IG-CRM: Area/Energy-Efficient IGZO-Based Circuits and Architecture Design for Reconfigurable CIM/CAM Applications
Authors: 
Zeyu Guo, Jinshan Yue, Shengzhe Yan, Zhuoyu Dai, Xiangqu Fu, Zhaori Cong, Zening Niu, Ke Hu, Lihua Xu, Jiawei Wang, Lingfei Wang, Guanhua Yang, Di Geng, Ling LiAuthors Info & Claims
Zeyu Guo, Jinshan Yue, Shengzhe Yan, Zhuoyu Dai, Xiangqu Fu, Zhaori Cong, Zening Niu, Ke Hu, Lihua Xu, Jiawei Wang, Lingfei Wang, Guanhua Yang, Di Geng, Ling LiAuthors Info & ClaimsArticle No.: 57, Pages 1 - 6
Abstract
Artificial intelligence is evolving with various algorithms such as deep neural network (DNN), Transformer, recommendation system (RecSys) and graph convolutional network (GCN). Correspondingly, multiply-accumulate (MAC) and content search are two main operations, which can be efficiently executed on the emerging computing-in-memory (CIM) and content-addressable-memory (CAM) paradigms. Recently, the emerging Indium-Gallium-Zine-Oxide (IGZO) transistor becomes a promising candidate for both CIM/CAM circuits, featuring ultra-low leakage with >300s data retention time and high-density BEOL fabrication. This paper proposes IG-CRM, the first IGZO-based circuits and architecture design for Reconfigurable CIM/CAM applications. The main contributions include: 1) at cell level, propose IGZO-based 3T0C/4T0C cell design that enables both CIM and CAM functionalities while matching IGZO/CMOS voltage; 2) at circuit level, utilize the BEOL IGZO transistor to reduce digital adder tree area in CIM circuits; 3) at architecture level, propose a reconfigurable CIM/CAM architecture with four macro structures based on 3T0C/4T0C cells. The proposed IG-CRM architecture shows high area/energy efficiency on various applications including DNN, Transformer, RecSys and GCN. Experiment results show that IG-CRM achieves 8.09X area saving compared with the SRAM-based non-reconfigurable CIM/CAM baseline, and 1.53×103X/51.9X speedup and 1.63×104X/7.62×103X energy efficiency improvement compared with CPU and GPU on average.
References
[1]
Kaiming He et al. "Deep residual learning for image recognition". In: Proceedings of IEEE conference on computer vision and pattern recognition. 2016, pp. 770--778.
[2]
Alexey Dosovitskiy et al. "An image is worth 16×16 words: Transformers for image recognition at scale". In: arXiv preprint arXiv:2010.11929 (2020).
[3]
Maxim Naumov et al. "Deep learning recommendation model for personalization and recommendation systems". In: arXiv preprint arXiv:1906.00091 (2019).
[4]
Thomas N Kipf and Max Welling. "Semi-supervised classification with graph convolutional networks". In: arXiv preprint arXiv:1609.02907 (2016).
[5]
Chuan-Jia Jhang et al. "Challenges and Trends of SRAM-Based Computing-In-Memory for AI Edge Devices". In: IEEE Transactions on Circuits and Systems I: Regular Papers 68.5 (2021), pp. 1773--1786.
[6]
Kostas Pagiamtzis and Ali Sheikholeslami. "Content-addressable memory (CAM) circuits and architectures: A tutorial and survey". In: IEEE journal of solid-state circuits 41.3 (2006), pp. 712--727.
[7]
Yu-Der Chih et al. "An 89TOPS/W and 16.3TOPS/mm2 all-digital SRAM-based full-precision compute-in memory macro in 22nm for machine-learning edge applications". In: IEEE International Solid-State Circuits Conference(ISSCC). 2021.
[8]
Cheng-Xin Xue et al. "A 22nm 2Mb ReRAM compute-in-memory macro with 121-28TOPS/W for multibit MAC computing for tiny AI edge devices". In: 2020 IEEE International Solid-State Circuits Conference-(ISSCC). IEEE. 2020.
[9]
A Belmonte et al. "Capacitor-less, long-retention (> 400s) DRAM cell paving the way towards low-power and high-density monolithic 3D DRAM". In: 2020 IEEE International Electron Devices Meeting (IEDM). IEEE. 2020, pp. 28--2.
[10]
Xinlv Duan et al. "Novel vertical channel-all-around (CAA) In-Ga-Zn-O FET for 2T0C-DRAM with high density beyond 4F2 by monolithic stacking". In: IEEE Transactions on Electron Devices 69.4 (2022), pp. 2196--2202.
