Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations

With the increasing demand for intelligent memory, the conventional memory system is more and more equipped with computational logic to support simple arithmetic and Boolean operations required by many real-world applications. Such a trend, called ‘Process-In-Memory’ architectu...

Full description

Saved in:
Bibliographic Details
Main Authors: Yerim An, Honggu Kim, Dongjun Son, Hakrae Yu, Yong Shim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11095698/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687513546883072
author Yerim An
Honggu Kim
Dongjun Son
Hakrae Yu
Yong Shim
author_facet Yerim An
Honggu Kim
Dongjun Son
Hakrae Yu
Yong Shim
author_sort Yerim An
collection DOAJ
description With the increasing demand for intelligent memory, the conventional memory system is more and more equipped with computational logic to support simple arithmetic and Boolean operations required by many real-world applications. Such a trend, called ‘Process-In-Memory’ architecture, tries to utilize most of the memory candidates ranging from the conventional charge-based memory such as SRAM, DRAM, and Flash to the emerging memory devices such as RRAM, PRAM and MRAM. From the application perspective, many researchers are putting efforts to develop efficient memory peripherals with CMOS circuits to support one of two operations: 1) Boolean function, and 2) simple arithmetic operations such as multiplication and accumulation (addition), which is typically referred to as MAC operation. However, there are not many previous works that support both operations in a single system. In this article, we propose a 2T1C DRAM-based PIM architecture that supports dual-mode operation with minimal additional hardware. The proposed architecture has been fabricated using a commercial 65nm CMOS technology and successfully proves that the target operations are performed with a reasonably good accuracy.
format Article
id doaj-art-22d0afb6f9b644b4a6a23c823b22f338
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-22d0afb6f9b644b4a6a23c823b22f3382025-08-20T03:22:19ZengIEEEIEEE Access2169-35362025-01-011313392513393610.1109/ACCESS.2025.359235211095698Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC OperationsYerim An0https://orcid.org/0009-0008-8939-2368Honggu Kim1https://orcid.org/0009-0007-1306-2824Dongjun Son2https://orcid.org/0009-0000-2897-2600Hakrae Yu3Yong Shim4https://orcid.org/0000-0002-7101-6718Department of Intelligent Semiconductor Engineering, Chung-Ang University, Dongjak-gu, Seoul, Republic of KoreaDepartment of Intelligent Semiconductor Engineering, Chung-Ang University, Dongjak-gu, Seoul, Republic of KoreaDepartment of Intelligent Semiconductor Engineering, Chung-Ang University, Dongjak-gu, Seoul, Republic of KoreaDepartment of Intelligent Semiconductor Engineering, Chung-Ang University, Dongjak-gu, Seoul, Republic of KoreaDepartment of Intelligent Semiconductor Engineering, Chung-Ang University, Dongjak-gu, Seoul, Republic of KoreaWith the increasing demand for intelligent memory, the conventional memory system is more and more equipped with computational logic to support simple arithmetic and Boolean operations required by many real-world applications. Such a trend, called ‘Process-In-Memory’ architecture, tries to utilize most of the memory candidates ranging from the conventional charge-based memory such as SRAM, DRAM, and Flash to the emerging memory devices such as RRAM, PRAM and MRAM. From the application perspective, many researchers are putting efforts to develop efficient memory peripherals with CMOS circuits to support one of two operations: 1) Boolean function, and 2) simple arithmetic operations such as multiplication and accumulation (addition), which is typically referred to as MAC operation. However, there are not many previous works that support both operations in a single system. In this article, we propose a 2T1C DRAM-based PIM architecture that supports dual-mode operation with minimal additional hardware. The proposed architecture has been fabricated using a commercial 65nm CMOS technology and successfully proves that the target operations are performed with a reasonably good accuracy.https://ieeexplore.ieee.org/document/11095698/Processing-in-memory (PIM)DRAMDRAM compute-in-memoryDNN acceleratordual mode operationBoolean function
spellingShingle Yerim An
Honggu Kim
Dongjun Son
Hakrae Yu
Yong Shim
Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations
IEEE Access
Processing-in-memory (PIM)
DRAM
DRAM compute-in-memory
DNN accelerator
dual mode operation
Boolean function
title Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations
title_full Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations
title_fullStr Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations
title_full_unstemmed Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations
title_short Dual-Mode 2T1C DRAM Process-In-Memory Architecture for Boolean and MAC Operations
title_sort dual mode 2t1c dram process in memory architecture for boolean and mac operations
topic Processing-in-memory (PIM)
DRAM
DRAM compute-in-memory
DNN accelerator
dual mode operation
Boolean function
url https://ieeexplore.ieee.org/document/11095698/
work_keys_str_mv AT yeriman dualmode2t1cdramprocessinmemoryarchitectureforbooleanandmacoperations
AT honggukim dualmode2t1cdramprocessinmemoryarchitectureforbooleanandmacoperations
AT dongjunson dualmode2t1cdramprocessinmemoryarchitectureforbooleanandmacoperations
AT hakraeyu dualmode2t1cdramprocessinmemoryarchitectureforbooleanandmacoperations
AT yongshim dualmode2t1cdramprocessinmemoryarchitectureforbooleanandmacoperations