It takes a lot of energy for computing systems or data centers to patch up critical errors, but what if we devoted less power to fixing less urgent issues? That's the basic idea behind EnerJ -- a new power-saving system that could cut a chip's energy consumption by 90 percent, simply by prioritizing critical problems over those that are less threatening. Unlike, say, liquid cooling techniques, the University of Washington's framework focuses exclusively on the programming side of the equation and revolves around two interlocking pieces of code: one that handles crucial, precision-based tasks (e.g., password encryption), and another designed to deal with processes that can continue to function, even when facing small errors. The system's software would separate the two codes, meaning that energy from one section of the chip would never be used to fix a major problem that the other should address, while allowing engineers to more efficiently allocate voltage to each region. The system has already cut energy usage by up to 50 percent in lab simulations, but researchers think the 90 percent threshold is well within their reach, with computer engineering professor Luis Ceze (pictured above) predicting that the system may even be able to increase battery life by a factor of ten. The team is hoping to release EnerJ as an open-source tool this summer.It takes a lot of energy for computing systems or data centers to patch up critical errors, but what if we devoted less power to fixing less urgent issues? That's the basic idea behind EnerJ -- a new power-saving system that could cut a chip's energy consumption by 90 percent, simply by prioritizing critical problems over those that are less threatening. Unlike, say, liquid cooling techniques, the University of Washington's framework focuses exclusively on the programming side of the equation and revolves around two interlocking pieces of code: one that handles crucial, precision-based tasks (e.g., password encryption), and another designed to deal with processes that can continue to function, even when facing small errors. The system's software would separate the two codes, meaning that energy from one section of the chip would never be used to fix a major problem that the other should address, while allowing engineers to more efficiently allocate voltage to each region. The system has already cut energy usage by up to 50 percent in lab simulations, but researchers think the 90 percent threshold is well within their reach, with computer engineering professor Luis Ceze (pictured above) predicting that the system may even be able to increase battery life by a factor of ten. The team is hoping to release EnerJ as an open-source tool this summer.
Comments
Post a Comment