Shai Bergman

I am a Principal Researcher at Huawei Zurich Research Center, Switzerland, where I serve as a team and technical lead. My team builds memory and storage solutions for modern data centers — including CXL-based memory systems — as well as systems for AI inference, with a shared goal of getting far more out of the hardware we already have.

At heart, I am a systems person. My research spans operating systems, virtualization, memory management, and storage, and increasingly sits at the intersection of systems and AI, where principled systems design translates directly into faster, more efficient, and more capable AI.

I received my Ph.D. in Electrical and Computer Engineering from the Technion — Israel Institute of Technology, where I was advised by Prof. Mark Silberstein and worked on memory management, virtualization, and I/O for modern systems.

selected publications

Accelerating Nested Virtualization with HyperTurtle

Ori Ben Zur, Jakob Krebs, Shai Bergman, and Mark Silberstein

In 2025 USENIX Annual Technical Conference (ATC 25) · Best Paper Award

@inproceedings{zur2025acc,
  title = {Accelerating Nested Virtualization with HyperTurtle},
  author = {Ben Zur, Ori and Krebs, Jakob and Bergman, Shai and Silberstein, Mark},
  booktitle = {2025 USENIX Annual Technical Conference (ATC 25)},
  pages = {987--1002},
}

Translation Pass-Through for Near-Native Paging Performance in VMs

Shai Bergman, Mark Silberstein, Takahiro Shinagawa, Peter Pietzuch, and Lluı́s Vilanova

In 2023 USENIX Annual Technical Conference (ATC 23)

@inproceedings{bergman2023tpt,
  title = {Translation Pass-Through for Near-Native Paging Performance in VMs},
  author = {Bergman, Shai and Silberstein, Mark and Shinagawa, Takahiro and Pietzuch, Peter and Vilanova, Llu{\'\i}s},
  booktitle = {2023 USENIX Annual Technical Conference (ATC 23)},
}

ZNSwap: un-Block your Swap

Shai Bergman, Niklas Cassel, Matias Bjørling, and Mark Silberstein

In 2022 USENIX Annual Technical Conference (ATC 22)

@inproceedings{bergman2022znswap,
  title = {ZNSwap: un-Block your Swap},
  author = {Bergman, Shai and Cassel, Niklas and Bj{\o}rling, Matias and Silberstein, Mark},
  booktitle = {2022 USENIX Annual Technical Conference (ATC 22)},
  pages = {1--18},
}

Reconsidering OS memory optimizations in the presence of disaggregated memory

Shai Bergman, Priyank Faldu, Boris Grot, Lluı́s Vilanova, and Mark Silberstein

In Proceedings of the 2022 ACM SIGPLAN International Symposium on Memory Management (ISMM 22)

@inproceedings{bergman2022reconsidering,
  title = {Reconsidering OS memory optimizations in the presence of disaggregated memory},
  author = {Bergman, Shai and Faldu, Priyank and Grot, Boris and Vilanova, Llu{\'\i}s and Silberstein, Mark},
  booktitle = {Proceedings of the 2022 ACM SIGPLAN International Symposium on Memory Management (ISMM 22)},
  pages = {1--14},
}

SPIN: Seamless Operating System Integration of Peer-to-Peer DMA Between SSDs and GPUs

Shai Bergman, Tanya Brokhman, Tzachi Cohen, and Mark Silberstein

In 2017 USENIX Annual Technical Conference (ATC 17)

@inproceedings{bergman2017spin,
  title = {SPIN: Seamless Operating System Integration of Peer-to-Peer DMA Between SSDs and GPUs},
  author = {Bergman, Shai and Brokhman, Tanya and Cohen, Tzachi and Silberstein, Mark},
  booktitle = {2017 USENIX Annual Technical Conference (ATC 17)},
  pages = {167--179},
}