Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Pocket Wars and Cores

timothy posted more than 3 years ago | from the shadow-conspiracy-of-armand-hammer dept.

Intel 159

An anonymous reader writes "If I were to ask you what is the most popular processor used in phones and pads, and you said, 'ARM,' you would be correct. Now comes the trick question, 'Who make ARM processors?' Not the ARM Holdings company. They design processors and license their designs to manufacturers. They also have a reputation for creating very low power designs. Interestingly, while almost everyone else was out ramping clocks and power consumption (until they hit a wall), ARM was chugging along addressing the low power end of the market. Now that low-power is all the rage, due to phones and pads, ARM has become quite a bit more popular."

cancel ×

159 comments

Sorry! There are no comments related to the filter you selected.

Too bad! (0, Interesting)

Anonymous Coward | more than 3 years ago | (#35427538)

Too bad nobody's making ultra-cheap machines yet.
Why aren't there 50$ SOC systems on the market ? Not tablets , desktops will do, or thin clients.
First post ?

Re:Too bad! (1)

nukem996 (624036) | more than 3 years ago | (#35427614)

HP makes a SOC system based on the Marvell Kirkwood design. Its the HP t5325 I beleive. It works great as a thinclient but local web browsing is kina slow and theres no flash.

Re:Too bad! (2)

psergiu (67614) | more than 3 years ago | (#35428290)

HP t5325 costs over 200 USD. OP asked about 50 USD machines.

Re:Too bad! (2)

White Flame (1074973) | more than 3 years ago | (#35427638)

There's no mass market yet. Plug computers are around $100-150, with 256-512MB of RAM and are somewhat taking off. Some might also have video-out, most have USB where you can hang a hub, storage, & keyboard/mouse off it.

The thing is, even with a cheap core and an inexpensive power supply, you're still going to have to pay to include usable amounts of memory. I'd think $100 is a reasonable place for inexpensive compu-bricks with a good selection of ports, until there's a killer app that ramps up the volume and lowers the price.

Re:Too bad! (2)

JWSmythe (446288) | more than 3 years ago | (#35427866)

    But you don't have to go with the wall wart form factor. I was working with an ARM on an industrial micro-ATX board, and that worked great. I was actually impressed with the speed, even though it was a 1Ghz machine. It was a tremendous step forward over another board they had chosen to use, where the only OS you could run was their own hacked up version of Linux, that required dozens of dodgy patches to rebuild the kernel.

    If you really pay attention, ARM processors show up all over the place. I bought a little eMachines (the square thing standing vertical on a little pedestal), that works very nicely for running my theater system. At about 5"x5"x1", it's nice to have an absolutely silent machine sitting there that I can run the OS of my choice on. The only problem I had with it is that it didn't have enough USB ports for everything I wanted to hang off it.

Re:Too bad! (2)

symbolset (646467) | more than 3 years ago | (#35427790)

Give it time. It will come because there's a market for it.

Re:Too bad! (3, Informative)

Anonymous Coward | more than 3 years ago | (#35427926)

I think you might want to check this out: http://www.genesi-usa.com/products/efika [genesi-usa.com] Comes in at $129. Not exactly 50$, but I guess that's due relatively small production volumes.

Re:Too bad! (1)

Eunuchswear (210685) | more than 3 years ago | (#35428362)

... Complete open source software solution ... ... 3D Graphics Processing Unit ...

Comes with open source OpenGL ES drivers?

Re:Too bad! (0)

Anonymous Coward | more than 3 years ago | (#35427932)

Too bad nobody's making ultra-cheap machines yet.
Why aren't there 50$ SOC systems on the market ? Not tablets , desktops will do, or thin clients.
First post ?

Actually they are getting closer: see Genesi [genesi-usa.com]

I actually find the desktop a bit expensive, but the netbook-class product is quite nice. It is indeed more expensive yes, but the display justifies the difference (plus the keyboard).

Re:Too bad! (1)

jimicus (737525) | more than 3 years ago | (#35428452)

Why aren't there 50$ SOC systems on the market ? Not tablets , desktops will do, or thin clients.
First post ?

Economies of scale, I'd think. IIRC most factory production is geared around (and indeed isn't economical unless) the idea of churning out tens of thousands of an item minimum. Preferably tens of thousands per month.

Something like that - unless it's being heavily pushed by someone who can give people something useful to do with it - isn't going to sell many. What are the likes of HP or Dell going to push? "Here, it's just like a desktop PC except you can't run any current software you're likely to want on it"?

Re:Too bad! (4, Interesting)

fuzzyfuzzyfungus (1223518) | more than 3 years ago | (#35428518)

Your off-brand Chinese importers can hook you up with an ARM-based netbook-esque mini-notebook for $80-$100, depending on exact specs, volume, and the whims of the ebay gods.

Trouble is, in most cases, these will either be running some dubiously-legit(and sometimes questionably well-localized) version of WinCE, or a mildly elderly version of Android. Actual cryptographic lockdowns, in the Apple or Motorola vein, are way outside the budget; but total lack of usable documentation, a confusing proliferation of part numbers, or rampant hardware switching between similar looking models has somewhat retarded the growth of decent sized 3rd-party release groups.

Curiously, the hardware built into these $80-$100, with (lousy) screen, keyboard, and battery doesn't generally seem to show up in $40-$50 versions with DC-in, VGA-out, and USB for peripherals. There are some machines with those specs, like HP's t5325; but the fact that that is a "thin client" and thus "enterprise" instantly doubles the price you'd expect for the specs.

You can also get quite capable hardware in Marvell's *plug line; but those are generally network appliances only, with your only display option being a USB-based Displaylink or similar. That certainly works; but nearly doubles the price and makes for a rather ugly donglefest.

The newer Marvell SoCs do support at least one lane of PCIe, in addition to a raft of other onboard peripherals, so it wouldn't be rocket surgery for an OEM to put out a *plug-esque design with an actual PCIe graphics chip(only a low-end one would really make sense; but even the cheapest PCIe graphics chips available can drive pretty much any monitor that doesn't require dual-link DVI) hanging off that lane. However, that is a bit hardcore to just hack onto an existing *plug board, and, as noted, nobody seems to have done that in commercial quantity.

