research-article

Juggle: proactive load balancing on multicore computers

Authors:

Steven Hofmeyr,

Juan A. Colmenares,

John KubiatowiczAuthors Info & Claims

HPDC '11: Proceedings of the 20th international symposium on High performance distributed computing

Pages 3 - 14

https://doi.org/10.1145/1996130.1996134

Published: 08 June 2011 Publication History

Abstract

We investigate proactive dynamic load balancing on multicore systems, in which threads are continually migrated to reduce the impact of processor/thread mismatches to enhance the flexibility of the SPMD-style programming model, and enable SPMD applications to run efficiently in multiprogrammed environments. We present Juggle, a practical decentralized, user-space implementation of a proactive load balancer that emphasizes portability and usability. Juggle shows performance improvements of up to 80% over static balancing for UPC, OpenMP, and pthreads benchmarks. We analyze the impact of Juggle on parallel applications and derive lower bounds and approximations for thread completion times. We show that results from Juggle closely match theoretical predictions across a variety of architectures, including NUMA and hyper-threaded systems. We also show that Juggle is effective in multiprogrammed environments with unpredictable interference from unrelated external applications.

References

[1]

R. D. Blumofe and D. Papadopoulos. The performance of work stealing in multiprogrammed environments (extended abstract). ACM SIGMETRICS Perform. Eval. Rev., 26(1):266--267, 1998.

Digital Library

[2]

C. Boneti et al. A Dynamic Scheduler for Balancing HPC Applications. In Proc. 2008 ACM/IEEE Supercomputing Conference, 2008.

Digital Library

[3]

F. Cedo et al. The Convergence of Realistic Distributed Load-Balancing Algorithms. Theory Computer Systems, 41:609--618, 2007.

Digital Library

[4]

D. G. Feitelson and L. Rudolph. Gang Scheduling Performance Benefits for Fine-Grain Synchronization. J. Parallel and Distributed Computing, 16:306--318, 1992.

[5]

C. Fonlupt et al. Data-parallel load balancing strategies. Parallel Computing, 24:1665--1684, 1996.

Digital Library

[6]

A. Gupta et al. The Impact Of Operating System Scheduling Policies And Synchronization Methods On Performance Of Parallel Applications. SIGMETRICS Perform. Eval. Rev., 19(1), 1991.

Digital Library

[7]

S. Hofmeyr et al. Load Balancing on Speed. In Proc. 15th ACM Sym. on Principles & Practice of Parallel Programming, 2010.

Digital Library

[8]

C. Iancu et al. Oversubscription on multicore processors. In Proc. 24rd Int'l Parallel and Distributed Processing Sym. (IPDPS), 2010.

[9]

T. Jones et al. Improving the Scalability of Parallel Jobs by adding Parallel Awareness to the OS. ACM Supercomputing, 2003.

Digital Library

[10]

Z. Khan et al. Performance analysis of Dynamic Load Balancing Techniques for Parallel and Distributed Systems. (IJCNS) Int'l J. of Computer and Network Security, 2, 2010.

[11]

A. Kukanov et al. The Foundations for Scalable Multi-Core Software in Intel® Threading Building Blocks. Intel Tech. Jour., 2007.

[12]

T. Li et al. Efficient And Scalable Multiprocessor Fair Scheduling Using Distributed Weighted Round-Robin. In Proc. 14th ACM SIGPLAN Sym. on Principles and Practice of Parallel Programming, 2009.

Digital Library

[13]

R. Nishtala et al. Optimizing Collective Communication on Multicores. In Proc. 1st USENIX Ws. on Hot Topics in Parallelism, 2009.

Digital Library

[14]

S. Olivier and J. Prins. Scalable Dynamic Load Balancing Using UPC. In Proc. 37th Int'l Conf. on Parallel Processing, pages 123--131, 2008.

Digital Library

[15]

J. Ousterhout. Scheduling Techniques for Concurrent Systems. In Proc. 3rd Int'l Conf. on Distributed Computing Systems, 1982.

[16]

A. Plastino et al. Developing SPMD Applications with Load Balancing. Parallel Computing, pages 743--766, 2003.

Digital Library

[17]

J. Roberson. ULE: A Modern Scheduler for FreeBSD. In USENIX BSDCon, pages 17--28, 2003.

Digital Library

[18]

M. Willebeek-LeMair and A. Reeves. Strategies for dynamic load balancing on highly parallel computers. IEEE Trans. on Parallel and Distributed Systems, 4, 1993.

Digital Library

[19]

C. Xu and F. C. Lau. Load Balancing in Parallel Computers: Theory and Practice. Kluwer Academic Publishers, 1997.

Digital Library

Cited By

Imes CColin AZhang NSrivastava APrasanna VWalters J(2020)Compiler Abstractions and Runtime for Extreme-scale SAR and CFD Workloads2020 IEEE/ACM Fifth International Workshop on Extreme Scale Programming Models and Middleware (ESPM2)10.1109/ESPM251964.2020.00010(1-7)Online publication date: Nov-2020
https://doi.org/10.1109/ESPM251964.2020.00010
Assis IOliveira ABarros TSardina IBianchini CXavier De-Souza S(2019)Distributed-Memory Load Balancing With Cyclic Token-Based Work-Stealing Applied to Reverse Time MigrationIEEE Access10.1109/ACCESS.2019.29391007(128419-128430)Online publication date: 2019
https://doi.org/10.1109/ACCESS.2019.2939100
Hale KDinda P(2016)Enabling Hybrid Parallel Runtimes Through Kernel and Virtualization SupportACM SIGPLAN Notices10.1145/3007611.289225551:7(161-175)Online publication date: 25-Mar-2016
https://dl.acm.org/doi/10.1145/3007611.2892255
Show More Cited By

