Metraipolis › archive › dc_ec2941ea7ee6

LLM Agent-Based Design of RISC-V CPUs with FPGA-in-the-Loop Evaluation — arXiv:2610.39570

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39570
License (as archived): CC0-1.0
Archived: 2026-10-31T06:13:19.227Z
SHA-256 of the archived text: 2f9f3efb291680bab17365ebcc0aabc753e49107832260ca80566e29b643487f
Stable URL of this page: https://metraipolis.com/documento/dc_ec2941ea7ee6

How to cite

LLM Agent-Based Design of RISC-V CPUs with FPGA-in-the-Loop Evaluation — arXiv:2610.39570 — arXiv (en), https://arxiv.org/abs/2610.39570 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec2941ea7ee6 (Metraipolis archive dc_ec2941ea7ee6, sha256 2f9f3efb291680bab17365ebcc0aabc753e49107832260ca80566e29b643487f)

BibTeX

@misc{dcec2941ea7ee6,
  title = {LLM Agent-Based Design of RISC-V CPUs with FPGA-in-the-Loop Evaluation — arXiv:2610.39570},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39570},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec2941ea7ee6; sha256 2f9f3efb291680bab17365ebcc0aabc753e49107832260ca80566e29b643487f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39570. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-run RTL simulation of CPU candidates can take hours, while short diagnostic runs may miss performance degradation that emerges later in execution. This evaluation cost can delay design decisions in LLM-agent-based CPU development. We present a development environment in which LLM agents implement CPU candidates on an FPGA and use on-board performance measurements to guide design decisions. We applied it to the human-supervised development of a single-cycle RV32I core into a three-wide out-of-order RV32IM core. The final design reaches 5.61 CoreMark/MHz at 130 MHz on a Artix-7 FPGA. For the same CPU candidate running 8,000 CoreMark iterations, FPGA evaluation, including implementation, was 9.6x faster than single-threaded RTL simulation. In one case, board measurements revealed long-run performance degradation in a candidate that improved in a short diagnostic run. The result guided candidate selection and led to RTL-based root-cause analysis and a fix.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Hardware Architecture (cs.AR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.39570 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:08.723Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).