A 22nm 41.8TFLOPS/W AI-Edge Transformer/CNN Nonvolatile-Processor Using QKV-Softmax-Layer-Fused Hybrid ReRAM-CIM and Concurrent-Transpose/Non-Transpose SRAM-CIM
Hung-Hsi Hsu(National Tsing Hua University), Meng‐Fan Chang(Taiwan Semiconductor Manufacturing Company (Taiwan)), Kea‐Tiong Tang(National Tsing Hua University), Chih-Cheng Hsieh(National Tsing Hua University), Shih-Hsin Teng(Taiwan Semiconductor Manufacturing Company (China)), Wei‐Ting Hsu(National Tsing Hua University), Chang-Yuan Chen(National Tsing Hua University), Ping-Sheng Wu(Taiwan Semiconductor Manufacturing Company (Taiwan)), Mon‐Shu Ho(National Chung Hsing University), Win-San Khwa(Taiwan Semiconductor Manufacturing Company (Taiwan)), Tai-Hao Wen(National Tsing Hua University), Yen-Che Huang(National Tsing Hua University), H. L. Lu(National Tsing Hua University), Yu‐Chen Chang(National Tsing Hua University), Hua-Jin Wen(National Tsing Hua University), Yu-Der Chih(Taiwan Semiconductor Manufacturing Company (Taiwan)), C.C. Wu(National Tsing Hua University), Ren-Shuo Liu(National Tsing Hua University), Tsung-Yung Jonathan Chang(Taiwan Semiconductor Manufacturing Company (Taiwan)), Chung‐Chuan Lo(National Tsing Hua University)
Cited by 1
Related Papers
An 8-Mb DC-Current-Free Binary-to-8b Precision ReRAM Nonvolatile Computing-in-Memory Macro using Time-Space-Readout with 1286.4-21.6TOPS/W for Edge-AI Devices
|2022 IEEE International Solid- State Circuits Conference (ISSCC)|2022|117
A 40-nm, 2M-Cell, 8b-Precision, Hybrid SLC-MLC PCM Computing-in-Memory Macro with 20.5 - 65.0TOPS/W for Tiny-Al Edge Devices
|2022 IEEE International Solid- State Circuits Conference (ISSCC)|2022|117
Fusion of memristor and digital compute-in-memory processing for energy-efficient edge computing
|Science|2024|99
A Nonvolatile Al-Edge Processor with 4MB SLC-MLC Hybrid-Mode ReRAM Compute-in-Memory Macro and 51.4-251TOPS/W
|Unknown|2023|72
8-b Precision 8-Mb ReRAM Compute-in-Memory Macro Using Direct-Current-Free Time-Domain Readout Scheme for AI Edge Devices
|IEEE Journal of Solid-State Circuits|2022|60