About Me

I am a Staff Software Engineer at Google, working on large-scale AI systems to enable efficienct Gemini training and serving on TPUs. My research interests include AI Systems, Energy-efficient Computing, and Hardware/Software Co-design.

Before I joined Google, I received my Ph.D. from the University of Illinois Urbana-Champaign (UIUC) in 2022. I was a Google Ph.D. Fellow and Mavis Future Faculty Fellow. My research was conducted under the supervision of Prof. Deming Chen, with close collaboration with Prof. Wen-mei Hwu and Prof. Junjun Xiong. I completed my B.S. and M.S. at UESTC in Chengdu, China.

News

JUL

2022

Successfully defended my Ph.D. Thesis

My thesis, Efficient AI Hardware Acceleration, is now available for open access.

OCT

2020

Xiaofan Receives 2020 Google Ph.D. Fellowship

Awarded the prestigious Google Ph.D. Fellowship, recognized as the only recipient in the mobile computing area worldwide for exceptional and innovative research.

Show 3 more items ↓

Publications

2025

ASAP: an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training

Yuran Ding, Xinwei Chen, Xiaofan Zhang, Zongwei Zhou.

Conference on Neural Information Processing Systems (NeurIPS) ML for Systems Workshop, Dec. 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gemini Team.

arXiv preprint arXiv:2507.06261, July 2025.

Reconfigurable Stream Network Architecture

Chengyue Wang, Xiaofan Zhang, Jason Cong, James C. Hoe.

International Symposium on Computer Architecture (ISCA), Jun. 2025.

Profile-Guided Quantization: a compiler solution to automate quantization for efficient LLM training

Gil Tabak, Clemens JS Schaefer, Xiaofan Zhang, Denali Molitor, Jinliang Wei, Zongwei Zhou, Philip G Hendrix, Mitchelle Rasquinha.

International Symposium on Computer Architecture (ISCA) workshop on Machine Learning for Computer Architecture and Systems (MLArchSys), Jun. 2025.

SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training

Kun Wu*, Jeongmin Brian Park*, Xiaofan Zhang*, Mert Hidayetoğlu, Vikram Sharma Mailthody, Sitao Huang, Steven Sam Lumetta, Wen-mei Hwu. (*equal contributors)

Design Automation Conference (DAC), Jun. 2025.

Show more publications ↓

Awards & Fellowships

Google Gold Perfy Award

2024, 2025

Google Silver Perfy Award

2023

Google Ph.D. Fellowship

2020, 2021

ACM Student Research Competition Winner Award (ICCAD)

2021

Mavis Future Faculty Fellowship (MF3)

2021

Rambus Computer Engineering Fellowship

2021

Sundaram Seshu International Student Fellowship

2020
Show more ↓

Service

Peer Reviewer

Journal Reviewer

  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)
  • IEEE Transactions on Circuits and Systems Part II (TCAS-II)
  • IEEE Embedded Systems Letters (ESL)
  • ACM Transactions on Reconfigurable Technology and Systems (TRETS)

Conference Technical Program Committee / Reviewer

  • 2025 International Symposium on Computer Architecture (ISCA) Workshop on Machine Learning for Computer Architecture and Systems (MLArchSys)
  • 2025 ACM/IEEE Design Automation Conference (DAC)
  • 2024 IEEE International Workshop on LLM-Aided Design (LAD)
  • 2023 - 2024 ACM/IEEE International Conference on Computer-Aided Design (ICCAD)
  • 2023 ACM/IEEE Supercomputing Conference (SC)
  • 2023 Great Lakes Symposium on VLSI (GLSVLSI)
  • 2023 Conference on Machine Learning and Systems (MLSys)
  • 2016 - 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)
  • 2018 - 2022 IEEE International Symposium On Field-Programmable Custom Computing Machines (FCCM)

Session Chair / Competition Judge

  • Technical Session Chair: 2024 ICCAD: Architectural Mapping
  • Technical Session Chair: 2024 ICCAD: Applications and Architectures
  • Technical Session Chair: 2023 ICCAD: Sustainable AI Training at the Large and Tiny Scales
  • Competition Judge: 2023 ACM Student Research Competition at ICCAD
  • Competition Judge: 2023 Ph.D. Forum at FCCM
  • Competition Judge: 2022 ACM Student Research Competition at ICCAD

Teaching

  • Guest Lecturer: ELEC 515: Embedded Machine Learning: FPGA for AI Inference (Rice University, Fall 2020)
  • Topic: Hardware Accelerator Design and Development

  • Guest Lecturer: IEEE Council on Electronic Design Automation (CEDA) Lecture Series
  • Topic: FPGA-based Accelerator Design for AI Inference

  • Head Teaching Assistant: ECE 498 ICC: IoT and Cognitive Computing (UIUC, Spring 2020)
  • Teaching Assistant: ECE 498 ICC: IoT and Cognitive Computing (UIUC, Spring 2019)