Title:
DEEP LEARNING INFERENCE SYSTEM
Document Type and Number:
WIPO Patent Application WO/2023/105616
Kind Code:
A1
Abstract:
This deep learning inference system comprises a DRAM (100a), and processors (101a-1, 101a-2) for reading an operation code (200) and a parameter (201) from a global memory space (1007) of the DRAM (100a) and performing computation of a neural network. The processors (101a-1, 101a-2) read data to be processed (202-1, 202-2) from local memory spaces (1000, 1001) that correspond to subject clients, perform computation, and then store the results of computation in the local memory spaces (1000, 1001) that correspond to the subject clients.
Inventors:
TANAKA KENJI (JP)
ARIKAWA YUKI (JP)
ITO TSUYOSHI (JP)
MIURA NAOKI (JP)
SAKAMOTO TAKESHI (JP)
ARIKAWA YUKI (JP)
ITO TSUYOSHI (JP)
MIURA NAOKI (JP)
SAKAMOTO TAKESHI (JP)
Application Number:
PCT/JP2021/044891
Publication Date:
June 15, 2023
Filing Date:
December 07, 2021
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06N3/10
Foreign References:
| US20180253635A1 | 2018-09-06 | |||
| US20200184320A1 | 2020-06-11 | |||
| JP2020515989A | 2020-05-28 |
Other References:
CHRISTOPHER OLSTON; NOAH FIEDEL; KIRIL GOROVOY; JEREMIAH HARMSEN; LI LAO; FANGWEI LI; VINU RAJASHEKHAR; SUKRITI RAMESH; JORDAN SOY: "TensorFlow-Serving: Flexible, High-Performance ML Serving", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 17 December 2017 (2017-12-17), 201 Olin Library Cornell University Ithaca, NY 14853 , XP080846818
Attorney, Agent or Firm:
YAMAKAWA, Shigeki et al. (JP)
Download PDF: