Babeș-Bolyai University’s High Performance Computing Center

published in Studia Universitatis Babeş-Bolyai, Seria Informatica, Vol. LXI, No. 2, pp. 54-69, 2016.

Cite as

Full paper

Babeș-Bolyai University’s High Performance Computing Center

Authors

Darius Bufnea*, Virginia Niculescu*, Gheorghe Silaghi**, Adrian Sterca*

* Department of Computer Science, Faculty of Mathematics and Computer Science,
Babeș-Bolyai University of Cluj-Napoca
** Faculty of Economics and Business Administration, Babeș-Bolyai University of Cluj-Napoca

Abstract

This paper presents the High Performance Computing Center of the Babeș-Bolyai University from its architectural point of view but also it takes a deep look at the HPC Center’s usability from a researcher’s perspective. Its hybrid architecture – Cloud and HPC – represents a novelty of this kind of data centers, and it was the result of the emphasized necessities based on the university research development. Besides containing an extensive presentation of the High Performance Computing Center, the aim of this paper is to be a useful support for researchers that need to interact and use the HPC facilities and its resources.

Key words

high performance computing, cloud computing, computing infrastructure, computationally intensive applications

BibTeX bib file

bufnea-niculescu-2016.bib

References

  1. David Watts, Ilya Krutov, Flex System Enterprise Chassis Product Guide, Lenovo Press, first published April 2012, last updated August 2016, https://lenovopress.com/tips0863-flex-system-enterprise-chassis
  2. IBM NeXtScale System, Next-generation dense platform provides superior building-block approach for hyperscale computing, IBM Corporation 2013, https://www.ibm.com/midmarket/att/pdf/Nextscale_Datasheet.pdf
  3. Jack J. Dongarra, Piotr Luszczek, Antoine Petitet, The LINPACK Benchmark: past, present and future in Concurrency and Computation: Practice and Experience, 2003, 15:803–820 (DOI: 10.1002/cpe.728), John Wiley & Sons, Ltd.
  4. Tesla K40 GPU Accelerator Overview, http://www.nvidia.com/content/PDF/kepler/nvidia-tesla-k40.pdf
  5. Intel Xeon Phi Coprocessor Architecture Overview, 2013, https://software.intel.com/sites/default/files/Intel%C2%AE_Xeon_Phi%E2%84%A2_Coprocessor_Architecture_Overview.pdf
  6. MADECIP project – “Disaster Management Research Infrastructure Based on HPC”, http://madecip.granturi.ubbcluj.ro/
  7. MPI official website, http://mpi-forum.org/
  8. Open MPI: Open Source High Performance Computing – A High Performance Message Passing Library, https://www.open-mpi.org/
  9. MVAPICH: MPI over InfiniBand, Omni-Path, Ethernet/iWARP, and RoCE, http://mvapich.cse.ohio-state.edu/
  10. Intel® MPI Library, Deliver Flexible, Efficient, and Scalable Cluster Messaging, https://software.intel.com/en-us/intel-mpi-library
  11. The official web page of the High Performance Computing Center, http://hpc.cs.ubbcluj.ro/
  12. William Gropp, Ewing Lusk, Anthony Skjellum, Using MPI: Portable Parallel Programming with the Message-Passing Interface (Scientific and Engineering Computation), 3rd edition, MIT Press, 2014, ISBN-10: 0262527391
  13. Wesley Kendall, Beginning MPI (An Introduction in C), Amazon Digital Services LLC, 2013, ASIN: B00HM7O0M8
  14. IBM Platform LSF Foundations, Version 8.3, May 2012, http://publibfp.dhe.ibm.com/epubs/pdf/c2253480.pdf
  15. IBM Platform LSF V9.1.3 documentation, September 2014, http://www.ibm.com/support/knowledgecenter/SSETD4_9.1.3/lsf_welcome.html

Darius Bufnea