COMPROF and COMPLACE: shared-memory communication profiling and automated thread placement via dynamic binary instrumentation

Ryan Kirkpatrick, Christopher Brown, Vladimir Janjic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

32 Downloads (Pure)

Abstract

This paper presents COMPROF and COMPLACE, a novel profiling tool and thread placement technique for shared-memory architectures that requires no recompilation or user intervention. We use dynamic binary instrumentation to intercept memory operations and estimate inter-thread communication overhead, deriving (and possibly visualising) a communication graph of data-sharing between threads. We then use this graph to map threads to cores in order to optimise memory traffic through the memory system. Different paths through a system's memory hierarchy have different latency, throughput and energy properties, COMPLACE exploits this heterogeneity to provide automatic performance and energy improvements for multi-threaded programs. We demonstrate COMPLACE on the NAS Parallel Benchmark (NPB) suite where, using our technique, we are able to achieve improvements of up to 12% in the execution time and up to 10% in the energy consumption (compared to default Linux scheduling) while not requiring any modification or recompilation of the application code.
Original languageEnglish
Title of host publication2022 IEEE 29th International Conference on High Performance Computing, Data, and Analytics (HiPC)
Place of PublicationBengaluru, India
PublisherIEEE
Pages236-245
Number of pages10
ISBN (Electronic)9781665494236
ISBN (Print)9781665494243
DOIs
Publication statusPublished - 26 Apr 2023
Event29th IEEE International Conference on High Performance Computing, Data, and Analytics - Bengaluru, India
Duration: 18 Dec 202221 Dec 2022
https://hipc.org/

Conference

Conference29th IEEE International Conference on High Performance Computing, Data, and Analytics
Abbreviated titleHiPC 2022
Country/TerritoryIndia
CityBengaluru
Period18/12/2221/12/22
Internet address

Keywords

  • NUMA
  • Thread Placement
  • Data Placement
  • Cache Optimisation
  • Energy Optimization
  • Refactoring
  • QA75 Electronic computers
  • Computer science
  • NDAS
  • Energy Optimisation

ASJC Scopus subject areas

  • Information Systems and Management
  • Artificial Intelligence
  • Control and Optimization
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'COMPROF and COMPLACE: shared-memory communication profiling and automated thread placement via dynamic binary instrumentation'. Together they form a unique fingerprint.

Cite this