A μ-NMC-Δ-IMC Heterogeneous STT-MRAM Compute-in-Memory Macro Using Δ-Clamping Bit Reduction for Noise-Tolerant Bayesian Neural Networks.

De-Qi You

De-Qi You Win-San Khwa Bo Zhang Fang-Yi Chen Andrew Lee Yu-Cheng Hung Yi-Ming Li Yu-Hui Wang Chung-Chuan Lo Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Yu-Der Chih Tsung-Yung Jonathan Chang Meng-Fan Chang A μ-NMC-Δ-IMC Heterogeneous STT-MRAM Compute-in-Memory Macro Using Δ-Clamping Bit Reduction for Noise-Tolerant Bayesian Neural Networks. 225-236 2026 January 61 IEEE J. Solid State Circuits 1 https://doi.org/10.1109/JSSC.2025.3617770 db/journals/jssc/jssc61.html#YouKZCLHLWLLHTCCC26 streams/journals/jssc

Hung-Hsi Hsu Win-San Khwa Yao-Kai Yeh Chih-Ling Wu Chang-Yuan Chen Yen-Che Huang Yen-Hua Lin Cheng-Feng Chang Yen-Tung Shao Jen-Chun Tien De-Qi You Ping-Sheng Wu Bo Zhang Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Meng-Fan Chang A 22nm 96Mb 50.6-to-90.2TFLOPS/W Non-Linear MLC ReRAM CIM Macro with High-Retention for Mamba/Transformer/CNN. ISSCC 2026 516-518 conf/isscc/2026 https://doi.org/10.1109/ISSCC49663.2026.11409297 db/conf/isscc/isscc2026.html#HsuKYWCHLCSTYWZLHTC26 streams/conf/isscc Jen-Chun Tien Win-San Khwa Le-Jung Hsieh Tsung-Han Lou Jyun-Cheng Bai Yu-Sheng Kao Ting-Hao Hsu Mai Tseng Hung-Hsi Hsu Yao-Kai Yeh De-Qi You Ashwin Sanjay Lele Brian Crafton Bo Zhang Ping-Sheng Wu Ya-Tang Yang Chung-Chuan Lo Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Meng-Fan Chang 30.5 A 16nm 72kb 120.5TFLOPS/W Versatile-Format Dual-Representation Gain-Cell CIM Macro for General Purpose AI Tasks. ISSCC 2026 520-522 conf/isscc/2026 https://doi.org/10.1109/ISSCC49663.2026.11409052 db/conf/isscc/isscc2026.html#TienKHLBKHTHYYLCZWYLLHT26 streams/conf/isscc Yao-Kai Yeh Jian-Wei Su Ting-Hao Hsu Mai Tseng Jen-Chun Tien Ko-Chi Chen Chih-Yen Yue Yu-En Lin Yu-Jia Hu Le-Jung Hsieh Jyun-Cheng Bai Yu-Sheng Kao Tsung-Han Lou Hung-Hsi Hsu De-Qi You Shyh-Shyuan Sheu Wei-Chung Lo Shih-Chieh Chang 0001 Ya-Tang Yang Chung-Chuan Lo Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Meng-Fan Chang A 16nm, 1Mb, 1-to-8b-Configurable 444.21TOPS/W Fully Digital SRAM Compute-in-Memory Macro for Hybrid SNN-CNN Edge Computing. ISSCC 2026 526-528 conf/isscc/2026 https://doi.org/10.1109/ISSCC49663.2026.11409250 db/conf/isscc/isscc2026.html#YehSHTTCYLHHBKLHYSLCYLL26 streams/conf/isscc De-Qi You Win-San Khwa Bo Zhang Fang-Yi Chen Andrew Lee Yu-Cheng Hung Yi-Ming Li Yu-Hui Wang Chung-Chuan Lo Ren-Shuo Liu Kea-Tiong Tang Chih-Cheng Hsieh Yu-Der Chih Tsung-Yung Jonathan Chang Meng-Fan Chang 14.1 A 22nm 104.5TOPS/W µ-NMC-Δ-IMC Heterogeneous STT-MRAM CIM Macro for Noise-Tolerant Bayesian Neural Networks. 1-3 2025 ISSCC https://doi.org/10.1109/ISSCC49661.2025.10904540 conf/isscc/2025 db/conf/isscc/isscc2025.html#YouKZCLHLWLLTHC25

