RaPiD: AI Accelerator for Ultra-Low Precision Training and Inference
- Swagath Venkataramani
- Vijayalakshmi Srinivasan
- et al.
- 2021
- ISCA 2021
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
24 results for Ankur Agrawal
Ultra-Low Precision 4-bit Training of Deep Neural Networks
- Xiao Sun
- Naigang Wang
- et al.
- 2020
- NeurIPS 2020
A Switched-Capacitor Integer Compute Unit with Decoupled Storage and Arithmetic for Cloud AI Inference in 5nm CMOS
- Ankur Agrawal
- Monodeep Kar
- et al.
- 2023
- VLSI Technology 2023
A 7nm 4-Core AI Chip with 25.6TFLOPS Hybrid FP8 Training, 102.4TOPS INT4 Inference and Workload-Aware Throttling
- Ankur Agrawal
- Saekyu Lee
- et al.
- 2021
- ISSCC 2021
Accumulation bit-width scaling for ultra-low precision training of deep networks
- Charbel Sakr
- Naigang Wang
- et al.
- 2019
- ICLR 2019
ADaComP: Adaptive residual gradient compression for data-parallel distributed training
- Chia-Yu Chen
- Jungwook Choi
- et al.
- 2018
- AAAI 2018
INVITED: Accelerator Design for Deep Learning Training: Extended Abstract: Invited
- Ankur Agrawal
- Chia-Yu Chen
- et al.
- 2017
- DAC 2017
A 25Gb/s ADC-based serial line receiver in 32nm CMOS SOI
- Sergey V. Rylov
- Troy Beukema
- et al.
- 2016
- ISSCC 2016
Deep learning with limited numerical precision
- Suyog Gupta
- Ankur Agrawal
- et al.
- 2015
- ICML 2015
An integrated silicon photonics technology for O-band datacom
- N. Feilchenfeld
- Frederick A. Anderson
- et al.
- 2015
- IEDM 2015