Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LOCATE NEURAL NETWORK PERFORMANCE HOT SPOTS
Document Type and Number:
WIPO Patent Application WO/2022/227869
Kind Code:
A1
Abstract:
Implementation for locating performance hot spots include collecting sample data having instruction addresses, the sample data being for a neural network model and determining instructions in the instruction addresses that are performance hot spots. A listing file is used to map the instructions of the sample data that are performance hot spots to locations in a lower-level intermediate representation. A mapping file is used to map the locations of the lower-level intermediate representation that are performance hot spots to operations in one or more higher-level representations, one or more of the operations corresponding to the performance hot spots, the mapping file being generated from compiling the neural network model.

Inventors:
CHEN QINYUE (CN)
CAO LI (CN)
LI FEIFEI (CN)
SU HAN (CN)
Application Number:
PCT/CN2022/079778
Publication Date:
November 03, 2022
Filing Date:
March 08, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
IBM (US)
IBM CHINA CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
CN110308909A2019-10-08
CN112529175A2021-03-19
CN112465108A2021-03-09
US20130031536A12013-01-31
Attorney, Agent or Firm:
KING & WOOD MALLESONS (CN)
Download PDF: