科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ IEEE DataPort2026-08-01· Design space exploration

"LLM-Guided Microarchitecture Design Space Exploration on RISC-V: CVA6 and BOOM Trials with CPI, Area, Power, and Reasoning Traces"

Weimin Fu

原始摘要(英文原文)· Original abstract
"This dataset records every trial from a study comparing large language models with classical and learned optimizers on microarchitecture design space exploration, for two RISC-V cores. CVA6 is a six-stage in-order core with 13 configuration knobs and 46,656 valid configurations; BOOM is an out-of-order core explored in both a 12-knob and a 25-knob space. Each trial pairs a configuration with measurements from the flow design teams actually use: cycles per instruction from cycle-accurate RTL simulation, and total cell area, maximum frequency, dynamic power, and leakage power from logic synthesis against a 32-nm standard cell library. The CVA6 database holds 42,565 trials from 11 language models and eight baselines across six workloads and five seeds, under prompt conditions that vary whether knob names are real or obfuscated and whether functional descriptions are supplied. Of the 36,085 model-driven trials, 32,284 carry the natural-language rationale the model gave for its proposal, averaging 612 characters, which makes the dataset usable for work on reasoning quality and not only on search efficiency."
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

"LLM-Guided Microarchitecture Design Space Exploration on RISC-V: CVA6 and BOOM Trials with CPI, Area, Power, and Reasoning Traces" — 科研速览 Science Skim