An Energy-Efficient Deep Convolutional Neural Network Inference Processor With Enhanced Output Stationary Dataflow in 65-nm CMOS
- 주제(키워드) Earth Observing System , Radio frequency , Energy consumption , System-on-chip , Memory management , Registers , Random access memory , Convolutional neural network (CNN) , dataflow , deep learning , energy-efficient processor , near-threshold voltage (NTV)
- 주제(기타) Computer Science, Hardware & Architecture
- 주제(기타) Engineering, Electrical & Electronic
- 설명문(일반) [Sim, Jaehyeong; Lee, Somin; Kim, Lee-Sup] Korea Adv Inst Sci & Technol, Sch Elect Engn, Daejeon 34141, South Korea; [Lee, Somin] Samsung Elect, Hwasung 18448, South Korea
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- 발행기관 IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- 발행년도 2020
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000182464
- 본문언어 영어
- Published As http://dx.doi.org/10.1109/TVLSI.2019.2935251
초록/요약
We propose a deep convolutional neural network (CNN) inference processor based on a novel enhanced output stationary (EOS) dataflow. Based on the observation that some activations are commonly used in two successive convolutions, the EOS dataflow employs dedicated register files (RFs) for storing such reused activation data to eliminate redundant memory accesses for highly energy-consuming SRAM banks. In addition, processing elements (PEs) are split into multiple small groups such that each group covers a tile of input activation map to increase the usability of activation RFs (ARFs). The processor has two different voltage/frequency domains. The computation domain with 512 PEs operates at near-threshold voltage (NTV) (0.4 V) and 60-MHz frequency to increase energy efficiency, while the rest of the processors including 848-KB SRAMs run at 0.7 V and 120-MHz frequency to increase both on-chip and off-chip memory bandwidths. The measurement results show that our processor is capable of running AlexNet at 831 GOPS/W, VGG-16 at 1151 GOPS/W, ResNet-18 at 1004 GOPS/W, and MobileNet at 948 GOPS/W energy efficiency.
more