English | 繁體

Search in the results

UM

Browse/Search Results:  1-10 of 52 Help

Selected(0)Clear Items/Page:    Sort:
A 362-TOPS/W Mixed-Signal MAC Macro With Sampling-Weight-Nonlinearity Cancellation and Dynamic-Amplified Accumulation Journal article
Zhang, Ran, Cen, Xueru, Un, Ka Fai, Guo, Mingqiang, Qi, Liang, Martins, Rui P., Sin, Sai Weng. A 362-TOPS/W Mixed-Signal MAC Macro With Sampling-Weight-Nonlinearity Cancellation and Dynamic-Amplified Accumulation[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2025, 1-13.
Authors:  Zhang, Ran;  Cen, Xueru;  Un, Ka Fai;  Guo, Mingqiang;  Qi, Liang; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:5.2/4.5 | Submit date：2025/01/22
Dac Driver  Dynamic Amplifier  Machine Learning (Ml)  Mixed-signal Multiply-and-accumulate (Mac)  Multi-bit Neural Network  
A 5T-SRAM Based Computing-in-Memory Macro Featuring Partial Sum Boosting and Analog Non-Uniform Quantization Conference paper
Xin, Guoqiang, Tan, Fei, Li, Junde, Chen, Junren, Yu, Wei Han, Un, Ka Fai, Martins, Rui P., Mak, Pui In. A 5T-SRAM Based Computing-in-Memory Macro Featuring Partial Sum Boosting and Analog Non-Uniform Quantization[C]:Institute of Electrical and Electronics Engineers Inc., 2024, 882-887.
Authors:  Xin, Guoqiang;  Tan, Fei;  Li, Junde;  Chen, Junren;  Yu, Wei Han; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0 | Submit date：2024/10/10
5t-sram  Analog Non-uniform Quantization (Anuq)  Computing-in-memory (Clm)  Machine Learning (Ml)  Matrix-vector Multiplication (Mvm)  Partial Sum Boosting (Psb)  
A 28-nm 18.7 TOPS/mm 2 89.4-to-234.6 TOPS/W 8b Single-Finger eDRAM Compute-in-Memory Macro With Bit-Wise Sparsity Aware and Kernel-Wise Weight Update/Refresh Journal article
Zhan, Yi, Yu, Wei Han, Un, Ka Fai, Martins, Rui P., Mak, Pui In. A 28-nm 18.7 TOPS/mm 2 89.4-to-234.6 TOPS/W 8b Single-Finger eDRAM Compute-in-Memory Macro With Bit-Wise Sparsity Aware and Kernel-Wise Weight Update/Refresh[J]. IEEE Journal of Solid-State Circuits, 2024, 59(11), 3866-3876.
Authors:  Zhan, Yi;  Yu, Wei Han;  Un, Ka Fai;  Martins, Rui P.;  Mak, Pui In
Favorite | TC[WOS]:2 TC[Scopus]:2  IF:4.6/5.6 | Submit date：2024/05/16
Compute-in-memory (Cim)  Deep Neural Network (Dnn)  Embedded Dynamic Random Access Memory (Edram)  Input-sparsity  Single-finger (Sf)  Weight Update/refresh  
GSLP-CIM: A 28-nm Globally Systolic and Locally Parallel CNN/Transformer Accelerator With Scalable and Reconfigurable eDRAM Compute-in-Memory Macro for Flexible Dataflow Journal article
Zhan, Yi, Yu, Wei Han, Un, Ka Fai, Martins, Rui P., Mak, Pui In. GSLP-CIM: A 28-nm Globally Systolic and Locally Parallel CNN/Transformer Accelerator With Scalable and Reconfigurable eDRAM Compute-in-Memory Macro for Flexible Dataflow[J]. IEEE Transactions on Circuits and Systems I-Regular Papers, 2024.
Authors:  Zhan, Yi;  Yu, Wei Han;  Un, Ka Fai;  Martins, Rui P.;  Mak, Pui In
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:5.2/4.5 | Submit date：2024/12/05
Neural Network (Nn)  Transformer  Embedded Dynamic Random-access Memory (Edram)  Compute-in-memory (Cim)  Systolic  Flexible Dataflow  
A 512-nW 0.003-mm2 Forward-Forward Black Box Trainer for an Analog Voice Activity Detector in 28-nm CMOS Journal article
