Analog-memory-based 14nm Hardware Accelerator for Dense Deep Neural Networks including Transformers
- Atsuya Okazaki
- Pritish Narayanan
- et al.
- 2022
- ISCAS 2022
Atsuya Okazaki
Pronouns
He/Him/His
Title
Senior Research Scientist, IBM Research - Tokyo
Publications
Fully On-Chip MAC at 14 nm Enabled by Accurate Row-Wise Programming of PCM-Based Weights and Parallel Vector-Transport in Duration-Format
- Pritish Narayanan
- Stefano Ambrogio
- et al.
- 2021
- IEEE T-ED
Fully on-chip MAC at 14nm enabled by accurate row-wise programming of PCM-based weights and parallel vector-transport in duration-format
- P. Narayanan
- S. Ambrogio
- et al.
- 2021
- VLSI 2021
On-Chip Trainable 1.4M 6T2R PCM Synaptic Array with 1.6K Stochastic LIF Neurons for Spiking RBM
- Masatoshi Ishii
- U. Shin
- et al.
- 2019
- IEDM 2019
Analysis of Effect of Weight Variation on SNN Chip with PCM-Refresh Method
- A. Nomura
- M. Ito
- et al.
- 2019
- Neural Processing Letters
Lightweight Refresh Method for PCM-based Neuromorphic Circuits
- M. Ito
- Masatoshi Ishii
- et al.
- 2018
- NANO 2018
Software-defined massive multicore networking via freespace optical interconnect
- Yasunao Katayama
- Atsuya Okazaki
- et al.
- 2013
- CF 2013
Universal optical multi-drop bus for heterogeneous memory architecture
- Atsuya Okazaki
- Yasunao Katayama
- et al.
- 2011
- CF 2011
Optical interconnect opportunities for future server memory systems
- Y. Katayama
- A. Okazaki
- 2007
- HPCA 2007
Patents
- GB
- 2620509
- CN
- ZL201980008114.1
- JP
- 7413367
- TW
- I820686
- US
- 11789857
- US
- 11763139
- JP
- 7228320
- US
- 11475946
- GB
- 2583302
- GB
- 2593081
Projects
Making Deep Neural Network systems more capable and energy-efficient.
Top collaborators
MI
Masatoshi Ishii
Research Scientist
AN
Akiyo Nomura
Staff Research Scientist
ST
Sidney Tsai
Manager, PRSM, AI Hardware and Cloud/AI for EDA
GB
Geoffrey Burr
Distinguished RSM