Cache Behavior Modelling for Codes Involving Banded Matrices
Understanding and improving the memory hierarchy behavior is one of the most important challenges in current architectures. Analytical models are a good approach for this, but they have been traditionally limited by either their restricted scope of application or their lack of accuracy. Most models can only predict the cache behavior of codes that generate regular access patterns. The Probabilistic Miss Equation(PME) model is able nevertheless to model accurately the cache behavior for codes with irregular access patterns due to data-dependent conditionals or indirections. Its main limitation is that it only considers irregular access patterns that exhibit an uniform distribution of the accesses. In this work, we extend the PME model to enable to analyze more realistic and complex irregular accesses. Namely, we consider indirections due to the compressed storage of most real banded matrices.
Unable to display preview. Download preview PDF.
- 2.Ammons, G., Ball, T., Larus, J.R.: Exploiting Hardware Performance Counters with Flow and Context Sensitive Profiling. In: SIGPLAN Conf. on Programming Language Design and Implementation, pp. 85–96 (1997)Google Scholar
- 5.Doallo, R., Fraguela, B.B., Zapata, E.L.: Cache probabilistic modeling for basic sparse algebra kernels involving matrices with a non uniform distribution. In: Proceedings of EUROMICRO Conference, Engineering Systems and Software for the Next Decade, August, pp. 345–348 (1998)Google Scholar
- 6.Cascaval, C.: Compile-time Performance Prediction of Scientific Programs. PhD thesis, Dept. of Computer Science, University of Illinois at Urbana-Champaign (2000)Google Scholar
- 8.Andrade, D., Fraguela, B.B., Doallo, R.: Precise automatable analytical modeling of the cache behavior of codes with indirections. ACM Transactions on Architecture and Code Optimization (Accepted for publication, 2006)Google Scholar
- 9.Andrade, D., et al.: Automated and accurate cache behavior analysis for codes with irregular access patterns. In: Proceedings of Workshop on Compilers for Parallel Computers, A Coruña, Spain, pp. 179–193 (2006)Google Scholar
- 11.Barrett, R., et al.: Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods. Society for Industrial and Applied Mathematics, Philadalphia (1994), citeseer.ist.psu.edu/article/barrett93templates.html Google Scholar
- 12.Chow, E., Saad, Y.: Tools and Libraries for Parallel Sparse Matrix Computations (1995)Google Scholar
- 13.Lin, Y., Padua, D.A.: On the automatic parallelization of sparse and irregular fortran programs. In: Languages, Compilers, and Run-Time Systems for Scalable Computers, Pittsburgh, pp. 41–56 (1998)Google Scholar
- 14.Duff, I.S., Grimes, R.G., Lewis, J.G.: Users’ guide for the Harwell-Boeing sparse matrix collection (Release I). Technical Report CERFACS TR-PA-92-96 (1992)Google Scholar
- 15.Bai, Z., Day, D., Demmel, J., Dongarra, J.: A test matrix collection for non-Hermitian eigenvalue problems, release 1.0 (1996)Google Scholar
- 17.Ladner, R.E., Fix, J.D., LaMarca, A.: Cache performance analysis of traversals and random accesses. In: Proceeding of the annual ACM-SIAM Symposium on Discrete Algorithms, Baltimore, Maryland, United States, pp. 613–622. Society for Industrial and Applied Mathematics, Philadelphia (1999)Google Scholar