Metraipolis › archive › dc_9ecf4b99ca39

Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication — arXiv:2609.19531

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19531
License (as archived)
CC0-1.0
Archived
2026-10-10T03:23:12.385Z
SHA-256 of the archived text
c43860f499693ebe5752a33d653521e1bfb0e80c615f7bd7224424c9cafd1d1f
Stable URL of this page
https://metraipolis.com/documento/dc_9ecf4b99ca39

How to cite

Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication — arXiv:2609.19531 — arXiv (en), https://arxiv.org/abs/2609.19531 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ecf4b99ca39 (Metraipolis archive dc_9ecf4b99ca39, sha256 c43860f499693ebe5752a33d653521e1bfb0e80c615f7bd7224424c9cafd1d1f)
BibTeX
@misc{dc9ecf4b99ca39,
  title = {Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication — arXiv:2609.19531},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19531},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ecf4b99ca39; sha256 c43860f499693ebe5752a33d653521e1bfb0e80c615f7bd7224424c9cafd1d1f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19531. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose PaRID (PaRallel Instruction Duplication), a software-directed soft error detection framework that requires only compile-time effort for multithreading parallel programs. PaRID addresses two key challenges: supporting parallel programs with mixed serial and parallel regions and minimizing performance overhead without relying on costly dynamic profiling. It combines parallel-aware code transformation with LLM-tuned performance modeling, guided by eight generalizable findings from an offline characterization study, to enable fast soft error detection in parallel applications. Evaluation on NPB benchmarks shows that PaRID reduces protection overhead from 162.79% to 59.84% on average and achieves up to 5x speedup while maintaining full error detection effectiveness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI); Programming Languages (cs.PL).
Pagina del lavoro: https://arxiv.org/abs/2609.19531 — 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 2026-10-10T03:04:13.822Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).