Kindle: A Comprehensive Framework for Exploring OS-Architecture Interplay in Hybrid Memory Systems

Computers with hybrid memory can offer the benefits of both DRAM and NVM technologies, where NVM provides higher capacity and data persistence while DRAM offers better performance. One of the primary objectives in hybrid memory systems is to design mechanisms and policies to take advantage of the underlying memory technologies to improve overall system performance and explore new usage scenarios. This paper introduces an open-source framework, Kindle, based on gem5 and gemOS, to explore and prototype research ideas in hybrid memory systems crossing the hardware-software boundaries, and perform comprehensive empirical evaluation. Kindle provides mechanisms to realize process persistence in hybrid memory systems while facilitating analysis of different design challenges and alternatives. As an illustration, we compare two design choices to maintain the virtual to physical address translation information (in the page table) for achieving process persistence in Kindle. Moreover, we demonstrate the utility of Kindle by prototyping state-of-the-art research ideas for hybrid memory systems to show that new insights can be derived using the facilities provided in the proposed framework.

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2024-10-01
DOI
https://doi.org/10.5281/zenodo.13292083
Primary Topic
Parallel Computing and Optimization Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Kindle: A Comprehensive Framework for Exploring OS-Architecture Interplay in Hybrid Memory Systems

Zenodo (CERN European Organization for Nuclear Research)
Parallel Computing and Optimization Techniques
article

Kindle: A Comprehensive Framework for Exploring OS-Architecture Interplay in Hybrid Memory Systems

article en

Abstract

Computers with hybrid memory can offer the benefits of both DRAM and NVM technologies, where NVM provides higher capacity and data persistence while DRAM offers better performance. One of the primary objectives in hybrid memory systems is to design mechanisms and policies to take advantage of the underlying memory technologies to improve overall system performance and explore new usage scenarios. This paper introduces an open-source framework, Kindle, based on gem5 and gemOS, to explore and prototype research ideas in hybrid memory systems crossing the hardware-software boundaries, and perform comprehensive empirical evaluation. Kindle provides mechanisms to realize process persistence in hybrid memory systems while facilitating analysis of different design challenges and alternatives. As an illustration, we compare two design choices to maintain the virtual to physical address translation information (in the page table) for achieving process persistence in Kindle. Moreover, we demonstrate the utility of Kindle by prototyping state-of-the-art research ideas for hybrid memory systems to show that new insights can be derived using the facilities provided in the proposed framework.

Zenodo (CERN European Organization for Nuclear Research)
Indian Institute of Technology Kanpur (IN)
Industry, innovation and infrastructure
Openalex Percentile: Top 52%
Parallel Computing and Optimization Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.