Metraipolis › archive › dc_785f2e66f464
XLA from the Trenches: Correctness on TPU Workloads at Scale — arXiv:2611.00624
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00624
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:21:55.948Z
- SHA-256 of the archived text
08e92db1a1a5e626b3317fb8ca325c8e65bbb6e51cae1d328e672e1cbfd08f28- Stable URL of this page
https://metraipolis.com/documento/dc_785f2e66f464
How to cite
XLA from the Trenches: Correctness on TPU Workloads at Scale — arXiv:2611.00624 — arXiv (en), https://arxiv.org/abs/2611.00624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_785f2e66f464 (Metraipolis archive dc_785f2e66f464, sha256 08e92db1a1a5e626b3317fb8ca325c8e65bbb6e51cae1d328e672e1cbfd08f28)
BibTeX
@misc{dc785f2e66f464,
title = {XLA from the Trenches: Correctness on TPU Workloads at Scale — arXiv:2611.00624},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00624},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_785f2e66f464; sha256 08e92db1a1a5e626b3317fb8ca325c8e65bbb6e51cae1d328e672e1cbfd08f28},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accelerating modern foundational models has pushed domain-specific compilers toward increasingly complex, multi-tiered optimization pipelines. However, this heavy optimization focus introduces delicate tradeoffs between peak execution performance and correctness. Subtle codegen defects can trigger numerical degradation and memory or buffer corruption, invalidating multi-million-dollar training runs and degrading live serving quality without raising obvious compiler errors. In this paper, we present a battle-tested methodology for verifying and triaging Google's XLA:TPU compiler at hyperscale. We leverage fuzzing techniques, combining synthetic program generation with real production traces, while orchestrating AI agent swarms to autonomously generate stress tests, reproduce failures, and draft fixes. To pinpoint root causes in full workloads, we pair this with a hierarchical differential pipeline that bisects large graphs down to individual failing operations inside fused kernels. Deployed in production, our framework has already driven the resolution of over 142 compiler bugs (with 103 additional findings under review), from which we distill pragmatic lessons learned. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Programming Languages (cs.PL). Pagina del lavoro: https://arxiv.org/abs/2611.00624 — 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 2026-11-03T10:19:49.778Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).