A local-cloud LLM framework improves Verilog power and timing optimization success rates by sending only abstracted design principles to the cloud, not the proprietary RTL code.
Do not ref- erence specific code details from the examples, but instead extract the underlying principles that make implementa- tions more power-efficient
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Principle-Guided Verilog Optimization: IP-Safe Knowledge Transfer via Local-Cloud Collaboration
A local-cloud LLM framework improves Verilog power and timing optimization success rates by sending only abstracted design principles to the cloud, not the proprietary RTL code.