Next Article in Journal
Data-Driven Analyses of Low Salinity Waterflooding in Carbonates
Next Article in Special Issue
A Novel Framework for Testing High-Speed Serial Interfaces in Multiprocessor Based Real-Time Embedded System
Previous Article in Journal
A Co-Rotational Meshfree Method for the Geometrically Nonlinear Analysis of Structures
Previous Article in Special Issue
Network Calculus-Based Latency for Time-Triggered Traffic under Flexible Window-Overlapping Scheduling (FWOS) in a Time-Sensitive Network (TSN)
 
 
Article

A Measurement-Based Message-Level Timing Prediction Approach for Data-Dependent SDFGs on Tile-Based Heterogeneous MPSoCs

1
OFFIS e.V., 26121 Oldenburg, Germany
2
Département Électronique et Technologies Numériques, University of Nantes, 44306 Nantes, France
3
Department für Informatik, Faculty II, University of Oldenburg, 26111 Oldenburg, Germany
*
Author to whom correspondence should be addressed.
Academic Editor: Luigi Pomante
Appl. Sci. 2021, 11(14), 6649; https://doi.org/10.3390/app11146649
Received: 31 May 2021 / Revised: 12 July 2021 / Accepted: 16 July 2021 / Published: 20 July 2021
(This article belongs to the Special Issue New Trends in Real-Time Embedded Systems)
Fast yet accurate performance and timing prediction of complex parallel data flow applications on multi-processor systems remains a very difficult discipline. The reason for it comes from the complexity of the data flow applications w.r.t. data dependent execution paths and the hardware platform with shared resources, like buses and memories. This combination may lead to complex timing interferences that are difficult to express in pure analytical or classical simulation-based approaches. In this work, we propose the combination of timing measurement and statistical simulation models for probabilistic timing and performance prediction of Synchronous Data Flow (SDF) applications on MPSoCs with shared memories. We exploit the separation of computation and communication in our SDF model of computation to set-up simulation-based performance prediction models following different abstraction approaches. We especially propose a message-level communication model driven by a data-dependent probabilistic execution phase timing model. We compare our work against measurement on two case-studies from the computer vision domain: a Sobel filter and a JPEG decoder. We show that the accuracy and execution time of our modeling and evaluation framework outperforms existing approaches and is suitable for a fast yet accurate design space exploration. View Full-Text
Keywords: system-level modeling; multi-processor; timing prediction system-level modeling; multi-processor; timing prediction
Show Figures

Figure 1

  • Externally hosted supplementary file 1
    Doi: https://doi.org/10.5281/zenodo.4876805
    Link: https://zenodo.org/record/4876805
    Description: Sources and data of the SystemC simulation used in our journal article for MDPI Applied Sciences Special Issue "New Trends in Real-Time Embedded Systems"
MDPI and ACS Style

Stemmer, R.; Vu, H.-D.; Le Nours, S.; Grüttner, K.; Pillement, S.; Nebel, W. A Measurement-Based Message-Level Timing Prediction Approach for Data-Dependent SDFGs on Tile-Based Heterogeneous MPSoCs. Appl. Sci. 2021, 11, 6649. https://doi.org/10.3390/app11146649

AMA Style

Stemmer R, Vu H-D, Le Nours S, Grüttner K, Pillement S, Nebel W. A Measurement-Based Message-Level Timing Prediction Approach for Data-Dependent SDFGs on Tile-Based Heterogeneous MPSoCs. Applied Sciences. 2021; 11(14):6649. https://doi.org/10.3390/app11146649

Chicago/Turabian Style

Stemmer, Ralf, Hai-Dang Vu, Sébastien Le Nours, Kim Grüttner, Sébastien Pillement, and Wolfgang Nebel. 2021. "A Measurement-Based Message-Level Timing Prediction Approach for Data-Dependent SDFGs on Tile-Based Heterogeneous MPSoCs" Applied Sciences 11, no. 14: 6649. https://doi.org/10.3390/app11146649

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop