US 12,169,677 B2
Standard cell layout generation with applied artificial intelligence
Haoxing Ren, Austin, TX (US); and Matthew Rudolph Fojtik, Chapel Hill, NC (US)
Assigned to NVIDIA Corp., Santa Clara, CA (US)
Filed by NVIDIA Corp., Santa Clara, CA (US)
Filed on Apr. 14, 2021, as Appl. No. 17/230,592.
Claims priority of provisional application 63/090,037, filed on Oct. 9, 2020.
Claims priority of provisional application 63/055,753, filed on Jul. 23, 2020.
Prior Publication US 2022/0027546 A1, Jan. 27, 2022
Int. Cl. G06F 30/398 (2020.01); G06F 30/394 (2020.01); G06N 3/047 (2023.01); G06N 3/12 (2023.01)
CPC G06F 30/398 (2020.01) [G06F 30/394 (2020.01); G06N 3/047 (2023.01); G06N 3/12 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A routing method for a circuit layout, the method comprising:
executing a genetic routing algorithm to generate routes in the circuit layout;
applying a reinforcement learning model to correct design rule constraint errors arising from the routes; and
applying a number of uncorrected ones of the design rule constraint errors to evolve the chromosomes of a genetic routing algorithm.