Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
NEURAL NETWORK GENERATION DEVICE, NEURAL NETWORK CONTROL METHOD, AND SOFTWARE GENERATION PROGRAM
Document Type and Number:
WIPO Patent Application WO/2022/085661
Kind Code:
A1
Abstract:
This neural network generation device generates a neural network execution model for computing a neural network, and comprises: an execution model generation unit that generates the neural network execution model on the basis of hardware information for hardware on which the neural network execution model operates, and network information for the neural network; and a software generation unit that generates software for operating neural network hardware in which the neural network execution model is installed on the hardware.

Inventors:
KANAI JUNICHI (JP)
YAMAOKA CHUTA (JP)
Application Number:
PCT/JP2021/038530
Publication Date:
April 28, 2022
Filing Date:
October 19, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
LEAPMIND INC (JP)
International Classes:
G06N3/04; G06N3/063; G06N3/10
Foreign References:
US20190286972A12019-09-19
Other References:
PARK JAY H, YUN GYEONGCHAN, YI CHANG M, NGUYEN NGUYEN T, LEE SEUNGMIN, CHOI JAESIK, NOH SAM H, CHOI YOUNG-RI: "HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism", PROCEEDINGS OF THE 2020 USENIX ANNUAL TECHNICAL CONFERENCE, USENIX ASSOCIATION, 15 July 2020 (2020-07-15) - 17 July 2020 (2020-07-17), pages 307 - 321, XP055903366
SONG LINGHAO; CHEN FAN; ZHUO YOUWEI; QIAN XUEHAI; LI HAI; CHEN YIRAN: "AccPar: Tensor Partitioning for Heterogeneous Deep Learning Accelerators", 2020 IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE COMPUTER ARCHITECTURE (HPCA), IEEE, 22 February 2020 (2020-02-22), pages 342 - 355, XP033755316, DOI: 10.1109/HPCA47549.2020.00036
Attorney, Agent or Firm:
NISHIZAWA Kazuyoshi et al. (JP)
Download PDF: