Matthew J. Koop
Ph.D. Candidate
Dept. of Computer Science and Engineering, The Ohio State University

  • Office Location:

    Network-Based Computing Lab
    774 Dreese Laboratories
    2015 Neil Ave.

  • Mailing Address:

    395 Dreese Laboratories
    2015 Neil Ave.
    Columbus, OH 43210-1277

Research:

I am a Graduate Research Associate of the Network-Based Computing Lab, advised by Dr. D.K. Panda. I work primarily on the MVAPICH MPI project. My research is currently focused on resource usage scalability and performance of MPI over high-speed interconnects.

During the summers of 2006 and 2007 I was a Summer Scholar at Lawrence Livermore National Laboratory (LLNL) in the Institute for Scientific Computing Research (ISCR). During Summer 2008 I was an intern at IBM Research (T.J. Watson, Hawthorne).

After graduating I will join CSC at the NASA Goddard Space Flight Center in Greenbelt, MD.

Publications:

M. Koop, M. Luo and D. K. Panda, "Reducing Network Contention with Mixed Workloads on Modern Multicore Clusters", Int'l Conference on Cluster Computing (Cluster '09) - New Orleans, LA, September 2009 [bibtex]
@inproceedings{koop-cluster09,
  author = {M. Koop and M. Luo and D. K. Panda},
  title = {{Reducing Network Contention with Mixed Workloads on Modern Multicore Clusters}},
  booktitle = {{Int'l Conference on Cluster Computing (Cluster '09)}},
  month = {September},
  year = {2009},
  location = {New Orleans, LA}
}

H. Subramoni, M. Koop and D. K. Panda, "Designing Next Generation Clusters: Evaluation of InfiniBand DDR/QDR on Intel Computing Platforms,", Int'l Symposium on Hot Interconnects (HotI) - New York, New York, August 2009 [bibtex]

@inproceedings{subramon-hoti09,
  author = {H. Subramoni and M. Koop and D. K. Panda},
  title = {{Designing Next Generation Clusters: Evaluation of InfiniBand DDR/QDR on Intel Computing Platforms,}},
  booktitle = {{Int'l Symposium on Hot Interconnects (HotI)}},
  month = {August},
  year = {2009},
  location = {New York, New York}
}

T. Gangadharappa, M. Koop and D. K. Panda, "Designing and Evaluating MPI-2 Dynamic Process Management Support for InfiniBand", Int'l Workshop on Parallel Programming Models and Systems Software for High-End Computing (P2S2 '09), in conjunction with International Conference on Parallel Processing (ICPP '09) - Vienna, Austria, September 2009 [bibtex]

@inproceedings{tejus-p2s209,
  author = {T. Gangadharappa and M. Koop and D. K. Panda},
  title = {{Designing and Evaluating MPI-2 Dynamic Process Management Support for InfiniBand}},
  booktitle = {{Int'l Workshop on Parallel Programming Models and Systems Software for High-End Computing (P2S2 '09), in conjunction with International Conference on Parallel Processing (ICPP '09)}},
  month = {September},
  year = {2009},
  location = {Vienna, Austria}
}

M. Koop, J. Sridhar and D. K. Panda, "TupleQ: Fully-Asynchronous and Zero-Copy MPI over InfiniBand", IEEE Int'l Parallel and Distributed Processing Symposium (IPDPS 2009) - Rome, Italy, May 2009 [pdf] [bibtex]

@inproceedings{koop-ipdps09,
  author = {M. Koop and J. Sridhar and D. K. Panda},
  title = {{TupleQ: Fully-Asynchronous and Zero-Copy MPI over InfiniBand}},
  booktitle = {{IEEE Int'l Parallel and Distributed Processing Symposium (IPDPS 2009)}},
  month = {May},
  year = {2009},
  location = {Rome, Italy}
}

K. Kandalla, H. Subramoni, G. Santhanaraman, M. Koop and D. K. Panda, "Designing Multi-Leader-Based Allgather Algorithms for Multi-Core Clusters", 9th Workshop on Communication Architecture for Clusters (CAC 09) - Rome, Italy, May 2009 [pdf] [bibtex]

