Task Concurrency Management Experiment for Power-Efficient Speed-Up of Embedded MPEG4 IM1 Player

Authors:
Aggeliki Prayati;Chun Wong;Paul Marchal;Francky Catthoor;Hugo de Man;Nathalie Cossement;Rudy Lauwereins;Diederik Verkest;Alexis Birbas
Affiliations:
-;-;-;-;-;-;-;-;-
Venue:
ICPP '00 Proceedings of the 2000 International Workshop on Parallel Processing
Year:
2000

Citing 0
Cited 9

Task concurrency management methodology summary

Proceedings of the conference on Design, automation and test in Europe
Task concurrency management methodology to schedule the MPEG4 IM1 player on a highly parallel processor platform

Proceedings of the ninth international symposium on Hardware/software codesign
Multiprocessor mapping of process networks: a JPEG decoding case study

Proceedings of the 15th international symposium on System Synthesis
Managing dynamic concurrent tasks in embedded real-time multimedia systems

Proceedings of the 15th international symposium on System Synthesis
Energy-Aware Runtime Scheduling for Embedded-Multiprocessor SOCs

IEEE Design & Test
Dynamic Memory Oriented Transformations in the MPEG4 IM1-Player on a Low Power Platform

PACS '00 Proceedings of the First International Workshop on Power-Aware Computer Systems-Revised Papers
Energy-optimizing source code transformations for operating system-driven embedded software

ACM Transactions on Embedded Computing Systems (TECS)
Efficiently migrating real-time systems to multi-cores

ETFA'09 Proceedings of the 14th IEEE international conference on Emerging technologies & factory automation
Energy and throughput aware fuzzy logic based reconfiguration for MPSoCs

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the concurrent task management of complex multimedia systems, like the MPEG4 IM1 player. Starting with a critical part of the code in the IM1 player, we extracted the concurrency hidden by implementation decisions and represented it with our 驴grey-box驴 modeling approach. Based on this 驴grey-box驴 model, high-level transformations have been made to improve the concurrency. By scheduling the transformed graph, we have improved the performance of an important bottleneck in the system layer of the IM1 player, while simultaneously lowering the system energy cost. A two-processor target platform is used in the experiment, combining processors running at a high Vdd and a low Vdd respectively.