Slashdot Mirror
Ice Cream Sandwich Ported To X86
angry tapir writes "Google's open-source Android 4.0 operating system for smartphones and tablets has been ported to work with x86 processors. The port means that tablets with Android 4.0 based on x86 chips could be on the horizon. Intel is the top x86 chipmaker, and the company has already said it is working with Google to bring Android 4.0 to smartphones and tablets."
It seems our technology continues to expand in all directions and then collapse into a single device. TVs, PCs, and phones are becoming part of the same thing.
Does this mean i can run the apps natively without using an emulator on a windows box?
Yes, but on the other hand, even an Intel Atom is significantly faster than even the fastest ARM... pity Intel insists on supplying their own GPU with Atoms, because the NVidia Ion + Intel Atom.combo was actually pretty sweet.
You could already do that.
Well, more or less. It's a port of the Android libraries to a Windows JVM, which is sufficient to run many/most Android apps (much like what RIM are doing). It's not a port of Android itself. But it does run Android apps in windows on your desktop (or fullscreen).
Why would anyone engrave "Elbereth"?
The better question is why the submission focuses on Intel when the port currently only works on AMD?
"The release isn’t fully stable — missing sound, camera, ethernet, and hardware acceleration for Intel chipsets. What will work however is Wi-Fi, sound, and hardware acceleration for AMD chipsets."
"A person is smart. People are dumb, panicky dangerous animals and you know it." - K
Well i guess that settles the question of what a chatbot with ADHD might say after reading the entire history of /.
I am literally 3000 tokens away from the chaotic crossbow --Stephen
Every build of Android since, as I recall, 1.5, has been ported to x86. It's part of Intel's (silly) strategy to put Atoms in cell phones and tablets.
I'd like an Atom in my cellphone. Then I could use it as a hand-warmer in the winter.
The X86 instruction set was silly, then it stopped being silly as instruction bandwidth became a limiting factor for RISC processors. Ideally you want a kind of huffman coding for instruction sizes, so that the most frequent instructions are the smallest. Traditional RISC makes all the instruction the same big size, so you get the worst bandwidth through a limited instruction bus.
In today's world, where on chip busses are so much faster than off chip busses and instruction bandwidths are limiting, having compact instructions over the pins, being converted on chip to regularized RISCy instructions makes complete sense. So X86 stopped being silly a while back.
If you wanted to design a new instruction set today, you'd optimize for things like instruction bandwidth minimization, security, parallelizability and important application loads (e.g. more DSP). In that light, X86 might be a bit messy, but it is far from silly, especially after the 64 bit cleanup.
Actually the Cortex A9 found in Tegra 2 and Ti's OMAP 4 series are at the same clockspeed marginally faster than even the top end Atom cpus, IONised or not, even at their standard speeds the differences in performance are not that huge.
http://parisbocek.typepad.com/blog/2010/11/arm-outmuscles-atom-on-benchmark.html
Pretty sure things like the tegra 3 would blow away any atom.
But, even things like the omap4 and tegra 2 might be pretty close. Memory bandwidth sucks on the omap, so for some things like large transfers of data atom may excel over omap but not really cpu speed issue. Tegra doesn't share this flaw with the omap.
I never did / read any benchmarks, but I have a dev board with an omap4 on it, and it "feels" just as fast as my netbook. The dev board is currently doing duty as the guest web browsing machine, wifi access point (two radios), radius server, ldap server, firewall, squid proxy, webserver, dhcp server, dns cache, network USB server (serves up a dvd writer to my netbook over wifi this way), and fileserver (laptop hard drive) for the house. It is running Debian wheezy armel (need a few more things to work on armhf before pulling that trigger, but armhf will make it even faster).
As for power, even with all the peripherals (radios, spinning hard drive, USB hub, doing a native build), it is pretty rare to see system power hit 5 watts. Atom is left in the dust here too.
It's called a singularity because like the singularity of a black hole it's impossible to see what's beyond it. We can see what's beyond this: more progress and more competition. More diversity, more sales, more fitness of technology to our human needs. More connectivity between people.
We've gone beyond moving the buttons around on the word processor to sell it again to the same people who bought it before. But we can still see the future from here and it looks grand.
The Singularity is an even bigger deal, and further out.
Help stamp out iliturcy.
As others have pointed out, Atom is pretty weak. It has a rep for being powerful, idky. The Atom is on par with the PowerPC G4... an old chip that uses a lot more energy. I'd be very surprised if ARM couldn't easily match it. If you want more proc power in a low power chip, AMD E-350 blows Atom away. I really don't undertand everyone's crush on Atom.
The Admin and the Engineer
Clock speed != performance. Especially not between such divergent systems as x86 and ARM. Even comparing clocks between Atoms and Cores is an unreliable indicator of relative performance, let alone comparing different fundamental architectures.
Intel's not the only foundry on 22nm. Obviously not, since they buy their lithography equipment from third parties that must have more than one customer. They're investing heavily in this area it's true. Trigate is slick, but there are a lot of up-and-coming technologies Intel can't prevent. Apparently Intel forgot to patent the 90 degree rotation of trigate.
Intel's problem isn't their hardware, it's the software that runs on their hardware. In the executive suite they've got a Windows habit that's hard to kick. That worked for a while, but that day is coming to an end. People are starting to look from their WinTel PC to their iPad, iPhone, Android tablet or phone and ask: WTF? Why is this all-day battery-powered thing more capable and responsive than the half-kilowatt new desktop before me? For a lot of years the proclivity of Windows to consume all of Intel's Moore's law progress in hardware with slower software was a good thing. It moved a lot of units - encouraging people to upgrade both hardware and software, but Apple and now Google have spoiled that game. It was a trick and now the trick is told, all bets are off. It's a new game now.
Truth be told I was always amazed that people with a 3GHz dual-core processor just accepted that to get a desktop they should fire it up and go get coffee because they knew it took five minutes. That's performance we wouldn't have stood for in 1984 when processors were less than 0.01GHz and storage was slower still. A 3GHz single core Intel processor from 2005 retiring 4 instructions per clock retires 3.6 trillion instructions in five minutes. A modern SATA hard drive can deliver something like 4.8GB in five minutes. A modern gigabit network connection passes 6GB in five minutes. A reasonable desktop environment takes about 3MB and a few million instructions to present. Do you get what I'm saying? The hardware isn't the problem and it hasn't been since about 1993. Just abandoning crap software isn't going to get Intel out of the woods though now. That might have worked in 2003.
Intel's software partner Microsoft got the clue first, and now the word is that Windows 8 will be expressive and performant even on Windows XP machines, and run on ARM too. That's not going to move a lot of Intel CPUs any more. By all reports the WinTel marriage is on the rocks and could be over soon.
In the executive suite Intel's focused on exactly the wrong things: improving what they're doing, not cannibalizing their current markets. That was a good strategy for a while, but it's not going to weather the current changes - as I tried to tell them seven years ago. Now they need something... different.
So now Android runs on X86. That's a good thing. It can run in a VM on your modern Windows desktop in W7 with Microsoft Virtual PC, and give you the Android apps from your phone in a window on your PC. They can share accounts and data in the cloud. HP should have (and I believe planned to) done this with WebOS, but I believe caved when MS explained the consequences. But Intel's focus is still on the widget, not solving the real problem. Android on x86 is just going to move people to ARM faster if Intel doesn't get their software religion under control. This should be dead simple. Intel doesn't sell Windows and they should not care whether Windows lives or dies. They sell platforms, and help software vendors implement those platforms. They need to shift from that to delivering experiences, and controlling those experiences to a limited extent.
There are others without Intel's history and established markets who are ready to solve the real problem. Intel can join them or get out of the way. This is going to happen very fast, so Intel doesn't have forever to dither about figuring out where the road ahead might be.
Help stamp out iliturcy.
x86 never was a champ in power efficiency. It excels in instructions (performance) though, that's why it has come to dominate the "productive computing" market. The architectures Android was tailored towards both in backend and in api were designed and utilized with instruction frugality and hardware limitations in mind.
Making Android available on the much more powerful x86 ecosystem and its hardware net is counterproductive at best. Why imped a device with the limitations of a toy OS when you can utilize a complete desktop environment?
-- no sig today
True. But did you read what the post you were replying to, which said that ARM Cortex A9 is *faster per clock* than Atom. The Atom is an in-order, dual issue processor with no speculative execution. The Cortex is a reordering dual issue with speculative execution. And the lack of register renaming on the Atom means its 6 general-purpose registers compare particularly badly with the Cortex's 15. Of course it's faster.
Now, OK, the faster A9's I've seen clock at 1.3GHz, compared to the Atom's 1.8GHz, but that means the two are in similar ballparks, and the A9 is *much* cheaper and *much* lower power. And a quad-core A9 typically draws less power (about 1.3W with all 4 cores running flat out) than a single-core Atom (about 2.5W). And there are no quad-core Atoms as of yet, so the A9-based systems (eg Tegra 3/iMX6) are clear winners in total peak performance in a mobile chip.
Totally agreed on the AMD E-350 as that is the reason i finally bought a netbook. After dealing with customers constantly saying "can you make this....I don't know...faster somehow?" and having to tell them that without ION Atom was pretty much a lame duck I avoided the hell out of them until I got to work on a customers E-350 and thought "Hell yeah, this is actually usable!"
As for TFA....why? if you want a killer low resource Linux on X86/64 frankly all you have to do is go buy the AMD E-350 based EEE (don't know if they have it on the Atom) and enjoy expressgate. Instant on, adds a couple of hours to the battery, at least for me, nice GUI, its all easy peasy. If the community would just get behind expressgate/splashtop and be writing apps for it frankly i could easily see the fabled "year of the Linux desktop" meme becoming reality.
If you want to beat MSFT the trick is NOT to try to get rid of Windows, its to go around it. With EG/ST they still have windows if they need it but as they play in EG/ST and if the community backs it I could easily see them not really needing to go back to Windows much. It already plays most media, has a nice book store and piles of radio stations, all it needs is more apps and games and you could slowly but surely wean users off constantly needing Windows.
ACs don't waste your time replying, your posts are never seen by me.