Intel researchers are working on a 48-core processor for smartphones and tablets, but it could be five to 10 years before it hits the market.
"If we're going to have this technology in five to 10 years, we could finally do things that take way too much processing power today," said Patrick Moorhead, an analyst with Moor Insights and Strategy. "This could really open up our concept of what is a computer... The phone would be smart enough to not just be a computer but it could be my computer."
Enric Herrero, a research scientist at Intel Labs in Barcelona, said the lab is working on finding new ways to use and manage many cores in mobile devices.
Today, some small mobile devices use multi-core chips. However, those multi-cores might be dual- or quad-core CPUs working with a few GPUs. Having a 48-core chip in a small mobile device would open up a whole new world of possibilities.
At this point, researchers are working to see how to best use so many cores for one device.
"Typically a processor with one core would do jobs one after another," Herrero told Computerworld. "With multiple cores, they can divide the work among them."
He explained that with many cores, someone could, for instance, be encrypting an email while also working on other power-intensive apps at the same time. It could be done today, but the operations might drag because they'd have to share resources.
Tanausu Ramirez, another Intel research scientist working on the 48-core chip, said that if someone was, for example, watching a high-definition video, a 48-core chip would be able to use different cores to decode different video frames at the same time, giving the user a more seamless video experience.
Ramirez also said that instead of one core working at near top capacity and using a lot of energy, many cores could run in parallel on different projects and use less energy.
"The chip also can take the energy and split it up and distribute it between different applications," he added.
Justin Rattner, Intel's CTO, told Computerworld that a 48-core chip for small mobile devices could hit the market "much sooner" than the researchers' 10-year prediction.
"I think the desire to move to more natural interfaces to make the interaction much more human-like is really going to drive the computational requirements," he said. "Having large numbers of cores to generate very high performance levels is the most energy efficient way to deliver those performance levels."
Rattner said functions such as speech recognition and augmented reality will push the need for more computational power.
"If it's doing speech recognition or computer vision... that's very computational intensive," he added. "It's just not practical to just take sound and pictures and send it up to the cloud and expect that some server is going to perform those tasks. So a lot of that will be pushed out to the client devices."
Rob Enderle, an analyst with the Enderle Group, said being able to have different device functions, as well as apps all running on their own cores would be a great advance.
