Computer Scientist
Computer Scientist

Biography

Sayan Ghosh’s research interests broadly cover different aspects of high performance computing (HPC), including performance characterization and analysis, proxy application-driven codesign, and the application of standardized parallel programming models for building application kernels and developing one-sided/partitioned global address space communication abstractions.

Ghosh is particularly interested in analyzing the systems aspect (such as communication or memory accesses) of various irregular graph-based application scenarios (e.g., graph analytics and machine learning workloads) on HPC platforms.

Research Interest

  • High performance computing
  • Programming models and runtimes
  • Scalable graph analytics
  • Performance analysis
  • Hardware/software codesign
  • Partitioned global address space
  • One-sided communication models
  • Parallel machine learning
  • Proxy applications

Education

  • PhD in computer science, Washington State University
  • MS in computer science, University of Houston
  • BTech in information technology, Maulana Abul Kalam Azad University of Technology

Publications

2022

  • Gawande, N. A., S. Ghosh, M. Halappanavar, A. Tumeo, and A. Kalyanaraman. 2022. “Towards Scaling Community Detection on Distributed-Memory Heterogeneous Systems.” Parallel Computing 111. PNNL-SA-156736. doi:10.1016/j.parco.2022.102898.
  • Ghosh, S. 2022. “Improved Distributed-memory Triangle Counting by Exploiting the Graph Structure.” In IEEE High Performance Extreme Computing Conference (HPEC 2022), September 19–23, 2022, Virtual, Online, 1–6. Piscataway, New Jersey: IEEE. PNNL-SA-175362. doi:10.1109/HPEC55821.2022.9926376.
  • Ghosh, S., N. R. Tallent, and M. Halappanavar. 2022. “Characterizing Performance of Graph Neighborhood Communication Patterns.” IEEE Transactions on Parallel and Distributed Systems 33 (4): 915–928. PNNL-SA-152879. doi:10.1109/TPDS.2021.3101425.
  • Jain, M., S. Ghosh, and S. Nandanoori. 2022. “Workload Characterization of a Time Series Prediction System for Spatial-Temporal Data.” In 19th ACM International Conference on Computing Frontiers. New York, NY: Association for Computing Machinery. PNNL-SA-165281. doi:10.1145/3528416.3530242.
  • Lee, H., M. Jain, and S. Ghosh. 2022. “Sparse Deep Neural Network Inference using different Programming Models.” In IEEE High Performance Extreme Computing Conference (HPEC 2022), September 19–23, 2022, Waltham, MA, 1–6. Piscataway, New Jersey: IEEE. PNNL-SA-175380. doi:10.1109/HPEC55821.2022.9926362.

2021

  • Alexander, F. J., J. A. Ang, J. A. Bilbrey, J. Balewski, T. Casey, R. Chard, and J. Choi, et al. 2021. “Co-design Center for Exascale Machine Learning Technologies (ExaLearn).” The International Journal of High Performance Computing Applications 35 (6): 598–616. PNNL-SA-156070. doi:10.1177/10943420211029302.
  • Ghosh S., N. R. Tallent, M. Minutoli, M. Halappanavar, R. Peri, and A. Kalyanaraman. 2021. “Single-node Partitioned-Memory for Huge Graph Analytics: Cost and Performance Trade-offs.” In Proceedings of the International Conference for High Performance Computing, Network, Storage and Analysis (SC 2021), November 14–19, 2021, Virtual, Online, 55. New York, New York: Association for Computing Machinery. PNNL-SA-161359. doi:10.1145/3458817.3476156.
  • Ghosh S., Y. Guo, P. Balaji, and A. Gebremedhin. 2021. “RMACXX: An Efficient High-Level C++ Interface over MPI-3 RMA.” In Proceedings of the 21st IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid 2021), May 10–13, 2021, Virtual, 143–155. Piscataway, New Jersey: IEEE. PNNL-SA-158770. doi:10.1109/CCGrid51090.2021.00024.

2020

  • Halappanavar, M. and S. Ghosh. 2020. “TriC: Distributed-memory Triangle Counting by Exploiting the Graph Structure.” In IEEE High Performance Extreme Computing Conference (HPEC 2020), September 22–24, 2020, Waltham, MA, 1–6. Piscataway, New Jersey: IEEE. PNNL-SA-154840. doi:10.1109/HPEC43674.2020.9286167.

2019

  • Ghosh, S., M. Halappanavar, A. Kalyanaraman, M. H. Khan, and A. Gebremedhin. 2019. “Exploring MPI Communication Models for Graph Applications Using Graph Matching as a Case Study.” In IEEE 33rd International Parallel & Distributed Processing Symposium (IPDPS 2019), May 20–24, 2019, Rio de Janeiro, Brazil, 761–779. Los Alamitos, California: IEEE Computer Society. PNNL-SA-138882. doi:10.1109/IPDPS.2019.00085.
  • Ghosh, S., M. Halappanavar, A. Tumeo, A. Kalyanaraman, and A. Gebremedhin. 2019. “miniVite: A Graph Analytics Benchmarking Tool for Massively Parallel Systems.” In IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS 2018), November 12, 2018, Dallas, TX, 51–56. Piscataway, New Jersey: IEEE. PNNL-SA-138790. doi:10.1109/PMBS.2018.8641631.
  • Ghosh, S., M. Halappanavar, A. Tumeo, and A. Kalyanaraman. 2019. “Scaling and Quality of Modularity Optimization Methods for Graph Clustering.” In IEEE High Performance Extreme Computing Conference (HPEC 2019), September 24–26, 2019, Waltham, MA. Piscataway, New Jersey: IEEE. PNNL-SA-145324. doi:10.1109/HPEC.2019.8916299.

2018

  • Ghosh, S., M. Halappanavar, A. Tumeo, A. Kalyanaraman, and A. Gebremedhin. 2018. “Scalable Distributed Memory Community Detection Using Vite.” In IEEE High Performance Extreme Computing Conference (HPEC 2018), September 25–27, 2018, Waltham, MA, 1–7. Piscataway, New Jersey: IEEE. PNNL-SA-136309. doi:10.1109/HPEC.2018.8547534.
  • Ghosh, S., M. Halappanavar, A. Tumeo, A. Kalyanaraman, H. Lu, D.G. Chavarría-Miranda, and M. H. Khan, et al. 2018. “Distributed Louvain Algorithm for Graph Community Detection.” In IEEE International Parallel & Distributed Processing Symposium (IPDPS 2018), May 21–25, 2018, Vancouver, BC, 885–895. Los Alamitos, California: IEEE Computer Society. PNNL-SA-130211. doi:10.1109/IPDPS.2018.00098.