article

Speculative parallelization of sequential loops on multicores

Authors:

Vijay Nagarajan,

Rajiv GuptaAuthors Info & Claims

International Journal of Parallel Programming, Volume 37, Issue 5

Pages 508 - 535

https://doi.org/10.1007/s10766-009-0111-z

Published: 01 October 2009 Publication History

Abstract

The advent of multicores presents a promising opportunity for speeding up the execution of sequential programs through their parallelization. In this paper we present a novel solution for efficiently supporting software-based speculative parallelization of sequential loops on multicore processors. The execution model we employ is based upon state separation, an approach for separately maintaining the speculative state of parallel threads and non-speculative state of the computation. If speculation is successful, the results produced by parallel threads in speculative state are committed by copying them into the computation's non-speculative state. If misspeculation is detected, no costly state recovery mechanisms are needed as the speculative state can be simply discarded. Techniques are proposed to reduce the cost of data copying between non-speculative and speculative state and efficiently carrying out misspeculation detection. We apply the above approach to speculative parallelization of loops in several sequential programs which results in significant speedups on a Dell PowerEdge 1900 server with two Intel Xeon quad-core processors.

References

[1]

Bridges, M., Vachharajani, N., Zhang, Y., Jablin, T., August, D.: Revisiting the sequential programming model for multi-core. In: MICRO, pp. 69-84 (2007).

[2]

Kulkarni, M., Pingali, K., Walter, B., Ramanarayanan, G., Bala, K., Paul Chew, L.: Optimistic parallelism requires abstractions. In: PLDI, pp. 211-222 (2007).

Digital Library

[3]

Luk, C., Cohn, R., Muth, R., Patil, H., Klauser, A., Lowney, G., Wallace, S., Reddi, v.J., Hazelwood, K.: Pin: building customized program analysis tools with dynamic instrumentation. In: PLDI, pp. 190-200 (2005).

Digital Library

[4]

Lattner, C., Adve, V.: Llvm: a compilation framework for lifelong program analysis & transformation. In: CGO, pp. 75-88 (2004).

Digital Library

[5]

http://www.spec.org

[6]

Guthaus, M.R., Ringenberg, J.S., Ernst, D., Austin, T.M., Mudge, T., Brown, R.B.: Mibench: a free, commercially representative embedded benchmark suite. In: IEEE 4th Annual Workshop on Workload Characterization (2001).

[7]

Cao Minh, C., Chung, J., Kozyrakis, C., Olukotun, K.: Stamp: stanford transactional applications for multi-processing. In: IISWC, pp. 35-46 (2005).

[8]

Dice, D., Shalev, O., Shavit, N.: Transactional locking ii. In: DISC, pp. 194-208 (2006).

Digital Library

[9]

Cintra, M.H., Martínez, J.F., Torrellas, J.: Architectural support for scalable speculative parallelization in shared-memory multiprocessors. In: ISCA, pp. 13-24 (2000).

[10]

Hammond, L., Willey, M., Olukotun, K.: Data speculation support for a chip multiprocessor. In: ASPLOS, pp. 58-69 (1998).

[11]

Vijaykumar, T.N., Gopal, S., Smith, J.E., Sohi, G.S.: Speculative versioning cache. IEEE Trans. Parallel Distrib. Syst. 12(12), 1305-1317 (2001).

Digital Library

[12]

Gregory Steffan, J., Colohan, C.B., Zhai, A., Mowry, T.C.: A scalable approach to thread-level speculation. In: ISCA, pp. 1-12 (2000).

[13]

Bhowmik, A., Franklin, M.: A general compiler framework for specUlative multithreading. In: SPAA, pp. 99-108 (2002).

[14]

Marcuello, P., González, A.: Clustered speculative multithreaded processors. In: ICS, pp. 365-372 (1999).

[15]

Zilles, C., Sohi, G.: Master/slave speculative parallelization. In: MICRO, pp. 85-96 (2002).

Digital Library

[16]

Ding, C., Shen, X., Kelsey, K., Tice, C., Huang, R., Zhang, C.: Software behavior oriented parallelization. In: PLDI, pp. 223-234 (2007).

