Open AccessResearch on the Overview of Image Processing Architecture of Computer Based Deep Neural Network Accelerator
Author(s) -
De-qin Shu,
Hao Fan,
Liang Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2074/1/012010
Subject(s) - computer science , computation , artificial neural network , hardware acceleration , acceleration , reuse , architecture , cache , process (computing) , image processing , image (mathematics) , computer engineering , computer architecture , artificial intelligence , parallel computing , computer hardware , algorithm , operating system , field programmable gate array , engineering , visual arts , waste management , art , physics , classical mechanics
DNN algorithm still has many shortcomings in the process of operation, which need to be further solved. Specifically, there is more data reuse, and the repeated access of global cache takes up more resources and computation, thus reducing the efficiency of operation. Based on this, this paper first analyses the research status and value of the DNN accelerator, then studies the image processing architecture of the DNN accelerator, and finally gives the computer DNN model and acceleration algorithm analysis.