You can get the cheap-and-nasty "PocketPC of yesteryear shoved into a clone of the EEE701" from any number of mystery OEMs on ebay; but the software will blow and 3rd party firmware support is kind of a gamble.

You can get a *plug-based design, which will have a much peppier ARM core (1.2GHz) and beween 128-512mb of RAM, depending on the exact model, for about the same money(Seagate Dockstars were going crazy cheap for a while, like $10-$20; but that was a firesale of sorts); but those are network-only unless you buy a Displaylink adapter, which pushes you up toward $150-$200, at which point Atom boxes that will run normal x86 OSes with zero hassle and take 1GB+ of RAM start to beckon...

The t5325 is pretty much exactly what you are asking for, except that it is an "enterprise" product, and has a price tag to match. If one could hunt down whatever OEM produces the board inside, and buy 10,000 of the same thing in generic black boxes, those would probably be precisely what you want; but I've never seen any hints on how to do that...

Re:Too bad! (0)

Anonymous Coward | more than 3 years ago | (#35429284)

Oops: The beagleboard is also worth a mention: In rough outline, it is the TI equivalent of Marvell's Plugs: the cheap, accessible, half dev, half reference design built around their respective ARM SoCs.

The Beagleboard is slower(720Mhz vs. 1.2Ghz); but has onboard video and audio, making it a much better out-of-the-box small computer. It is, however, weaker on storage(SD/MMC vs. eSATA) and networking (non built in vs. 1xGbE) and slightly more expensive.

The Pandaboard is the Beagleboard's successor: More expensive; but 1 gig of RAM, 2 USB ports, LAN/WLAN/BT, dual monitor support, and a dual-core 1GHz ARM. Still weak on storage, SDHC/MMC only and $180 only gets you the dev board, to which you'll need to add a case and PSU; but a pretty cool little toy.

Again, many parties seem to be nibbling around what you are asking for; but nothing quite hits.

The Chinese cheapies are mostly netbook-lite or low-end android tablets, they never seem to cram the same board into a teeny desktop case with a discount for the nonexistent screen, keyboard and battery.

The Marvel *Plug designs are much friendlier from the software side, and rather more powerful; but a touch more expensive than you want, being semi-devboard products, and make no explicit provision for a display.

The TI Beagleboard is a little weaker and a touch pricier and "dev-y"er; but has actual display support. The Pandaboard is substantially punchier; but still very dev-y and you really can't kit one out as a desktop system for less than an Atom "nettop" would run you, that takes normal RAM, has SATA, and so forth...

The Atom is substantially more power-hungry, of course(the beagleboard can run from a USB port, while the nettop will be feeding off a standardish laptop line-lump); but you really have to care about that for its own sake when you are talking desktop systems...

I think my first ARM device was a Gameboy Advance (1)

atari2600a (1892574) | more than 3 years ago | (#35427548)

So thanks for that ARM...

Re:I think my first ARM device was a Gameboy Advan (1)

SimonTheSoundMan (1012395) | more than 3 years ago | (#35427660)

Mine was a BBC Micro back in the 1980's. Pretty much stuck with Acorn Computers until 2000/2001. Acorn was owned by ARM, hence the older acronym "Acorn RISC Machines", they now use "Advanced".

Re:I think my first ARM device was a Gameboy Advan (4, Interesting)

PhunkySchtuff (208108) | more than 3 years ago | (#35427748)

Acorn machines were incredible for their time. Their GUI had concepts that have only been realised in mass market GUIs just recently, the flexibility of their OS and their advanced typographical features were many years ahead of their time. Things like the save dialog for a new file having an icon of the file that you could give a name to and then drag that icon to a folder to save it there (rather than having to navigate to the folder in the dialog). Built in BASIC in ROM (most of the OS in ROM, so boot times were on the order of seconds). I could go on...

Re:I think my first ARM device was a Gameboy Advan (1)

ChunderDownunder (709234) | more than 3 years ago | (#35427946)

I hated that 'save dialog'. finding a folder in the filesystem and having to drag just seemed slow and clunky in the days of mice with balls that got clogged and before the days of accelerated graphics. The Mac System 6 file chooser was primitive by comparison but did its job.

Cambridge Mathematical Laboratory (1)

Kupfernigk (1190345) | more than 3 years ago | (#35427950)

Acorn's roots are in the Cambridge Mathematics Laboratory. It's nice to think that, while the USA overtook the UK rapidly in computer science after our Civil Service fsck-up postwar, the typical low power do it on the cheap approach of British engineering is coming into its own again.

Re:I think my first ARM device was a Gameboy Advan (1)

asdf7890 (1518587) | more than 3 years ago | (#35427842)

IIRC ARM was a spin-off or Acorn (initially an internal research team working on the CPU that would power the Archimedes line, that chip being the great great granddaddy of the current ARM designs) rather than the other way around.

Re:I think my first ARM device was a Gameboy Advan (1)

Midnight Thunder (17205) | more than 3 years ago | (#35428504)

Indeed Acorn existed long before the advent of the Archimedes and the ARM chip it powered. It was the first time I had ever heard about a RISC chip. It sounds like ARM was one of the first RISC chips, and has managed to stay around while others just fell back into the unknown.

The BBC Micro before it was based on the 6502 chip.

Re:I think my first ARM device was a Gameboy Advan (3, Informative)

bhtooefr (649901) | more than 3 years ago | (#35428000)

BBC Micro ran a 6502, the Archimedes was the original ARM-based line.

Re:I think my first ARM device was a Gameboy Advan (0)

Anonymous Coward | more than 3 years ago | (#35428386)

One could install an ARM1 option via the "tube".

whats the news here? (2, Insightful)

neurocutie (677249) | more than 3 years ago | (#35427570)

ok, so?
(qualcomm, intel, samsung, marvell, etc.)

