Article

Combining Models and Guided Empirical Search to Optimize for Multiple Levels of the Memory Hierarchy

Authors:

Jacqueline Chame,

Mary HallAuthors Info & Claims

CGO '05: Proceedings of the international symposium on Code generation and optimization

Pages 111 - 122

https://doi.org/10.1109/CGO.2005.10

Published: 20 March 2005 Publication History

Abstract

This paper describes an algorithm for simultaneously optimizing across multiple levels of the memory hierarchy for dense-matrix computations. Our approach combines compiler models and heuristics with guided empirical search to take advantage of their complementary strengths. The models and heuristics limit the search to a small number of candidate implementations, and the empirical results provide the most accurate information to the compiler to select among candidates and tune optimization parameter values. We have developed an initial implementation and applied this approach to two case studies, Matrix Multiply and Jacobi Relaxation. For Matrix Multiply, our results on two architectures, SGI R10000 and Sun UltraSparc IIe, outperform the native compiler, and either outperform or achieve comparable performance as the ATLAS self-tuning library and the hand-tuned vendor BLAS library. Jacobi results also substantially outperform the native compilers.

References

[1]

{1} D. F. Bacon, J. Chow, R. Ju, K. Muthukumar, and V. Sarkar. A compiler framework for restructuring data declarations to enhance cache and TLB effectiveness. In Proc. of the Conference of the Center for Advanced Studies on Collaborative Research, Nov. 1994.

Digital Library

[2]

{2} J. Bilmes, K. Asanovi¿, C. Chin, and J. Demmel. Optimizing matrix multiply using PHiPAC: a portable, high-performance, ANSI C coding methodology. In Proc. of the International Conference on Supercomputing , June 1997.

Digital Library

[3]

{3} S. Browne, J. Dongarra, N. Garner, G. Ho, and P. Mucci. A portable programming interface for performance evaluation on modern processors. International Journal of High Performance Computing Applications, 14(3):189-204, Aug. 2000.

Digital Library

[4]

{4} E. Bugnion, J. M. Anderson, T. C. Mowry, M. Rosenblum, and M. S. Lam. Compiler-directed page coloring for multiprocessors. In Proc. of the International Conference on Architectural Support for Programming Languages and Operating Systems, Oct. 1996.

Digital Library

[5]

{5} S. Carr and K. Kennedy. Improving the ratio of memory operations to floating-point operations in loops. ACM Transactions on Programming Languages and Systems, 16(6):1768-1810, Nov. 1994.

Digital Library

[6]

{6} S. Chatterjee, E. Parker, P. J. Hanlon, and A. R. Lebeck. Exact analysis of the cache behavior of nested loops. In Proc. of the Conference on Programming Language Design and Implementation, June 2001.

Digital Library

[7]

{7} S. Coleman and K. S. McKinley. Tile size selection using cache organization and data layout. In Proc. of the Conference on Programming Language Design and Implementation, June 1995.

Digital Library

[8]

{8} K. D. Cooper, P. J. Schielke, and D. Subramanian. Optimizing for reduced code space using genetic algorithms. In Proc. of the Workshop on Languages, Compilers, and Tools for Embedded Systems, May 1999.

Digital Library

[9]

{9} M. Frigo. A fast Fourier transform compiler. In Proc. of the Conference on Programming Language Design and Implementation, May 1999.

Digital Library

[10]

{10} S. Ghosh, M. Martonosi, and S. Malik. Precise miss analysis for program transformations with caches of arbitrary associativity. In Proc. of the International Conference on Architectural Support for Programming Languages and Operating Systems, Oct. 1998.

Digital Library

[11]

{11} P. M. W. Knijnenburg, T. Kisuki, K. Gallivan, and M. F. P. O'Boyle. The effect of cache models on iterative compilation for combined tiling and unrolling. Concurrency and Computation: Practice and Experience , 16(2-3):247-270, 2004.

Digital Library

[12]

{12} M. S. Lam, E. E. Rothberg, and M. E. Wolf. The cache performance and optimizations of blocked algorithms. In Proc. of the International Conference on Architectural Support for Programming Languages and Operating Systems, Apr. 1991.

Digital Library

[13]

{13} N. Mitchell, K. Högstedt, L. Carter, and J. Ferrante. Quantifying the multi-level nature of tiling interactions. In Proc. of the Workshop on Languages and Compilers for Parallel Computing, Aug. 1997.

