It looks like you're new here. If you want to get involved, click one of these buttons!
As you likely know, Windows 8 has a number of design features targeted at tablets. Microsoft is scheduled to launch it later this month. But just because the OS is ready (and there are doubts about that as well) doesn't mean that the hardware will be.
For desktops and laptops, of course, Windows 8 should run on the same hardware as Windows 7. That's not a problem. This thread is about tablets.
Microsoft is trying to hedge its bets, with both an x86 version and an ARM version, with the latter called Windows RT. Let's take them one at a time.
Only three companies have an x86 license, so Microsoft will have to hope that at least one of them makes a good tablet processor for Windows 8. On the Intel side, we mainly have Clover Trail Atom.
This is basically a tablet variant of Cedar Trail Atom, which was such a colossal flop that Intel wanted no attention for it whatsoever. The initial launch consisted of adding the parts to a list on Intel's web site, without so much as a press release. The press release did come later, but not review samples, as Intel didn't want to get buried in a barrage of negative reviews for a part that lost to AMD's older Brazos platform in just about every way imaginable.
Intel also has ULV Ivy Bridge parts available. But 17 W is a bad idea in a tablet.
On the bright side, Haswell is coming next year. Intel is putting a heavy focus on bringing power consumption down in Haswell, and there will commonly be 10 W bins of it. Haswell will probably bring impressive CPU performance for a 10 W TDP, and plenty of CPU performance for a tablet.
The trouble is, to get low power for a tablet, you need integrated graphics. The next respectable graphics product that Intel launches will be their first. And Haswell probably won't be it. Intel has already announced that API support won't even catch up to aging Radeon HD 5000 and GeForce 400 series cards. Haswell graphics are mostly derivative of Intel's last few disastrous generations (Intel HD anything).
Broadwell is supposedly going to bring a huge overhaul on the graphics side. But that's not coming until 2014. Besides, until Intel ships a good video driver for some older generation product, you shouldn't trust them to have a good one for a newer generation product. We're getting close to 15 years of waiting on the former, and still no luck.
Next up, we have AMD. Here, Hondo will be a killer product for tablets. It sports two enhanced Bobcat cores on a 28 nm process node with AMD integrated graphics in a 4.5 W TDP. It was also cancelled (along with Wichita and Krishna, the laptop parts) due to serial delays of Global Foundries' 28 nm process node. Oops.
Rumor is that AMD has reappropriated the name and Hondo will be a 40 nm product that is basically the older Desna chip with some bits removed that aren't relevant to tablets, in order to save on power consumption. AMD is supposedly going to launch something or other on October 9. But a warmed-over version of a laptop chip that is nearly two years old isn't exactly ideal.
On the bright side, Temash is coming, and is far more optimized for tablets. It will feature up to four Jaguar cores on a Global Foundries 28 nm process node, probably with GCN graphics. But that's not until next year, so it won't be in time for Windows 8.
AMD also has Trinity for laptops, and could squeeze that into a tablet. But as with Ivy Bridge, 17 W in a tablet is a bad idea. AMD has a 19 W bin of Trinity that is a quad core with 6 SIMD engines. Could they make a 10-12 W bin that is a dual core with three SIMD engines (currently being sold as A6 versions of Trinity)? Likely. Should they? That's still quite a bit of power for a tablet, even if they could do it.
And then there is VIA. Were you even aware that VIA made x86 processors? VIA has a significant share of the market for ultra-low budget x86 processors in embedded systems, but nothing with the energy efficiency needed for a tablet.
So what about ARM? There are problems here, too. The ARM processors on the market are basically targeted at cell phones at best, or even lower power alternatives otherwise. If you put a cell phone chip into a tablet, you get cell phone performance. Tablets should be able to have bigger batteries and more heat dissipation than cell phones, which would allow for higher performance. But ARM Cortex A9 doesn't get there.
ARM Cortex A15, on the other hand, does. And lots of ARM partners have chips that use ARM Cortex A15 cores. They've shown them off at trade shows, but everything seems to be delayed, and I'm not aware of any that are in commercial products yet. There is the Samsung Exynos 5250, the ST-Ericsson Nova A9600, Nvidia Tegra 4, and TI OMAP something or other.
All coming--but all not here yet. Some of them were supposed to be here by now, too.
Well, maybe not all coming. TI is reportedly shutting down its OMAP division and cancelling everything. Oops.
What about custom ARM cores based on the Cortex A15? Well, there is the Qualcomm Krait. Qualcomm showed it off earlier this year, and performance is impressive. But it's still not here. My guess is that the Qualcomm Krait will be the first of the good tablet processors to show up at retail, but I really don't know.
There is also Apple, which is tight-lipped about upcoming CPU plans. The Apple A6 is even a custom chip, rather than a Samsung chip with an Apple label on it like previous generations. But don't expect to see an Apple chip show up in a Windows RT device.
And it's not like ARM vendors are going to wait for Windows RT to launch products. Google Android dominates the ARM phone/tablet market, and it's available today. Furthermore, there isn't much reason to believe that Windows RT will change that.
One huge advantage that Windows 8 has is that it will run software designed for Windows 7, Vista, XP, and so forth. There is a huge software base already in place. For ARM chips, Apple and Google have a huge software base, and Windows RT has... nothing. Now add to that a high price tag and rumors that potential partners are furious that Microsoft is launching their own tablets and may opt out of making Windows RT tablets at all. The Windows brand name is universally recognized, but Windows RT doesn't really have anything going for it that various versions of Windows Phone didn't, and none of those turned out well.