ML-native Dataplane Operating Systems
Performance tuning has never been more critical in modern datacenters, where rapid advances in networking and I/O speeds expose potential bottlenecks in CPUs, memory, and operating systems. Yet, tuning remains notoriously complex, brittle, and opaque, especially at the microsecond-scale latencies demanded by modern dataplanes. We argue that there is a pressing need to unleash the power of machine learning in datacenter operating systems.
Authors
- Irene Zhang (ORCID: https://orcid.org/0009-0007-9033-3640)
- Joshua Fried (ORCID: https://orcid.org/0000-0002-5761-3516)
- Anand Bonde
- Jialin Li (ORCID: https://orcid.org/0000-0003-3530-7662)
- Jing Liu (ORCID: https://orcid.org/0000-0003-2485-4038)
- Inho Choi (ORCID: https://orcid.org/0009-0007-9835-4040)
Institutions
- Microsoft (United States) (US)
- National University of Singapore (SG)
- Microsoft Research Asia (China) (CN)
- Microsoft Research (United Kingdom) (GB)
Publication Details
- Published
- 2025-10-09
- DOI
- https://doi.org/10.1145/3725783.3764392
- Primary Topic
- Cloud Computing and Resource Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00