Superhuman floorplans for microchips

Seminal innovations in the mathematical field of applied optimization, such as a method known as simulated annealing4, have been motivated by the challenge of chip placement. Because macro blocks can be thousands or even millions of times larger than standard cells, placing cells and blocks simultaneously is extremely challenging. The authors report that, when their agent is pre-trained on a set of 10,000 chip floorplans, it is already quite successful when used in a 'one shot' mode on a new design: with no more than six extra hours of fine-tuning steps, the agent can produce floorplans that are superior to those developed by human experts for existing chips. [...]the agent's solutions are very different from those of trained human experts (Fig. 1). The trained agent's macro-block placements somehow evade such landmines in the design process, achieving superhuman outcomes for timing (ensuring that signals produced in the chip arrive at their destinations on time) and for the feasibility and efficiency with which wiring can be routed between components. [...]Mirhoseini and colleagues' use of simple metrics as proxies for key parameters of the chip design works surprisingly well - it will be interesting to understand why these proxies are so successful.