A Heterogeneous RISC-V Processor for Efficient DNN Application in Smart Sensing System
| Autor: | Meng Zhang, Yuyu Du, Yidong Yuan, Shengbing Zhang, Chuxi Li, Haifeng Zhang, Hongqing Guo, Xiaoti Wu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Edge device
Dataflow Computer science Chemical technology Pipeline (computing) intelligent computing architecture RISC-V TP1-1185 Biochemistry Article SIMD Atomic and Molecular Physics and Optics Analytical Chemistry Computer architecture Parallel processing (DSP implementation) Very long instruction word sensing system VLIW Neural Networks Computer Electrical and Electronic Engineering Latency (engineering) Instrumentation dnn |
| Zdroj: | Sensors Volume 21 Issue 19 Sensors, Vol 21, Iss 6491, p 6491 (2021) Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| Popis: | Extracting features from sensing data on edge devices is a challenging application for which deep neural networks (DNN) have shown promising results. Unfortunately, the general micro-controller-class processors which are widely used in sensing system fail to achieve real-time inference. Accelerating the compute-intensive DNN inference is, therefore, of utmost importance. As the physical limitation of sensing devices, the design of processor needs to meet the balanced performance metrics, including low power consumption, low latency, and flexible configuration. In this paper, we proposed a lightweight pipeline integrated deep learning architecture, which is compatible with open-source RISC-V instructions. The dataflow of DNN is organized by the very long instruction word (VLIW) pipeline. It combines with the proposed special intelligent enhanced instructions and the single instruction multiple data (SIMD) parallel processing unit. Experimental results show that total power consumption is about 411 mw and the power efficiency is about 320.7 GOPS/W. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |