Impact of Phase-Change Memory Drift on Energy Efficiency and Accuracy of Analog Compute-in-Memory Deep Learning Inference (Invited)-Reference-Cited by-同舟云学术

Impact of Phase-Change Memory Drift on Energy Efficiency and Accuracy of Analog Compute-in-Memory Deep Learning Inference (Invited)

Published:2023-03 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE International Reliability Physics Symposium (IRPS)
language:
Short-container-title:

Author:

Frank Martin M.¹,Li Ning¹,Rasch Malte J.¹,Jain Shubham¹,Chen Ching-Tzu¹,Muralidhar Ramachandran¹,Han Jin-Ping¹,Narayanan Vijay¹,Philip Timothy M.²,Brew Kevin²,Simon Andrew²,Saraf Iqbal²,Saulnier Nicole²,Boybat Irem³,Woźniak StanisŁaw³,Sebastian Abu³,Narayanan Pritish⁴,Mackin Charles⁴,Chen An⁴,Tsai Hsinyu⁴,Burr Geoffrey W.⁴

Affiliation:

1. IBM T. J. Watson Research Center,NY,USA

2. IBM Research - Albany,Albany,NY,USA

3. IBM Research - Zurich,Rüschlikon,Switzerland

4. IBM Research - Almaden,San Jose,CA,USA

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10117589/10117581/10117874.pdf?arnumber=10117874

Reference47 articles.

1. HERMES-Core—A 1.59-TOPS/mm² PCM on 14-nm CMOS In-Memory Compute Core Using 300-ps/LSB Linearized CCO-Based ADCs

2. Optimization of Projected Phase Change Memory for Analog In‐Memory Computing Inference

3. HERMES Core – A 14nm CMOS and PCM-based In-Memory Compute Core using an array of 300ps/LSB Linearized CCO-based ADCs and local digital processing

4. Design of projected phase-change memory mushroom cells for low-resistance drift

5. An 8-Mb DC-Current-Free Binary-to-8b Precision ReRAM Nonvolatile Computing-in-Memory Macro using Time-Space-Readout with 1286.4-21.6TOPS/W for Edge-AI Devices

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Prospects and challenges of electrochemical random-access memory for deep-learning accelerators;Current Opinion in Solid State and Materials Science;2024-09

2. Resistive Processing Unit-based On-chip ANN Training with Digital Memory;2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS);2024-04-22