A 5–11 GHz 8-bit Precision Passive True-Time Delay in 65-nm CMOS Technology
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3150313
Abstract: In this paper, we present an 8-bit precision passive true-time delay (TTD) operating at 5–11 GHz in 65-nm CMOS technology. To achieve a precision time delay control, the 8-bit TTD employs a 4-bit time delay… read more here.
Keywords: time delay; delay; bit; precision passive ... See more keywords
Design of Processing-in-Memory With Triple Computational Path and Sparsity Handling for Energy-Efficient DNN Training
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Journal on Emerging and Selected Topics in Circuits and Systems"
DOI: 10.1109/jetcas.2022.3168852
Abstract: As machine learning (ML) and artificial intelligence (AI) have become mainstream technologies, many accelerators have been proposed to cope with their computation kernels. However, they access the external memory frequently due to the large size… read more here.
Keywords: bit; training; pim; energy ... See more keywords
A Mobile DNN Training Processor With Automatic Bit Precision Search and Fine-Grained Sparsity Exploitation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Micro"
DOI: 10.1109/mm.2021.3135457
Abstract: In this article, an energy-efficient deep learning processor is proposed for deep neural network (DNN) training in mobile platforms. Conventional mobile DNN training processors suffer from high-bit precision requirement and high ReLU-dependencies. The proposed processor… read more here.
Keywords: training; dnn training; bit precision; processor ... See more keywords