Digital Library

[14]

{14} N. Park, B. Hong, and V. K. Prasanna. Tiling, block data layout, and memory hierarchy performance. IEEE Transactions on Parallel and Distributed Systems , 14(7):640-654, July 2003.

Digital Library

[15]

{15} G. Pike and P. N. Hilfinger. Better tiling and array contraction for compiling scientific programs. In Proc. of Supercomputing '02, Nov. 2002.

Digital Library

[16]

{16} G. Rivera and C. Tseng. Data transformations for eliminating conflict misses. In Proc. of the Conference on Programming Language Design and Implementation , June 1998.

Digital Library

[17]

{17} B. Singer and M. Veloso. Stochastic search for signal processing algorithm optimization. In Proc. of Supercomputing '01, Nov. 2001.

Digital Library

[18]

{18} M. Stephenson, S. Amarasinghe, M. Rinard, and U. O'Reilly. Meta optimization: Improving compiler heuristics with machine learning. In Proc. of the Conference on Programming Language Design and Implementation , June 2003.

Digital Library

[19]

{19} O. Temam, E. D. Granston, and W. Jalby. To copy or not to copy: A compile-time technique for assessing when data copying should be used to eliminate cache conflicts. In Proc. of Supercomputing '93, Nov. 1993.

Digital Library

[20]

{20} X. Vera, J. Abella, A. González, and J. Llosa. Optimizing program locality through CMEs and GAs. In Proc. of the International Conference on Parallel Architectures and Compilation Techniques, Sept. 2003.

Digital Library

[21]

{21} R. C. Whaley, A. Petitet, and J. J. Dongarra. Automated empirical optimization of software and the ATLAS project. Parallel Computing, 27(1-2):3-35, Jan. 2001.

Digital Library

[22]

{22} M. E. Wolf. Improving Locality and Parallelism in Nested Loops. PhD thesis, Dept. of Computer Science, Stanford University, Aug. 1992.

Digital Library

[23]

{23} M. E. Wolf and M. S. Lam. A data locality optimizing algorithm. In Proc. of the Conference on Programming Language Design and Implementation, June 1991.

Digital Library

[24]

{24} M. E. Wolf, D. E. Maydan, and D.-K. Chen. Combining loop transformations considering caches and scheduling. In Proc. of the 29th Annual IEEE/ACM International Symposium on Microarchitecture, Dec. 1996.

Digital Library

[25]

{25} J. Xiong, J. Johnson, R. Johnson, and D. Padua. SPL: A language and compiler for DSP algorithms. In Proc. of the Conference on Programming Language Design and Implementation, June 2001.

Digital Library

[26]

{26} K. Yotov, X. Li, G. Ren, M. Cibulskis, G. DeJong, M. Garzaran, D. Padua, K. Pingali, P. Stodghill, and P. Wu. A comparison of empirical and model-driven optimization. In Proc. of the Conference on Programming Language Design and Implementation, June 2003.

Digital Library

[27]

{27} K. Yotov, X. Li, G. Ren, M. Garzaran, D. Padua, K. Pingali, and P. Stodghill. Is search really necessary to generate high-performance BLAS? Proceedings of the IEEE, 93(2), Feb. 2005.

Cited By

Anthimopoulos TKeramidas GKelefouras VStamoulis I(2024)Register Blocking: An Analytical Modelling Approach for Affine Loop KernelsProceedings of the 21st ACM International Conference on Computing Frontiers10.1145/3649153.3649194(71-79)Online publication date: 7-May-2024
https://dl.acm.org/doi/10.1145/3649153.3649194
Gerard BGrosser TKong MEgger BSmith A(2022)QRANE: lifting QASM programs to an affine IRProceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction10.1145/3497776.3517775(15-28)Online publication date: 19-Mar-2022
https://dl.acm.org/doi/10.1145/3497776.3517775
Chelini LGysi TGrosser TKong MCorporaal HSarkar VKim H(2020)Automatic Generation of Multi-Objective Polyhedral Compiler TransformationsProceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques10.1145/3410463.3414635(83-96)Online publication date: 30-Sep-2020
https://dl.acm.org/doi/10.1145/3410463.3414635
Show More Cited By

Index Terms

Combining Models and Guided Empirical Search to Optimize for Multiple Levels of the Memory Hierarchy

