Abstract
In this research, we parallelized the dynamic programming algorithm of calculating edit distance for GPU, and evaluated the performance. In GPU computing, access to the device memory is likely to be one of the primal bottleneck due to its high latency, and this effect gets noticeable especially when sufficient number of active threads cannot be secured because of the lack of parallelism or overuse of GPU resources. Then, we constructed a model that approximates the relations between the values of parameters and the execution time considering latency hiding, and by using this model, we devised a method of automatic tuning of parallelization parameters in order to attain high performance stably even when the problem size is relatively small.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dohi, K., Benkrid, K., Ling, C., Hamada, T., Shibata, Y.: Highly efficient mapping of the Smith-Waterman algorithm on CUDA-compatible GPUs. In: ASAP, pp. 29–36 (2010)
Ling, C., Benkrid, K., Hamada, T.: A parameterisable and scalable Smith-Waterman algorithm implementation on CUDA-compatible GPUs. In: 2009 IEEE 7th Symposium on Application Specific Processors, pp. 94–100 (2009)
Liu, Y., Huang, W., Johnson, J., Vaidya, S.: GPU accelerated Smith-Waterman. In: Alexandrov, V.N., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2006. LNCS, vol. 3994, pp. 188–195. Springer, Heidelberg (2006)
Liu, Y., Maskell, D.L., Schmidt, B.: CUDASW++: optimizing Smith-Waterman sequence database searches for CUDA-enabled graphics processing units. BMC Research Notes 2(1), 73 (2009)
Manavski, S.A., Valle, G.: CUDA compatible GPU cards as efficient hardware accelerators for Smith-Waterman sequence alignment. BMC Bioinformatics 9(suppl. 2), S10 (2008)
Munekawa, Y., Ino, F., Hagihara, K.: Design and implementation of the Smith-Waterman algorithm on the CUDA-compatible GPU. In: BIBE, pp. 1–6 (2008)
NVIDIA Corporation. NVIDIA CUDA C Programming Guide Version 4.0
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tomiyama, A., Suda, R. (2013). Automatic Parameter Optimization for Edit Distance Algorithm on GPU. In: Daydé, M., Marques, O., Nakajima, K. (eds) High Performance Computing for Computational Science - VECPAR 2012. VECPAR 2012. Lecture Notes in Computer Science, vol 7851. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38718-0_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-38718-0_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38717-3
Online ISBN: 978-3-642-38718-0
eBook Packages: Computer ScienceComputer Science (R0)