article

A unified framework for schedule and storage optimization

Authors:

Frédéric Vivien,

Jeffrey Sheldon,

Saman AmarasingheAuthors Info & Claims

ACM SIGPLAN Notices, Volume 36, Issue 5

Pages 232 - 242

https://doi.org/10.1145/381694.378852

Published: 01 May 2001 Publication History

Abstract

We present a unified mathematical framework for analyzing the tradeoffs between parallelism and storage allocation within a parallelizing compiler. Using this framework, we show how to find a good storage mapping for a given schedule, a good schedule for a given storage mapping, and a good storage mapping that is valid for all legal schedules. We consider storage mappings that collapse one dimension of a multi-dimensional array, and programs that are in a single assignment form with a one-dimensional schedule. Our technique combines affine scheduling techniques with occupancy vector analysis and incorporates general affine dependences across statements and loop nests. We formulate the constraints imposed by the data dependences and storage mappings as a set of linear inequalities, and apply numerical programming techniques to efficiently solve for the shortest occupancy vector. We consider our method to be a first step towards automating a procedure that finds the optimal tradeoff between parallelism and storage space.

References

[1]

D. Barthou, A. Cohen, and J. Collard. Maximal static expansion. In Principles of Programming Languages, pages 98-106, San Diego, CA, Jan. 1998.

Digital Library

[2]

A. Cohen. Parallelization via constrained storage mapping optimization. Lecture Notes in Computer Science, 1615:83-94, 1999.

Digital Library

[3]

A. Cohen and V. Lefebvre. Optimization of storage mappings for parallel programs. Technical Report 1998/46, PRiSM, U. of Versailles, 1988.

[4]

A. Darte, Y. Robert, and F. Vivien. Scheduling and Automatic Parallelization. Birkh. auser Boston, 2000.

Digital Library

[5]

P. Feautrier. Array expansion. In ACM Int. Conf. on Supercomputing, pages 429-441, 1988.

Digital Library

[6]

P. Feautrier. Data ow analysis of array and scalar references. Int. J. of Parallel Programming, 20(1):23-51, 1991.

[7]

P. Feautrier. Some efficient solutions to the affine scheduling problem. part I. one-dimensional time. Int. J. of Parallel Programming, 21(5):313-347, Oct. 1992.

Digital Library

[8]

P. Feautrier. Some efficient solutions to the affine scheduling problem. part II. multidimensional time. Int. J. of Parallel Programming, 21(6):389-420, Dec. 1992.

Digital Library

[9]

P. Feautrier, J.-F. Collard, M. Barreteau, D. Barthou, A. Cohen, and V. Lefebvre. The interplay of expansion and scheduling in paf. Technical Report 1998/6, PRiSM, U. of Versailles, 1988.

[10]

F. Irigoin and R. Triolet. Supernode partitioning. In Proc. 15th Annual ACM Symp. Principles of Prog. Languages, pages 319-329, San Diego, CA, Jan. 1988.

Digital Library

[11]

V. Lefebvre and P. Feautrier. Automatic storage management for parallel programs. Parallel Computing, 24(3-4):649-671, May 1998.

Digital Library

[12]

A. Lim and M. Lam. Maximizing parallelism and minimizing synchronization with affine transforms. In Proceedings of the 24th Annual ACM SIGPLAN-SIGACT Symp. on Principles of Prog. Languages, Jan. 1997.

Digital Library

[13]

V. Loechner and D. K. Wilde. Parameterized polyhedra and their vertices. Int. J. of Parallel Programming, 25(6):525-549, Dec. 1997.

Digital Library

[14]

S. B. Needleman and C. D. Wunsch. A general method applicable to the search of similarities in the amino acid sequence of two proteins. Journal of Molecular Biology, 48:443-453, 1970.

[15]

W. Pugh. The Omega test: a fast and practical integer programming algorithm for dependence analysis. Communications of the ACM, 8:102-114, Aug. 1992.

Digital Library

[16]

A. Schrijver. Theory of Linear and Integer Programming. John Wiley and Sons, New York, 1986.

Digital Library

[17]

M. M. Strout, L. Carter, J. Ferrante, and B. Simon. Schedule-independent storage mapping for loops. In Architectural Support for Programming Languages and Operating Systems, pages 24-33, 1998.

Digital Library

[18]

D. Wilde and S. Rajopadhye. Memory reuse analysis in the polyhedral model. Parallel Processing Letters, 7(2):203-215, June 1997.

