Chip Implementation of Accelerator, CIM, and Optical Solution for AI Applications
![Druckversion Druckversion](/sites/all/modules/print/icons/print_icon.gif)
![Per E-Mail senden Per E-Mail senden](/sites/all/modules/print/icons/mail_icon.gif)
![PDF-Version PDF-Version](/sites/all/modules/print/icons/pdf_icon.gif)
Prof. Chua-Chin Wang, Distinguished Professor and VP of R&D Office
Department of Electrical Engineering, National Sun Yat-Sen University, TW
Abstract
The presentation will cover 3 recent in-house chip designs for AI applications, which are as follows.
1. Hardware accelerator ASIC design and measurement
2. CIM (computation in memory) using single-ended SRAM cells.
3. Optical-based MAC based on MZI to realize the CNN convolution
Besides hardware implementation, brief theoretical introduction and performance comparison will be disclosed.
Contact information
http://vlsi.ee.nsysu.edu.tw/index_en.html
Email: ccwangee [dot] nsysu [dot] edu [dot] tw