VCCIM: a voltage coupling based computing-in-memory architecture in 28 nm for edge AI applications

被引：2

作者：

Guo, An ^{[1
]}

Xue, Chen ^{[1
]}

Chen, Xi ^{[1
]}

Si, Xin ^{[1
]}

机构：

[1] Southeast Univ, Nanjing 210018, Jiangsu, Peoples R China

来源：

CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING | 2022年 / 4卷 / 04期

关键词：

Neural network; Computing-in-memory; Configurability; MACRO; OPERATION;

D O I：

10.1007/s42514-022-00111-1

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Computing-in-memory (CIM) has been widely explored for parallelizing multiply-and-accumulation (MAC) operations and reducing data access to overcome "Von-Neumann bottleneck". However, most CIM works lack configurability regardless of custom demands. In this paper, we proposed a 28 nm 128 Kb configurable CIM architecture based on voltage coupling (VCCIM) and a CIM-based modeling and predicting (CIMMP) method. This macro achieves an energy efficiency of 12.1-17.6 TOPS/W and 71.70-72.01% inference accuracy when applied to a VGG-16 network CIFAR-100 data set.

引用

页码：407 / 420

页数：14

共 30 条

[1]

Bong K, 2017, ISSCC DIG TECH PAP I, P248, DOI 10.1109/ISSCC.2017.7870354

[2] PXNOR-BNN: In/With Spin-Orbit Torque MRAM Preset-XNOR Operation-Based Binary Neural Networks [J].

Chang, Liang ;

Ma, Xin ;

Wang, Zhaohao ;

Zhang, Youguang ;

Xie, Yuan ;

Zhao, Weisheng .

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2019, 27 (11) :2668-2679

[3]

Chen YH, 2016, ISSCC DIG TECH PAP I, V59, P262, DOI 10.1109/ISSCC.2016.7418007

[4] PRIME: A Novel Processing-in-memory Architecture for Neural Network Computation in ReRAM-based Main Memory [J].

Chi, Ping ;

Li, Shuangchen ;

Xu, Cong ;

Zhang, Tao ;

Zhao, Jishen ;

Liu, Yongpan ;

Wang, Yu ;

Xie, Yuan .

2016 ACM/IEEE 43RD ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2016, :27-39

[5] An 89TOPS/W and 16.3TOPS/mm2 All-Digital SRAM-Based Full-Precision Compute-In Memory Macro in 22nm for Machine-Learning Edge Applications [J].

Chih, Yu-Der ;

Lee, Po-Hao ;

Fujiwara, Hidehiro ;

Shih, Yi-Chun ;

Lee, Chia-Fu ;

Naous, Rawan ;

Chen, Yu-Lin ;

Lo, Chieh-Pu ;

Lu, Cheng-Han ;

Mori, Haruki ;

Zhao, Wei-Cheng ;

Sun, Dar ;

Sinangil, Mahmut E. ;

Chen, Yen-Huei ;

Chou, Tan-Li ;

Akarvardar, Kerem ;

Liao, Hung-Jen ;

Wang, Yih ;

Chang, Meng-Fan ;

Chang, Tsung-Yung Jonathan .

2021 IEEE INTERNATIONAL SOLID-STATE CIRCUITS CONFERENCE (ISSCC), 2021, 64 :252-+

[6] A 5.99-to-691.1TOPS/W Tensor-Train In-Memory-Computing Processor Using Bit-Level-Sparsity-Based Optimization and Variable-Precision Quantization [J].

Guo, Ruiqi ;

Yue, Zhiheng ;

Si, Xin ;

Hu, Te ;

Li, Hao ;

Tang, Limei ;

Wang, Yabing ;

Liu, Leibo ;

Chang, Meng-Fan ;

Li, Qiang ;

Wei, Shaojun ;

Yin, Shouyi .

2021 IEEE INTERNATIONAL SOLID-STATE CIRCUITS CONFERENCE (ISSCC), 2021, 64 :242-+

[7] Functional Read Enabling In-Memory Computations in 1Transistor-1Resistor Memory Arrays [J].

Jaiswal, Akhilesh ;

Andrawis, Robert ;

Agrawal, Amogh ;

Roy, Kaushik .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2020, 67 (12) :3347-3351

[8] C3SRAM: An In-Memory-Computing SRAM Macro Based on Robust Capacitive Coupling Computing Mechanism [J].

Jiang, Zhewei ;

Yin, Shihui ;

Seo, Jae-Sun ;

Seok, Mingoo .

IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2020, 55 (07) :1888-1897

[9]

Khwa WS, 2018, ISSCC DIG TECH PAP I, P496, DOI 10.1109/ISSCC.2018.8310401

[10] A Charge-domain 10T SRAM based In-Memory-Computing Macro for Low Energy and Highly Accurate DNN inference [J].

Kim, Joonhyung ;

Park, Jongsun .

18TH INTERNATIONAL SOC DESIGN CONFERENCE 2021 (ISOCC 2021), 2021, :89-90

← 1 2 3 →