Cited By

Shirako JSarkar V(2022)An Affine Scheduling Framework for Integrating Data Layout and Loop TransformationsLanguages and Compilers for Parallel Computing10.1007/978-3-030-95953-1_1(3-19)Online publication date: 16-Feb-2022
https://doi.org/10.1007/978-3-030-95953-1_1
Aggarwal KBondhugula U(2020)Optimizing the Linear Fascicle Evaluation Algorithm for Multi-core and Many-core SystemsACM Transactions on Parallel Computing10.1145/34180757:4(1-45)Online publication date: 25-Nov-2020
https://dl.acm.org/doi/10.1145/3418075
Bhaskaracharya SBondhugula UCohen A(2016)SMO: an integrated approach to intra-array and inter-array storage optimizationACM SIGPLAN Notices10.1145/2914770.283763651:1(526-538)Online publication date: 11-Jan-2016
https://dl.acm.org/doi/10.1145/2914770.2837636
Show More Cited By

Index Terms

Recommendations

A unified framework for schedule and storage optimization
PLDI '01: Proceedings of the ACM SIGPLAN 2001 conference on Programming language design and implementation

We present a unified mathematical framework for analyzing the tradeoffs between parallelism and storage allocation within a parallelizing compiler. Using this framework, we show how to find a good storage mapping for a given schedule, a good schedule ...
Schedule-independent storage mapping for loops

This paper studies the relationship between storage requirements and performance. Storage-related dependences inhibit optimizations for locality and parallelism. Techniques such as renaming and array expansion can eliminate all storage-related ...
Schedule-independent storage mapping for loops

This paper studies the relationship between storage requirements and performance. Storage-related dependences inhibit optimizations for locality and parallelism. Techniques such as renaming and array expansion can eliminate all storage-related ...

Comments

Information & Contributors

Information

Published In

cover image ACM SIGPLAN Notices

ACM SIGPLAN Notices Volume 36, Issue 5

May 2001

330 pages

ISSN:0362-1340

EISSN:1558-1160

DOI:10.1145/381694

Issue’s Table of Contents

PLDI '01: Proceedings of the ACM SIGPLAN 2001 conference on Programming language design and implementation
June 2001
331 pages
ISBN:1581134142
DOI:10.1145/378795
Chairmen:
Michael Burke
IBM T.J. Watson Research Center
,
Mary Lou Soffa
Univ. of Pittsburgh

Copyright © 2001 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]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 May 2001

Published in SIGPLAN Volume 36, Issue 5

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

50
Total Citations
View Citations
481
Total Downloads

Downloads (Last 12 months)14
Downloads (Last 6 weeks)2

Reflects downloads up to 16 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Shirako JSarkar V(2022)An Affine Scheduling Framework for Integrating Data Layout and Loop TransformationsLanguages and Compilers for Parallel Computing10.1007/978-3-030-95953-1_1(3-19)Online publication date: 16-Feb-2022
https://doi.org/10.1007/978-3-030-95953-1_1
Aggarwal KBondhugula U(2020)Optimizing the Linear Fascicle Evaluation Algorithm for Multi-core and Many-core SystemsACM Transactions on Parallel Computing10.1145/34180757:4(1-45)Online publication date: 25-Nov-2020
https://dl.acm.org/doi/10.1145/3418075
Bhaskaracharya SBondhugula UCohen A(2016)SMO: an integrated approach to intra-array and inter-array storage optimizationACM SIGPLAN Notices10.1145/2914770.283763651:1(526-538)Online publication date: 11-Jan-2016
https://dl.acm.org/doi/10.1145/2914770.2837636
Bhaskaracharya SBondhugula UCohen A(2016)Automatic Storage Optimization for ArraysACM Transactions on Programming Languages and Systems10.1145/284507838:3(1-23)Online publication date: 8-Apr-2016
https://dl.acm.org/doi/10.1145/2845078
Yuki TGupta GKim DPathan TRajopadhye S(2013)AlphaZ: A System for Design Space Exploration in the Polyhedral ModelLanguages and Compilers for Parallel Computing10.1007/978-3-642-37658-0_2(17-31)Online publication date: 2013
https://doi.org/10.1007/978-3-642-37658-0_2
Deschinkel KTouati SBriais S(2011)SIRALINAJournal of Combinatorial Optimization10.1007/s10878-010-9332-822:4(819-844)Online publication date: 1-Nov-2011
https://dl.acm.org/doi/10.1007/s10878-010-9332-8
Rajopadhye SRenganarayana LMills Strout MGautam (2009)Computations on Iteration SpacesThe Compiler Design Handbook10.1201/9781420043839.ch15(15-1-15-52)Online publication date: 7-Dec-2009
https://doi.org/10.1201/9781420043839.ch15
Touati SMathe Z(2009)Periodic register saturation in innermost loopsParallel Computing10.1016/j.parco.2008.12.00135:4(239-254)Online publication date: 1-Apr-2009
https://dl.acm.org/doi/10.1016/j.parco.2008.12.001
Deschinkel KTouati S(2008)Efficient Method for Periodic Task Scheduling with Storage Requirement MinimizationProceedings of the 2nd international conference on Combinatorial Optimization and Applications10.1007/978-3-540-85097-7_41(438-447)Online publication date: 21-Aug-2008
https://dl.acm.org/doi/10.1007/978-3-540-85097-7_41
TOUATI SEISENBEIS C(2004)Early Periodic Register Allocation on ILP ProcessorsParallel Processing Letters10.1142/S012962640400188X14:02(287-313)Online publication date: Jun-2004
https://doi.org/10.1142/S012962640400188X
Show More Cited By

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.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents