Compiler and runtime support for high-performance machine learning
Parallelization for data-intensive and compute-intensive applications
Programming models for irregular applications
Selected Publication:
Peng Jiang, Linchuan Chen, Gagan Agrawal. Revealing Parallel Scans and Reductions in Recurrences through Function Reconstruction. The 27th International Conference on Parallel Architectures and Compilation Techniques
Peng Jiang, Gagan Agrawal. A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication. Thirty-second Conference on Neural Information Processing Systems
Peng Jiang, Gagan Agrawal. Combining SIMD and Many/Multi-core Parallelism for Finite State Machines with Enumerative Speculation. Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
Peng Jiang, Gagan Agrawal. Efficient SIMD and MIMD Parallelization of Hash-based Aggregation by Conflict Mitigation. Proceedings of the 2017 International Conference on Supercomputing