Skip to Main Content U.S. Department of Energy
Computational Sciences & Mathematics

Staff information

Abhinav Vishnu

Abhinav Vishnu

High Performance Computing
Pacific Northwest National Laboratory
PO Box 999
MSIN: J4-30
Richland, WA 99352


Abhinav Vishnu, Senior Research Scientist, joined the High Performance Computing Group at Pacific Northwest National Laboratory in 2009. His interests include research and development on one-sided programming models with modern architectures and emerging interconnects. Vishnu primarily focuses on Global Arrays and Aggregate Remote Memory Copy Interface (ARMCI). Global Arrays is a widely used programming model for many scientific applications, including the PNNL-developed NWChem. Vishnu completed his PhD at The Ohio State University under the guidance of Prof. D K Panda.

Before joining PNNL, Vishnu worked on projects related to designing efficient substrates for multi-rail clusters, avoiding hot-spots and leveraging InfiniBand mechanisms for network fault tolerance with two-sided and one-sided programming models. His dissertation focused on designing high-performance and network fault tolerant MPI with multi-pathing over InfiniBand. The results of his dissertation are available in an open source software with MVAPICH/MVAPICH2, high-performance MPI-1/MPI-2 implementations over InfiniBand from Ohio State University. MVAPICH/MVAPICH2 have helped many supercomputers achieve TOP500 rankings. The current users include 600 organizations from 33 countries, ranging from national labs, academia, and industry. MVAPICH/MVAPICH2 are being used to power the 3rd, 22nd and 29th ranked supercomputers in Nov'07 TOP500 supercomputer rankings.

Research Interests

  • Communication Protocol
  • High Speed Interconnect
  • Reliable Data Transmission
  • Fault Discovery
  • High Availability

Education and Credentials

  • Ph.D, Ohio State University, 2007
  • MS, Ohio State University, 2007
  • Bachelor of Technology, Banaras Hindu University, 2002

Awards and Recognitions

  • Best Paper Award Nomination, Hot-Spot Avoidance with Multi-Pathing Over InfiniBand:
    An MPI Perspective, CCGrid, 2007
  • TCPP Travel Award, IPDPS 2007, Long Beach, CA, 2007
  • IBM PhD Fellowship Award, 2006 - 2007
  • Who's Who in America, 2006
  • TCSC Travel Award, SuperComputing, 2006
  • National Talent Search Examination, 1995

PNNL Publications


  • Kerbyson DJ, KJ Barker, A Vishnu, and A Hoisie. 2013. "Comparing the Performance of Blue Gene/Q with Leading Cray XE6 and InfiniBand Systems." In Proceedings of 18th IEEE International Conference on Parallel and Distributed Systems (ICPADS), December 17-19, 2012, Singapore, pp. 556-563.  IEEE Computer Society, Los Alamitos, CA.  doi:10.1109/ICPADS.2012.81
  • van Dam HJJ, A Vishnu, and WA De Jong. 2013. "A Case for Soft Error Detection and Correction in Computational Chemistry." Journal of Chemical Theory and Computation 9(9):3995-4005.  doi:10.1021/ct400489c


  • Vishnu A, JA Daily, and BJ Palmer. 2012. "Designing Scalable PGAS Communication Subsystems on Cray Gemini Interconnect." In 19th International Conference on High Performance Computing (HiPC), December 18-22, 2012, Pune, India.  Institute of Electrical and Electronics Engineers , Piscataway, NJ.  doi:10.1109/HiPC.2012.6507506
  • Chavarría-Miranda D, S Krishnamoorthy, and A Vishnu. 2012. "Global Futures: a multithreaded execution model for Global Arrays-based applications." In Proceedings of the 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid 2012), May 13-16, 2012, Ottawa, Canada, pp. 393-401.  Institute of Electrical and Electronics Engineers , Piscataway, NJ.  doi:10.1109/CCGrid.2012.105


  • Vishnu A, MK Krishnan, and P Balaji. 2011. "Dynamic Time-Variant Connection Management for PGAS Models on InfiniBand." In Proceedings of the 25th IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW 2011), May 16-20, 2011, Anchorage, Alaska, pp. 740 - 746.  IEEE Computer Society, Los Alamitos, CA. 
  • van Dam HJJ, A Vishnu, and WA De Jong. 2011. "Designing a Scalable Fault Tolerance Model for High Performance Computational Chemistry: A Case Study with Coupled Cluster Perturbative Triples." Journal of Chemical Theory and Computation 7(1):66-75.  doi:10.1021/ct100439u


  • Vishnu A, and MK Krishnan. 2010. "Efficient On-demand Connection Management Mechanisms with PGAS Models on InfiniBand." In 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing (CCGrid 2010), pp. 175-184.  Institute of Electrical and Electronics Engineers, Piscataway, NJ.  doi:10.1109/CCGRID.2010.58
  • Vishnu A, S Song, A Marquez, KJ Barker, DJ Kerbyson, K Cameron, and P Balaji. 2010. "Designing Energy Efficient Communication Runtime Systems for Data Centric Programming Models." In IEEE/ACM Internationall Conference on Green Computing and Communications (GreenCom 2010) and the International Conference on Cyber, Physical and Social Computing (CPSCom 2010), December 18-20, 2010, Hangzhou, China, ed. P Zhu, et al, pp. 229-236.  Institute of Electrical and Electronics Engineers, Inc., Piscatawy, NJ.  doi:10.1109/GreenCom-CPSCom.2010.133
  • Kandalla K, H Subramoni, A Vishnu, and DK Panda. 2010. "Designing Topology-Aware Collective Communication Algorithms for Large Scale InfiniBand Clusters: Case Studies with Scatter and Gather." In IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW 2010).  Institute of Electrical and Electronics Engineers, Piscataway, NJ.  doi:10.1109/IPDPSW.2010.5470853
  • Krishnan MK, RR Lewis, and A Vishnu. 2010. "Scaling Linear Algebra Kernels using Remote Memory Access." In Proceedings of the 39th International Conference on Parallel Processing Workshops (ICPPW), pp. 369-376.  IEEE Computer Society, Los Alamitos, CA.  doi:10.1109/ICPPW.2010.57


  • Vishnu A, MJ Koop, A Moody, A Mamidala, S Narravula, and DK Panda. 2009. "Topolgy Agnostic Hot-Spot Avoidance with InfiniBand." Concurrency and Computation. Practice & Experience 21(3):301-319.  doi:10.1002/cpe.1359
  • Vishnu A, MK Krishnan, and DK Panda. 2009. "An Efficient Hardware-Software Approach to Network Fault Tolerance with InfiniBand." In IEEE International Conference on Cluster Computing and Workshops (CLUSTER 2009).  Institute of Electrical and Electronics Engineers, Piscataway, NJ.  doi:10.1109/CLUSTR.2009.5289168

Computational Sciences & Mathematics


Seminar Series

Fundamental & Computational Sciences

CSMD Research

Research highlights

View All CSMD Highlights