Reproduce “BOOMerang: Autonomous Translation from RTL to Microarchitectural Simulators and Back” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ferran Hermida-Rivera, Jack Toubes, Angela Cui, Chengyi Lux Zhang, Sagar Karandikar
The authors introduce BOOMerang, feedback loops that align a processor simulator with BOOM RTL and translate simulator features back into the design. They evaluate 72 translations and combine eight features. On SPECint 2017 intspeed reference-input workloads in FireSim on AWS F2, the design achieves 28.9% higher IPC than unmodified MegaBOOM, with a 3% synthesized critical-path increase.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.