ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article PartitionTuner: An operator scheduler for deep‐learning compilers supporting multiple heterogeneous processing units
Cited 1 time in scopus Download 202 time Share share facebook twitter linkedin kakaostory
Authors
Misun Yu, Yongin Kwon, Jemin Lee, Jeman Park, Junmo Park, Taeho Kim
Issue Date
2023-04
Citation
ETRI Journal, v.45, no.2, pp.318-328
ISSN
1225-6463
Publisher
한국전자통신연구원
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.4218/etrij.2021-0446
Abstract
Recently, embedded systems, such as mobile platforms, have multiple processing units that can operate in parallel, such as centralized processing units (CPUs) and neural processing units (NPUs). We can use deep‐learning compilers to generate machine code optimized for these embedded systems from a deep neural network (DNN). However, the deep‐learning compilers proposed so far generate codes that sequentially execute DNN operators on a single processing unit or parallel codes for graphic processing units (GPUs). In this study, we propose PartitionTuner, an operator scheduler for deep‐learning compilers that supports multiple heterogeneous PUs including CPUs and NPUs. PartitionTuner can generate an operator‐scheduling plan that uses all available PUs simultaneously to minimize overall DNN inference time. Operator scheduling is based on the analysis of DNN architecture and the performance profiles of individual and group operators measured on heterogeneous processing units. By the experiments for seven DNNs, PartitionTuner generates scheduling plans that perform 5.03% better than a static type‐based operator‐scheduling technique for SqueezeNet. In addition, PartitionTuner outperforms recent profiling‐based operator‐scheduling techniques for ResNet50, ResNet18, and SqueezeNet by 7.18%, 5.36%, and 2.73%, respectively.
KSP Keywords
Deep neural network(DNN), Graphic processing unit(GPU), Heterogeneous processing, Machine code, Mobile platform, Neural processing, Scheduling plans, Scheduling technique, centralized processing, embedded system, neural network(NN)
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
Type 4: