A Parametrizable High-Level Synthesis Library for Accelerating Neural Networks on FPGAs
Autor: | Diana Gohringer, Arsany Iskander, Lester Kalms, Muhammad Ali, Pedram Amini Rad |
---|---|
Rok vydání: | 2021 |
Předmět: |
Artificial neural network
Computer science Image processing 02 engineering and technology Data type Convolutional neural network Object detection 020202 computer hardware & architecture Theoretical Computer Science Computer engineering Hardware and Architecture Control and Systems Engineering Modeling and Simulation High-level synthesis Signal Processing Scalability 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Field-programmable gate array Information Systems |
Zdroj: | Journal of Signal Processing Systems. 93:513-529 |
ISSN: | 1939-8115 1939-8018 |
DOI: | 10.1007/s11265-021-01651-5 |
Popis: | In recent years, Convolutional Neural Network CNN have been incorporated in a large number of applications, including multimedia retrieval and image classification. However, CNN based algorithms are computationally and resource intensive and therefore difficult to be used in embedded systems. FPGA based accelerators are becoming more and more popular in research and industry due to their flexibility and energy efficiency. However, the available resources and the size of the on-chip memory can limit the performance of the FPGA accelerator for CNN. This work proposes an High-Level Synthesis HLS library for CNN algorithms. It contains seven different streaming-capable CNN (plus two conversion) functions for creating large neural networks with deep pipelines. The different functions have many parameter settings (e.g. for resolution, feature maps, data types, kernel size, parallelilization, accuracy, etc.), which also enable compile-time optimizations. Our functions are integrated into the HiFlipVX library, which is an open source HLS FPGA library for image processing and object detection. This offers the possibility to implement different types of computer vision applications with one library. Due to the various configuration and parallelization possibilities of the library functions, it is possible to implement a high-performance, scalable and resource-efficient system, as our evaluation of the MobileNets algorithm shows. |
Databáze: | OpenAIRE |
Externí odkaz: |