A new reinforcement-learning algorithm has learned to optimize the placement of components on a computer chip to make it more efficient and less power-hungry.

3D Tetris: Chip placement, also known as chip floor planning, is a complex three-dimensional design problem. It requires the careful configuration of hundreds, sometimes thousands, of components across multiple layers in a constrained area. Traditionally, engineers will manually design configurations that minimize the amount of wire used between components as a proxy for efficiency. They then use electronic design automation software to simulate and verify their performance, which can take up to 30 hours for a single floor plan.

Time lag: Because of the time investment put into each chip design, chips are traditionally supposed to last between two and five years. But as machine-learning algorithms have rapidly advanced, the need for new chip architectures has also accelerated. In recent years, several algorithms for optimizing chip floor planning have sought to speed up the design process, but they’ve been limited in their ability to optimize across multiple goals, including the chip’s power draw, computational performance, and area.

Researchers are using AI to search satellite images for unexploded bombs dropped in Cambodia during the Vietnam War.

The system uses object recognition algorithms that detect the unique features of bomb craters, including their shapes, colors, textures, and sizes. These algorithms then scan satellite images for signals of the craters.

The Ohio State University team first used the system to find craters in a village in the province of Prey Veng, a heavily bombed area around 30 kilometers from the Vietnam border.