UM

Browse/Search Results:  1-2 of 2 Help

Selected(0)Clear Items/Page:    Sort:
FLEX-CIM: A Flexible Kernel Size 1-GHz 181.6-TOPS/W 25.63-TOPS/mm2 Analog Compute-in-Memory Macro Journal article
Fu, Yuzhao, Yu, Wei Han, Un, Ka Fai, Chan, Chi Hang, Zhu, Yan, Zhang, Minglei, Martins, Rui P., Mak, Pui In. FLEX-CIM: A Flexible Kernel Size 1-GHz 181.6-TOPS/W 25.63-TOPS/mm2 Analog Compute-in-Memory Macro[J]. IEEE Journal of Solid-State Circuits, 2024.
Authors:  Fu, Yuzhao;  Yu, Wei Han;  Un, Ka Fai;  Chan, Chi Hang;  Zhu, Yan; et al.
Favorite | TC[WOS]:1 TC[Scopus]:1  IF:4.6/5.6 | Submit date:2024/05/16
Analog Partial Sum (Aps)  Compute-in-memory (Cim)  Convolutional Neural Network (Cnn)  Flexible Kernel Size  Utilization  
CLUT-CIM: A Capacitance Lookup Table-Based Analog Compute-in-Memory Macro With Signed-Channel Training and Weight Updating for Nonuniform Quantization Journal article
Fu, Yuzhao, Li, Jixuan, Yu, Wei Han, Un, Ka Fai, Chan, Chi Hang, Zhu, Yan, Martins, Rui P., Mak, Pui In. CLUT-CIM: A Capacitance Lookup Table-Based Analog Compute-in-Memory Macro With Signed-Channel Training and Weight Updating for Nonuniform Quantization[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2024.
Authors:  Fu, Yuzhao;  Li, Jixuan;  Yu, Wei Han;  Un, Ka Fai;  Chan, Chi Hang; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:5.2/4.5 | Submit date:2024/07/04
Capacitance Lookup Table (Clut)  Circuits  Common Information Model (Computing)  Compute-in-memory (Cim)  Energy Efficiency  High Energy Efficiency  In-memory Computing  Indexes  Nonuniform Quantization (Nuq)  Table Lookup  Thermometers  Weight Updating