A digital 3D TCAM accelerator for the inference phase of Random Forest

Chieh Lin Tsai; Chun Feng Wu; Yuan Hao Chang; Han Wen Hu; Yung Chun Lee; Hsiang Pang Li; Tei Wei Kuo

doi:10.1109/DAC56929.2023.10247695

A digital 3D TCAM accelerator for the inference phase of Random Forest

Chieh Lin Tsai^*
, Chun Feng Wu
, Yuan Hao Chang
, Han Wen Hu
, Yung Chun Lee
, Hsiang Pang Li
, Tei Wei Kuo

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

Random forest is a popular ensemble machine-learning algorithm for classification and regression tasks. However, the irregular tree shapes and non-deterministic memory access patterns make it hard for the current von Neumann architecture to handle random forest efficiently. This paper proposes a digital 3D TCAM-based accelerator for the random forest, adopting the idea of processing-in-memory (PIM) to reduce data movement. By utilizing this accelerator, we propose a TCAM-based approach to provide real-time inference with low energy consumption, making it suitable for edge or embedded environments. In the experiments, the proposed approach achieves an average of 3.13 times higher throughput with 22 times more energy saving than the GPU approach.

Original language	English
Title of host publication	2023 60th ACM/IEEE Design Automation Conference, DAC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350323481
DOIs	https://doi.org/10.1109/DAC56929.2023.10247695
State	Published - 2023
Event	60th ACM/IEEE Design Automation Conference, DAC 2023 - San Francisco, United States Duration: 9 Jul 2023 → 13 Jul 2023

Publication series

Name	Proceedings - Design Automation Conference
Volume	2023-July
ISSN (Print)	0738-100X

Conference

Conference	60th ACM/IEEE Design Automation Conference, DAC 2023
Country/Territory	United States
City	San Francisco
Period	9/07/23 → 13/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access to Document

10.1109/DAC56929.2023.10247695

Cite this

Tsai, C. L., Wu, C. F., Chang, Y. H., Hu, H. W., Lee, Y. C., Li, H. P., & Kuo, T. W. (2023). A digital 3D TCAM accelerator for the inference phase of Random Forest. In 2023 60th ACM/IEEE Design Automation Conference, DAC 2023 (Proceedings - Design Automation Conference; Vol. 2023-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DAC56929.2023.10247695

@inproceedings{c2d59a7ba806488683b2e2aa8c7a3bf2,

title = "A digital 3D TCAM accelerator for the inference phase of Random Forest",

abstract = "Random forest is a popular ensemble machine-learning algorithm for classification and regression tasks. However, the irregular tree shapes and non-deterministic memory access patterns make it hard for the current von Neumann architecture to handle random forest efficiently. This paper proposes a digital 3D TCAM-based accelerator for the random forest, adopting the idea of processing-in-memory (PIM) to reduce data movement. By utilizing this accelerator, we propose a TCAM-based approach to provide real-time inference with low energy consumption, making it suitable for edge or embedded environments. In the experiments, the proposed approach achieves an average of 3.13 times higher throughput with 22 times more energy saving than the GPU approach.",

author = "Tsai, \{Chieh Lin\} and Wu, \{Chun Feng\} and Chang, \{Yuan Hao\} and Hu, \{Han Wen\} and Lee, \{Yung Chun\} and Li, \{Hsiang Pang\} and Kuo, \{Tei Wei\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 60th ACM/IEEE Design Automation Conference, DAC 2023 ; Conference date: 09-07-2023 Through 13-07-2023",

year = "2023",

doi = "10.1109/DAC56929.2023.10247695",

language = "English",

series = "Proceedings - Design Automation Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 60th ACM/IEEE Design Automation Conference, DAC 2023",

address = "美國",

}

Tsai, CL, Wu, CF, Chang, YH, Hu, HW, Lee, YC, Li, HP & Kuo, TW 2023, A digital 3D TCAM accelerator for the inference phase of Random Forest. in 2023 60th ACM/IEEE Design Automation Conference, DAC 2023. Proceedings - Design Automation Conference, vol. 2023-July, Institute of Electrical and Electronics Engineers Inc., 60th ACM/IEEE Design Automation Conference, DAC 2023, San Francisco, United States, 9/07/23. https://doi.org/10.1109/DAC56929.2023.10247695

A digital 3D TCAM accelerator for the inference phase of Random Forest. / Tsai, Chieh Lin; Wu, Chun Feng; Chang, Yuan Hao et al.
2023 60th ACM/IEEE Design Automation Conference, DAC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - Design Automation Conference; Vol. 2023-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A digital 3D TCAM accelerator for the inference phase of Random Forest

AU - Tsai, Chieh Lin

AU - Wu, Chun Feng

AU - Chang, Yuan Hao

AU - Hu, Han Wen

AU - Lee, Yung Chun

AU - Li, Hsiang Pang

AU - Kuo, Tei Wei

PY - 2023

Y1 - 2023

N2 - Random forest is a popular ensemble machine-learning algorithm for classification and regression tasks. However, the irregular tree shapes and non-deterministic memory access patterns make it hard for the current von Neumann architecture to handle random forest efficiently. This paper proposes a digital 3D TCAM-based accelerator for the random forest, adopting the idea of processing-in-memory (PIM) to reduce data movement. By utilizing this accelerator, we propose a TCAM-based approach to provide real-time inference with low energy consumption, making it suitable for edge or embedded environments. In the experiments, the proposed approach achieves an average of 3.13 times higher throughput with 22 times more energy saving than the GPU approach.

AB - Random forest is a popular ensemble machine-learning algorithm for classification and regression tasks. However, the irregular tree shapes and non-deterministic memory access patterns make it hard for the current von Neumann architecture to handle random forest efficiently. This paper proposes a digital 3D TCAM-based accelerator for the random forest, adopting the idea of processing-in-memory (PIM) to reduce data movement. By utilizing this accelerator, we propose a TCAM-based approach to provide real-time inference with low energy consumption, making it suitable for edge or embedded environments. In the experiments, the proposed approach achieves an average of 3.13 times higher throughput with 22 times more energy saving than the GPU approach.

UR - https://www.scopus.com/pages/publications/85173126933

U2 - 10.1109/DAC56929.2023.10247695

DO - 10.1109/DAC56929.2023.10247695

M3 - Conference contribution

AN - SCOPUS:85173126933

T3 - Proceedings - Design Automation Conference

BT - 2023 60th ACM/IEEE Design Automation Conference, DAC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 60th ACM/IEEE Design Automation Conference, DAC 2023

Y2 - 9 July 2023 through 13 July 2023

ER -

A digital 3D TCAM accelerator for the inference phase of Random Forest

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this