De-Qi You Yen-Cheng Chiu Win-San Khwa Chung-Yuan Li Fang-Ling Hsieh Yu-An Chien Chung-Chuan Lo Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Yu-Der Chih Tsung-Yung Jonathan Chang Meng-Fan Chang An 8b-Precision 8-Mb STT-MRAM Near-Memory-Compute Macro Using Weight-Feature and Input-Sparsity Aware Schemes for Energy-Efficient Edge AI Devices. 219-230 2024 January 59 IEEE J. Solid State Circuits 1 https://doi.org/10.1109/JSSC.2023.3324335 db/journals/jssc/jssc59.html#YouCKLHCLLHTCCC24

De-Qi You Win-San Khwa Jui-Jen Wu Chuan-Jia Jhang Guan-Yi Lin Po-Jung Chen Ting-Chien Chiu Fang-Yi Chen Andrew Lee Yu-Cheng Hung Chung-Chuan Lo Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Yu-Der Chih Tsung-Yung Jonathan Chang Meng-Fan Chang A 22nm Nonvolatile AI-Edge Processor with 21.4TFLOPS/W using 47.25Mb Lossless-Compressed-Computing STT-MRAM Near-Memory-Compute Macro. 1-2 2024 VLSI Technology and Circuits https://doi.org/10.1109/VLSITechnologyandCir46783.2024.10631408 conf/vlsit/2024 db/conf/vlsit/vlsit2024.html#YouKWJLCCCLHLLH24 Yen-Cheng Chiu Win-San Khwa Chung-Yuan Li Fang-Ling Hsieh Yu-An Chien Guan-Yi Lin Po-Jung Chen Tsen-Hsiang Pan De-Qi You Fang-Yi Chen Andrew Lee Chung-Chuan Lo Ren-Shuo Liu Chih-Cheng Hsieh Kea-Tiong Tang Yu-Der Chih Tsung-Yung Jonathan Chang Meng-Fan Chang A 22nm 8Mb STT-MRAM Near-Memory-Computing Macro with 8b-Precision and 46.4-160.1TOPS/W for Edge-AI Devices. 496-497 2023 ISSCC https://doi.org/10.1109/ISSCC42615.2023.10067563 conf/isscc/2023 db/conf/isscc/isscc2023.html#ChiuKLHCLCPYCLLLHTCCC23 Hung-Hsi Hsu Tai-Hao Wen Ping-Chun Wu Chuan-Jia Jhang De-Qi You Ping-Cheng Chen Meng-Fan Chang Challenges in Circuits of Nonvolatile Compute-In-Memory for Edge AI Chips. 98-102 2023 MWSCAS https://doi.org/10.1109/MWSCAS57524.2023.10405877 conf/mwscas/2023 db/conf/mwscas/mwscas2023.html#HsuWWJYCC23 Jyun-Cheng Bai Cheng-Feng Chang Meng-Fan Chang Shih-Chieh Chang 0001 Tsung-Yung Jonathan Chang Chang-Yuan Chen Fang-Yi Chen Ko-Chi Chen Ping-Cheng Chen Po-Jung Chen Yu-An Chien Yu-Der Chih Ting-Chien Chiu Yen-Cheng Chiu Brian Crafton Chih-Cheng Hsieh Fang-Ling Hsieh Le-Jung Hsieh Hung-Hsi Hsu Ting-Hao Hsu Yu-Jia Hu Yen-Che Huang Yu-Cheng Hung Chuan-Jia Jhang Yu-Sheng Kao Win-San Khwa Andrew Lee Ashwin Sanjay Lele Chung-Yuan Li Yiming LiYi-Ming Li Guan-Yi Lin Yen-Hua Lin Yu-En Lin Ren-Shuo Liu Chung-Chuan Lo Wei-Chung Lo Tsung-Han Lou Tsen-Hsiang Pan Yen-Tung Shao Shyh-Shyuan Sheu Jian-Wei Su Kea-Tiong Tang Jen-Chun Tien Mai Tseng Yuhui WangYu-Hui Wang Tai-Hao Wen Chih-Ling Wu Jui-Jen Wu Ping-Chun Wu Ping-Sheng Wu Ya-Tang Yang Yao-Kai Yeh Chih-Yen Yue Bo Zhang