Abstract
A single-ring may become performance bottleneck for multi-consumer and multi-producer. Although multi-ring can solve above problems by allocating one ring for each task, it may decrease resource utilization. Thus, we put forward a sharing-memory based ring framework. It mainly consists of a series of small rings and a special mechanism: active-window. It uses active-window to translate task-speed into ring-speed, and to make ring-speed adapt to changes of task-speed by adjusting active-window, which can efficiently avoid performance bottleneck. At last, our experimental results show that big-ring is evidently better than single-ring at most times, and big-ring is better than multi-ring when task-speed exceeds one certain value.
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
References
Kaashoek, F.: The click modular router. ACM Trans. Comput. Syst. 33(5), 263–297 (2000)
Etsion, Y., Cabarcas, F., Rico, A., et al.: Task superscalar: an out-of-order task pipeline. In: Proceedings of the 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture, pp. 89–100. IEEE Computer Society Publications (2010)
Olivier, S.L., Prins, J.F.: Comparison of OpenMP 3.0 and other task parallel frameworks on unbalanced task graphs. Int. J. Parallel Program. 38(5–6), 341–360 (2010)
Wang, B.: Task parallel scheduling over multi-core system. In: Jaatun, M.G., Zhao, G., Rong, C. (eds.) Cloud Computing. LNCS, vol. 5931, pp. 423–434. Springer, Heidelberg (2009)
Chakrabarti, S., Yelick, K., Demmel, J.: Models and scheduling algorithms for mixed data and task parallel programs. J. Parallel Distrib. Comput. 47(2), 168–184 (1997)
Wu, J., Ding, L., Wang, Y., et al.: Identification and evaluation of sharing memory covert timing channel in Xen virtual machines. In: 2012 IEEE Fifth International Conference on Cloud Computing, pp. 283–291. IEEE (2011)
Li-Ping, M.A., Hai-Bo, G.E., Lei, O.Y.: A new design for multiprocessor parallel rapid communication based on sharing memory. Electron. Des. Eng. 7, 020 (2011)
Krishna, P., Patel, N.S., Charny, A., et al.: On the speedup required for work-conserving crossbar switches. In: 1998 Sixth International Workshop on Quality of Service, (IWQoS 1998), pp. 225–234. IEEE (1998)
Lim, K.Y., Kumar, M., Das, S.K.: Message ring-based channel reallocation scheme for cellular networks. In: International Symposium on Parallel Architectures, Algorithms, and Networks, p. 426. IEEE Computer Society (1999)
Soundarabai, P.B., Thriveni, J., Manjunatha, H.C., Venugopal, K.R., Patnaik, L.M.: Message efficient ring leader election in distributed systems. In: Chaki, N., Meghanathan, N., Nagamalai, D. (eds.) Computer Networks and Communications (NetCom). LNEE, vol. 131, pp. 835–843. Springer, Heidelberg (2011)
Acknowledgments
This work is supported by Program for National Basic Research Program of China (973 Program) ‘Reconfigurable Network Emulation Testbed for Basic Network Communication’, and research on XXX access authentication and authorization protocol standards.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ma, S., Wang, B., Gao, X., Zhang, X. (2015). A Sharing-Memory Based Ring Framework. In: Wang, G., Zomaya, A., Martinez, G., Li, K. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2015. Lecture Notes in Computer Science(), vol 9532. Springer, Cham. https://doi.org/10.1007/978-3-319-27161-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-27161-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27160-6
Online ISBN: 978-3-319-27161-3
eBook Packages: Computer ScienceComputer Science (R0)