• Home
  • Search
  • Characterizing and mitigating work time inflation in task parallel programs
  • Cite Icon39
  • https://doi.org/10.5555/2388996.2389085Copy DOI Icon

Characterizing and mitigating work time inflation in task parallel programs

  • Nov 10, 2012
  • Stephen L Olivier +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Task parallelism raises the level of abstraction in shared memory parallel programming to simplify the development of complex applications. However, task parallel applications can exhibit poor performance due to thread idleness, scheduling overheads, and work time inflation -- additional time spent by threads in a multithreaded computation beyond the time required to perform the same work in a sequential computation. We identify the contributions of each factor to lost efficiency in various task parallel OpenMP applications and diagnose the causes of work time inflation in those applications. Increased data access latency can cause significant work time inflation in NUMA systems. Our locality framework for task parallel OpenMP programs mitigates this cause of work time inflation. Our extensions to the Qthreads library demonstrate that locality-aware scheduling can improve performance up to 3X compared to the Intel OpenMP task scheduler.

Similar Papers
  • Research Article
  • Citations35

A Transformation Framework for Optimizing Task-Parallel Programs

  • Apr 01, 2013
  • ACM Transactions on Programming Languages and Systems
  • V Krishna Nandivada +3
  • Conference Article
  • Citations21

Parallel data race detection for task parallel programs with locks

  • Nov 01, 2016
  • Adarsh Yoga +2
  • Conference Article
  • Citations9

TFProf: Profiling Large Taskflow Programs with Modern D3 and C++

  • Nov 01, 2021
  • Tsung-Wei Huang
  • Research Article
  • Citations48

The NAS Parallel Benchmarks for evaluating C++ parallel programming frameworks on shared-memory architectures

  • Jul 19, 2021
  • Future Generation Computer Systems
  • Júnior Löff +6
  • Book Chapter

Asynchronous Request Handling

  • Jan 01, 2013
  • Adam Freeman
  • Conference Article

A Quest for Unified, Global View Parallel Programming Models for Our Future

  • Jun 01, 2016
  • Kenjiro Taura
  • Conference Article

Session 1: performance analysis

  • Jan 09, 2002
  • N Podhorszki
  • Research Article
  • Citations9

Requirements-preserving design automation for multiprocessor embedded system applications

  • Jun 05, 2020
  • Journal of Ambient Intelligence and Humanized Computing
  • Md Al Maruf +1
  • Conference Article
  • Citations37

Communication and memory requirements as the basis for mapping task and data parallel programs

  • Nov 14, 1994
  • Jaspal Subhlok +4
  • Conference Article
  • Citations55

A work-stealing scheduler for X10's task parallelism with suspension

  • Feb 25, 2012
  • Olivier Tardieu +2
  • Research Article
  • Citations1

Tuning Task Granularity and Data Locality of Data Parallel GPH Programs

  • Dec 01, 2001
  • Parallel Processing Letters
  • H Loidl
  • Research Article
  • Citations4

Automating resource allocation for multiprocessors

  • Jan 01, 1989
  • Journal of Systems and Software
  • Karsten Schwan +1
  • Book Chapter
  • Citations4

Language constructs and runtime systems for compositional parallel programming

  • Jan 01, 1994
  • Ian Foster +1
  • Conference Article
  • Citations3

An object-based parallel programming assistant

  • Jan 01, 1988
  • E T Hvannberg +1
  • Research Article

Characterizing and Mitigating Work Time Inflation in Task Parallel Programs

  • Jan 01, 2013
  • Carolina Digital Repository (University of North Carolina at Chapel Hill)
  • Stephen L Olivier +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.