Assistant Professor, CSE department @ University of California Merced.
Hyeran Jeon's main research interests lie in energy-efficient, reliable and secure computer architecture and systems design. Her research lab has been sponsored by National Science Foundation, California Energy Commission, LAM Research, NVIDIA (equipment), and Xilinx. She earned her Ph.D. at the University of Southern California, under the supervision of Prof. Murali Annavaram, where she received Viterbi dean’s doctoral fellowship. She has industry experiences as an intern at IBM T.J. Watson Research Center and AMD Research, and as a systems software engineer at Samsung Electronics.
* I am looking for PhD students. If you are interested in research on computer architecture in general, GPU architecture, deep learning acceleration, or heterogeneous system, submit an application with my name marked as your faculty interest (here).
Why UC Merced? UC Merced campus is in 2-hour proximity from Silicon Valley. We are the youngest campus in the prestigious University of California system. Students will get the same benefit with the other campuses inspite of cheaper living expenses. Check our ranking for computer architecture and high-performance research here.
Selected Publications (link to full list, google scholar)
[BOOK CHAPTER] Jeon, H. (2023). GPU Architecture. In: Chattopadhyay, A. (eds) Handbook of Computer Architecture. Springer.
[STANDARD] IEEE Recommended Practice for Developing Energy-Efficient Power-Proportional Digital Architectures IEEE 1924.1 2022
Too Noisy To Extract: Pitfalls of Model Extraction Attacks, NOPE In conjunction with ASPLOS 2022
Sentinel: Efficient Tensor Migration and Allocation on Heterogeneous Memory Systems for Deep Learning, HPCA 2021
Locality-aware GPU Register File, IEEE CAL 2019
Tango: A Deep Neural Network Benchmark Suite for Various Accelerators, ISPASS 2019
CORF: Coalescing Operand Register File for GPUs, ASPLOS 2019
Pilot Register File: Energy Efficient Partitioned Register File for GPUs, HPCA 2017
Efficient Intra-SM Slicing through Dynamic Resource Partitioning for GPU Multiprogramming, ISCA 2016
GPGPU Register File Virtualization, MICRO 2015
Warped-Compression: Enabling Power Efficient GPUs through Register Compression, ISCA 2015
Warped-DMR: Light-weight Error Detection for GPGPU, MICRO 2012
I will serve as an Artifact Evaluation Co-chair for ASPLOS'24.
We received an NSF IUCRC fund for founding the Center for Memory System Research (CEMSYS)! Lots of interesting research activities will follow between UC Merced, UC Davis, and the potential industry partners!!
The discussions made at the HCM workshop is summarized in a SigArch blog post. Hope this article helps guide current/future research on HCM.
The GPU Architecture chapter of the Handbook of Computer Architecture (Springer) is published! Hope you find it helpful for understanding GPU architectures.
Yuan got a summer internship from Alibaba Group. Congrats!
Our paper on fault tolerance for converged computing platforms is accepted in WOCC, co-located with ISC'23.
Our work-in-progress paper about performance scalability on multi-GPU systems has been accepted to GPGPU'23! Congrats, Yuan!
Hoa successfully finished his master project and will join MathWorks in Jan! Congrats, Hoa!
I am co-chairing a brand new workshop on Heterogeneous and Composable Memory, HCM'23, co-located with HPCA'23. Please submit your preliminary work in 2-page abstract and get feedback from our expert PC members. The due is 12/12.
I am co-chairing GPGPU'23. The paper due is 12/9. Please consider submitting your work!
Yuan presented at SRC poster session at MICRO about his on-going work on memoization!
IEEE TCuARCH that I am serving on the executive committee is running a new Youtube Channel, People in Computer Architecture. Please visit and learn about the community.
IEEE Standard on Power-Proportional Digital Architectures (1924.1) that I co-authored as a co-vice chair and a co-secretary has been published! The standard provides guidelines for the designers and developers of digital architectures for creating power-proportionality at different levels of the system.
CWIDCA will be held with MICRO in Oct. Please consider submitting a poster and travel application!
I will serve on the program committee for ISCA'23. Submit your best work to ISCA!
I will serve on the program committee for HPCA'23. Submit your best work to HPCA!
Our work on the characterization of semantic segmentation models for self-navigation system is accepted to IEEE Access. Congrats, Ryan!
Aishwaria and Xavier will join MoCA Lab as summer interns. Welcome!
Dr. Gabe Loh will visit us to give a CITRIS-FIT talk about the Chiplet design of AMD Research!
Prof. Dongyoon Lee from Stony Brook University visited us for giving a talk about the security issues of regex engines!
REU fund is granted for our Secure GPU project. Thank you, NSF!