Details
Poster
Presenter(s)
![Udara De Silva Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/18151.jpg?h=fbf7a813&itok=JZ_6HGMO)
Display Name
Udara De Silva
- Affiliation
-
AffiliationFlorida International University
- Country
Abstract
The high adoption rate of deep learning has set new demands on computational throughput, latency, and power efficiency of the computing infrastructure. Hence, there is renewed interest in high-frequency analog circuits for deep learning inference. This paper presents early work on the design of an analog CMOS accelerator that performs CNN inference in parallel and in real-time. The accelerator was designed in a 45 nm CMOS process and simulated in Cadence Spectre. The proposed solution also employs Xilinx RF System-on-Chip (SoC) devices to interface digital inputs and outputs with the proposed RF-rate inference accelerator.