@inproceedings{kandalla-cac09,
  author = {K. Kandalla and H. Subramoni and G. Santhanaraman and M. Koop and D. K. Panda},
  title = {{Designing Multi-Leader-Based Allgather Algorithms for Multi-Core Clusters}},
  booktitle = {{9th Workshop on Communication Architecture for Clusters (CAC 09)}},
  month = {May},
  year = {2009},
  location = {Rome, Italy}
}

J. Sridhar, M. Koop, J. Perkins and D. K. Panda, "ScELA: Scalable and Extensible Launching Architecture for Clusters", International Conference in High Performance Computing (HiPC08) - Bangalore, India, December 2008 [pdf] [bibtex]

@inproceedings{sridharj-hipc08,
  author = {J. Sridhar and M. Koop and J. Perkins and D. K. Panda},
  title = {{ScELA: Scalable and Extensible Launching Architecture for Clusters}},
  booktitle = {{International Conference in High Performance Computing (HiPC08)}},
  month = {December},
  year = {2008},
  location = {Bangalore, India}
}

M. Koop, J. Sridhar and D. K. Panda, "Scalable MPI Design over InfiniBand using eXtended Reliable Connection", IEEE Int'l Conference on Cluster Computing (Cluster 2008) - Tsukuba, Japan, September 2008 [pdf] [bibtex]

@inproceedings{koop-cluster08,
  author = {M. Koop and J. Sridhar and D. K. Panda},
  title = {{Scalable MPI Design over InfiniBand using eXtended Reliable Connection}},
  booktitle = {{IEEE Int'l Conference on Cluster Computing (Cluster 2008)}},
  month = {September},
  year = {2008},
  location = {Tsukuba, Japan}
}

W. Huang, M. Koop and D. K. Panda, "Efficient One-Copy MPI Shared Memory Communication in Virtual Machines", IEEE Int'l Conference on Cluster Computing (Cluster 2008) - Tsukuba, Japan, September 2008 [pdf] [bibtex] [ Best Paper ]

@inproceedings{huangwei-cluster08,
  author = {W. Huang and M. Koop and D. K. Panda},
  title = {{Efficient One-Copy MPI Shared Memory Communication in Virtual Machines}},
  booktitle = {{IEEE Int'l Conference on Cluster Computing (Cluster 2008)}},
  month = {September},
  year = {2008},
  location = {Tsukuba, Japan}
}

R. Kumar, A. Mamidala, M. Koop, G. Santhanaraman and D. K. Panda, "Lock-free Asynchronous Rendezvous Design for MPI Point-to-point communication", EuroPVM/MPI 2008 - Dublin, Ireland, September 2008 [pdf] [bibtex]

@inproceedings{kumarra-europvm08,
  author = {R. Kumar and A. Mamidala and M. Koop and G. Santhanaraman and D. K. Panda},
  title = {{Lock-free Asynchronous Rendezvous Design for MPI Point-to-point communication}},
  booktitle = {{EuroPVM/MPI 2008}},
  month = {September},
  year = {2008},
  location = {Dublin, Ireland}
}

M. Koop, W. Huang, K. Gopalakrishnan and D. K. Panda, "Performance Analysis and Evaluation of PCIe 2.0 and Quad-Data Rate InfiniBand", 16th IEEE Int'l Symposium on Hot Interconnects (HotI16) - Palo Alto, CA, August 2008 [pdf] [bibtex]

@inproceedings{koop-hoti08,
  author = {M. Koop and W. Huang and K. Gopalakrishnan and D. K. Panda},
  title = {{Performance Analysis and Evaluation of PCIe 2.0 and Quad-Data Rate InfiniBand}},
  booktitle = {{16th IEEE Int'l Symposium on Hot Interconnects (HotI16)}},
  month = {August},
  year = {2008},
  location = {Palo Alto, CA}
}

M. Koop, R. Kumar and D. K. Panda, "Can Software Reliability Outperform Hardware Reliability on High Performance Interconnects? A Case Study with MPI over InfiniBand", 22nd ACM International Conference on Supercomputing (ICS08) - Island of Kos, Greece, June 2008 [pdf] [bibtex]

@inproceedings{koop-ics08,
  author = {M. Koop and R. Kumar and D. K. Panda},
  title = {{Can Software Reliability Outperform Hardware Reliability on High Performance Interconnects? A Case Study with MPI over InfiniBand}},
  booktitle = {{22nd ACM International Conference on Supercomputing (ICS08)}},
  month = {June},
  year = {2008},
  location = {Island of Kos, Greece}
}