Digital Library

[17]

Kulkarni, M., Pingali, K., Ramanarayanan, G., Walter, B., Bala, K., Paul Chew, L.: Optimistic parallelism benefits from data partitioning. In: ASPLOS, pp. 233-243 (2008).

[18]

Ottoni, G., Rangan, R., Stoler, A., August, D.I.: Automatic thread extraction with decoupled software pipelining. In: MICRO, pp. 105-118 (2005).

[19]

Raman, E., Ottoni, G., Raman, A., Bridges, M.J., August, D.I.: Parallel-stage decoupled software pipelining. In: CGO, pp. 114-123 (2008).

[20]

Vachharajani, N., Rangan, R., Raman, E., Bridges, M.J., Ottoni, G., August, D.I.: Speculative decoupled software pipelining. In: PACT, pp. 49-59 (2007).

Digital Library

[21]

Buck, I.: Stream computing on graphics hardware. PhD thesis, Stanford, CA, USA (2005).

[22]

Fan, K., Park, H., Kudlur, M., Mahlke, S.A.: Modulo scheduling for highly customized datapaths to increase hardware reusability. In: CGO, pp. 124-133 (2008).

[23]

Kapasi, U.J., Rixner, S., Dally, W.J., Khailany, B., Ahn, J.H., Mattson, P., Owens, J.D.: Programmable stream processors. Computer 36(8), 54-62 (2003).

Digital Library

[24]

Kudlur, M., Mahlke, S.: Orchestrating the execution of stream programs on multicore platforms. In: PLDI, pp. 114-124 (2008).

[25]

Thies, W., Chandrasekhar, V., Amarasinghe, S.: A practical approach to exploiting coarse-grained pipeline parallelism in c programs. In: MICRO, pp. 356-369 (2007).

[26]

Vijaykumar, T.N., Sohi, G.S.: Task selection for a multiscalar processor. In: MICRO, pp. 81-92 (1998).

Digital Library

[27]

Chu, M., Ravindran, R., Mahlke, S.: Data access partitioning for fine-grain parallelism on multicore architectures. In: MICRO, pp. 369-380 (2007).

[28]

Adl-Tabatabai, A.-R., Lewis, B.T., Menon, V., Murphy, B.R., Saha, B., Shpeisman, T.: Compiler and runtime support for efficient software transactional memory. In: PLDI, pp. 26-37 (2006).

Digital Library

[29]

Damron, P., Fedorova, A., Lev, Y., Luchangco, V., Moir, M., Nussbaum, D.: Hybrid transactional memory. In: ASPLOS, pp. 336-346 (2006).

Digital Library

[30]

Herlihy, M., Moss, J.E.B.: Transactional memory: architectural support for lock-free data structures. In: ISCA, pp. 289-300 (1993).

[31]

Moravan, M.J., Bobba, J., Moore, K.E., Yen, L., Hill, M.D., Liblit, B., Swift, M.M., Wood, D.A.: Supporting nested transactional memory in logtm. SIGOPS Oper. Syst. Rev. 40(5), 359-370 (2006).

Digital Library

Cited By

Martínez MFraguela BCabaleiro JRivera F(2024)A new thread-level speculative automatic parallelization model and library based on duplicate code executionThe Journal of Supercomputing10.1007/s11227-024-05987-080:10(13714-13737)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/s11227-024-05987-0
Estebanez ALlanos DGonzalez-Escribano A(2016)A Survey on Thread-Level Speculation TechniquesACM Computing Surveys10.1145/293836949:2(1-39)Online publication date: 30-Jun-2016
https://dl.acm.org/doi/10.1145/2938369
Estebanez ALlanos DGonzalez-Escribano A(2016)New Data Structures to Handle Speculative Parallelization at RuntimeInternational Journal of Parallel Programming10.1007/s10766-014-0347-044:3(407-426)Online publication date: 1-Jun-2016
https://dl.acm.org/doi/10.1007/s10766-014-0347-0
Show More Cited By

Speculative parallelization of sequential loops on multicores
1. Theory of computation
  1. Models of computation
    1. Concurrency

Recommendations

A cost-driven compilation framework for speculative parallelization of sequential programs
PLDI '04

