Metraipolis › archive › dc_b04e663dc92d
BitIR: Cross-Architecture Fault Injection for Resilience Analysis of Heterogeneous GPU Applications — arXiv:2610.04037
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04037
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:28:58.719Z
- SHA-256 of the archived text
35005f74399b00229600522a9f7d215e19994a95b75a0f381114fcf988a89d03- Stable URL of this page
https://metraipolis.com/documento/dc_b04e663dc92d
How to cite
BitIR: Cross-Architecture Fault Injection for Resilience Analysis of Heterogeneous GPU Applications — arXiv:2610.04037 — arXiv, https://arxiv.org/abs/2610.04037 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b04e663dc92d (Metraipolis archive dc_b04e663dc92d, sha256 35005f74399b00229600522a9f7d215e19994a95b75a0f381114fcf988a89d03)
BibTeX
@misc{dcb04e663dc92d,
title = {BitIR: Cross-Architecture Fault Injection for Resilience Analysis of Heterogeneous GPU Applications — arXiv:2610.04037},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04037},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b04e663dc92d; sha256 35005f74399b00229600522a9f7d215e19994a95b75a0f381114fcf988a89d03},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04037. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern GPU-based HPC systems rely on heterogeneous vendor stacks, yet resilience studies are largely limited to single architectures, leaving it unclear how faults behave across different GPU backends. We present \emph{BitIR}, a cross-architecture fault injection framework that injects deterministic single-bit faults at the LLVM IR level, ensuring semantically equivalent perturbations prior to backend lowering and enabling direct cross-vendor comparison across NVIDIA, Intel, and AMD GPUs. We evaluate BitIR on three production supercomputers -- Polaris (ALCF, NVIDIA A100), Aurora (ALCF, Intel GPU Max 1550), and Frontier (OLCF, AMD Instinct MI250X) -- representing the full spectrum of current leadership-class GPU architectures. Using representative heterogeneous benchmarks, we conduct large-scale injection campaigns across all three systems and classify outcomes into masked results, silent data corruptions (SDCs), and failures. Our results show that identical faults produce markedly different behaviors across vendors: Intel most often masks faults but exhibits more hangs when faults escape masking, NVIDIA exposes more detectable hard failures, and AMD alternates between SDC-dominant and failure-dominant behavior depending on the benchmark and fault site. These findings demonstrate that resilience is not backend-invariant, underscoring the need for backend-aware and workload-aware fault mitigation.
Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2610.04037 — 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 2026-10-06T05:24:35.292Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).