Hybrid Multicore and Exascale Computing for Scientific Applications

Funded by NSF, DOE/NNSA, and AFOSR

My group develops algorithms and software for multicore CPUs, GPUs, and heterogeneous computing systems. We focus on applications with sparse data and changing computational structure, including compressible multiphase turbulence, synthetic aperture radar reconstruction, and sparse matrix factorization.

The research addresses task-to-core mapping, dynamic load balancing, communication and synchronization, memory organization, and energy-aware scheduling. Our methods consider both computational performance and energy requirements, including dynamic voltage and frequency choices and reconfigurable caches.

Work on compressible multiphase turbulence includes particle–particle collision and particle–fluid interpolation algorithms, workload decomposition, and load balancing for large MPI-based simulations. Our sparse linear algebra work includes GPU implementations of Cholesky and QR factorization.

Related research develops scalable scientific-data compression and resilient scientific workflows. Awards listed in the July 2026 vitae include DOE RAPIDS3, MAGNET, and REDWOOD.

Selected Publications

1. A. Wijayasiri, T. Banerjee, S. Ranka, S. Sahni, and M. S. Schmalz. Multiobjective Optimization of SAR Reconstruction on Hybrid Multicore Systems. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13:4674-4688, 2020.
2. K. Zhai, T. Mishra, J. Hackl, D. Zwick, R. Koneru, and S. Ranka. Dynamic Load Balancing for a Mesh-Based Scientific Application. Concurrency and Computation: Practice and Experience, 32(9), Jan. 2020, 24 pp.
3. M. Gadou, T. Banerjee, M. Arunachalam, and S. Ranka. Multiobjective Evaluation and Optimization of CMT-Bone on Multiple CPU/GPU Systems. Sustainable Computing, 22:259–271, 2019.
4. M. Tang, M. Gadou, S. C. Rennich, T. A. Davis, and S. Ranka. Optimized Sparse Cholesky Factorization on Hybrid Multicore Architectures. Journal of Computational Science, 26:246–253, 2018.
5. S. N. Yeralan, T. A. Davis, W. M. Sid-Lakhdar, and S. Ranka. Algorithm 980: Sparse QR Factorization on the GPU. ACM Transactions on Mathematical Software, 44(2): article 17, July 2017, 29 pp.
6. M. Gadou, T. Banerjee, M. Arunachalam, G. Shipman, and S. Ranka. Multiobjective Evaluation and Optimization of CMT-Bone on Intel Knights Landing. Proceedings of IEEE International Green and Sustainable Computing, 2018, pp. 1–6. doi: 10.1109/IGCC.2018.8752152.
7. A. Wijayasiri, T. Banerjee, S. Ranka, S. Sahni, and M. Schmalz. Performance and Energy Evaluation of SAR Reconstruction on Intel Knights Landing. Proceedings of IEEE International Green and Sustainable Computing, 2018, pp. 1–8. doi: 10.1109/IGCC.2018.8752136.
8. M. Tang, M. Gadou, S. C Rennich, T. A Davis, and S. Ranka. A Multilevel Subtree Method for Single and Batched Sparse Cholesky Factorization. Proceedings of the 47th International Conference on Parallel Processing, 2018, pp. 50:1–50:10.