The emerging hardware support for thread-level speculation opens new opportunities to parallelize sequential programs beyond the traditional limits. By speculating that many data dependences are unlikely during runtime, consecutive iterations of a ...
A cost-driven compilation framework for speculative parallelization of sequential programs
PLDI '04: Proceedings of the ACM SIGPLAN 2004 conference on Programming language design and implementation

The emerging hardware support for thread-level speculation opens new opportunities to parallelize sequential programs beyond the traditional limits. By speculating that many data dependences are unlikely during runtime, consecutive iterations of a ...
Speculative parallelization on GPGPUs
PPoPP '12: Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming

This paper overviews the first speculative parallelization technique for GPUs that can exploit parallelism in loops even in the presence of dynamic irregularities that may give rise to cross-iteration dependences. The execution of a speculatively ...

Comments

Information & Contributors

Information

Published In

cover image International Journal of Parallel Programming

International Journal of Parallel Programming Volume 37, Issue 5

October 2009

103 pages

ISSN:0885-7458

Issue’s Table of Contents

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 01 October 2009

Accepted: 31 May 2009

Received: 12 January 2009

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 14 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Martínez MFraguela BCabaleiro JRivera F(2024)A new thread-level speculative automatic parallelization model and library based on duplicate code executionThe Journal of Supercomputing10.1007/s11227-024-05987-080:10(13714-13737)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/s11227-024-05987-0
Estebanez ALlanos DGonzalez-Escribano A(2016)A Survey on Thread-Level Speculation TechniquesACM Computing Surveys10.1145/293836949:2(1-39)Online publication date: 30-Jun-2016
https://dl.acm.org/doi/10.1145/2938369
Estebanez ALlanos DGonzalez-Escribano A(2016)New Data Structures to Handle Speculative Parallelization at RuntimeInternational Journal of Parallel Programming10.1007/s10766-014-0347-044:3(407-426)Online publication date: 1-Jun-2016
https://dl.acm.org/doi/10.1007/s10766-014-0347-0
Holewinski JRamamurthi RRavishankar MFauzia NPouchet LRountev ASadayappan P(2012)Dynamic trace-based analysis of vectorization potential of applicationsACM SIGPLAN Notices10.1145/2345156.225410847:6(371-382)Online publication date: 11-Jun-2012
https://dl.acm.org/doi/10.1145/2345156.2254108
Holewinski JRamamurthi RRavishankar MFauzia NPouchet LRountev ASadayappan PVitek JLin HTip F(2012)Dynamic trace-based analysis of vectorization potential of applicationsProceedings of the 33rd ACM SIGPLAN Conference on Programming Language Design and Implementation10.1145/2254064.2254108(371-382)Online publication date: 11-Jun-2012
https://dl.acm.org/doi/10.1145/2254064.2254108
Tian CLin CFeng MGupta R(2011)Enhanced speculative parallelization via incremental recoveryACM SIGPLAN Notices10.1145/2038037.194158046:8(189-200)Online publication date: 12-Feb-2011
https://dl.acm.org/doi/10.1145/2038037.1941580
Tian CLin CFeng MGupta RCascaval CYew P(2011)Enhanced speculative parallelization via incremental recoveryProceedings of the 16th ACM symposium on Principles and practice of parallel programming10.1145/1941553.1941580(189-200)Online publication date: 12-Feb-2011
https://dl.acm.org/doi/10.1145/1941553.1941580
Tian CFeng MGupta R(2010)Speculative parallelization using state separation and multiple value predictionACM SIGPLAN Notices10.1145/1837855.180666345:8(63-72)Online publication date: 5-Jun-2010
https://dl.acm.org/doi/10.1145/1837855.1806663
Tian CFeng MGupta R(2010)Supporting speculative parallelization in the presence of dynamic data structuresACM SIGPLAN Notices10.1145/1809028.180660445:6(62-73)Online publication date: 5-Jun-2010
https://dl.acm.org/doi/10.1145/1809028.1806604
Tian CFeng MGupta RVitek JLea D(2010)Speculative parallelization using state separation and multiple value predictionProceedings of the 2010 international symposium on Memory management10.1145/1806651.1806663(63-72)Online publication date: 5-Jun-2010
https://dl.acm.org/doi/10.1145/1806651.1806663
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents