Tampere University of Technology

TUTCRIS Research Portal

Instrumentation-Driven Validation of Dataflow Applications

Research output: Contribution to journalArticleScientificpeer-review


Original languageEnglish
Pages (from-to)383–397
JournalJournal of Signal Processing Systems
Issue number3
Publication statusPublished - 2016
Publication typeA1 Journal article-refereed


Dataflow modeling offers a myriad of tools for designing and optimizing signal processing systems. A designer is able to take advantage of dataflow properties to effectively tune the system in connection with functionality and different performance metrics. However, a disparity in the specification of dataflow properties and the final implementation can lead to incorrect behavior that is difficult to detect. This motivates the problem of ensuring consistency between dataflow properties that are declared or otherwise assumed as part of dataflow-based application models, and the dataflow behavior that is exhibited by implementations that are derived from the models. In this paper, we address this problem by introducing a novel dataflow validation framework (DVF) that is able to identify disparities between an application’s formal dataflow representation and its implementation. DVF works by instrumenting the implementation of an application and monitoring the instrumentation data as the application executes. This monitoring process is streamlined so that DVF achieves validation without major overhead. We demonstrate the utility of our DVF through design and implementation case studies involving an automatic speech recognition application, a JPEG encoder, and an acoustic tracking application.


  • Dataflow graphs, Design validation, Models of computation, Signal processing systems

Publication forum classification

Field of science, Statistics Finland