Index Terms

Juggle: proactive load balancing on multicore computers
1. Computing methodologies
  1. Parallel computing methodologies
    1. Parallel programming languages
2. Software and its engineering
  1. Software notations and tools
    1. General programming languages
      1. Language types
        Parallel programming languages

Recommendations

Juggle: addressing extrinsic load imbalances in SPMD applications on multicore computers

We investigate proactive dynamic load balancing on multicore systems, in which threads are continually migrated to reduce the impact of processor/thread mismatches. Our goal is to enhance the flexibility of the SPMD-style programming model and enable ...
A Comparison of 12 Parallel FORTRAN Dialects

A simple program that approximates pi by numerical quadrature is rewritten to run on nine commercially available processors to illustrate the compilations that arise in parallel programming in FORTRAN. The machines used are the Alliant FX/8, BBN ...
Tools-supported HPF and MPI parallelization of the NAS parallel benchmarks
FRONTIERS '96: Proceedings of the 6th Symposium on the Frontiers of Massively Parallel Computation

High Performance Fortran (HPF) compilers and communication libraries with the standardized Message Passing Interface (MPI) are becoming widely available, easing the development of portable parallel applications. The Annai tool environment supports ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

HPDC '11: Proceedings of the 20th international symposium on High performance distributed computing

June 2011

296 pages

ISBN:9781450305525

DOI:10.1145/1996130

General Chair:
Arthur "Barney" Maccabe
Oak Ridge National Lab, USA
,
Program Chair:
Douglas Thain
University of Notre Dame, USA

Copyright © 2011 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

University of Arizona: University of Arizona
SIGARCH: ACM Special Interest Group on Computer Architecture

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 June 2011

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

HPDC '11

Sponsor:

University of Arizona
SIGARCH

HPDC '11: The 20th International Symposium on High-Performance Parallel and Distributed Computing

June 8 - 11, 2011

California, San Jose, USA

Acceptance Rates

Overall Acceptance Rate 166 of 966 submissions, 17%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
422
Total Downloads

Downloads (Last 12 months)9
Downloads (Last 6 weeks)1

Reflects downloads up to 02 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Imes CColin AZhang NSrivastava APrasanna VWalters J(2020)Compiler Abstractions and Runtime for Extreme-scale SAR and CFD Workloads2020 IEEE/ACM Fifth International Workshop on Extreme Scale Programming Models and Middleware (ESPM2)10.1109/ESPM251964.2020.00010(1-7)Online publication date: Nov-2020
https://doi.org/10.1109/ESPM251964.2020.00010
Assis IOliveira ABarros TSardina IBianchini CXavier De-Souza S(2019)Distributed-Memory Load Balancing With Cyclic Token-Based Work-Stealing Applied to Reverse Time MigrationIEEE Access10.1109/ACCESS.2019.29391007(128419-128430)Online publication date: 2019
https://doi.org/10.1109/ACCESS.2019.2939100
Hale KDinda P(2016)Enabling Hybrid Parallel Runtimes Through Kernel and Virtualization SupportACM SIGPLAN Notices10.1145/3007611.289225551:7(161-175)Online publication date: 25-Mar-2016
https://dl.acm.org/doi/10.1145/3007611.2892255
Hale KDinda PGupta-Cledat VPorter DSarkar V(2016)Enabling Hybrid Parallel Runtimes Through Kernel and Virtualization SupportProceedings of the12th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments10.1145/2892242.2892255(161-175)Online publication date: 25-Mar-2016
https://dl.acm.org/doi/10.1145/2892242.2892255
Wu SPeng YJin H(2016)Time Donating Barrier for efficient task scheduling in competitive multicore systemsFuture Generation Computer Systems10.1016/j.future.2015.04.00554(469-477)Online publication date: Jan-2016
https://doi.org/10.1016/j.future.2015.04.005
Pusukuri KGupta RBhuyan L(2015)TumblerACM Transactions on Architecture and Code Optimization10.1145/282769812:4(1-24)Online publication date: 16-Nov-2015
https://dl.acm.org/doi/10.1145/2827698
Kim MNoh SHuh SHong S(2015)Fair-Share Scheduling for Performance-Asymmetric Multicore Architecture via Scaled Virtual RuntimeProceedings of the 2015 IEEE 21st International Conference on Embedded and Real-Time Computing Systems and Applications10.1109/RTCSA.2015.10(60-69)Online publication date: 19-Aug-2015
https://dl.acm.org/doi/10.1109/RTCSA.2015.10
Sironi FSciuto DSantambrogio M(2014)A performance-aware quality of service-driven scheduler for multicore processorsACM SIGBED Review10.1145/2597457.259746411:1(50-55)Online publication date: 1-Feb-2014
https://dl.acm.org/doi/10.1145/2597457.2597464
Padoin ECastro MPilla LNavaux PMehaut J(2014)Saving energy by exploiting residual imbalances on iterative applications2014 21st International Conference on High Performance Computing (HiPC)10.1109/HiPC.2014.7116895(1-10)Online publication date: Dec-2014
https://doi.org/10.1109/HiPC.2014.7116895
Pilla LRibeiro CCordeiro DMei CBhatele ANavaux PBroquedis FMehaut JKale L(2012)A Hierarchical Approach for Load Balancing on Parallel Multi-core SystemsProceedings of the 2012 41st International Conference on Parallel Processing10.1109/ICPP.2012.9(118-127)Online publication date: 10-Sep-2012
https://dl.acm.org/doi/10.1109/ICPP.2012.9

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten