research-article

Performance implications of fence-based memory models

Author:

Hans-J. BoehmAuthors Info & Claims

MSPC '11: Proceedings of the 2011 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness

Pages 13 - 19

https://doi.org/10.1145/1988915.1988919

Published: 05 June 2011 Publication History

Get Access

Abstract

Most mainstream shared-memory parallel programming languages are converging to a memory model, or shared variable semantics, centered on providing sequential consistency for most data-race-free programs.

OpenMP, along with a small number of other languages, defines its memory model in terms of implicit fence (e.g. OpenMP flush) operations that force memory accesses to become visible to other threads in order. Synchronization operations provided by the language implicitly include such fences. In the simplest cases this is equivalent to a promise of sequential consistency for data-race-free programs.

However, real languages typically also provide atomic operations with weak memory ordering constraints, such as the OpenMP atomic directives. These break the above equivalence, making the fence-based model stronger in ways that are observable, but not generally useful. As a result, conventional lock implementations are often accidentally prohibited, adding significant overhead for uncontended locks.

We show that this problem affects both OpenMP and, in a more subtle way, UPC. We have been working with the OpenMP ARB to resolve these issues in future versions of OpenMP.

References

[1]

H.-J. Boehm. Reordering constraints for pthread-style locks. In Proc. 12th Symp. Principles and Practice of Parallel Programming, pages 173--182, 2007.

Digital Library

Google Scholar

[2]

H.-J. Boehm and S. Adve. Foundations of the C++ concurrency memory model. In Proc. Conf. on Programming Language Design and Implementation, pages 68--78, 2008.

Digital Library

Google Scholar

[3]

G. Bronevetsky and B. R. de Supinski. Complete formal specification of the OpenMP memory model. International Journal of Parallel Programming, 35(4):335--392, August 2007.

Digital Library

Google Scholar

[4]

C++ Standards Committee, Pete Becker, ed. Programming Languages - C++ (final committee draft). C++ standards committee paper WG21/N3092=J16/10-0082, http://www.open-std.org/JTC1/SC22/WG21/docs/papers/2010/n3092.pdf, March 2010.

Google Scholar

[5]

C Standards Committee (WG14). Committee Draft: Programming Languages --- C. C standards committee paper WG14 N1539, http://www.open-std.org/jtc1/sc22/wg14/www/docs/n1539.pdf, November 2010.

Google Scholar

[6]

L. Lamport. How to make a multiprocessor computer that correctly executes multiprocess programs. IEEE Transactions on Computers, C-28(9):690--691, 1979.

Digital Library

Google Scholar

[7]

J. Manson, W. Pugh, and S. Adve. The Java memory model. In Proc. Symp. on Principles of Programming Languages, 2005.

Digital Library

Google Scholar

[8]

P. Sewell, S. Sarkar, S. Owens, F. Z. Nardelli, and M. O. Myreen. x86-tso: A rigorous and usable programmer's model for x86 multiprocesors. Communications of the ACM, 53(7):89--97, July 2010.

Digital Library

Google Scholar

[9]

The OpenMP ARB. OpenMP application programming interface: Version 3.0. http://www.openmp.org/mp-documents/spec30.pdf, May 2008.

Google Scholar

[10]

UPC Consortium. UPC language specifications v1.2. http://upc.gwu.edu/docs/upc_specs_1.2.pdf, May 2005.

Google Scholar

Cited By

View all

Boehm HChakrabarti D(2016)Persistence programming models for non-volatile memoryACM SIGPLAN Notices10.1145/3241624.292670451:11(55-67)Online publication date: 14-Jun-2016
https://dl.acm.org/doi/10.1145/3241624.2926704
Boehm HChakrabarti DFlood CZhang Z(2016)Persistence programming models for non-volatile memoryProceedings of the 2016 ACM SIGPLAN International Symposium on Memory Management10.1145/2926697.2926704(55-67)Online publication date: 14-Jun-2016
https://dl.acm.org/doi/10.1145/2926697.2926704
Boehm HZhang LMutlu O(2012)Can seqlocks get along with programming language memory models?Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness10.1145/2247684.2247688(12-20)Online publication date: 16-Jun-2012
https://dl.acm.org/doi/10.1145/2247684.2247688

Index Terms

Performance implications of fence-based memory models
1. Software and its engineering
  1. Software notations and tools
    1. General programming languages
      1. Language features
        Concurrent programming structures

Recommendations

Can seqlocks get along with programming language memory models?
MSPC '12: Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness

Seqlocks are an important synchronization mechanism and represent a significant improvement over conventional reader-writer locks in some contexts. They avoid the need to update a synchronization variable during a reader critical section, and hence ...
Nonblocking Algorithms and Preemption-Safe Locking on Multiprogrammed Shared Memory Multiprocessors

Most multiprocessors are multiprogrammed to achieve acceptable response time and to increase their utilization. Unfortunately, inopportune preemption may significantly degrade the performance of synchronized parallel applications. To address this ...
Position paper: nondeterminism is unavoidable, but data races are pure evil
RACES '12: Proceedings of the 2012 ACM workshop on Relaxing synchronization for multicore and manycore scalability

Modern mainstream programming languages distinguish between "atomic" (or sometimes "volatile") variables, and ordinary data. Atomic accesses are treated as synchronization constructs, and support concurrent access with well-defined semantics. In ...

Comments

Information & Contributors

Information

Published In

MSPC '11: Proceedings of the 2011 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness

June 2011

74 pages

ISBN:9781450307949

DOI:10.1145/1988915

General Chair:
Jeffrey Vetter
Oak Ridge National Lab and Georgia Institute of Technology
,
Program Chairs:
Madanlal Musuvathi
Microsoft Research
,
Xipeng Shen
College of William & Mary

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]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 June 2011

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

PLDI '11

Sponsor:

SIGPLAN

PLDI '11: ACM SIGPLAN Conference on Programming Language Design and Implementation

June 5, 2011

California, San Jose

Acceptance Rates

Overall Acceptance Rate 6 of 20 submissions, 30%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
311
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Boehm HChakrabarti D(2016)Persistence programming models for non-volatile memoryACM SIGPLAN Notices10.1145/3241624.292670451:11(55-67)Online publication date: 14-Jun-2016
https://dl.acm.org/doi/10.1145/3241624.2926704
Boehm HChakrabarti DFlood CZhang Z(2016)Persistence programming models for non-volatile memoryProceedings of the 2016 ACM SIGPLAN International Symposium on Memory Management10.1145/2926697.2926704(55-67)Online publication date: 14-Jun-2016
https://dl.acm.org/doi/10.1145/2926697.2926704
Boehm HZhang LMutlu O(2012)Can seqlocks get along with programming language memory models?Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness10.1145/2247684.2247688(12-20)Online publication date: 16-Jun-2012
https://dl.acm.org/doi/10.1145/2247684.2247688

View Options

Get Access

Login options

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

Cited By

Index Terms

Recommendations

Can seqlocks get along with programming language memory models?

Nonblocking Algorithms and Preemption-Safe Locking on Multiprogrammed Shared Memory Multiprocessors

Position paper: nondeterminism is unavoidable, but data races are pure evil