Re:whats the news here? (1)

pep939 (1957678) | more than 3 years ago | (#35428052)

I agree. No news here, move along.
Been telling people that RISC will overlive CISC ever since my first line of asm...

Re:whats the news here? (1)

Narishma (822073) | more than 3 years ago | (#35428622)

Intel doesn't make ARM processors anymore.

Re:whats the news here? (1)

bdleonard (931507) | more than 3 years ago | (#35429070)

Last time I checked, Intel's IXP and IOP embedded product lines were still ARM (XScale) based.

Wrong logo (3, Insightful)

treeves (963993) | more than 3 years ago | (#35427578)

Why the Intel logo for this story? They're ones who do *not* make ARM processors, ever since they sold that business to Marvell (oops). I guess the TI logo isn't as cool.

Re:Wrong logo (2)

mcvos (645701) | more than 3 years ago | (#35427644)

Why the Intel logo for this story?

Because it's about processors, and processors means Intel. Duh.

(I've always rooted for ARM against Intel since the early '90s. The Risc PC, the StrongARM, etc.)

Re:Wrong logo (1)

symbolset (646467) | more than 3 years ago | (#35427808)

I may be mistaken, but I do believe that Intel holds through acquisition not just one, but two ARM licenses they haven't divested yet. And there's no ARM logo. Yet.

Re:Wrong logo (2)

JWSmythe (446288) | more than 3 years ago | (#35427886)

ARM [arm.com] does have a logo. It's just rather plain. typing it out is close enough. Maybe they're going with elegance in simplicity, even in their logo. :)

Re:Wrong logo (0)

Anonymous Coward | more than 3 years ago | (#35427930)

Digital had the Arm license and made the StrongArm. Succesive company merges gave Intel that part of Digital's catalog and the X-scale was developed based. Losing more compatibility with the general ARM designs along the road. Then Intel sold what was left to Marvell but it still has an ARM license. There is a variety of licenses so it is hard to say what the practical value of that license is right now.

Still a wrong Logo.

Re:Wrong logo (1)

bhtooefr (649901) | more than 3 years ago | (#35428036)

Technically, Intel does still own some XScale stuff, for their IOP line of SoCs meant for storage arrays.

(Oh, and as for StrongARM being incompatible... ARM9 made the same changes. The only other thing I can think that XScale did to break compatibility, relative to contemporary ARMs, was WMMX support in later versions, which used the same coprocessor ID as ARM's original FPA floating point unit, which meant that code that called the FPA would crash and burn, rather than throw an invalid instruction exception and get handled in software. Contemporary ARMs also started using Thumb, which couldn't coexist with support for 26-bit addressing. Both of those problems would've only affected Acorn's RISC OS, though. (The WMMX one didn't, as there wasn't any money to design any RISC OS-specific hardware by the time WMMX became an issue, and now that there's a shared source version, the porting efforts have focused on more modern SoCs that don't have WMMX either. 26-bit addressing, that one caused major issues, but the work was done to mitigate those issues in 2001, with the Iyonix, which uses an IOP321 (IIRC) XScale.)

Re:Wrong logo (1)

TonyJohn (69266) | more than 3 years ago | (#35428638)

Intel's aquisitions may be changing that. See their quote on this recent press release [arm.com] .

Re:Wrong logo (1)

cb88 (1410145) | more than 3 years ago | (#35429150)

Intel XScale ... is ARM!

Where's the news for nerds in this? (2, Insightful)

mukund (163654) | more than 3 years ago | (#35427584)

I had always loved Slashdot, but is there any alternative community run site without the Slashvertisements?

Re:Where's the news for nerds in this? (1)

the positive path (1288162) | more than 3 years ago | (#35427640)

alterslash.org

Re:Where's the news for nerds in this? (2)

somersault (912633) | more than 3 years ago | (#35427792)

And yet, this story is also on alterslash :p

Re:Where's the news for nerds in this? (1)

somersault (912633) | more than 3 years ago | (#35427796)

(not that I think this is a Slashvertisement, but it is something that all of us should know already)

Re:Where's the news for nerds in this? (1)

BeardedChimp (1416531) | more than 3 years ago | (#35427956)

I've almost completely given up on it. I've stopped reading the articles, not because of lack of interest but because they never point towards the original source anymore. In fact what they link to also rarely even link to the original source. I've taken to just reading the comments waiting to see if some inquisitive poster has tracked it down.

The editors purposefully manipulate whats posted usually to increase the hyperbole but often are outright lies. In some case the posts are so warped that they say the opposite of what was originally posted.

We've reached the point where I think we need to fork. People complain about the problems in nearly every story and yet it falls on deaf ears. The recent forks with respect to Oracle seem to have been all fairly successful, why can't we?

Re:Where's the news for nerds in this? (1)

Midnight Thunder (17205) | more than 3 years ago | (#35428538)

That is why ArsTechnica is on my daily list.

If you come to /. you should realise that many stories summaries seem to be designed as flames. Once you realise that you know to do you own research on the side, if the story matters at all.

Re:Where's the news for nerds in this? (2)

kwerle (39371) | more than 3 years ago | (#35428224)

I, too, would like to find a place where the editors edit. Maybe even research a little. And where they don't comment in the stories. Where non-stories don't get posted. I mean - this is /. You would think that an editor could pick up the phone and actually call the subject of a story on rare occasion and maybe get a little insight into what is really going on.

Oh, and a site that doesn't end up slashdotting the subject without warning.

I use
* http://www.foresight.org/nanodot/ [foresight.org] for nano tech news
* http://www.macrumors.com/ [macrumors.com] for mac news

I would like to find outlets for
* Programmer related news (in addition to http://thedailywtf.com/ [thedailywtf.com] :-)
* Hardware related news
* Tech/Social new

To be fair, I think /. has done a pretty good job of covering tech and the recent middle-east events. It's just the other 95% that's pretty much crap.

Re:Where's the news for nerds in this? (3, Informative)

Iskender (1040286) | more than 3 years ago | (#35428468)

I think it's rather the constant shouting of "slashvertisement" that's getting old.

Take a second look at this story:
-It links to some Linux site or other which is certainly not ARM.
-The article actually explains something quite insightful about the way ARM is advancing. Sure, some might have known this, but those who want to complain about that should realize that the discussion would be pretty shitty here if everyone was completely ignorant in advance. Do you ask the world what's wrong every time you hear something you already know?
-There's the interesting point that you can't get a Windows desktop on ARM, and in the future when you can most probably won't want it either.
-It's a story about a successful Intel competitor being even more successful (because face it, Intel wants to make every processor on Earth).

Hell, there's no end to interesting things in connection with this. It's a story about something that's changing which could change a lot of things, possibly for the better. I'd ask what's wrong with you rather than what's wrong with Slashdot.

Think beowulf cluster of arm processors (0, Redundant)

Anonymous Coward | more than 3 years ago | (#35427610)

or don't...

Re:Think beowulf cluster of arm processors (1)

symbolset (646467) | more than 3 years ago | (#35427820)

Were you looking for this link? [theregister.co.uk]

Re:Think beowulf cluster of arm processors (1)

xophos (517934) | more than 3 years ago | (#35427974)

those are not arm chips but mips-based x86 emulators.

It's a bit more complex than this article... (5, Interesting)

rcs1000 (462363) | more than 3 years ago | (#35427612)

...makes out

There are many, many makers of ARM based 'application processors' and the like: Texas Instruments, Samsung, Apple, ST Microelectronics, nVidia to name but a few. In addition, some people - like Qualcomm with their Snapdragon processor - have licensed the instruction set from ARM, but then have basically built their own core around that.

The nice thing about ARM is that - if you are looking to embed processing power - you can license a core (or two), design them into your own chip and then make it. Said chip can also include a USB controller, or a wireless baseband, or whatever. Intel will not sell you an x86 core for you to design into your own chip; ARM will.

Now: before this thread descends into meaningless ARM versus Intel rivalry, can I point out that the two architectures are optimized for entirely different situations. To say ARM is better than Intel, is like saying a bicycle is better than a ship - it's not a meaningful comparison. If you want to embed processing functionality, or you want low-power (particularly low standby power), then you need ARM. If you need raw processing power, optimised to run desktop or server operating systems, then you'll be wanting x86.

And the reason why x86 is so power hungry? It's because it's on big bits of silicon. And why's it on big bits of silicon? Because it support hyper-threading, out-of-order executon, has hardware virtualisation extensions, has extensive branch prediction, and tonnes of on chip cache.

There is no reason why ARM cannot offer all of these things too (and their Eagle design goes some way to do this). But if you want to do this, then your chip is going to get bigger, and more expensive, and more power hungry.

Over the next five years, we are going to continue to see mobility become more important: and that means more and more ARM cores, and a diminution of the importance of the traditional PC market. ARM has a very bright future - but, I suspect, it will probably have a great deal of trouble getting into the traditional PC space.

Re:It's a bit more complex than this article... (5, Insightful)

KiloByte (825081) | more than 3 years ago | (#35427712)

A single amd64 core can emulate an arm core from about the same market segment via qemu. A cross-compile which on my lousy $400 6 core desktop takes 44 seconds needs 132 minutes natively on 1 core n900. For any activity that actually needs CPU power, x86 chips are not going away. If something replaces them, it'd be something designed for speed -- rather than 8086 compatibility or low power.

Yet, for most daily uses, you don't need much CPU power. We got so used to "Intel giveth, Microsoft taketh away" that most people forget they ran software with about the same functionality ten years ago on machines a hundred times slower. Dropping some of worst software bloat can get us a really long way.

Re:It's a bit more complex than this article... (2)

somersault (912633) | more than 3 years ago | (#35427830)

most people forget they ran software with about the same functionality ten years ago on machines a hundred times slower. Dropping some of worst software bloat can get us a really long way.

Indeed. My phone actually kicks my netbook in the teeth when it comes to video playback, as well as power consumption. A modest processor with decent graphics hardware is all you need for basic multimedia, web browsing and such.

The PC is become a blowtorch when we need a lamp. (2)

symbolset (646467) | more than 3 years ago | (#35427844)

If that surplus processing power could be harnessed it would be a different story, but Windows isn't up to that task.

Re:The PC is become a blowtorch when we need a lam (0)

Anonymous Coward | more than 3 years ago | (#35428090)

And neither is Linux to my disappointment.

Sure you can run DSL or TinyCore and the like, but try to install a modern Ubuntu on an old laptop(that will happily run XP) and you'll be pulling your hair out.

Re:The PC is become a blowtorch when we need a lam (1)

drinkypoo (153816) | more than 3 years ago | (#35428376)

Sure you can run DSL or TinyCore and the like, but try to install a modern Ubuntu on an old laptop(that will happily run XP) and you'll be pulling your hair out.

The only way in which this is true is when you have little memory. XP will run in 64MB (swap!) but recent Ubuntu will fall all over itself with less than about 256MB, and if you want to run Firefox, you're going to need at least 512MB or have fun swapping. If you use a lightweight desktop like Matchbox and a lightweight Firefox like Seamonkey then you can do okay in 256. Since you really have to copy the CABs to disk to make Windows XP administration not a complete nightmare, the storage footprint is similar. Also, the necessity of loading antivirus software makes XP basically untenable on antique hardware unless you're using it for a specific single purpose.

Re:The PC is become a blowtorch when we need a lam (1)

Nursie (632944) | more than 3 years ago | (#35428446)

Wait, so you expect one distro to make good use of modern hardware and be installable on something ten years old and you have trouble?

Colour me surprised.

FWIW I've had debian squeeze running happily enough on a 266MHz machine with 32MB RAM. But then that's headless and running on ARM.

