Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory

Chan Gi Yook; Wonbo Shim

doi:10.1109/ITC-CSCC58803.2023.10212837

Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory

Chan Gi Yook
, Wonbo Shim

Dept. of Electrical and Information Engineering

Seoul National University of Science and Technology (SNUST)

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

Abstract

Processing-in-memory (PIM) technology has been expected to be an effective memory technology for artificial intelligence (AI) computation with high data throughput and energy efficiency. Among various PIM component devices, 2-transistor (2TOC) DRAM has attracted attention due to its superior sensing speed, on/off ratio, and chip density. However, its retention characteristic requires frequent refresh, which results in considerable power consumption. Therefore, finding the effective refresh method that minimizes energy consumption while maintaining accuracy is crucial. In this paper, we introduce burst refresh and periodic refresh methods and compare their performance. We extract the accuracy-time graph when the refresh techniques described above are applied through our developed 2TOC DRAM-based PIM simulation framework, which can evaluate inference accuracy. Under the conditions of this paper, when a 32 ms refresh is performed, burst refresh causes the accuracy drop to 83 % just before the refresh, while periodic refresh showed an improved performance to maintain accuracy at around 88-92 %.

Original language	English
Title of host publication	2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350326413
DOIs	https://doi.org/10.1109/ITC-CSCC58803.2023.10212837
State	Published - 2023
Event	2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023 - Jeju, Korea, Republic of Duration: 25 Jun 2023 → 28 Jun 2023

Publication series

Name	2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023

Conference

Conference	2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023
Country/Territory	Korea, Republic of
City	Jeju
Period	25/06/23 → 28/06/23

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

2TOC DRAM
benchmark simulator
DRAM
inference accuracy
Processing-in-Memory (PIM)
refresh

Access to Document

10.1109/ITC-CSCC58803.2023.10212837

Cite this

Yook, C. G., & Shim, W. (2023). Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory. In 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023 (2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITC-CSCC58803.2023.10212837

Yook, Chan Gi ; Shim, Wonbo. / Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory. 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023).

@inproceedings{b585401b7a3840b2a0b8d9d0d30607a8,

title = "Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory",

abstract = "Processing-in-memory (PIM) technology has been expected to be an effective memory technology for artificial intelligence (AI) computation with high data throughput and energy efficiency. Among various PIM component devices, 2-transistor (2TOC) DRAM has attracted attention due to its superior sensing speed, on/off ratio, and chip density. However, its retention characteristic requires frequent refresh, which results in considerable power consumption. Therefore, finding the effective refresh method that minimizes energy consumption while maintaining accuracy is crucial. In this paper, we introduce burst refresh and periodic refresh methods and compare their performance. We extract the accuracy-time graph when the refresh techniques described above are applied through our developed 2TOC DRAM-based PIM simulation framework, which can evaluate inference accuracy. Under the conditions of this paper, when a 32 ms refresh is performed, burst refresh causes the accuracy drop to 83 \% just before the refresh, while periodic refresh showed an improved performance to maintain accuracy at around 88-92 \%.",

keywords = "2TOC DRAM, benchmark simulator, DRAM, inference accuracy, Processing-in-Memory (PIM), refresh",

author = "Yook, \{Chan Gi\} and Wonbo Shim",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023 ; Conference date: 25-06-2023 Through 28-06-2023",

year = "2023",

doi = "10.1109/ITC-CSCC58803.2023.10212837",

language = "English",

series = "2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023",

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

booktitle = "2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023",

}

Yook, CG & Shim, W 2023, Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory. in 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023. 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023, Institute of Electrical and Electronics Engineers Inc., 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023, Jeju, Korea, Republic of, 25/06/23. https://doi.org/10.1109/ITC-CSCC58803.2023.10212837

Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory. / Yook, Chan Gi; Shim, Wonbo.
2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023).

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

TY - GEN

T1 - Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory

AU - Yook, Chan Gi

AU - Shim, Wonbo

PY - 2023

Y1 - 2023

N2 - Processing-in-memory (PIM) technology has been expected to be an effective memory technology for artificial intelligence (AI) computation with high data throughput and energy efficiency. Among various PIM component devices, 2-transistor (2TOC) DRAM has attracted attention due to its superior sensing speed, on/off ratio, and chip density. However, its retention characteristic requires frequent refresh, which results in considerable power consumption. Therefore, finding the effective refresh method that minimizes energy consumption while maintaining accuracy is crucial. In this paper, we introduce burst refresh and periodic refresh methods and compare their performance. We extract the accuracy-time graph when the refresh techniques described above are applied through our developed 2TOC DRAM-based PIM simulation framework, which can evaluate inference accuracy. Under the conditions of this paper, when a 32 ms refresh is performed, burst refresh causes the accuracy drop to 83 % just before the refresh, while periodic refresh showed an improved performance to maintain accuracy at around 88-92 %.

AB - Processing-in-memory (PIM) technology has been expected to be an effective memory technology for artificial intelligence (AI) computation with high data throughput and energy efficiency. Among various PIM component devices, 2-transistor (2TOC) DRAM has attracted attention due to its superior sensing speed, on/off ratio, and chip density. However, its retention characteristic requires frequent refresh, which results in considerable power consumption. Therefore, finding the effective refresh method that minimizes energy consumption while maintaining accuracy is crucial. In this paper, we introduce burst refresh and periodic refresh methods and compare their performance. We extract the accuracy-time graph when the refresh techniques described above are applied through our developed 2TOC DRAM-based PIM simulation framework, which can evaluate inference accuracy. Under the conditions of this paper, when a 32 ms refresh is performed, burst refresh causes the accuracy drop to 83 % just before the refresh, while periodic refresh showed an improved performance to maintain accuracy at around 88-92 %.

KW - 2TOC DRAM

KW - benchmark simulator

KW - DRAM

KW - inference accuracy

KW - Processing-in-Memory (PIM)

KW - refresh

UR - https://www.scopus.com/pages/publications/85169836839

U2 - 10.1109/ITC-CSCC58803.2023.10212837

DO - 10.1109/ITC-CSCC58803.2023.10212837

M3 - Conference contribution

AN - SCOPUS:85169836839

T3 - 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023

BT - 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023

Y2 - 25 June 2023 through 28 June 2023

ER -

Yook CG, Shim W. Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory. In 2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 International Technical Conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023). doi: 10.1109/ITC-CSCC58803.2023.10212837

Refresh Methods and Accuracy Evaluation for 2T0C DRAM based Processing-in-memory

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this