Review on FPGA-Based Accelerators in Deep Learning
For the past few years, with rapid development of Internet and big data, artificial intelligence has become popular, and it is the rise of deep learning that promotes the rapid development of AI. The problem that needs to be solved urgently in the era of big data is how to effectively analyze and u...
Guardado en:
Autor principal: | |
---|---|
Formato: | article |
Lenguaje: | ZH |
Publicado: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/76e948fca2fc46b29ce8fef02523a493 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:76e948fca2fc46b29ce8fef02523a493 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:76e948fca2fc46b29ce8fef02523a4932021-11-10T08:07:17ZReview on FPGA-Based Accelerators in Deep Learning10.3778/j.issn.1673-9418.21040121673-9418https://doaj.org/article/76e948fca2fc46b29ce8fef02523a4932021-11-01T00:00:00Zhttp://fcst.ceaj.org/CN/abstract/abstract2949.shtmlhttps://doaj.org/toc/1673-9418For the past few years, with rapid development of Internet and big data, artificial intelligence has become popular, and it is the rise of deep learning that promotes the rapid development of AI. The problem that needs to be solved urgently in the era of big data is how to effectively analyze and use extremely complex and diverse data, and then make full use of the value of data and benefit mankind. As a technology of machine learning, deep learning which has been widely used in speech recognition, image recognition, natural language processing and many other fields is an important magic weapon to solve this problem. It plays an increasingly important role in data processing and changes traditional machine learning methods. How to effectively accelerate the computing power of deep learning has always been the focus of scientific research. With strong parallel computing power and low power consumption, FPGA has become a strong competitor of GPU in the field of deep learning acceleration. Starting from the typical models of deep learning, on the basis of the existing characteristics of FPGA acceleration technology, the research status of various accelerators is summarized from four aspects: accelerators for neural network models, accelerators for a specific application, accelerators for optimization strategies, and general accelerator frameworks with hardware templates. Then, the performance of different acceleration technologies in different models is compared. Finally, the possible development direction in the future is prospected.LIU Tengda1, ZHU Junwen1, ZHANG Yiwen2+Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Pressarticledeep learning; neural networksfield programmable gate array (fpga)hardware acceleratorElectronic computers. Computer scienceQA75.5-76.95ZHJisuanji kexue yu tansuo, Vol 15, Iss 11, Pp 2093-2104 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
ZH |
topic |
deep learning; neural networks field programmable gate array (fpga) hardware accelerator Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
deep learning; neural networks field programmable gate array (fpga) hardware accelerator Electronic computers. Computer science QA75.5-76.95 LIU Tengda1, ZHU Junwen1, ZHANG Yiwen2+ Review on FPGA-Based Accelerators in Deep Learning |
description |
For the past few years, with rapid development of Internet and big data, artificial intelligence has become popular, and it is the rise of deep learning that promotes the rapid development of AI. The problem that needs to be solved urgently in the era of big data is how to effectively analyze and use extremely complex and diverse data, and then make full use of the value of data and benefit mankind. As a technology of machine learning, deep learning which has been widely used in speech recognition, image recognition, natural language processing and many other fields is an important magic weapon to solve this problem. It plays an increasingly important role in data processing and changes traditional machine learning methods. How to effectively accelerate the computing power of deep learning has always been the focus of scientific research. With strong parallel computing power and low power consumption, FPGA has become a strong competitor of GPU in the field of deep learning acceleration. Starting from the typical models of deep learning, on the basis of the existing characteristics of FPGA acceleration technology, the research status of various accelerators is summarized from four aspects: accelerators for neural network models, accelerators for a specific application, accelerators for optimization strategies, and general accelerator frameworks with hardware templates. Then, the performance of different acceleration technologies in different models is compared. Finally, the possible development direction in the future is prospected. |
format |
article |
author |
LIU Tengda1, ZHU Junwen1, ZHANG Yiwen2+ |
author_facet |
LIU Tengda1, ZHU Junwen1, ZHANG Yiwen2+ |
author_sort |
LIU Tengda1, ZHU Junwen1, ZHANG Yiwen2+ |
title |
Review on FPGA-Based Accelerators in Deep Learning |
title_short |
Review on FPGA-Based Accelerators in Deep Learning |
title_full |
Review on FPGA-Based Accelerators in Deep Learning |
title_fullStr |
Review on FPGA-Based Accelerators in Deep Learning |
title_full_unstemmed |
Review on FPGA-Based Accelerators in Deep Learning |
title_sort |
review on fpga-based accelerators in deep learning |
publisher |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
publishDate |
2021 |
url |
https://doaj.org/article/76e948fca2fc46b29ce8fef02523a493 |
work_keys_str_mv |
AT liutengda1zhujunwen1zhangyiwen2 reviewonfpgabasedacceleratorsindeeplearning |
_version_ |
1718440387690889216 |