LNPU: A 25.3TFLOPS/W Sparse Deep-Neural-Network Learning Processor with Fine-Grained Mixed Precision of FP8-FP16

被引：0

|

作者：

Lee, Jinsu ^{[1
]}

Lee, Juhyoung ^{[1
]}

Han, Donghyeon ^{[1
]}

Lee, Jinmook ^{[1
]}

Park, Gwangtae ^{[1
]}

Yoo, Hoi-Jun ^{[1
]}

机构：

[1] Korea Adv Inst Sci & Technol, Daejeon, South Korea

来源：

2019 IEEE INTERNATIONAL SOLID-STATE CIRCUITS CONFERENCE (ISSCC) | 2019年 / 62卷

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

引用

收藏

页码：142 / +

页数：3

相关论文

共 4 条

[1] An Energy-Efficient Sparse Deep-Neural-Network Learning Accelerator With Fine-Grained Mixed Precision of FP8-FP16
Lee, Jinsu
Lee, Juhyoung
Han, Donghyeon
Lee, Jinmook
Park, Gwangtae
Yoo, Hoi-Jun
[J]. IEEE SOLID-STATE CIRCUITS LETTERS, 2019, 2 (11): : 232 - 235
[2] A 4.27TFLOPS/W FP4/FP8 Hybrid-Precision Neural Network Training Processor Using Shift-Add MAC and Reconfigurable PE Array
Lee, Sunwoo
Park, Jeongwoo
Jeon, Dongsuk
[J]. IEEE 49TH EUROPEAN SOLID STATE CIRCUITS CONFERENCE, ESSCIRC 2023, 2023, : 221 - 224
[3] A Dynamic Execution Neural Network Processor for Fine-Grained Mixed-Precision Model Training Based on Online Quantization Sensitivity Analysis
Liu, Ruoyang
Wei, Chenhan
Yang, Yixiong
Wang, Wenxun
Yuan, Binbin
Yang, Huazhong
Liu, Yongpan
[J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2024, 59 (09) : 3082 - 3093
[4] A 146.52 TOPS/W Deep-Neural-Network Learning Processor with Stochastic Coarse-Fine Pruning and Adaptive Input/Output/Weight Skipping
Kim, Sangyeob
Lee, Juhyoung
Kang, Sanghoon
Lee, Jinmook
Yoo, Hoi-Jun
[J]. 2020 IEEE SYMPOSIUM ON VLSI CIRCUITS, 2020,