Hongzheng Tian

Ph.D. Candidate in Computer Engineering, University of California, Irvine

prof_pic.jpg

EECS, UC Irvine

CORSA Research Group

hongzhet [at] uci [dot] edu

I am a Ph.D. candidate in Computer Engineering at the EECS Department of the University of California, Irvine, advised by Prof. Sitao Huang in the CORSA research group.

My research lies at the intersection of compilers, optimization, and heterogeneous computing. I build compiler and benchmarking systems that translate high-level workloads into efficient, architecture-aware code targeting CPUs, GPUs, and FPGAs. My recent work studies benchmark design, MLIR-based compilation, task scheduling, and hardware/software co-optimization for diverse accelerator platforms.

I am broadly interested in compiler infrastructure for heterogeneous systems, performance portability, accelerator design automation, and practical tools that help researchers and developers reason about efficiency across modern hardware.

news

May 01, 2025 HeteroBench received the Best Paper Award - Artifact Track at ICPE 2025.
Nov 17, 2024 Presented CoVA at the SC24 ACM Student Research Competition.
Oct 01, 2024 Published work on optimized spatial architecture mapping for Transformer accelerators on arXiv.

selected publications

  1. HeteroBench: Multi-kernel Benchmarks for Heterogeneous Systems
    Hongzheng Tian, Alok Mishra, Zhiheng Chen, and 4 more authors
    In Proceedings of the ACM/SPEC International Conference on Performance Engineering, 2025
  2. arXiv
    Optimized Spatial Architecture Mapping Flow for Transformer Accelerators
    Haocheng Xu, Faraz Tahmasebi, Ye Qiao, and 3 more authors
    arXiv preprint arXiv:2410.07407, 2024
  3. SC
    CoVA: An MLIR-Based Compilation Flow for Versatile Architecture
    Hongzheng Tian, Alok Mishra, and Sitao Huang
    2024
  4. A Sparsity-Aware Autonomous Path Planning Accelerator with HW/SW Co-Design and Multi-Level Dataflow Optimization
    Yifan Zhang, Xiaoyu Niu, Hongzheng Tian, and 4 more authors
    In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, 2024
  5. DAC
    PyAIE: A Python-based Programming Framework for Versal ACAP AI Engines
    Hongzheng Tian, Shining Yang, Yoonha Cha, and 1 more author
    2023