Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
BNRP-BASED CONFIGURABLE PARALLEL GENERAL CONVOLUTIONAL NEURAL NETWORK ACCELERATOR
Document Type and Number:
WIPO Patent Application WO/2020/258529
Kind Code:
A1
Abstract:
A BNRP-based configurable parallel general convolutional neural network accelerator, which relates to the technical fields of calculation, inference and counting. The accelerator comprises: a mode configurator, a convolution calculator, a BNRP calculator, a data communication unit, and a data compression encoder/decoder. The convolution calculator comprises T systolic convolution arrays having a size of R*C, and each systolic convolution array is configured with corresponding input and output feature map buffer regions and configuration information data buffer regions. The BNRP calculator may execute two calculation modes, and comprises: R*T data input and output interfaces, R*T poolers, a normalization calculation module and a nonlinear activation calculation module, wherein each functional module is executed in parallel in a pipeline. According to the characteristics of various network structures, the execution mode of parallel acceleration calculation modules may be dynamically configured, and the versatility is good. For convolutional neural networks that have complex network structures and that are relatively large scale, the complexity of calculation may be greatly reduced, while power consumption is low and throughput is high.

Inventors:
LU SHENGLI (CN)
FAN XUEMEI (CN)
PANG WEI (CN)
LIU HAO (CN)
SHU CHENGHAO (CN)
FU CHENGLONG (CN)
Application Number:
PCT/CN2019/105534
Publication Date:
December 30, 2020
Filing Date:
September 12, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV SOUTHEAST (CN)
International Classes:
G06N3/04
Foreign References:
CN109635944A2019-04-16
CN105631519A2016-06-01
CN107239824A2017-10-10
CN105184366A2015-12-23
US20180341495A12018-11-29
Attorney, Agent or Firm:
NANJING RUIHONG PATENT & TRADEMARK AGENCY (ORDINARY PARTNERSHIP) (CN)
Download PDF: