Scaling Up Performance of Managed Applications on NUMA Systems

Orion Papadakis, Andreas Andronikakis, Nikolaos Foutris, Michail Papadimitriou, Athanasios Stratikopoulos, Foivos Zakkak, Polychronis Xekalakis, Christos-Efthymios Kotselidis

Research output: Contribution to conferencePaperpeer-review

99 Downloads (Pure)


Scaling up the performance of managed applications on Non-Uniform Memory Access (NUMA) architectures has been a challenging task, as it requires a good understanding of the underlying architecture and managed runtime environments (MRE). Prior work has studied this problem from the scope of specific components of the managed runtimes, such as the Garbage Collectors, as a means to increase the NUMA awareness in MREs.

In this paper, we follow a different approach that complements prior work by studying the behavior of managed applications on NUMA architectures during mutation time. At first, we perform a characterization study that classifies several Dacapo and Renaissance applications as per their scalability-critical properties.
Based on this study, we propose a novel lightweight mechanism in MREs for optimizing the scalability of managed applications on NUMA systems, in an application-agnostic way. Our experimental results show that the proposed mechanism can result in relative performance ranging from 0.66x up to 3.29x, with a geometric mean of 1.11x, against a NUMA-agnostic execution.
Original languageEnglish
Publication statusAccepted/In press - 24 Apr 2023
EventThe 2023 ACM SIGPLAN International Symposium on Memory Management (ISMM 2023) - Florida, United States
Duration: 18 Jun 202318 Jun 2023


ConferenceThe 2023 ACM SIGPLAN International Symposium on Memory Management (ISMM 2023)
Abbreviated titleISMM 2023
Country/TerritoryUnited States
Internet address


  • NUMA
  • Scalability
  • Optimization
  • JVM
  • Managed Runtimes
  • Dacapo
  • Renaissance
  • MaxineVM


Dive into the research topics of 'Scaling Up Performance of Managed Applications on NUMA Systems'. Together they form a unique fingerprint.

Cite this