Abstract
BLAS (Basic Linear Algebra Subprograms) plays a very important role in scientific computing and engineering applications. ATLAS is often recommended as a way to generate an optimized BLAS library. Based on ATLAS, this paper optimizes the algorithms of triangular matrix functions on 750 MHZ Loongson 2F processor-specific architecture. Using loop unrolling, instruction scheduling and data pre-fetching techniques, computing time and memory access delay are both reduced, and thus the performance of functions is improved. Experimental results indicate that these optimization techniques can effectively reduce the running time of functions. After optimization, double-precision type function of TRSM has the speed of 1300Mflops, while single-precision type function has the speed of 1800Mflops. Compared with ATLAS, the performance of function TRSM is improved by 50% to 60%, even by 100% to 200% under small-scale input.
Chapter PDF
Similar content being viewed by others
References
Lawson, C., Hanson, R., Kincaid, D., Krogh, F.: Basic Linear Algebra Subprograms for FORTRAN usage. ACM Transaction on Mathematical Software 5(3), 308–323 (1979)
Dumas, J.G., Gautier, T., Pernet, C.: Finite Field Linear Algebra Subroutines. In: Proceedings of the 2002 International Symposium on Symbolic on Symbolic and Algebraic Computation (2002)
Elmroth, E., Gustavson, F., Jonsson, I., Kagstrom, B.: Recursive Blocked Algorithms and Hybrid Data Structures for Dense Matrix Library Software. In: SIAM Review (2004)
Chowdhury, R.A., Ramachandran, V.: The Cache-oblivious Gaussian Elimination Paradigm: Theoretical Framework, Parallelization and Experimental Evaluation. In: Proceedings of the Nineteenth Annual ACM Symposium on Algorithms and Computation Theory, pp. 71–80 (2007)
Low, T.M., Robert, A., et al.: API for Manipulating Matrices Stored by Blocks. Department of Computer Sciences, the University of Texas at Austin (2004), http://www.cs.utexas.edu/users/flame/pubs/flash.ps
Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimization of software and the ATLAS project. Parallel Computing 27, 3–35 (2001)
Demmel, J., Dongarra, J., Eijkhout, V., Fuentes, E., et al.: Self adapting linear algebra algorithms and software. Proceedings of the IEEE. Special Issue on Program Generation, Optimization, and Adaptation 93(2) 2005
Goto, K., van de Geijn, R.: On reducing tlb misses in matrix multiplication. Technical Report TR02-55, Department of Computer Sciences, U. of Texas at Austin (2002)
Koenker, R., Pin, N.G.: SparseM: A sparse matrix package for R. J. of Statistical Software 8(6) (2003)
Gu, N.J., Li, K., et al.: Optimization for BLAS on Loongson 2F architecture. Journal of University of Science and Technology of China 38(7) (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 IFIP International Federation for Information Processing
About this paper
Cite this paper
Xu, Y., Shao, M., Teng, D. (2010). Optimization of Triangular Matrix Functions in BLAS Library on Loongson2F. In: Ding, C., Shao, Z., Zheng, R. (eds) Network and Parallel Computing. NPC 2010. Lecture Notes in Computer Science, vol 6289. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15672-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-15672-4_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15671-7
Online ISBN: 978-3-642-15672-4
eBook Packages: Computer ScienceComputer Science (R0)