LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation
Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-layer framework that separates large language model (LLM) orchestration from deterministic FPGA implementation and evaluation. Across sixteen designs and seven LLMs, a sin...
Shuang-Long Gu, Matthew Youngman, Yu-Qin Zhao et al.
· 0 citations