Je-Min Hung
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Je-Min Hung has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Meng-Fan Chang
National Tsing Hua University
4 shared publications Cheng-Xin Xue
National Tsing Hua University (NTHU), Hsinchu, Republic of China
2 shared publicationsChuan-Jia Jhang
National Tsing Hua University (NTHU), Hsinchu, Republic of China
2 shared publicationsMon-Shu Ho
National Chung Hsing University (NCHU), Taichung, Republic of China
2 shared publicationsSheng-Po Huang
National Tsing Hua University (NTHU), Hsinchu, Republic of China
2 shared publicationsYu-Der Chih
Taiwan, Semiconductor Manufacturing Company, Hsinchu, Taiwan
2 shared publications
Latest Publications
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 61 (4) , 1502-1512
A 3 nm FinFET 125 TOPS/W-29 TFLOPS/W, 90 TOPS/mm 2 -17 TFLOPS/mm 2 SRAM-Based INT8, and FP16 Digital-CIM Compiler With Support for Multi-Weight Update/Cycle
This article presents an static random-access memory (SRAM)-based digital compute-in-memory (CIM) compiler implemented with 3 nm high- $\kappa $ metal gate (HKMG) FinFET technology, supporting flexible INT8 and FP16 formats for weight and activation multiply-accumulate (MAC) operations, offering configuration flexibility, high accuracy, and improved area and power efficiency. The FP16 digital computing in memory (DCIM) compiler achieves high arithmetic accuracy by adopting a multiplication-first (MF) FP computation flow, while the INT8 DCIM compiler provides improved power-performance-area (PPA). The DCIM compiler engine enables the automatic generation of flexible CIM macro configurations based on the tiling of block-level leaf cells. Our test chip in 3 nm technology is fully validated and exhibits 124.6 TOPS/W at 0.5 V and 90.2 TOPS/mm2 at 1.1 V for INT8 DCIM, and 28.6 TFLOPS/W at 0.5 V and 17.4 TFLOPS/mm2 at 1.1 V for FP16 DCIM, respectively.
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 61 (4) , 1502-1512
A 3 nm FinFET 125 TOPS/W-29 TFLOPS/W, 90 TOPS/mm 2 -17 TFLOPS/mm 2 SRAM-Based INT8, and FP16 Digital-CIM Compiler With Support for Multi-Weight Update/Cycle
This article presents an static random-access memory (SRAM)-based digital compute-in-memory (CIM) compiler implemented with 3 nm high- $\kappa $ metal gate (HKMG) FinFET technology, supporting flexible INT8 and FP16 formats for weight and activation multiply-accumulate (MAC) operations, offering configuration flexibility, high accuracy, and improved area and power efficiency. The FP16 digital computing in memory (DCIM) compiler achieves high arithmetic accuracy by adopting a multiplication-first (MF) FP computation flow, while the INT8 DCIM compiler provides improved power-performance-area (PPA). The DCIM compiler engine enables the automatic generation of flexible CIM macro configurations based on the tiling of block-level leaf cells. Our test chip in 3 nm technology is fully validated and exhibits 124.6 TOPS/W at 0.5 V and 90.2 TOPS/mm2 at 1.1 V for INT8 DCIM, and 28.6 TFLOPS/W at 0.5 V and 17.4 TFLOPS/mm2 at 1.1 V for FP16 DCIM, respectively.
- 20 December 2021
- Published by Springer Nature in Nature Electronics
- Vol. 4 (12) , 921-930
A four-megabit compute-in-memory macro with eight-bit precision based on CMOS and resistive random-access memory for AI edge devices
- 20 December 2021
- Published by Springer Nature in Nature Electronics
- Vol. 4 (12) , 921-930
A four-megabit compute-in-memory macro with eight-bit precision based on CMOS and resistive random-access memory for AI edge devices
- Open Access
- 26 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Solid-State Circuits Society
- Vol. 1, 171-183
Challenges and Trends of Nonvolatile In-Memory-Computation Circuits for AI Edge Devices
Nonvolatile memory (NVM)-based computing-in-memory (nvCIM) is a promising candidate for artificial intelligence (AI) edge devices to overcome the latency and energy consumption imposed by the movement of data between memory and processors under the von Neumann architecture. This paper explores the background and basic approaches to nvCIM implementation, including input methodologies, weight formation and placement, and readout and quantization methods. This paper outlines the major challenges in the further development of nvCIM macros and reviews trends in recent silicon-verified devices.