M. Koop, T. Jones and D. K. Panda, "MVAPICH-Aptus: Scalable High-Performance Multi-Transport MPI over InfiniBand", IEEE Int'l Parallel and Distributed Processing Symposium (IPDPS 2008) - Miami, FL, April 2008 [pdf] [bibtex]

@inproceedings{koop-ipdps08,
  author = {M. Koop and T. Jones and D. K. Panda},
  title = {{MVAPICH-Aptus: Scalable High-Performance Multi-Transport MPI over InfiniBand}},
  booktitle = {{IEEE Int'l Parallel and Distributed Processing Symposium (IPDPS 2008)}},
  month = {April},
  year = {2008},
  location = {Miami, FL}
}

W. Huang, M. Koop, Q. Gao and D. K. Panda, "Virtual Machine Aware Communication Libraries for High Performance Computing", SuperComputing (SC07) - Reno, NV, November 2007 [pdf] [bibtex] [ Best Student Paper Finalist ]

@inproceedings{huangwei-sc07,
  author = {W. Huang and M. Koop and Q. Gao and D. K. Panda},
  title = {{Virtual Machine Aware Communication Libraries for High Performance Computing}},
  booktitle = {{SuperComputing (SC07)}},
  month = {November},
  year = {2007},
  location = {Reno, NV}
}

M. Koop, S. Sur and D. K. Panda, "Zero-Copy Protocol for MPI using InfiniBand Unreliable Datagram", IEEE Int'l Conference on Cluster Computing (Cluster 2007) - Austin, TX, September 2007 [pdf] [bibtex]

@inproceedings{koop-cluster07,
  author = {M. Koop and S. Sur and D. K. Panda},
  title = {{Zero-Copy Protocol for MPI using InfiniBand Unreliable Datagram}},
  booktitle = {{IEEE Int'l Conference on Cluster Computing (Cluster 2007)}},
  month = {September},
  year = {2007},
  location = {Austin, TX}
}

Q. Gao, W. Huang, M. Koop and D. K. Panda, "Group-based Coordinated Checkpointing for MPI: A Case Study on InfiniBand", International Conference on Parallel Processing (ICPP07) - XiAn, China, September 2007 [pdf] [bibtex]

@inproceedings{gaoq-icpp07,
  author = {Q. Gao and W. Huang and M. Koop and D. K. Panda},
  title = {{Group-based Coordinated Checkpointing for MPI: A Case Study on InfiniBand}},
  booktitle = {{International Conference on Parallel Processing (ICPP07)}},
  month = {September},
  year = {2007},
  location = {XiAn, China}
}

S. Sur, M. Koop, L. Chai and D. K. Panda, "Performance Analysis and Evaluation of Mellanox ConnectX InfiniBand Architecture with Multi-Core Platforms", 15th IEEE Int'l Symposium on Hot Interconnects (HotI15) - Palo Alto, CA, August 2007 [pdf] [bibtex]

@inproceedings{surs-hoti07,
  author = {S. Sur and M. Koop and L. Chai and D. K. Panda},
  title = {{Performance Analysis and Evaluation of Mellanox ConnectX InfiniBand Architecture with Multi-Core Platforms}},
  booktitle = {{15th IEEE Int'l Symposium on Hot Interconnects (HotI15)}},
  month = {August},
  year = {2007},
  location = {Palo Alto, CA}
}

M. Koop, S. Sur, Q. Gao and D. K. Panda, "High Performance MPI Design using Unreliable Datagram for Ultra-Scale InfiniBand Clusters", 21st ACM International Conference on Supercomputing (ICS07) - Seattle, WA, June 2007 [pdf] [bibtex]

@inproceedings{koop-ics07,
  author = {M. Koop and S. Sur and Q. Gao and D. K. Panda},
  title = {{High Performance MPI Design using Unreliable Datagram for Ultra-Scale InfiniBand Clusters}},
  booktitle = {{21st ACM International Conference on Supercomputing (ICS07)}},
  month = {June},
  year = {2007},
  location = {Seattle, WA}
}

