This article is more than 1 year old

Intel clones your phone in the cloud

Data center in your pocket

Research@Intel Your smartphone will have access to massive computing power if Intel's Clone Cloud finds a place in the sky.

Intel demoed this fledgling tech this morning at its seventh annual Research@Intel event in Mountain View, California. As Intel researcher Byung-Gon Chun told The Reg, the Clone Cloud is designed - as its name suggests - to create a clone of your smartphone's data and apps and run them in a cloud environment where they can take advantage of far more computing power than could ever be squeezed into a pocketable device.

Thanks to a stack living on your smartphone and another on a host device - which could either be dedicated hardware or a virtualized instance - your phone (or netbook, nettop, MID, or whatever) could live a schizoid life, existing both in your pocket and in the cloud.

When you ask your handheld to perform a computational task that would benefit from more horsepower, the device and the cloud could negotiate at run-time to determine how best to satisfy your request. If the cloud can help, it will - delivering the results back to your handheld.

Of course, offloading computationally expensive operations from clients to hosts is not new. The Clone Cloud is different, however, in that the client/host relationship dissolves into the cloud. The smartphone isn't getting data from an application running in the cloud. The smartphone itself is running in the cloud in clone form.

The cloud, by the way, doesn't have to live on big iron in a data center. The Clone Cloud concept is designed to scale down to a point where the host could be your laptop or desktop machine.

To demonstrate the power of the Clone Cloud, Chun ran an image-processing task that took a minute and a half on a smartphone. On the smartphone's clone, the same task took a second and a half - including the transmission time - and the process was seamless. To the user, it simply looked like one hella-fast smartphone.

Chun sees five major types of usage for the Clone Cloud:

Primary: In this most-basic implementation, the handheld manages user interface and other "low-octane" tasks, and offloads more computationally intensive processes to the cloud. Communication between the devices is done in real time, transparent to the user.

Background: This scenario is designed to allow processes that don't require immediate user interaction - virus scans, for example - to take place on the clone of the device that resides in the cloud, and then communicate back to the device when they're complete.

Mainline: A cross between the Primary and Background scenarios, in this implementation the clone checks in with the handheld at predetermined intervals during the running of an application. It could, for example, be used for debugging, where the clone could "rewind" at a given checkpoint if a bug appeared.

Hardware: In this scenario, the clone calls on other hardware resources and file systems to drastically boost the clone's capabilities. For example, instead of running a process on an ARM emulator in the clone, it could instead dig directly down to its underlying hardware. In effect, you could have a Xeon 5500, InfiniBand smartphone.

Multiplicity: Finally, multiple clones of the same handheld could be created to enable parallelization of tasks. While Chun refers to this as an "extravagant" use of compute power in terms of the energy used, it could provide a decisive computational boost in, for example, critical parallelized statistical analyses in emergency medical use.

You can find more information on the Clone Cloud concept in Chun's detailed paper (PDF), "Augmented Smartphone Applications Through Clone Cloud Execution", co-authored by fellow Intel researcher Petros Maniatis. ®

More about

TIP US OFF

Send us news


Other stories you might like