3 papers
cs.AR2023
PIM-GPT: A Hybrid Process-in-Memory Accelerator for Autoregressive Transformers
Yuting Wu, Ziyu Wang, Wei D. Lu
Decoder-only Transformer models such as GPT have demonstrated exceptional performance in text generation, by autoregressively predicting the next token. However, the efficacy of ru…
cs.CR2023
PowerGAN: A Machine Learning Approach for Power Side-Channel Attack on Compute-in-Memory Accelerators
Ziyu Wang, Yuting Wu, Yongmo Park +4
Analog compute-in-memory (CIM) systems are promising for deep neural network (DNN) inference acceleration due to their energy efficiency and high throughput. However, as the use of…
cs.AR2023
Bulk-Switching Memristor-based Compute-In-Memory Module for Deep Neural Network Training
Yuting Wu, Qiwen Wang, Ziyu Wang +5
The need for deep neural network (DNN) models with higher performance and better functionality leads to the proliferation of very large models. Model training, however, requires in…