Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
並列性及びオンチップ・メモリを介した時間、空間及びエネルギー効率のよいニューラル推論
Document Type and Number:
Japanese Patent JP7220007
Kind Code:
B2
Abstract:
Neural inference chips and cores adapted to provide time, space, and energy efficient neural inference via parallelism and on-chip memory are provided. In various embodiments, the neural inference chips comprise: a plurality of neural cores interconnected by an on-chip network; a first on-chip memory for storing a neural network model, the first on-chip memory being connected to each of the plurality of cores by the on-chip network; a second on-chip memory for storing input and output data, the second on-chip memory being connected to each of the plurality of cores by the on-chip network.

Inventors:
Moda, Damendra
Arthur, John, Vernon
Sawada Jun
Ether, Stephen, Kyle
Apaswamy, Latinakumar
Taba, Brian, Saishaw
Cassidy, Andrew, Stephen
Datta, Parab
Flickner, Myron
Penner, Heart Moot
Clamo, Jennifer
Application Number:
JP2020551391A
Publication Date:
February 09, 2023
Filing Date:
March 28, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION
International Classes:
G06N3/063
Foreign References:
US9710265
US20160321537
Other References:
Giacomo Indiveri, et al.,Memory and Information Processing in Neuromorphic Systems,Proceedings of the IEEE,IEEE,2015年07月15日,Vol. 103, No. 8,Pages 1379-1397,,E-ISSN: 1558-2256
Attorney, Agent or Firm:
Tadashi Taneichi