W. Huang, J. Liu, M. Koop, B. Abali and D. K. Panda, "Nomad: Migrating OS-bypass Networks in Virtual Machines", 3rd International ACM Conference on Virtual Execution Environments (VEE07) - San Diego, CA, June 2007 [pdf] [bibtex]

@inproceedings{huangwei-vee07,
  author = {W. Huang and J. Liu and M. Koop and B. Abali and D. K. Panda},
  title = {{Nomad: Migrating OS-bypass Networks in Virtual Machines}},
  booktitle = {{3rd International ACM Conference on Virtual Execution Environments (VEE07)}},
  month = {June},
  year = {2007},
  location = {San Diego, CA}
}

M. Koop, T. Jones and D. K. Panda, "Reducing Connection Memory Requirements of MPI for InfiniBand Clusters: A Message Coalescing Approach", 7th IEEE Int'l Symposium on Cluster Computing and the Grid (CCGrid07) - Rio de Janeiro, Brazil, May 2007 [pdf] [bibtex]

@inproceedings{koop-ccgrid07,
  author = {M. Koop and T. Jones and D. K. Panda},
  title = {{Reducing Connection Memory Requirements of MPI for InfiniBand Clusters: A Message Coalescing Approach}},
  booktitle = {{7th IEEE Int'l Symposium on Cluster Computing and the Grid (CCGrid07)}},
  month = {May},
  year = {2007},
  location = {Rio de Janeiro, Brazil}
}

A. Vishnu, M. Koop, A. Moody, A. Mamidala, S. Narravula and D. K. Panda, "Hot-Spot Avoidance With Multi-Pathing Over InfiniBand: An MPI Perspective", 7th IEEE Int'l Symposium on Cluster Computing and the Grid (CCGrid07) - Rio de Janeiro, Brazil, May 2007 [pdf] [bibtex] [ Best Paper Finalist ]

@inproceedings{vishnu-ccgrid07,
  author = {A. Vishnu and M. Koop and A. Moody and A. Mamidala and S. Narravula and D. K. Panda},
  title = {{Hot-Spot Avoidance With Multi-Pathing Over InfiniBand: An MPI Perspective}},
  booktitle = {{7th IEEE Int'l Symposium on Cluster Computing and the Grid (CCGrid07)}},
  month = {May},
  year = {2007},
  location = {Rio de Janeiro, Brazil}
}

S. Sur, M. Koop and D.K. Panda, "High-Performance and Scalable MPI over InfiniBand with Reduced Memory Usage: An In-Depth Performance Analysis", SuperComputing (SC06) - Tampa, FL, November 2006 [pdf] [bibtex]

@inproceedings{surs-sc06,
  author = {S. Sur and M. Koop and D.K. Panda},
  title = {{High-Performance and Scalable MPI over InfiniBand with Reduced Memory Usage: An In-Depth Performance Analysis}},
  booktitle = {{SuperComputing (SC06)}},
  month = {November},
  year = {2006},
  location = {Tampa, FL}
}

M. Koop, W. Huang, A. Vishnu and D.K. Panda, "Memory Scalability Evaluation of the Next-Generation Intel Bensley Platform with InfiniBand", 14th IEEE Int'l Symposium on Hot Interconnects (HotI14) - Palo Alto, CA, August 2006 [pdf] [bibtex]

@inproceedings{koop-hoti06,
  author = {M. Koop and W. Huang and A. Vishnu and D.K. Panda},
  title = {{Memory Scalability Evaluation of the Next-Generation Intel Bensley Platform with InfiniBand}},
  booktitle = {{14th IEEE Int'l Symposium on Hot Interconnects (HotI14)}},
  month = {August},
  year = {2006},
  location = {Palo Alto, CA}
}

Teaching:

CSE201: Elementary Computer Programming
Autumn 2004, Winter 2005, Spring 2005, Autumn 2005

Grading:

CSE777: Telecommunication Networks
Spring 2008

CSE875: Advanced Computer Architecture
Spring 2007

Education:

Sep 2004 - Present: Ph.D. Student, The Ohio State University, Columbus, OH
Sep 2000 - May 2004: B.C.S. in Computer Science, Calvin College, Grand Rapids, MI

This page is XHTML 1.0 Strict validated