Abstract
In this paper, we propose a new GPGPU based erasure codes encoding method using non-sparse coding vector. The proposed method can be applied to various erasure codes and efficiently utilize GPU cores and GPU memory by using non-sparse coding vector instead of large sparse coding matrix, and erasing multiplication operation and reducing unnecessary XOR operations. The experimental results show that the average encoding times of SPC, RDP, EVENODD erasure codes using the proposed method are 39.26%, 37.5%, 37.85% less than traditional GPU based encoding, respectively.
Chapter PDF
References
Pirahandeh, M., Kim, D.-H.: Energy-aware GPU-RAID scheduling for reducing energy consumption in cloud storage systems. In: Park, J.J.J.H., Stojmenovic, I., Jeong, H.Y., Yi, G. (eds.) Computer Science and Its Applications. LNEE, vol. 330, pp. 705–712. Springer, Heidelberg (2015)
Roman, W., Woźniak, M., Kuczyński, L.: Efficient Execution of Erasure Codes on AMD APU Architecture. Parallel Processing and Applied Mathematics, pp. 613–621. Springer, Heidelberg (2014)
Wyrzykowski, R., Kuczynski, L., Wozniak, M.: Towards efficient execution of erasure codes on multicore architectures. In: Jónasson, K. (ed.) PARA 2010, Part II. LNCS, vol. 7134, pp. 357–367. Springer, Heidelberg (2012)
Maheswaran, S., et al.: Xoring elephants: novel erasure codes for big data. In: Proceedings of the VLDB Endowment, vol. 6, no. 5. VLDB Endowment (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer Science+Business Media Singapore
About this paper
Cite this paper
Lee, K., Heo, H., Song, T., Kim, DH. (2015). Erasure Codes Encoding Performance Enhancing Techniques Using GPGPU Based Non-sparse Coding Vector in Storage Systems. In: Park, DS., Chao, HC., Jeong, YS., Park, J. (eds) Advances in Computer Science and Ubiquitous Computing. Lecture Notes in Electrical Engineering, vol 373. Springer, Singapore. https://doi.org/10.1007/978-981-10-0281-6_115
Download citation
DOI: https://doi.org/10.1007/978-981-10-0281-6_115
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0280-9
Online ISBN: 978-981-10-0281-6
eBook Packages: Computer ScienceComputer Science (R0)