LI JUNDE, XIN GUOQIANG, YU WEI HAN, UN KA FAI, RUI P MARTINS, MAK PUI IN. A 512-nW 0.003-mm2 Forward-Forward Black Box Trainer for an Analog Voice Activity Detector in 28-nm CMOS[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2024, 71(11), 4703-4707.
Authors:  LI JUNDE;  XIN GUOQIANG;  YU WEI HAN;  UN KA FAI;  RUI P MARTINS; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:4.0/3.7 | Submit date：2024/08/29
Voice Activity Detection  Convolution Neural Network  Edge Learning  Forward-forward Algorithm  Black Box Training  Back Propagation  
A 97.8 GOPS/W FPGA-Based Residual-Block-Aware CNN Accelerator Featuring Multi-Clock PW2 Pipeline and Adaptive-Resolution Quantization Journal article
Li, Jixuan, Li, Ke, Un, Ka Fai, Yu, Wei Han, Martins, Rui P., Mak, Pui In. A 97.8 GOPS/W FPGA-Based Residual-Block-Aware CNN Accelerator Featuring Multi-Clock PW2 Pipeline and Adaptive-Resolution Quantization[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2024.
Authors:  Li, Jixuan;  Li, Ke;  Un, Ka Fai;  Yu, Wei Han;  Martins, Rui P.; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:5.2/4.5 | Submit date：2024/12/26
Convolutional Neural Network (Cnn)  Digital Signal Processing (Dsp)  Field-programmable Gate Array (Fpga)  Processing Unit (Pe) Utilization  Residual Block  
An FPGA-Based Transformer Accelerator With Parallel Unstructured Sparsity Handling for Question-Answering Applications Journal article
Cao, Rujian, Zhao, Zhongyu, Un, Ka Fai, Yu, Wei Han, Martins, Rui P., Mak, Pui In. An FPGA-Based Transformer Accelerator With Parallel Unstructured Sparsity Handling for Question-Answering Applications[J]. IEEE Transactions on Circuits and Systems II-Express Briefs, 2024, 71(11), 4688-4692.
Authors:  Cao, Rujian;  Zhao, Zhongyu;  Un, Ka Fai;  Yu, Wei Han;  Martins, Rui P.; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:4.0/3.7 | Submit date：2024/10/10
Sparse Matrices  Computational Modeling  Transformers  Hardware  Energy Efficiency  Circuits  Throughput  Dataflow  Digital Accelerator  Energy-efficient  Field-programmable Gate Array (Fpga)  Sparsity  Transformer  
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, 71(11), 4996-5004.
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  
A 1.8% FAR, 2 ms Decision Latency, 1.73 nJ/Decision Keywords-Spotting (KWS) Chip Incorporating Transfer-Computing Speaker Verification, Hybrid-IF-Domain Computing and Scalable 5T-SRAM Journal article
TAN FEI, YU WEI HAN, LIN JINHAI, UN KA FAI, RUI P. MARTINS, MAK PUI IN. A 1.8% FAR, 2 ms Decision Latency, 1.73 nJ/Decision Keywords-Spotting (KWS) Chip Incorporating Transfer-Computing Speaker Verification, Hybrid-IF-Domain Computing and Scalable 5T-SRAM[J]. IEEE Journal of Solid State Circuits, 2024.
Authors:  TAN FEI;  YU WEI HAN;  LIN JINHAI;  UN KA FAI;  RUI P. MARTINS; et al.
Favorite |  | Submit date：2024/08/19
An FPGA-Based Transformer Accelerator with Parallel Unstructured Sparsity Handling for Question-Answering Applications Journal article
CAO RUJIAN, ZHAO ZHONGYU, UN KA FAI, YU WEI HAN, RUI P. MARTINS, MAK PUI IN. An FPGA-Based Transformer Accelerator with Parallel Unstructured Sparsity Handling for Question-Answering Applications[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2024.
Authors:  CAO RUJIAN;  ZHAO ZHONGYU;  UN KA FAI;  YU WEI HAN;  RUI P. MARTINS; et al.
Favorite |  | Submit date：2024/08/29