Advanced Data Storage Technologies Open access Peer reviewed

Revisiting CPU Silent Data Corruptions in Modern Datacenters

S. M. Wang, Guangyan Zhang

Communications of the ACM | Jul 31, 2026

Scollr summary

What this paper is about

Examining CPU SDCs from a production-oriented perspective reveals discrepancies between traditional assumptions and practical observations, helping to explain why many existing strategies and models remain inefficient or misaligned with practice.

Full abstract

Read the full abstract

Silent data corruptions (SDCs) originating from CPUs are increasingly recognized as a reliability concern in modern datacenters. Unlike crashes and exceptions, SDCs silently compromise data integrity, often remaining undetected until their impact propagates through large-scale datacenters. Despite growing awareness, existing strategies against CPU SDCs remain inefficient, in part because they are grounded in assumptions that do not fully reflect operational realities. In this article, we revisit CPU SDCs from a systematic, production-oriented perspective. Drawing on practical observations, we examine their presence in the wild, analyze patterns in corrupted data and SDC occurrence, and reassess existing strategies against CPU SDCs. Our findings reveal discrepancies between traditional assumptions and practical observations, helping to explain why many existing strategies and models remain inefficient or misaligned with practice. Based on these insights, we outline future directions for promoting the reliability of modern datacenter services.

Direct answer

What can I do from this paper page?

Use this page to scan "Revisiting CPU Silent Data Corruptions in Modern Datacenters" quickly: start with the summary and abstract, then check the authors, source, topics, and related papers. From here, open Scollr to follow Advanced Data Storage Technologies research, save the paper, or map adjacent work.

Authors

Researchers on this paper

S. M. Wang

first | Tsinghua University | ORCID 0009-0007-6842-3148

Guangyan Zhang

last | Tsinghua University | ORCID 0000-0002-3480-5902

Research areas

Follow related topics

Citation

BibTeX

@article{Wang2026Revisiting,
  title = {Revisiting CPU Silent Data Corruptions in Modern Datacenters},
  author = {S. M. Wang and Guangyan Zhang},
  journal = {Communications of the ACM},
  year = {2026},
  doi = {10.1145/3799406},
  url = {https://doi.org/10.1145/3799406}
}

FAQ

Using this paper in a discovery workflow

How do I find related work for this paper?

Use the related papers and topic links on this page as starting points. In Scollr, you can also open the paper and build a literature map around its references, citing papers, and related work.

How can I keep up with new Advanced Data Storage Technologies research papers?

Follow Advanced Data Storage Technologies research in Scollr. New papers from the topic flow into a personalized feed, and you can save useful studies to revisit later.

Can I cite this paper from this page?

This page includes a static BibTeX block for Revisiting CPU Silent Data Corruptions in Modern Datacenters. Always verify the DOI, source, and publication details against the publisher record before submitting a manuscript.

Follow this research in Scollr

Follow the topics and authors behind this paper, save useful studies, and build a literature map when you are ready to go deeper.

Get the app