- 26 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Solid-State Circuits Society
- Vol. 1, 171-183
Open AccessChallenges and Trends of Nonvolatile In-Memory-Computation Circuits for AI Edge Devices
Nonvolatile memory (NVM)-based computing-in-memory (nvCIM) is a promising candidate for artificial intelligence (AI) edge devices to overcome the latency and energy consumption imposed by the movement of data between memory and processors under the von Neumann architecture. This paper explores the background and basic approaches to nvCIM implementation, including input methodologies, weight formation and placement, and readout and quantization methods. This paper outlines the major challenges in the further development of nvCIM macros and reviews trends in recent silicon-verified devices.
- Open Access
- 9 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
- Vol. 7 (1) , 79-87
CiM3D: Comparator-in-Memory Designs Using Monolithic 3-D Technology for Accelerating Data-Intensive Applications
The compare operation is widely used in many applications, from fundamental sorting to primitive operations in the database and AI systems. We present SRAM-based 3-D-CAM circuit designs using a monolithic 3-D (M3D) integration process for realizing beyond-Boolean in-memory compare operation without any area overheads. We also fabricated a processing-in-memory (PiM) macro with the same 3-D-CAM circuit using M3D for performing massively parallel compare operations used in the database, machine learning, and scientific applications. We show various system designs with the 3-D-CAM supporting operations, such as data filtering, sorting, and sparse matrix–matrix multiplication (SpGEMM). Our systems exhibit up to$272\times $ ,$200\times $ , and$226\times $ speedups and$151\times $ ,$37\times $ , and$156\times $ energy savings compared to systems using near memory compute for the data filtering, sorting, and SpGEMM applications, respectively.- 9 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
- Vol. 7 (1) , 79-87
Open AccessCiM3D: Comparator-in-Memory Designs Using Monolithic 3-D Technology for Accelerating Data-Intensive Applications
The compare operation is widely used in many applications, from fundamental sorting to primitive operations in the database and AI systems. We present SRAM-based 3-D-CAM circuit designs using a monolithic 3-D (M3D) integration process for realizing beyond-Boolean in-memory compare operation without any area overheads. We also fabricated a processing-in-memory (PiM) macro with the same 3-D-CAM circuit using M3D for performing massively parallel compare operations used in the database, machine learning, and scientific applications. We show various system designs with the 3-D-CAM supporting operations, such as data filtering, sorting, and sparse matrix–matrix multiplication (SpGEMM). Our systems exhibit up to$272\times $ ,$200\times $ , and$226\times $ speedups and$151\times $ ,$37\times $ , and$156\times $ energy savings compared to systems using near memory compute for the data filtering, sorting, and SpGEMM applications, respectively. - 10 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 67 (4) , 1444-1453
Challenges and Trends inDeveloping Nonvolatile Memory-Enabled Computing Chips for Intelligent Edge Devices
Under the von Neumann computing architecture, the edge devices used for artificial intelligence (AI) and the Internet of Things (IoTs) are limited in terms of latency and energy efficiency due to the movement of data between the memory and the processor. Nonvolatile memory-based computation-in-memory (nvCIM) is a promising candidate to overcome this issue, referred to as the memory wall. This article outlines the background and major challenges in the development of nvCIM macros as well as some of the recent progress in nvCIM for logic computation, pattern-matching computation, and multiply-and-accumulate (MAC) computation. We also summarize recent trends in nvCIM development at the end of each section.
- 10 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 67 (4) , 1444-1453
Challenges and Trends inDeveloping Nonvolatile Memory-Enabled Computing Chips for Intelligent Edge Devices
Under the von Neumann computing architecture, the edge devices used for artificial intelligence (AI) and the Internet of Things (IoTs) are limited in terms of latency and energy efficiency due to the movement of data between the memory and the processor. Nonvolatile memory-based computation-in-memory (nvCIM) is a promising candidate to overcome this issue, referred to as the memory wall. This article outlines the background and major challenges in the development of nvCIM macros as well as some of the recent progress in nvCIM for logic computation, pattern-matching computation, and multiply-and-accumulate (MAC) computation. We also summarize recent trends in nvCIM development at the end of each section.