Energy optimization for multiprocessor embedded software

2015 Fiscal Year Final Research Report

• Project/Area Number: 24500036
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Software
• Research Institution: Nagoya University
• Principal Investigator: ZENG GANG 名古屋大学, 工学(系)研究科(研究院), 講師 (90456632)
• Co-Investigator(Kenkyū-buntansha): MATSUBARA YUTAKA 名古屋大学, 情報科学研究科, 助教 (30547500)
• Project Period (FY): 2012-04-01 – 2016-03-31
• Keywords: 組込みリアルタイムシステム / マルチプロセッサ / 省エネルギー / タスクスケジューリング

Outline of Final Research Achievements

First, we have proposed a tool chain and a real time operating system for energy optimization of embedded real-time application. The framework conducts both design time and run time optimization so that the energy consumption can be minimized. Its effectiveness has been validated by simulation and experiments on a real chip. Second, to save energy for task with long execution time, we have proposed a task migration model and an ILP (Integer linear Programming) formulation to divide the large task into two small subtasks which can migrate between two processors. The simulation results demonstrated our method can save as much as 10% energy than existing methods.

Free Research Field

ソフトウェア