[11]
Jingrui Guo et al. "A new surface potential and physics based compact model for a-IGZO TFTs at multinanoscale for high retention and low-power DRAM application". In: IEEE International Electron Devices Meeting (IEDM). IEEE. 2021.
[12]
Ping Chi et al. "Prime: A novel processing-in-memory architecture for neural network computation in reram-based main memory". In: ACM/IEEE International Symposium on Computer Architecture (ISCA) (2016).
[13]
Linghao Song et al. "Pipelayer: A pipelined reram-based accelerator for deep learning". In: IEEE high performance computer architecture (HPCA). IEEE. 2017.
[14]
Lixia Han et al. "A Convolution Neural Network Accelerator Design with Weight Mapping and Pipeline Optimization". In: 2023 60th ACM/IEEE Design Automation Conference (DAC). IEEE. 2023, pp. 1--6.
[15]
Nagadastagiri Challapalle et al. "Crossbar based processing in memory accelerator architecture for graph convolutional networks". In: 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD). IEEE. 2021.
[16]
Nagadastagiri Challapalle et al. "GaaS-X: Graph analytics accelerator supporting sparse data representation using crossbar architectures". In: 2020 ACM/IEEE International Symposium on Computer Architecture (ISCA). IEEE. 2020.
[17]
Linghao Song et al. "GraphR: Accelerating graph processing using ReRAM". In: 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE. 2018, pp. 531--543.
[18]
Tao Yang et al. "PIMGCN: a reram-based PIM design for graph convolutional network acceleration". In: 2021 58th ACM/IEEE Design Automation Conference (DAC). IEEE. 2021, pp. 583--588.
[19]
Mengyuan Li et al. "Imars: An in-memory-computing architecture for recommendation systems". In: Proceedings of the 59th ACM/IEEE Design Automation Conference. 2022, pp. 463--468.
[20]
Zhuang Liu et al. "A convnet for the 2020s". In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, pp. 11976--11986.
[21]
Prithviraj Sen et al. "Collective classification in network data". In: AI magazine 29.3 (2008), pp. 93--93.
[22]
Ali Keshavarzi et al. "Ferroelectronics for edge intelligence". In: IEEE MICRO 40.6 (2020), pp. 33--48.
[23]
Menggan Liu et al. "Analog Monolayer MoS2 Transistor with Record-high Intrinsic Gain (> 100 dB) and Ultra-low Saturation Voltage (< 0.1 V) by Source Engineering". In: 2021 Symposium on VLSI Technology. IEEE. 2021, pp. 1--2.
Index Terms
- IG-CRM: Area/Energy-Efficient IGZO-Based Circuits and Architecture Design for Reconfigurable CIM/CAM Applications
Index terms have been assigned to the content through auto-classification.
Recommendations
Reconfigurable content-addressable memory (CAM) on FPGAs: A tutorial and survey
AbstractContent-addressable memory (CAM) is a massively parallel searching device that returns the address of a given search input in one clock cycle. Field-programmable gate array (FPGA)-based CAMs are becoming popular due to their ...
Highlights- It describes all the works proposed in the past 10-15 years on FPGA-based CAM/TCAM.
Implementation of a Standby-Power-Free CAM Based on Complementary Ferroelectric-Capacitor Logic
ASP-DAC '07: Proceedings of the 2007 Asia and South Pacific Design Automation ConferenceA complementary ferroelectric-capacitor (CFC) logic-circuit style is proposed for a compact and standby-power-free content-addressable memory (CAM). Since the use of the CFC logic circuit in designing a CAM cell makes it possible to merge both logic and ...
A Single-Phase Adiabatic CAM Using Improved CAL Circuits
PACCS '09: Proceedings of the 2009 Pacific-Asia Conference on Circuits, Communications and SystemsA 16 X 16 CAM (Content-Addressable Memory) based on improved CAL (Clocked Adiabatic Logic) circuits is presented, which is realized using TSMC 0.18um process. The CAL is a dual-rail logic that operates from a single-phase AC power-clock supply. For a ...
Comments
Information & Contributors
Information
Published In
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 November 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key R&D Program of China
- National Natural Science Foundation of China
- Beijing Nova Program
- China Postdoctoral Science Foundation
- Strategic Priority Research Program of Chinese Academy of Sciences
Conference
DAC '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,770 of 5,499 submissions, 32%
Upcoming Conference
DAC '25
- Sponsor:
- sigda
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 190Total Downloads
- Downloads (Last 12 months)190
- Downloads (Last 6 weeks)125
Reflects downloads up to 15 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in