Metraipolis › archive › dc_99e35ba06e56

Formalizing PTX in Lean to Prove GPU Kernel Correctness — arXiv:2611.04447

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04447
License (as archived)
CC0-1.0
Archived
2026-11-04T21:37:59.743Z
SHA-256 of the archived text
57b579b77381bff21160c96ab526d0b01e3015f49dcf47d24036da30ce7fcb58
Stable URL of this page
https://metraipolis.com/documento/dc_99e35ba06e56

How to cite

Formalizing PTX in Lean to Prove GPU Kernel Correctness — arXiv:2611.04447 — arXiv (en), https://arxiv.org/abs/2611.04447 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99e35ba06e56 (Metraipolis archive dc_99e35ba06e56, sha256 57b579b77381bff21160c96ab526d0b01e3015f49dcf47d24036da30ce7fcb58)
BibTeX
@misc{dc99e35ba06e56,
  title = {Formalizing PTX in Lean to Prove GPU Kernel Correctness — arXiv:2611.04447},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04447},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99e35ba06e56; sha256 57b579b77381bff21160c96ab526d0b01e3015f49dcf47d24036da30ce7fcb58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04447. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present an approach to mathematically formalizing PTX, an approach that allows modeling and reasoning about patterns common in GPU kernels for Deep Learning, including acquire-release, tensor cores, proxies, async operations, multi-kernel pipelines and data-dependent control flow. We implement it in Lean and use it to prove the correctness of simple implementations of a WGMMA GEMM kernel, FlashAttention, and a 3-kernel MoE pipeline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04447 — 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 2026-11-04T21:35:49.547Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).