Dynamo: Facebook's Data Center-Wide Power Management System

By Qiang Wu, Qingyuan Deng, Lakshmi Ganesh, Chang-Hong Hsu, Yun Jin, Sanjeev Kumar, Bin Li, Justin Meza, YeeJiun Song. 2016

158 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. David A. Patterson
2. N. Jouppi
3. George Kurian
4. Brian Towles
5. Ricardo Bianchini
6. Lifeng Nai
7. Mark Russinovich
8. Chunqiang Tang

In Information Systems

1. David A. Patterson
2. Zongwei Zhou
3. Ricardo Bianchini
4. Mark Russinovich

In ML Systems & Hardware

1. David A. Patterson
2. N. Jouppi
3. Lifeng Nai
4. Mark Russinovich

Citations in the corpus

• Resource Central: Understanding and Predicting Workloads for Improved Resource Management in Large Cloud Platforms (2017, background): “In contrast, we predict a broader set of VM behaviors (including VM lifetimes, maximum deployment sizes, and workload classes) for a broader set of purposes (including health management and power capping [26]).”
• Twine: A Unified Cluster Management System for Shared Infrastructure (2020, background): “We need 112 ≈ 8.3% of buffer capacity to guard against the failure of one MSB.”
• TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings (2023, background): “Computer architects improved PUE by helping advance the state-of-the-art of warehouse scale computers (WSCs) [2, 3, 16, 30, 44, 62].”