Fully on-chip MAC at 14nm enabled by accurate row-wise programming of PCM-based weights and parallel vector-transport in duration-formatP. NarayananS. Ambrogioet al.2021VLSI 2021
An analog-AI chip for energy-efficient speech recognition and transcriptionS. AmbrogioPritish Narayananet al.2023Nature
Analog-memory-based 14nm Hardware Accelerator for Dense Deep Neural Networks including TransformersAtsuya OkazakiPritish Narayananet al.2022ISCAS 2022
Fully On-Chip MAC at 14 nm Enabled by Accurate Row-Wise Programming of PCM-Based Weights and Parallel Vector-Transport in Duration-FormatPritish NarayananStefano Ambrogioet al.2021IEEE T-ED