2021 [ to top ]

• 
  Zhou, N., Georgiou, Y., Pospieszny, M., Zhong, L., Zhou, H., Niethammer, C., Pejak, B., Marko, O., Hoppe, D.: Container orchestration on HPC systems through Kubernetes. Journal of Cloud Computing. 10, 1--14 (2021).
   
• 
  Zhou, H., Niethammer, C., Azcue, M.H.: Usage Experiences of Performance Tools for Modern C $$$$ Code Analysis and Optimization. Tools for High Performance Computing 2018/2019. S. 103--121. Tools for High Performance Computing 2018/2019 (2021).
   

2020 [ to top ]

• 
  Zhou, H., Gracia, J.'e, Zhou, N., Schneider, R.: Collectives in hybrid MPI+ MPI code: Design, practice and performance. Parallel Computing. 102669 (2020).
  [ URL ]
   
• 
  Herrer\'ias Azcu'e, M., Capdevila, H., Zhou, H., Hammer, A.: Simulation of Large PV Plants Using a Continuous Radiance Distribution Model and Cell-Resolution Mismatch Calculation. European Photovoltaic Solar Energy Conference and Exhibition. S. 1311--1316. European Photovoltaic Solar Energy Conference and Exhibition (2020).
   

2019 [ to top ]

• 
  Zhou, H., Gracia, J.'e, Schneider, R.: MPI Collectives for Multi-core Clusters: Optimized Performance of the Hybrid MPI+ MPI Parallel Codes. Proceedings of the 48th International Conference on Parallel Processing: Workshops. S. 1--10. Proceedings of the 48th International Conference on Parallel Processing: Workshops (2019).
   

2017 [ to top ]

• 
  Zhou, H., Gracia, J.: Application Productivity and Performance Evaluation of Transparent Locality-aware One-sided Communication Primitives. International Journal of Networking and Computing. 7, 136--153 (2017).
  [ Abstract ] [ URL ]
   
  Nowadays, the individual nodes of a distributed parallel computer consist of multi- or many-core processors allowing to execute more than one process per node. The large difference in communication speed within a node through shared memory, versus across nodes through the network interconnect, requires to use locality-aware communication schemes for any efficient distributed application. However, writing an efficient locality-aware MPI code is complex and error-prone, because the developer has to use very different APIs for communication operations within and across nodes, respectively, and manage inter-process synchronization. In this paper, we analyze and enhance a recent one-sided communication model, namely DART-MPI, which is implemented on top of MPI-3. In this runtime system, the complexities of handling locality-awareness of MPI memory access operations, either remote or local, and the related synchronization calls are hidden inside the related DART-MPI interfaces resulting in concise code and improved application and developer productivity. We have carried out in-depth evaluation of our DART-MPI system. Foremost, a micro benchmark is conducted to help understanding the prime performance overhead of implementing APIs in DART-MPI system, which is small and becomes negligible with the growing message sizes. We then compare the performance of DART-MPI and flat MPI without locality awareness, in particular blocking and non-blocking memory operations, using a realistic scientific application on a large-scale supercomputer. The comparison demonstrates that in most cases the DART-MPI version of this application shows better performance than the flat MPI version. Further, we compare the DART-MPI version to a functionally equivalent MPI version, which thus includes code to deal with data-locality, and show that DART-MPI realizes almost the full potential of highly optimized MPI while maintaining high productivity for non-expert programmers.

2016 [ to top ]

• 
  Zhou, H., Gracia, J.: Asynchronous Progress Design for a MPI-Based PGAS One-Sided Communication System. ICPADS. S. 999–1006. ICPADS (2016).
  [ URL ]
   
• 
  Zhou, H., Gracia, J.: Towards Performance Portability through Locality-Awareness for Applications Using One-Sided Communication Primitives. CANDAR. S. 536–542. CANDAR (2016).
  [ URL ]
   

2015 [ to top ]

• 
  Zhou, H., Marjanovic, V., Niethammer, C., Gracia, J.: A Bandwidth-saving Optimization for MPI Broadcast Collective Operation. Proceedings of the International Conference on Parallel Processing Workshops, ICPPW. Proceedings of the International Conference on Parallel Processing Workshops, ICPPW, Beijing, China (2015).
   
• 
  Niethammer, C., Khabi, D., Zhou, H., Marjanovic, V., Gracia, J.: Impact of Late-Arrivals on MPI Collective Operations. INFOCOMP 2015. INFOCOMP 2015, Brussels, Belgium (2015).
   
• 
  Zhou, H., Idrees, K., Gracia, J.: Leveraging MPI-3 Shared-Memory Extensions for Efficient PGAS Runtime Systems. In: Träff, J.L., Hunold, S., und Versaci, F. (Hrsg.) Euro-Par. S. 373–384. Euro-Par (2015).
  [ URL ]
   

2014 [ to top ]

• 
  Zhou, H., Mhedheb, Y., Idrees, K., Glass, C.W., Gracia, J., Fürlinger, K.: DART-MPI: An MPI-based Implementation of a PGAS Runtime System. In: Malony, A.D. und Hammond, J.R. (Hrsg.) PGAS. S. 3:1–3:11. PGAS (2014).
  [ URL ]
   
• 
  Fürlinger, K., Glass, C.W., Gracia, J., Knüpfer, A., Tao, J., Hünich, D., Idrees, K., Maiterth, M., Mhedheb, Y., Zhou, H.: DASH: Data Structures and Algorithms with Support for Hierarchical Locality. Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International Workshops, Porto, Portugal, August 25-26, 2014, Revised Selected Papers, Part II. S. 542–552. Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International Workshops, Porto, Portugal, August 25-26, 2014, Revised Selected Papers, Part II (2014).