Bio

My research interests lie broadly at the intersection between computer architecture, systems software, and applications. In particular, my current research activities spawn different directions: design of programming models, compiler and runtime techniques for heterogeneous systems containing coprocessor devices; acceleration of bioinformatics, pattern recognition, and data analytics algorithms on parallel architectures; and high-speed implementation of networking applications (e.g., deep packet inspection). I am interested in any kind of parallel hardware: multi-core CPUs, GPUs and other many-core devices, network processors, field programmable gate arrays, and clusters of computers. I enjoy working at the boundary between hardware and software.

Publications

• Exploring Sparse Matrix Multiplication Kernels on the Cerebras CS-3 , arXiv (Cornell University) (2026)
• A Comprehensive Analysis of Graph Neural Networks Training at Different Scales , IEEE International Symposium on Workload Characterization (2025)
• DIMPLES: Distributed Influence Maximization for Pandemic pLanning on Exascale Systems , ACM International Conference on Supercomputing (ICS) (2025)
• Exploring Lossy Compression of Activation Data for Emerging AI Accelerators: A Case Study on the Graphcore IPU , IEEE International Symposium on Workload Characterization (2025)
• A Portable, Fast, DCT-based Compressor for AI Accelerators , ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) (2024)
• A Transducers-based Programming Framework for Efficient Data Transformation , International Conference on Parallel Architectures and Compilation Techniques (2024)
• FuseIM: Fusing Probabilistic Traversals for Influence Maximization on Exascale Systems , ACM International Conference on Supercomputing (ICS) (2024)
• Picasso: Memory-Efficient Graph Coloring Using Palettes With Applications in Quantum Computing , Proceedings - IEEE International Parallel and Distributed Processing Symposium (2024)
• Significantly Improving Fixed-Ratio Compression Framework for Resource-limited Applications , Proceedings of the International Conference on Parallel Processing (2024)
• A Code Transformation to Improve the Efficiency of OpenCL Code on FPGA through Pipes , ACM International Conference on Computing Frontiers (CF) (2023)

View all publications