Recommendations

Model-guided empirical optimization for memory hierarchy
Improving memory hierarchy performance by store-load renaming and locality-guided parallelization
An Improved Non-negative Matrix Factorization Algorithm for Combining Multiple Clusterings
MVHI '10: Proceedings of the 2010 International Conference on Machine Vision and Human-machine Interface

Cluster ensemble has recently become a hotspot in machine learning communities. The key problem in cluster ensemble is how to combine multiple clusterings to yield a final superior result. In this paper, an Improved Non-negative Matrix Factorization (...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

CGO '05: Proceedings of the international symposium on Code generation and optimization

March 2005

313 pages

ISBN:076952298X

Sponsors

Publisher

IEEE Computer Society

United States

Publication History

Published: 20 March 2005

Check for updates

Qualifiers

Article

Conference

CGO05

Sponsor:

CGO05: 3rd Annual IEEE / ACM International Symposium on Code Generation and Optimization

March 20 - 23, 2005

Acceptance Rates

CGO '05 Paper Acceptance Rate 26 of 75 submissions, 35%;

Overall Acceptance Rate 312 of 1,061 submissions, 29%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

47
Total Citations
View Citations
394
Total Downloads

Downloads (Last 12 months)2
Downloads (Last 6 weeks)0

Reflects downloads up to 12 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Anthimopoulos TKeramidas GKelefouras VStamoulis I(2024)Register Blocking: An Analytical Modelling Approach for Affine Loop KernelsProceedings of the 21st ACM International Conference on Computing Frontiers10.1145/3649153.3649194(71-79)Online publication date: 7-May-2024
https://dl.acm.org/doi/10.1145/3649153.3649194
Gerard BGrosser TKong MEgger BSmith A(2022)QRANE: lifting QASM programs to an affine IRProceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction10.1145/3497776.3517775(15-28)Online publication date: 19-Mar-2022
https://dl.acm.org/doi/10.1145/3497776.3517775
Chelini LGysi TGrosser TKong MCorporaal HSarkar VKim H(2020)Automatic Generation of Multi-Objective Polyhedral Compiler TransformationsProceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques10.1145/3410463.3414635(83-96)Online publication date: 30-Sep-2020
https://dl.acm.org/doi/10.1145/3410463.3414635
Pfaffe PGrosser TTillmann MEigenmann RDing CMcKee S(2019)Efficient hierarchical online-autotuningProceedings of the ACM International Conference on Supercomputing10.1145/3330345.3330377(354-366)Online publication date: 26-Jun-2019
https://dl.acm.org/doi/10.1145/3330345.3330377
Kong MPouchet LMcKinley KFisher K(2019)Model-driven transformations for multi- and many-core CPUsProceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation10.1145/3314221.3314653(469-484)Online publication date: 8-Jun-2019
https://dl.acm.org/doi/10.1145/3314221.3314653
Liu JTan GLuo YLi JMo ZSun N(2019)An Autotuning Protocol to Rapidly Build AutotunersACM Transactions on Parallel Computing10.1145/32915275:2(1-25)Online publication date: 4-Jan-2019
https://dl.acm.org/doi/10.1145/3291527
Zhao JCui HZhang YXue JFeng X(2018)Revisiting Loop Tiling for DatacentersProceedings of the 2018 International Conference on Supercomputing10.1145/3205289.3205306(328-340)Online publication date: 12-Jun-2018
https://dl.acm.org/doi/10.1145/3205289.3205306
Ashouri AKillian WCavazos JPalermo GSilvano C(2018)A Survey on Compiler Autotuning using Machine LearningACM Computing Surveys10.1145/319797851:5(1-42)Online publication date: 18-Sep-2018
https://dl.acm.org/doi/10.1145/3197978
Khan AAl-Mouhamed MAl-Mulhem MAhmed A(2017)RT-CUDAInternational Journal of Parallel Programming10.1007/s10766-016-0433-645:3(551-594)Online publication date: 1-Jun-2017
https://dl.acm.org/doi/10.1007/s10766-016-0433-6
Jain ALaurenzano MTang LMars JHsu WYang CLipasti MLee H(2016)Continuous shape shiftingThe 49th Annual IEEE/ACM International Symposium on Microarchitecture10.5555/3195638.3195666(1-12)Online publication date: 15-Oct-2016
https://dl.acm.org/doi/10.5555/3195638.3195666
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 Table of Contents