University of Pennsylvania researchers say their photonic chip that uses light instead of electricity, can radically cut down the energy consumption of AI and is commercially available for use now.
<p>Penn Engineers have developed a new chip that uses light waves, rather than electricity, to perform the complex math essential to training AI. The chip has the potential to radically accelerate the processing speed of computers while also reducing their energy consumption.</p>
Computers are starting to use staggering amounts of electricity. There is a trade-off here between the utility of the tasks they perform and the climate damage caused by generating all the electricity they need. Bitcoin mining is thought to be currently using 2% of America's electricity and seems an especially egregious waste of energy.
Radically diminishing computer's electricity requirements as they become more powerful should be seen as an urgent task.
Imo, analog computation is the way forward with this whole AI thing. It seems like a waste to perform calculations bit-by-bit when neural nets are generally okay with "fuzzy math" anyway.
Idk, maybe. But i think you may have issues with tolerances and reproducibility. With analog and neutral nets your going to have edgecases where some devices will give vastly differing outcomes. For something that's fine but not for others.