Aokun Hu

According to our database, Aokun Hu authored at least 6 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

CoDA: A Co-Design Framework for Versatile and Efficient Attention Accelerators.

Wenjie Li, Aokun Hu, Ningyi Xu, Guanghui He

IEEE Trans. Computers, August, 2024

Quantization and Hardware Architecture Co-Design for Matrix-Vector Multiplications of Large Language Models.

Wenjie Li, Aokun Hu, Ningyi Xu, Guanghui He

IEEE Trans. Circuits Syst. I Regul. Pap., June, 2024

A Precision-Scalable Deep Neural Network Accelerator With Activation Sparsity Exploitation.

Wenjie Li, Aokun Hu, Ningyi Xu, Guanghui He

IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., January, 2024

Hardware-oriented algorithms for softmax and layer normalization of large language models.

Wenjie Li, Dongxu Lyu, Gang Wang, Aokun Hu, Ningyi Xu, Guanghui He

Sci. China Inf. Sci., 2024

2023

Low-Complexity Precision-Scalable Multiply-Accumulate Unit Architectures for Deep Neural Network Accelerators.

Wenjie Li, Aokun Hu, Gang Wang, Ningyi Xu, Guanghui He

IEEE Trans. Circuits Syst. II Express Briefs, April, 2023

2022

An Efficient Stochastic Convolution Accelerator based on Pseudo-Sobol Sequences.

Aokun Hu, Wenjie Li, Dongxu Lv, Guanghui He

Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, 2022