Daniel S. Berger

À propos

I am a researcher in the Azure Systems Research Group (opens in new tab) in Redmond. My main research interests are efficiency, sustainability, and reliability of cloud platforms. My recent focus has been the systems stack for sustainability with a particular focus on memory (opens in new tab), repair operations (opens in new tab), and cooling (opens in new tab) (Zissou). My toolset spans system prototyping, simulation, statistical modeling and learning, and telemetry at cloud scale.

Recent work:

• Managing Memory Tiers with CXL in Virtualized Environments (opens in new tab)
  Yuhong Zhong, Daniel S. Berger, Carl Waldspurger, Ishwar Agarwal, Rajat Agarwal, Frank Hady, Karthik Kumar, Mark D. Hill, Mosharaf Chowdhury, Asaf Cidon
  USENIX OSDI 2024
• FairyWREN : A Sustainable Cache for Emerging Write-Read-Erase Flash Interfaces (opens in new tab)
  Sara McAllister, Sherry Wang, Benjamin Berg, Daniel S. Berger, George Amvrosiadis, Nathan Beckmann, G. R. Ganger
  USENIX OSDI 2024
• Designing Cloud Servers for Lower Carbon (opens in new tab)
  Jaylen Wang, Daniel S. Berger, Fiodar Kazhamiaka, Celine Irvene, Chaojie Zhang, Esha Choukse, Kali Frost, Rodrigo Fonseca, Brijesh Warrier, Chetan Bansal, Jonathan Stern, Ricardo Bianchini, Akshitha Sriraman
  ISCA 2024
• Hyrax: Fail-in-Place Operation in Cloud Platforms (opens in new tab)
  Jialun Lyu, Daniel S. Berger, Marisa You, Celine Irvene, Mark Jung, Tyler Narmore, Jacob Shapiro, Luke Marshall, Savyasachi Samal, Ioannis Manousakis, Ashish Raniwala, Ricardo Bianchini, Bianca Schroeder
  USENIX OSDI 2023
• Ensō: A Streaming Interface for NIC-Application Communication (opens in new tab)
  Hugo Sadok, Nirav Atre, Zhipeng Zhao, Daniel S. Berger, James C. Hoe, Aurojit Panda, Justine Sherry, Ren Wang
  USENIX OSDI 2023. Best Paper.
• Myths and Misconceptions Around Reducing Carbon Embedded in Cloud Platforms (opens in new tab)
  Jialun Lyu, Jaylen Wang, Kali Frost, Chaojie Zhang, Celine Irvene, Esha Choukse, Rodrigo Fonseca, Ricardo Bianchini, Fiodar Kazhamiaka. Daniel S. Berger
  HotCarbon 2023.
• Pond: CXL-Based Memory Pooling Systems for Cloud Platforms (opens in new tab)
  Huaicheng Li, Daniel S. Berger, Stanko Novakovic, Lisa Hsu, Dan Ernst, Pantea Zardoshti, Monish Shah, Samir Rajadnya, Scott Lee, Ishwar Agarwal, Mark D. Hill, Marcus Fontoura, Ricardo Bianchini
  ASPLOS 2023. Distinguished Paper Award.
• SOL: Safe On-Node Learning in Cloud Platforms. (opens in new tab)
  Yawen Wang,Daniel Crankshaw, Neeraja J. Yadwadkar, Daniel S. Berger, Christos Kozyrakis, Ricardo Bianchini.
  ASPLOS 2022.
• Redy: A Remote Dynamic Memory Cache. (opens in new tab)
  Qizhen Zhang, Philip A. Bernstein, Daniel S. Berger, Badrish Chandramouli.
  PVLDB 2022.
• Kangaroo: Caching Billions of Tiny Objects on Flash (opens in new tab).
  Sara McAllister, Benjamin Berg, Julian Tutuncu-Macias, Juncheng Yang, Sathya Gunasekar, Jimmy Lu, Daniel S. Berger, Nathan Beckmann, Gregory R. Ganger.
  ACM SOSP, October 2021. Best Paper Award.

Within Microsoft I am collaborating across Azure including hardware and OS development. Outside of Microsoft, I am an affiliate assistant professor at the Paul G. Allen School of Computer Science at the University of Washington (opens in new tab) where I teach graduate classes (opens in new tab). I am fortunate to be working closely with a bright group of PhD students, postdocs, and their mentors, including:

• Yuhong Zhong (opens in new tab), advised Asaf Cidon at Columbia
• Jialun Lyu (opens in new tab), advised by Bianca Schroeder at U of Toronto
• Sara McAllister (opens in new tab), advised by Nathan Beckmann and Greg Ganger at CMU
• Zhenyu Song (opens in new tab), advised by Wyatt Lloyd and Kai Li at Princeton
• Dongsheng Yang (opens in new tab), advised by Kai Li and Wyatt Lloyd at Princeton

To contact me for Microsoft collaborations, my alias is firstname «dot» secondname under the Microsoft domain.