Logo image
A Pipeline-Based Scheduler for Optimizing Latency of Convolution Neural Network Inference over Heterogeneous Multicore Systems
Conference paper

A Pipeline-Based Scheduler for Optimizing Latency of Convolution Neural Network Inference over Heterogeneous Multicore Systems

Hsin-I. Wu, Da-Yi Guo, Hsu-Hsun Chin and Ren-Song Tsay
Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020, pp.46-49
08/2020

Abstract

embedded system heterogeneous scheduler parallel computing Artificial Intelligence Computer Science Applications Hardware and Architecture Electrical and Electronic Engineering
Parallelization is a common design practice for throughput improvement on multicore systems. However, the existing operating systems' schedulers for CNN inference essentially divide the computational tasks of each convolution layer onto different CPU cores and cause significant inter-core feature-map data movement. Therefore, the overall performance is often degraded. In this paper, we propose a pipeline-based scheduler for convolution neural network inference parallelization with minimal feature-map data movement requirements. The experimental results show that our approach can achieve 73% performance improvement on throughput compared to the existing multi-thread scheduler.

Metrics

1 Record Views

Details

Logo image