ARM-Based Windows 8 Notebooks in Mid-2013?

[loomis86]

system on a chip is the future for PCs, folks, whether you want to believe it or not. It may not be ARM, but it will be something with SOC. When shrinking everything down, there comes a point when separate components no longer makes any sense. In 20 years a PC will be about the size of a smart phone and 10 times the computing power of today's most expensive laptop...and x86 is not going to get us there. If you think they will continue constructing a PC the old way, you're nuts. Ain't gonna happen.

 

[sonofliberty08]

 

[Guest]

"*Shudder*

And you realize that Atom's are the absolute slowest low power x86 CPU you can get. AMD and Via both produce faster CPU's that drink approximately the same amounts of power (once the whole platform is taken together). Atom's are deliberately crippled worse then the Celerons where, to prevent them from competing with Intel's budget processors."

Not true! If you throw in the nVidia ION, then yes they do use the same power, but not the base Intel chipset. The Intel chipset is of course a bit crippled but it is lower powered than either AMD or Via's solutions. As far as performance, it is still way above that of the ARM and when Silvermont comes out, it will be in a similar power envelope. ATOM >>> ARM.

 

[danwat1234]

I can see a bunch of computer newbies buying these laptops and not realizing that it's a new architecture than they have been using, not knowing that they just bought something closer in architecture to a smart phone rather than an x86 laptop. Poor newbies that don't have a clue.

 

[techguy378]

[citation][nom]amk-aka-Phantom[/nom]Windows does NOT perform on an ARM processor yet, troll, it's x86-only.[/citation]
I was speaking of Windows 8. Windows 8 is available for ARM processors right now even if it is a beta version and it performs significantly faster on an ARM processor than it does on an x86 processor.

 

[de5_Roy]

i see a lot of people being optimistic about arm on notebooks. it's good. but writing off current architecture in favor of arm is kinda pathetic. people should wait and see how arm+windows pan out in real world testing.
i mentioned soc size because while 40 nm arm socs are frugal in terms of power consumption, they're not exactly up to performing desktop/laptop type tasks. smaller socs haven't come out or haven't been tested yet. so wait and see what happens.
if intel didn't use atom to popularize netbooks we'd still use laptops and crappy symbian and windows ce/6 phones. now atoms are slow as snails compared to what is available in the market but atoms (and celerons) did kinda pioneer this.
idiots predicting death of the pc: you've been doing this long enough to know that pc has outlived most of you. you are and will forever be wrong.

 

[captaincharisma]

Sure, but Windows CE is a very different OS from desktop Windows. Just try to port a simple app to CE. . .

actually when i threw that out there i was thinking of the versions of windows NT 4.0 that supported ARM CPU's.MS did it in the past so its not like they are going in not knowing anything about this architecture .

 

[Guest]

No one mentions cost. Intel enjoyed profit margins ARM suppliers can only dream of. There are dozens of companies making ARM processors, that competitive market keeps them cheap. Intel processors are hundreds of dollars, Arm are dollars, even cents. Consider most of the 7 billion people on the planet don't live in the afluent 'West'. They are never going to afford Intel's offering, but a cheap as chips $100 computer is possible with ARM. Smaller profit, HUGE market.

 

[ojas]

[citation][nom]Zanny[/nom]Kal'el Tegra chips are 45nm, the Wayne series after that in early 2012 will be 28nm, and I expect ~20nm by 2013. They use TSMC for both gpus and socs, while AMD is using TSMC for the radeon 7000 gpus that are on their way.ARM processors are extremely power efficient, and once you have 4 cores at 2ghz each performance on consumer grade laptops becomes a non issue. I expect by 2015 for there to be a general market of $300 - 500 ARM windows laptops with battery life in the neighborhood of a day under load, and the $1k + market will be dominated by skylake by Intel at 16nm.[/citation]
Man your info and speculation is a bit off.
For starters, skylake=14nm. Ivy bridge is 22nm already, and we have no idea about its IPC. Sandy bridge procs are going as low 35W for the DESKTOP versions and still performing really well, TDPs are going to drop way lower in the coming years. Remember, Skylake will be a new micro-architecture, and Intel's probably already has a fair idea what it can do.
For every shrink in architecture, there seems to be a drop of about 20W. So Broadwell would be running at about 60W (max), with Skymont (10nm) that comes in 2016 probably going all the way to a 40W max. Current low voltage SB procs have a 60W lower TDP than the mainstream parts, so imagine low voltage parts then to be sitting around 1-5W. Not talking about Atom procs here. I mean any -T designated desktop processor.

Couple this with a very, very high IPC, and x86 + Intel looks to stay. It's not going to be so easy for chip makers like Nvidia to move to 20nm too soon without hitting any issues, they're having trouble already with the 28nm process.

though i suspect we may finally see cheaper intel procs...

 

[PhilFrisbie]

actually when i threw that out there i was thinking of the versions of windows NT 4.0 that supported ARM CPU's.MS did it in the past so its not like they are going in not knowing anything about this architecture .

Despite what Wikipedia says, Windows NT never officially supported ARM CPUs, just x86, MIPS, Alpha, and PowerPC. Windows CE was the only version of Windows that officially supported ARM.

 

[PhilFrisbie]

port application from CE to windows or windows to CE is relatively easy, as long as on .Net framework, it works on both CE and Windows

also back in win2K, there is windows support for RISC CPU, even back to windows NT

OK, I admit I was talking about native apps, and not interpreted .Net apps. There are enough differences in the various Win32 APIs that all but trivial apps must be rewritten. For example, CE only supports unicode, low level threads act differently, and some common C runtime functions are missing.

Yes, NT has supported RISC CPUs such as PowerPC and MIPS, but ARM was never officially supported.

 

[PhilFrisbie]

x86 is junk? Holy crap are you an idiot.

No, I don't think x86 is junk either, but billybobser does have a good point: x86 has so much legacy support that the CPUs are larger and slower because of it. I mean, you can load DOS on a PC with the latest Intel CPU and run a 30 year old 8086 program on it!

I do not see switching to an ARM desktop anytime in the near future, but I would consider a light ARM laptop for longer battery life. . .

 

[captaincharisma]

Despite what Wikipedia says, Windows NT never officially supported ARM CPUs, just x86, MIPS, Alpha, and PowerPC. Windows CE was the only version of Windows that officially supported ARM.

screw wikipedia i got that out of an old windows NT textbook

FAIL

 

[eddieroolz]

Why do we keep talking about this as if this may or may not happen? We already know Microsoft is adding support for ARM with Windows 8, and we already know ARM is working on optimizing its system for Windows 8. It's just a matter of time when desktops with ARM processors come out...

 

[palladin9479]

Why do we keep talking about this as if this may or may not happen? We already know Microsoft is adding support for ARM with Windows 8, and we already know ARM is working on optimizing its system for Windows 8. It's just a matter of time when desktops with ARM processors come out...

Which will run absolutely nothing. Key to Windows success has been backwards compatibility, you can't run x86 machine code on an ARM CPU you need to recompile at a minimum.