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

Jinsu Lee, Juhyoung Lee, Donghyeon Han, Jinmook Lee, Gwangtae Park, Hoi-Jun Yoo. LNPU: A 25.3TFLOPS/W Sparse Deep-Neural-Network Learning Processor with Fine-Grained Mixed Precision of FP8-FP16. In IEEE International Solid- State Circuits Conference, ISSCC 2019, San Francisco, CA, USA, February 17-21, 2019. pages 142-144, IEEE, 2019. [doi]

Abstract

Abstract is missing.