Remote memory
Introduction
We explore the ability of a host to access the memory of another host without involving the remote processor.
Summary
Remote memory is memory that a host can access from another host directly without involving the remote processor. This is possible through technologies such as RDMA that are getting commoditized. In this project, we study the potential and issues of remote memory, proposing new abstractions, models, and algorithms to work with it.Researchers
Palo Alto, CA, US
2021 Interns
2020 Interns
External Researchers
- Erez Petrank
- Hasan Maruf
- Naama Ben-David
- Nadav Amit
- Rachid Guerraoui
- Sam Toueg
- Stanko Novakovic
- Yizhou Shan
- Yizhou Shan
Related Publications
- Logical memory pools: Flexible and local disaggregated memory November, 2023
- DINOMO: An Elastic, Scalable, High-Performance Key-Value Store for Disaggregated Persistent Memory August, 2023
- Memory Disaggregation: Why Now and What Are the Challenges June, 2023
- Nu: Achieving Microsecond-Scale Resource Fungibility with Logical Processes April, 2023
- Frugal Byzantine Computing October, 2021
- Can Far Memory Improve Job Throughput? April, 2020
- The Impact of RDMA on Agreement July, 2019
- Storm: a Fast Transactional Dataplane for Remote Data Structures June, 2019
- Designing Far Memory Data Structures: Think Outside the Box May, 2019
Category
- Active Research Projects