If there was ARM Windows, this would not exist. The Intel CPU is now an added cost so that users can have their familiar windows interface, and a powerful processor when plugged in.
Now, consider the case of a dual ARM CPU box. Longer battery life, no x86 premium (cheaper). You can turn the additional CPU on or off if you're on battery or not.
Since you're asking vendors to support arm, it makes no difference now that they have to support two CPUs and three OSs.
After we subtract everything we have the added c
Re: (Score:2)
Who thinks the AC is still a n00b?
Basically, all of us that predate those efforts by well over a decade, I suppose....
http://en.wikipedia.org/wiki/Asymmetric_multiprocessing [wikipedia.org]
Or who outboarded other processors on Apples ][+ before the things you mention hit the market....
BTW - I think if you challenge n00b status hard enough using simple temporal references, you're liable to get an answer from Babbage himself - this is /.