Re:It's a bit more complex than this article... (1)

drinkypoo (153816) | more than 3 years ago | (#35428144)

If intel is right and the future includes boatloads of cores then you'll just make -j128 or something and you'll get it done in approximately the same time... if you have SSD and a big fat block cache.

Re:It's a bit more complex than this article... (1)

KiloByte (825081) | more than 3 years ago | (#35428454)

Not really since in this example link itself takes more than 10 minutes and can't be parallelized.

Most of current software is woefully single-threated too. I can't really think of any thing other than compilation (with makefiles that allow -j6) which uses more than one core. At most, it's decompression (a small portion of a core) feeding a thread that uses 100% of another, or something in this vein.

"Nine women can't make a baby in one month" -- Fred Brooks

Microsoft is changing that (1)

MikeRT (947531) | more than 3 years ago | (#35428514)

Yet, for most daily uses, you don't need much CPU power. We got so used to "Intel giveth, Microsoft taketh away" that most people forget they ran software with about the same functionality ten years ago on machines a hundred times slower. Dropping some of worst software bloat can get us a really long way.

I have a nearly 6 year old Dell laptop running Windows XP. For fun, I put a demo license of Windows 7 on it and found that Windows 7 actually runs faster than XP on it. Not only that, but I get the full Aero desktop. Four years ago, I would have expected that from Linux. Instead, I find that Linux runs slower than ever on that older hardware.

Re:Microsoft is changing that (1)

KiloByte (825081) | more than 3 years ago | (#35428786)

Are you sure we are talking about the same Windows 7?

XP runs barely on 64MB, adequately for small tasks on 256MB, ok on 512MB.
7 runs barely on 512MB, adequately for small tasks on 2GB, ok on 4GB.
Let's not even mention Vista...

There are reasons for running 7: some hardware, especially shitty laptops, doesn't get drivers for XP. Also, XP 64 is a bad joke, meaning you can't use more than ~3GB due to sketchy PAE support. None of these matter for old boxes, though.

There's no excuse to skimp on memory on new systems, but on old hardware and virtual machines, you'd want to use the more efficient edition. Especially businesses don't want to throw perfectly functional hardware away -- and around here, companies have piles of boxes that can't handle 7 but work just fine for all tasks thrown at them. Having some XP and some 7 would be a maintenance nightmare, thus no wonders I haven't seen a _single_ Win7 desktop at any customer (mostly car dealers).

And Win7 is full of gems like transfer speed of ~20KBps over wired Ethernet when XP and Linux on the very same hardware get roughly the nominal speed.

Re:It's a bit more complex than this article... (0)

Anonymous Coward | more than 3 years ago | (#35427764)

What about sustainability. If a large health-care organisation has 5000 computers on for an average 20 hours a day (most are on 24 hours) and the CPU is using 80 watts on average the cost to the organisation (in the UK) is £450,000 per annum.
If ARM processors were used and the CPU used 1 watt the cost would be £5,600 per annum. What would the finance director say about that! I think that this is the reason Microsoft is porting proper Windows to ARM.

Re:It's a bit more complex than this article... (2)

hairyfeet (841228) | more than 3 years ago | (#35427852)

Your hypothetical director would say "oh great lets switch".....only to find out that NONE of tens of millions of dollars worth of custom software designed to speed productivity will run and it will cost a billion dollars or so to have it all written in house, that is of course if you don't get sued because half of it is patented up the wazoo, and then say "Fuck the electricity".

The reason nobody runs ARM on the desktop is the same reason why you don't see masses of Linux machines at your local Walmart...its the apps, not the OS and MSFT cooking up some half baked .NET based about as useful as WinCE OS and calling it "Windows for ARM devices" won't change a bit of that.

The simple facts are these: Those running x86/x64 Windows don't have the code for their programs, it would cost orders of magnitude to write code to replace those programs, and that is of course after the vendors spend the next 10 years dragging you through the courts for trying to rip off their IP.

To try to make the Linux ARM world fit the Windows x86 world simply doesn't work, they are two COMPLETELY different ecosystems that are as different as the top of a mountain and the bottom of the Marianas trench. People will happily take Linux ARM because they have ZERO or near ZERO invested in code for the platform. They literally have billions of dollars in mission critical programs tied to x86, most of which would simply never be ported to ARM and would cost incredible amount of money to be written from scratch in house.

So while it might make cool back of the envelope math to compare the two IRL it simply wouldn't work.

Re:It's a bit more complex than this article... (1)

rcs1000 (462363) | more than 3 years ago | (#35428294)

In fact, it would be very simple: he'd say "hmmmm... I wonder if there's any other way to get lower power consumption PCs, that continue to run all the existing software, and don't require new skills, and which run on proven technology. hang on! there's this Atom chip, x86 compatible with a TDP of c. 10Watts! I can achieve 95% of the savings without betting my career on unproven technology that might be ditched by Microsoft down the line. (As they did with Windows support for DEC Alpha, for example)"

Re:It's a bit more complex than this article... (1)

Midnight Thunder (17205) | more than 3 years ago | (#35428636)

I was reading that the ARM chips support Big and Little endian. Is this selected by the OS or by the firmware? Also does this make a difference for compiled software, such as a binary for a Linux application?

Re:It's a bit more complex than this article... (1)

Daengbo (523424) | more than 3 years ago | (#35428676)

You move the legacy apps to a server or two and still save money.

Re:It's a bit more complex than this article... (1)

YoopDaDum (1998474) | more than 3 years ago | (#35427938)

Just a comment on "If you want to embed processing functionality, or you want low-power (particularly low standby power), then you need ARM."

Stand-by power is really process related, and not so much related to the IA. It's true that ARM SoCs are using the LP (low power, and low leakage) variant of silicon processes while Intel/AMD processors use the high performance variants (faster, but higher power and leakage). But nothing prevents Intel optimizing for lower power, and the Atom goes in this direction while still targeting higher performance than current ARMs (that could change with A15, Denver...). Moreover, with recent processes (40 nm and below) the leakage is so high even in LP that for good stand-by performance one has to implement power gating. Intel can do that too. And I would guess the 50x improvement on recent Atoms come from this. Once you do power gating most design would consume negligible power in deep stand-by. ARM SoCs would still have an advantage as they are better integrated, but Intel has indicated they will go to more integration over time for Atoms. So it's really implementation choices, and different goals, that hard intrinsic advantage here IMHO.

ARM cores are available at three level: as a hard macro (ready to use for a specific process, you can't change anything), as RTL (you do the routing, and there some amount of configuration for caches, TCM, FP, etc.) or as an instruction licensee (you do the implementation yourself). In theory nothing would prevent an instruction licensee to do a super high performance implementation for example. It's just that in practice ARM licensee target for now low power devices, and as you explain target a different performance/power trade-off than even current Atom/Bobcat chips.

Re:It's a bit more complex than this article... (1)

cfriedt (1189527) | more than 3 years ago | (#35428254)

And the reason why x86 is so power hungry? It's because it's on big bits of silicon. And why's it on big bits of silicon? Because it support hyper-threading, out-of-order executon, has hardware virtualisation extensions, has extensive branch prediction, and tonnes of on chip cache.

And then there is of course the lack of 1.3 GHz memory bus speed. Yeah... that might also be a biggie, although ARM might win due to interconnect distance alone if a licensee ever decided to get in the high-speed memory game. Package-on-package, baby.

Re:It's a bit more complex than this article... (1)

Relayman (1068986) | more than 3 years ago | (#35428672)

Correction to that: If you need raw processing power, optimised to run desktop or server operating systems, then you'll be wanting PowerPC. PowerPC chips run circles around Intel processors.

Re:It's a bit more complex than this article... (0)

Anonymous Coward | more than 3 years ago | (#35428864)

To say ARM is better than Intel, is like saying a bicycle is better than a ship - it's not a meaningful comparison.

Indeed not. You can bike on water [wikipedia.org] , but can you ship on land? Can you? Huh?! HUH?!?!?

That's right, mister.
(walks off, secure in the knowledge of superiority of bikes over ships).

How is babby form (-1)

Anonymous Coward | more than 3 years ago | (#35427624)

'Who make ARM processors?'

Who care?

Re:How is babby form (0)

outsider007 (115534) | more than 3 years ago | (#35427766)

My babby ARM. Who dat?

Re:How is babby form (1)

White Flame (1074973) | more than 3 years ago | (#35427838)

We need to way instain Intel processors who consume more power!

and... (0)

Anonymous Coward | more than 3 years ago | (#35427628)

ill get back to work then if there is nothing to see here.

There's more to it (1)

i-linux123 (2003962) | more than 3 years ago | (#35427650)

Since most of us don't need the mobile device to continue functioning after heavy usage for more than maybe 48 hours, ARM has also hit a wall with how much lower power consumption is needed.

I'm guessing (2)

symbolset (646467) | more than 3 years ago | (#35427856)

I'm guessing here, but you live in a place where watts are cheap and reliable, right? Did you know most of the rest of the world isn't like that?

Fallacy (2)

dtmos (447842) | more than 3 years ago | (#35428152)

ARM has also hit a wall with how much lower power consumption is needed.

This is a line of reasoning I've been fighting most of my career.

Lower power consumption is always needed. In a battery-powered, portable device, energy use is use of a limited resource and, therefore, is never low enough. Even if "most of us don't need the mobile device to continue functioning after heavy usage for more than maybe 48 hours" -- a statement of dubious validity -- the energy saved in performing feature set X can be used to perform additional features, features that may be used to competitive advantage in the marketplace. (Reducing the power consumption of a cell phone enabled manufacturers to add things like audio players, video, big displays, etc. to the device.) Alternatively, it can be used to reduce battery size and weight, which can also be used to competitive advantage.

Like product cost, power consumption is an expense that is never low enough. Designers (or their organizations) that think their product cost or power consumption is low enough are setting themselves up for obsolescence.

Revenge of ARM (2)

NuShrike (561140) | more than 3 years ago | (#35427666)

ARM derived from the ideas of MOS and WDC (the 6502 and descendents) to make a low-power, efficient processor without fancy overheads.

Remember the rumors when the Apple II flirted with using ARM cpus toward the end of the line when Jobs was herding the company heavily toward Motorola and the 68K? Well the II line died with that, and so went any disruptive chances. Then strangely, it sorta came back again in the Newton, but Jobs killed that when he got the chance again while flirting with the PowerPC.

Then suddenly, Jobs embraced the ARM the next time around in the iPod and then later the iPhone (one-upping Sony in CE), and things have been going swimmingly for them.

Meanwhile, others picked up ARM for portable game devices, PDAs, and WinMob phones. It evolved slowly and not very well -- poor graphics drivers, poor OS/hardware implementations, hardware cycles focused on selling hardware, not the experience, etc.

Then the Jobs and iPhone said, "only the best combination of ARM cpu and graphics hardware for us. No more cheaping out to hardware designers for years like you guys have been doing", and boom explodes the market.

Companies are falling over themselves to make the best ARM hardware they can, although some are still missing the forest for the trees like Samsung. Others dumped the market because they thought it had no money like Intel's (formerly DEC's) Xscale(StrongARM) and ATI's Imageon graphics division (now Qualcomm's) and got caught with the pants down and what are now important toe-holds.

Nvidia whom only abortively were in the market and missed a cycle with the Tegra and half of it with Tegra 2, but seems to be holding their own. Imagination as PowerVR was pushed out of the PC market by Nvidia and ATI but flips it and now dominates as the best and reference hardware for mobile graphics over "newcomers" Nvidia/ATI. Funny enough, ATI's Adreno (from the former Bitboys) got recycled by Qualcomm into something that still viable after a stretch of horrible MSM720x hardware. Apple knowing they need to one-up these old-school houses, got PA-Semi and Intrinsity, fabbed by Samsung to own their own supply line for this critical hardware.

Ya this story just wonders what could've happened if Jobs wasn't so obstinate and denied using the ARM long ago.

Re:Revenge of ARM (4, Informative)

White Flame (1074973) | more than 3 years ago | (#35427700)

ARM-based CPUs owned the cell phone market long before Apple. Even back when Palm owned the PDA market, everything was shifting to ARM away from the mixed market that included MIPS and Super-H.

Now, while your claim that Apple's embrace of the "experience" instead of just raw features might have some merit in changing the consumer landscape, I don't think they had any affect on ARM's presence in that market. They already had it.

Re:Revenge of ARM (1)

Salvo (8037) | more than 3 years ago | (#35427810)

ARM development had stagnated; Hardware Manufacturers wanted cheap chips and were hesitant about pumping any more funds into R&D.
The original iPhone had a 1176JZ underclocked to 412 MHz and still blew away other handsets. The 3GS had a Cortex A8 and once again set the pace for the rest of the industry to catch up.

Re:Revenge of ARM (1)

marsalan (2012232) | more than 3 years ago | (#35427870)

all right..

Re:Revenge of ARM (1)

Alioth (221270) | more than 3 years ago | (#35427952)

ARM already had it thanks to Apple: when Apple chose the ARM for the Newton, other companies started taking ARM seriously and began to use it too.

This comes directly from Steve Furber and Sophie Wilson, the designers of the ARM (both of whom I've had the pleasure of meeting).

Re:Revenge of ARM (2)

itsdapead (734413) | more than 3 years ago | (#35427912)

Remember the rumors when the Apple II flirted with using ARM cpus toward the end of the line when Jobs was herding the company heavily toward Motorola and the 68K?

Eh? The ARM might have been a contender for the last, education-only, gasps of the Apple II line, but Apple had committed to the 68K (with Lisa and then the Mac) back in the early 80s when the ARM was still a twinkle in Wilson & Furbers eyes.

It might have been a viable alternative to the PPC, though - that would have been interesting, but I fear it would have eventually hit the same problem: the chipmakers not keeping up with the brute-force Intel megahertz wars on the desktop because their main interests lay elsewhere (one of the factors that worked against Acorn's ARM workstations and eventually forced Apple to dump the PPC).

Re:Revenge of ARM (1)

ChunderDownunder (709234) | more than 3 years ago | (#35428010)

I'm pretty sure a powerpc would spank an ARM on every benchmark so was never a consideration for PowerMacs.

Re:Revenge of ARM (1)

itsdapead (734413) | more than 3 years ago | (#35428282)

I'm pretty sure a powerpc would spank an ARM on every benchmark

If you're talking about a G5 vs. your cellphone, of course - but an early-1990s desktop ARM chip vs. a early-1990s PPC would be a more interesting contest. Remember, ARM started out as a desktop chip - the first Acorn ARM systems in the late 80s smoked the competition (but, no DOS, no deal). Later they made the smart decision to focus on the mobile/low power market and leave the desktop to Intel space-heaters.

It would partly have been up to Apple to take the ARM core and team up with a chipmaker to specify a chip with the performance they needed, throwing in cache, FPUs and SIMD units to taste.

Re:Revenge of ARM (1)

Midnight Thunder (17205) | more than 3 years ago | (#35428712)

I doubt it would win on performance per watt. Freescale and IBM didn't seem to care about that. IBM made it clear they just wanted to concrete or sheer processing capability. I suspect that was one if the reasons Apple moved to Intel - well that and cost.

drinking water filter ! (-1)

Anonymous Coward | more than 3 years ago | (#35427708)

Drinking water filter [webchuyennghiep.net]

alterslash.org (0)

Anonymous Coward | more than 3 years ago | (#35427724)

right

ARM employees (0)

Anonymous Coward | more than 3 years ago | (#35427850)

Did anyone notice how the salaries at ARM are terrible.

tv wars now playing in the bars? (-1)

Anonymous Coward | more than 3 years ago | (#35427940)

we saw a guy (walking dead talknician) on vdo last night, he said; we won't get behind letting ourselves kill both sides, until we see some horrific (even more exploding babys?) crap on tv, or attack ourselves again? so it looks like we're still safe? from ourselves/'them', for now?

/. irrelevant (0)

oisteink (234061) | more than 3 years ago | (#35427958)

Haven't been on /. for a few months now, and I totally understand why when I read the "news"

Even digg does this better by clearly marking their infomercial. Where did 1997 go?

ARM works best when your power supply has no LEGS (1)

Bob_Who (926234) | more than 3 years ago | (#35428008)

....they went to extremities with the appendages . Give 'em a hand for getting a leg up !

Back in 2004 ... (2)

cimetmc (602506) | more than 3 years ago | (#35428018)

Back in 2004 I've read a quite interresting article on ARM. http://news.cnet.com/The-unheralded-monopoly/2010-1006_3-5262581.html [cnet.com] As you can see, the strong position of the ARM is not new, maybe just a bit more visible these days.

Re:Back in 2004 ... (1)

marsalan (2012232) | more than 3 years ago | (#35428100)

hmmm good one..

my phone gets warm (-1)

Anonymous Coward | more than 3 years ago | (#35428032)

when i click on 'stuff' that matters', & discover it's stuff that only matters to convoluted advertising buffs. as for stuff that really matters, there's lots of it going on, in real time, right now. rob will get to it? after all the pre-paid 'submissions' have been exhausted?

pre-paid comments too? censorship? what's this? (0)

Anonymous Coward | more than 3 years ago | (#35428066)

used to be mostly just fuddles' pr firm decepticons, defending his right to conduct gangsterious softwars, both here & abroad. & lest we forget the still 'posting' stock markup liars, touts etc... now, there's a shill for almost every (sensitive) occasion. as for the babys et al (some already have missing limbs), WE'LL type (even if it's not perfect) for them, no charge. see you there?

better pay posting on tweeter, myface... now (0)

Anonymous Coward | more than 3 years ago | (#35428176)

makes sense? a 'good' (convincing) phony makes 1-2k.. per DAY, for lying to us. that's fair? like a 'war' of words. seems like almost everything now....

No Windows 7 Mobile on ARM (3, Interesting)

erroneus (253617) | more than 3 years ago | (#35428138)

I read through the article and found it very informative. One thing I didn't realize was that Microsoft will not do Windows 7 mobile on ARM.

That was a surprising statement. I googled on it and found this:

http://www.xbitlabs.com/news/other/display/20090603123741_Microsoft_Windows_7_Will_Not_Support_ARM_Microprocessors.html [xbitlabs.com]

This article says "Micrsoft does not believe ARM can deliver the performance needed." To that I wonder "why is everyone else able to make amazing performance happen with ARM???"

Every time I hear another Microsoft shill claim "but this is not Windows, it is entirely new from the ground up" I have to chuckle a little. If that were true, then they wouldn't have any problem getting performance out of low-power hardware if they designed their OS with that in mind "from the ground up." The truth of the matter is that Microsoft simply can't get away from its legacy code and rebuild from scratch. I shouldn't say they can't -- I should say they are unwilling. Apple did it when they went with OSX. A completely new OS and while the transition was painful for users and developers, it was the right choice. I have been saying for nearly a decade that Microsoft should do the same... others have too... but they simply choose not to at every opportunity.

This whole scenario gives me a better understanding of why Windows Mobile isn't catching on even with hard core MS fans. The "desktop experience" doesn't fit in your hand and they simply don't know how to do it any other way.... (Or maybe they are afraid to since MS Bob...)

Re:No Windows 7 Mobile on ARM (1)

ElephanTS (624421) | more than 3 years ago | (#35428416)

I shouldn't say they can't -- I should say they are unwilling.

I totally agree with the MS problem but I think they can't. Ten years ago they should have got away from everything that Windows had become and start again but they were too scared they would lose their base customers on the way. It shows they were insecure about their product and thought that it was a success they couldn't repeat again - too dependent on a naive market. Instead they came up with the compromise way forward (fix it - let's make Vista) and got terribly stuck as the complexity of the task overwhelmed them.

Re:No Windows 7 Mobile on ARM (0)

Anonymous Coward | more than 3 years ago | (#35428990)

I think it might be true that the actually can't.

Microsoft's main cash cow isn't home useres it's enterprise users. Most large companies would rather keep using an increasingly obsolete system that has proven reliabale than spend money to try a system that is new and wouln't work with the old (look at how hard it's been to kill IE6).

Microsoft lives on their legacy support. If they messed with that they'd probably see a lot of their customers just stop buying their products.

Re:No Windows 7 Mobile on ARM (1)

TonyJohn (69266) | more than 3 years ago | (#35428602)

Not sure what you mean by "Windows 7 Mobile" given:
- Windows Mobile - has long supported ARM, but has no version 7.
- Windows Phone 7 - only supports ARM.
- Windows CE - supports ARM.

The only thing that doesn't support ARM is "big" Windows 7, and this is changing:
http://www.microsoft.com/presspass/press/2011/jan11/01-05socsupport.mspx [microsoft.com]

Re:No Windows 7 Mobile on ARM (2)

erroneus (253617) | more than 3 years ago | (#35428736)

Yeah, I realized my mistake only after I read that article again. That said, I also found this:

http://www.pcworld.com/businesscenter/article/215779/windows_8_on_arm_expands_microsofts_mobile_horizons.html [pcworld.com]

And while it is a nice attempt (so far) what I expect to see is the same things we have seen from Microsoft for decades -- they will support Alpha or some other processor for a while and realize "we can save money by dropping support for this minority thing" and then kill it. And according to the review above, while the machines made an admirable attempt, it is still the same old Windows being a resource hog and barely making it work. (For that matter, the 64 bit x86 processor support seems to be really lacking too -- they just can't convince software developers to update their code to 64 bit!! Think your new 64 bit quad core monster will deliver awesome performance on your game machine with nVidia optimus driving the graphics? Nope!!)

Once again, Microsoft is attempting to shoe-horn their old code into new places. I just don't expect it to work. What I expect to see, however, is Microsoft giving a ton of money to ARM makers to boost performance on their machines in order to support their software. This will benefit Microsoft but will also benefit Linux and other OSes on the same hardware in a much more dramatic way... (Unless, of course, they manage to bribe ARM makers to keep their performance enhancements locked down in a way similar to GPU makers like NVidia who only really supports Windows.)

I'm still waiting for something really surprising to happen... been waiting for a very long time. I wasn't surprised that Vista was an utter failure. I wasn't surprised that Windows 7 was more of an apology than a new OS. Microsoft exists on its defense of its market dominance alone. They haven't done anything exceptional with the Windows OS since Win9X or possibly Windows 2000.

Microsoft is eroding away due to its failure to keep up with the changes. Most people can't see it yet, but I certainly can. I think it became rather evident when the public stopped cheering at MS Product announcements.

Re:No Windows 7 Mobile on ARM (0)

Anonymous Coward | more than 3 years ago | (#35428988)

Actually - Windows 8 will have ARM support.

http://hardware.slashdot.org/story/11/03/06/1546207/Taiwanese-OEMs-Consider-ARM-Products-For-Windows-8

Why make a statement when a question will do, eh? (0)

Anonymous Coward | more than 3 years ago | (#35428308)

If I were to ask you what is the most popular processor used in phones and pads, and you said, 'ARM,' you would be correct.

Or you could stop being condescending and just tell us that that is the case instead of framing it in a hypothetical question. I'm beginning to see what the Plain English Society have been banging on about all these years.

Re:Why make a statement when a question will do, e (0)

Anonymous Coward | more than 3 years ago | (#35428662)

If I were to have mod points I'd have modded you +1 agree

Server motherboard with ARM CPU? (0)

Anonymous Coward | more than 3 years ago | (#35428822)

This may be offtopic but I would so like to see a server motherboard with an ARM cpu. Does anyone know if there's something like that in the works? And I mean for personal use, not for high end enterprise data center...

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>