Zhihao Shu

Zhihao Shu

Auto-generated profile, based on publicly available information

Zhihao Shu

University of Georgia, Athens, GA, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 April 2024
Verified
Conference Paper
Open access
WNWei Niu
Wei Niu
MSMusfiqur Rahman Sanim
Musfiqur Rahman Sanim
ZSZhihao Shu
Zhihao Shu
JGJiexiong Guan
Jiexiong Guan
XSXipeng Shen
Xipeng Shen
BRBin Ren
Bin Ren
This work is motivated by recent developments in Deep Neural Networks, particularly the Transformer architectures underlying applications such as ChatGPT, and the need for performing inference on mobile devices. Focusing on emerging transformers (specifically the ones with computationally efficient Swin-like architectures) and large models (e.g., Stable Diffusion and LLMs) based on transformers, we observe that layout transformations between the computational operators cause a significant slowdown in these applications. This paper presents SmartMem, a comprehensive framework for eliminating most layout transformations, with the idea that multiple operators can use the same tensor layout through careful choice of layout and implementation of operations. Our approach is based on classifying the operators into four groups, and considering combinations of producer-consumer edges between the operators. We develop a set of methods for searching such layouts. Another component of our work is developing efficient memory layouts for 2.5 dimensional memory commonly seen in mobile devices. Our experimental results show that SmartMem outperforms 5 state-of-the-art DNN execution frameworks on mobile devices across 18 varied neural networks, including CNNs, Transformers with both local and global attention, as well as LLMs. In particular, compared to DNNFusion, SmartMem achieves an average speedup of 2.8×, and outperforms TVM and MNN with speedups of 6.9× and 7.9×, respectively, on average.

7 November 2026
Verified
Conference Paper
Open access
HZHangyu Zheng
Hangyu Zheng
ZSZhihao Shu
Zhihao Shu
KZKunxiong Zhu
Kunxiong Zhu
MQMinghai Qin
Minghai Qin
XMXiaolong Ma
Xiaolong Ma
WNWei Niu
Wei Niu

22 March 2026
Verified
Conference Paper
Open access
ZSZhihao Shu
Zhihao Shu
MSMusfiqur Rahman Sanim
Musfiqur Rahman Sanim
HZHangyu Zheng
Hangyu Zheng
KZKunxiong Zhu
Kunxiong Zhu
MYMiao Yin
Miao Yin
WNWei Niu
Wei Niu