If we’re going to embed chips into roads, bury them in fields and even slap them on produce at the grocery store, we’re going to have to dump the battery. They are expensive, bulky, require changing and can also leak toxins into the environment. And while many people are focused on how to best to power these future sensors, the chip architecture firm ARM is thinking about how to build chips for sensors that harvest their own energy.
Maybe these sensors are gathering power from RF signals in the air, kinetically, or even through a chemical reaction that they are built to recognize and report. No matter how they gather the energy, if they can’t store it then the way the chips use that power may have to change. At least that’s what Mike Muller, the CTO of ARM, told Peter Clarke of EETimes last week. In this story he explains how ARM is rethinking chip design for specific internet of things applications:
“Normally, the best strategy is to do processing as fast as possible and then go to sleep for as long as possible — get in and get out,” Muller said. “But for energy scavenging, it can be different.” In these cases, it may be best to power up and get the packet out at minimum energy as soon as enough energy has been harvested. “And it turns out the design tradeoffs are different.”
The story explains how the design considerations mean that an energy-harvesting chip might operate at near the power threshold required to flip a transistor on or off as opposed to the norm of powering something all the way up and down. ARM is working on this technology with its foundry partners to ensure that such a different design could be manufactured.
Should this design win converts, it would take ARM’s reputation as a power-sipping core to entirely new levels. Of course, these chips would be slower than page loads on a 2G network, but perfectly tailored for delivering little bits of environment information.