Highly Reconfigurable Computing Platform for High Performance Computing Infrastructure as a Service: Hi-IaaS

Akihiro Misawa, Susumu Date, Keichi Takahashi, Takashi Yoshikawa, Masahiko Takahashi, Masaki Kan, Yasuhiro Watashiba, Yoshiyuki Kido, Chonho Lee, Shinji Shimojo

2017

Abstract

It has become increasingly difficult for high performance computing (HPC) users to own a HPC platform for themselves. As user needs and requirements for HPC have diversified, the HPC systems have the capacity and ability to execute diverse applications. In this paper, we present computer architecture for dynamically and promptly delivering high performance computing infrastructure as a cloud computing service in response to users’ requests for the underlying computational resources of the cloud. To obtain the flexibility to accommodate a variety of HPC jobs, each of which may require a unique computing platform, the proposed system reconfigures software and hardware platforms, taking advantage of the synergy of Open Grid Scheduler/Grid Engine and OpenStack. An experimental system developed in this research shows a high degree of flexibility in hardware reconfigurability as well as high performance for a benchmark application of Spark. Also, our evaluation shows that the experimental system can execute twice as many as jobs that need a graphics processing unit (GPU), in addition to eliminating the worst case of resource congestion in the real-world operational record of our university’s computer center in the previous half a year.

References

  1. Docs.aws.amazon.com. (2017). Linux Accelerated Computing Instances - Amazon Elastic Compute Cloud. [online] Available at: http://docs.aws.amazon.com/ AWSEC2/latest/UserGuide/accelerated-computinginstances.html [Accessed 15 Mar. 2017].
  2. GitHub. (2017). irifed/softlayer-mpicluster. [online] Available at: https://github.com/irifed/softlayermpicluster [Accessed 15 Mar. 2017].
  3. Sanders, C. (2017). Azure N-Series preview availability. [online] Azure.microsoft.com. Available at: https://azure. microsoft.com/en-us/blog/azure-n-seriespreview-availability/ [Accessed 15 Mar. 2017].
  4. Hadoop.apache.org. (2017). Welcome to Apache™ Hadoop®!. [online] Available at: http://hadoop. apache.org/ [Accessed 15 Mar. 2017].
  5. Spark.apache.org. (2017). Apache Spark™ - LightningFast Cluster Computing. [online] Available at: http://spark.apache.org/ [Accessed 15 Mar. 2017].
  6. Presentations.interop.com. (2017). Intel Rack Scale Architecture Overview. [online] Available at: http:// presentations.interop.com/events/las-vegas/ 2013/freesessions---keynote-presentations/download/463 [Accessed 15 Mar. 2017].
  7. Open Compute. (2017). Home. [online] Available at: http://www.opencompute.org/ [Accessed 15 Mar. 2017].
  8. Han, S., Egi, N., Panda, A., Ratnasamy, S., Shi, G. and Shenker, S. (2013). Network support for resource disaggregation in next-generation datacenters. Proceedings of the 12th ACM Workshop on Hot Topics in Networks - HotNets-XII.
  9. Suzuki, J., Hidaka, Y., Higuchi, J., Yoshikawa, T. and Iwata, A. (2006). ExpressEther - Ethernet-Based Virtualization Technology for Reconfigurable Hardware Platform. 14th IEEE Symposium on HighPerformance Interconnects (HOTI'06).
  10. Yoshikawa, T., Suzuki, J., Hidaka, Y., Higuchi, J. and Abe, S. (2014). Bridge chip composing a PCIe switch over ethernet to make a seamless disaggregated computer in data-center scale. 2014 IEEE Hot Chips 26 Symposium (HCS).
  11. OpenStack. (2017). Software » OpenStack Open Source Cloud Computing Software. [online] Available at: https://www.openstack.org/software/ [Accessed 15 Mar. 2017].
  12. Gridscheduler.sourceforge.net. (2017). Open Grid Scheduler: The official Open Source Grid Engine. [online] Available at: http://gridscheduler. sourceforge.net/ [Accessed 15 Mar. 2017].
  13. Nomura, S., Mitsuishi, T., Suzuki, J., Hayashi, Y., Kan, M. and Amano, H. (2014). Performance Analysis of the Multi-GPU System with ExpEther. ACM SIGARCH Computer Architecture News, 42(4), pp.9-14.
  14. Mitsuishi, T., Suzuki, J., Hayashi, Y., Kan, M. and Amano, H. (2016). Breadth First Search on Cost-efficient MultiGPU Systems. ACM SIGARCH Computer Architecture News, 43(4), pp.58-63.
  15. Hpc.cmc.osaka-u.ac.jp. (2017). Cybermedia Center, Osaka University. [online] Available at: http://www.hpc.cmc. osaka-u.ac.jp/en/ [Accessed 15 Mar. 2017].
  16. Klusácek, D. and Rudová, H. (2010). Alea 2: job scheduling simulator. Proceedings of the 3rd International ICST Conference on Simulation Tools and Techniques, 61, pp.1-10.
  17. Suzuki, J., Hidaka, Y., Higuchi, J., Hayashi, Y., Kan, M. and Yoshikawa, T. (2016). Disaggregation and Sharing of I/O Devices in Cloud Data Centers. IEEE Transactions on Computers, 65(10), pp.3013-3026.
  18. Katrinis, K., Syrivelis, D., Pnevmatikatos, D., Zervas, G., Theodoropoulos, D., Koutsopoulos, I., Hasharoni, K., Raho, D., Pinto, C., Espina, F., Lopez-Buedo, S., Chen, Q., Nemirovsky, M., Roca, D., Klos, H. and Berends, T. (2016). Rack-scale disaggregated cloud data centers: The dReDBox project vision. Proceedings of the 20th Design, Automation & Test in Europe Conference & Exhibition (DATE), pp.690-695.
  19. Sefraoui, O., Aissaoui, M. and Eleuldj, M. (2014). Dynamic Reconfigurable Component for Cloud Computing Resources. International Journal of Computer Applications, 88(7), pp.1-5.
  20. Xu, F., Liu, F., Jin, H. and Vasilakos, A. (2014). Managing Performance Overhead of Virtual Machines in Cloud Computing: A Survey, State of the Art, and Future Directions. Proceedings of the IEEE, 102(1), pp.11-31.
  21. Lee, G., Chun, B. and Katz, R. (2011). Heterogeneity-aware resource allocation and scheduling in the cloud. Proceedings of the 3rd USENIX Conference on Hot Topics in Cloud Computing (HotCloud'11), pp.1-5.
  22. Wheeler, M., Pencheva, G., Tavakoli, R., Shae, Z., Jamjoom, H., Sexton, J., Sachdeva, V., Jordan, K., Kim, H., Parashar, M. and AbdelBaky, M. (2012). Enabling High-Performance Computing as a Service. Computer, 45(10), pp.72-80.
Download


Paper Citation


in Harvard Style

Misawa A., Date S., Takahashi K., Yoshikawa T., Takahashi M., Kan M., Watashiba Y., Kido Y., Lee C. and Shimojo S. (2017). Highly Reconfigurable Computing Platform for High Performance Computing Infrastructure as a Service: Hi-IaaS . In Proceedings of the 7th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER, ISBN 978-989-758-243-1, pages 163-174. DOI: 10.5220/0006302501630174


in Bibtex Style

@conference{closer17,
author={Akihiro Misawa and Susumu Date and Keichi Takahashi and Takashi Yoshikawa and Masahiko Takahashi and Masaki Kan and Yasuhiro Watashiba and Yoshiyuki Kido and Chonho Lee and Shinji Shimojo},
title={Highly Reconfigurable Computing Platform for High Performance Computing Infrastructure as a Service: Hi-IaaS},
booktitle={Proceedings of the 7th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,},
year={2017},
pages={163-174},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006302501630174},
isbn={978-989-758-243-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,
TI - Highly Reconfigurable Computing Platform for High Performance Computing Infrastructure as a Service: Hi-IaaS
SN - 978-989-758-243-1
AU - Misawa A.
AU - Date S.
AU - Takahashi K.
AU - Yoshikawa T.
AU - Takahashi M.
AU - Kan M.
AU - Watashiba Y.
AU - Kido Y.
AU - Lee C.
AU - Shimojo S.
PY - 2017
SP - 163
EP - 174
DO - 10.5220/0006302501630174