About Me
I am a PhD student at UC San Diego in the Alternative Computing Technologies (ACT) Lab, advised by Prof. Hadi Esmaeilzadeh, where my research focuses on cross-domain acceleration in robotics and domain-specific architectures and systems for LLMs. My work has appeared at top computer architecture venues, including ISCA, ASPLOS, and HPCA, and has been recognized with an IEEE Micro Top Picks Honorable Mention and selection as a Qualcomm Innovation Fellowship finalist. I am the lead contributor to GeneSys, an open-source end-to-end acceleration framework for emerging deep learning networks.
I received my Bachelor’s degree in Electrical and Computer Engineering at the University of Washington and my M.S. in Computer Engineering at the University of California, San Diego.
You can reach me through LinkedIn or at hax032 [at] ucsd [dot] edu!
Publications
Accelerator Polymorphism: Transcending Domain-Specific Architectures with Robotics
Hanyang Xu, SeongRyong Oh, Yubin Lee, Ashwin Rohit Alagiri Rajan, Rohan Mahapatra, Om Patil, Yuchuan Li, Jongse Park, Hadi Esmaeilzadeh
ISCA, 2026 [Paper] (To Appear)
In-Storage Acceleration of Retrieval Augmented Generation as a Service
Rohan Mahapatra, Harsha Santhanam, Christopher Priebe, Hanyang Xu, Hadi Esmaeilzadeh
ISCA, 2025 [Paper]
Tandem Processor: Grappling with Emerging Operators in Neural Networks
Soroush Ghodrati, Sean Kinzer, Hanyang Xu, Rohan Mahapatra, Yoonsung Kim, Byung Hoon Ahn, Dong Kai Wang, Lavanya Karthikeyan, Amir Yazdanbakhsh, Jongse Park, Nam Sung Kim, Hadi Esmaeilzadeh
ASPLOS, 2024 [Paper]
In-Storage Domain-Specific Acceleration for Serverless Computing
Rohan Mahapatra, Soroush Ghodrati, Byung Hoon Ahn, Sean Kinzer, Shu-Ting Wang, Hanyang Xu, Lavanya Karthikeyan, Hardik Sharma, Amir Yazdanbakhsh, Mohammad Alian, Hadi Esmaeilzadeh
ASPLOS, 2024 [Paper]
Data Motion Acceleration: Chaining Cross-Domain Multi Accelerators
Shu-Ting Wang, Hanyang Xu, Amin Mamandipoor, Rohan Mahapatra, Byung Hoon Ahn, Soroush Ghodrati, Krishnan Kailas, Mohammad Alian, Hadi Esmaeilzadeh
HPCA, 2024 [Paper]
GENERIC: Highly Efficient Learning Engine on Edge Using Hyperdimensional Computing
Behnam Khaleghi, Jaeyoung Kang, Hanyang Xu, Justin Morris, Tajana Rosing
DAC, 2022 [Paper]
VeriGOOD-ML: An Open-Source Flow for Automated ML Hardware Synthesis
Hadi Esmaeilzadeh, Soroush Ghodrati, Jie Gu, Shiyu Guo, Andrew B. Kahng, Joon Kyung Kim, Sean Kinzer, Rohan Mahapatra, Susmita Dey Manasi, Edwin Mascarenhas, Sachin S. Sapatnekar, Ravi Varadarajan, Zhiang Wang, Hanyang Xu, Brahmendra Reddy Yatham, Ziqing Zeng
ICCAD, 2021 [Paper]
tiny-HD: Ultra-Efficient Hyperdimensional Computing Engine for IoT Applications
Behnam Khaleghi, Hanyang Xu, Justin Morris, Tajana Šimunić Rosing
DATE, 2021 [Paper]
Splatty — A Unified Image Demosaicing and Rectification Method
Pulkit Verma, Dominique E. Meyer, Hanyang Xu, Falko Kuester
WACV, 2021 [Paper]
Patents
Architectures and Instruction Sets for Non-General Matrix Multiplication Operations
Hadi Esmaeilzadeh, Soroush Ghodrati, Sean Kinzer, Rohan Mahapatra, Hanyang Xu
U.S. Patent Application 18/803,386, 2026 [Patent]
Deep Neural Network Operation via Patterned Filter Clustering and Activation Group Reuse
Behnam Khaleghi, Jaeyoung Kang, Hanyang Xu, Justin Morris, Tajana Rosing, Uday Bhanu Sharma Mallappa, Haichao Yang, Monil Shah
U.S. Patent Application 18/441,569, 2024 [Patent]
High-Dimensional Vector Space Encoding Techniques for Hyperdimensional Computing Systems
Behnam Khaleghi, Jaeyoung Kang, Hanyang Xu, Justin Morris, Tajana Rosing, Uday Bhanu Sharma Mallappa, Haichao Yang, et al.
U.S. Patent Application 18/441,318, 2024 [Patent]
Open-Source Projects
GeneSys — I am a major contributor to the architecture, implementation, verification, and bring-up of the GeneSys accelerator architecture and its compilation stack. We have hosted GeneSys workshops at all major computer architecture conferences: MICRO’23 [Workshop], HPCA’24 [Workshop], ASPLOS’24 [Workshop] [Talk], and ISCA’24 [Workshop].
Honors & Awards
- Qualcomm Innovation Fellowship — Finalist, 2024
- IEEE Micro Top Picks 2024 — Honorable Mention
Teaching
- CSE 240D: System Design for Machine Intelligence — UC San Diego, Spring 2026. Co-planned, co-taught, and led discussions for this graduate-level course on advanced computer architecture for LLMs (with Prof. Hadi Esmaeilzadeh).
- CSE 240A: Principles of Computer Architecture — UC San Diego, Fall 2024. Lead TA: led discussion sections and office hours, and prepared homework and exams (with Prof. Hadi Esmaeilzadeh).
Education
- Ph.D. in Computer Science, University of California, San Diego (in progress)
- M.S. in Computer Engineering, University of California, San Diego
- B.S. in Electrical & Computer Engineering, University of Washington