Using RL to refine existing macro placements, rather than generate them from scratch, improves wirelength, congestion, and timing on chip placement benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
Using RL to refine existing macro placements, rather than generate them from scratch, improves wirelength, congestion, and timing on chip placement benchmarks.