Document Open Access Logo

Towards Adaptive Multi-Alternative Process Network

Authors Hasna Bouraoui , Chadlia Jerad , Jeronimo Castrillon

PDF
Thumbnail PDF

File

OASIcs.PARMA-DITAM.2021.1.pdf
  • Filesize: 1.03 MB
  • 11 pages

Document Identifiers

Author Details

Hasna Bouraoui
  • Technische Universität Dresden, Germany
Chadlia Jerad
  • University of Manouba, Tunisia
  • University of Carthage, Tunis, Tunisia
Jeronimo Castrillon
  • Technische Universität Dresden, Germany

Cite AsGet BibTex

Hasna Bouraoui, Chadlia Jerad, and Jeronimo Castrillon. Towards Adaptive Multi-Alternative Process Network. In 12th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures and 10th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2021). Open Access Series in Informatics (OASIcs), Volume 88, pp. 1:1-1:11, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
https://doi.org/10.4230/OASIcs.PARMA-DITAM.2021.1

Abstract

With the increase of voice-controlled systems, speech based recognition applications are gaining more attention. Such applications need to adapt to hardware platforms to offer the required performance. Given the streaming nature of these applications, dataflow models are a common choice for model-based design and execution on parallel embedded platforms. However, most of today’s models are built on top of classical static dataflow with adaptivity extensions to express data parallelism. In this paper, we define and describe an approach for algorithmic adaptivity to express richer sets of variants and trade-offs. For this, we introduce multi-Alternative Process Network (mAPN), a high-level abstract representation where several process networks of the same application coexist. We describe an algorithm for automatic generation of all possible alternatives. The mAPN is enriched with meta-data serving to endow the alternatives with annotations in terms of a specific metric, helping to extract the most suitable alternative depending on the available computational resources and application/user constraints. We motivate the approach by the automatic subtitling application (ASA) as use case and run the experiments on an mAPN sample consisting of 12 randomly selected possible variants.

Subject Classification

ACM Subject Classification
  • Theory of computation → Streaming models
Keywords
  • High level process network
  • algorithmic adaptivity
  • automatic subtitling application

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

References

  1. C. Aliprandi, C. Scudellari, I. Gallucci, N. Piccinini, M. Raffaelli, A. del Pozo, A. Alvarez, Ha. Arzelus, R. Cassaca, T. Luis, et al. Automatic live subtitling: state of the art, expectations and current trends. In Proceedings of NAB Broadcast Engineering Conference: Papers on Advanced Media Technologies, Las Vegas, page 23, 2014. Google Scholar
  2. Jason Ansel, Cy Chan, Yee Lok Wong, Marek Olszewski, Qin Zhao, Alan Edelman, and Saman Amarasinghe. Petabricks: a language and compiler for algorithmic choice. ACM Sigplan Notices, 44(6):38-49, 2009. Google Scholar
  3. Bishnupriya Bhattacharya and Shuvra S Bhattacharyya. Parameterized dataflow modeling for dsp systems. IEEE Transactions on Signal Processing, 49(10):2408-2421, 2001. Google Scholar
  4. G. Bilsen, M. Engels, R. Lauwereins, and J. Peperstraete. Cycle-static dataflow. IEEE Transactions on Signal Processing, 44(2):397-408, 1996. Google Scholar
  5. Adnan Bouakaz, Pascal Fradet, and Alain Girault. A survey of parametric dataflow models of computation. ACM Transactions on Design Automation of Electronic Systems (TODAES), 22(2):1-25, 2017. Google Scholar
  6. Hasna Bouraoui, Chadlia Jerad, Anupam Chattopadhyay, and Nejib Ben Hadj-Alouane. Hardware architectures for embedded speaker recognition applications: a survey. ACM Transactions on Embedded Computing Systems (TECS), 16(3):78, 2017. Google Scholar
  7. Dai Bui and Edward A Lee. Streamorph: a case for synthesizing energy-efficient adaptive programs using high-level abstractions. In Proceedings of EMSOFT, page 20. IEEE Press, 2013. Google Scholar
  8. Jeronimo Castrillon, Stefan Schürmans, Anastasia Stulova, Weihua Sheng, Torsten Kempf, Rainer Leupers, Gerd Ascheid, and Heinrich Meyr. Component-based waveform development: The nucleus tool flow for efficient and portable software defined radio. Analog Integrated Circuits and Signal Processing, 69(2-3):173-190, December 2011. Google Scholar
  9. Marco Danelutto, Daniele De Sensi, and Massimo Torquati. A power-aware, self-adaptive macro data flow framework. Parallel Processing Letters, 27(01):1740004, 2017. Google Scholar
  10. Karol Desnos, Maxime Pelcat, Jean-François Nezan, Shuvra S Bhattacharyya, and Slaheddine Aridhi. Pimm: Parameterized and interfaced dataflow meta-model for mpsocs runtime reconfiguration. In 2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS), pages 41-48. IEEE, 2013. Google Scholar
  11. Brecht Desplanques, Kris Demuynck, and Jean-Pierre Martens. Adaptive speaker diarization of broadcast news based on factor analysis. Computer Speech & Language, 46:72-93, 2017. Google Scholar
  12. Pascal Fradet, Alain Girault, Ruby Krishnaswamy, Xavier Nicollin, and Arash Shafiei. RDF: Reconfigurable Dataflow (extended version). Research Report RR-9227, INRIA Grenoble - Rhône-Alpes, December 2018. URL: https://hal.inria.fr/hal-02079683.
  13. Amir Hossein Ghamarian, Marc CW Geilen, Sander Stuijk, Twan Basten, Bart D Theelen, Mohammad Reza Mousavi, Arno JM Moonen, and Marco JG Bekooij. Throughput analysis of synchronous data flow graphs. In Sixth International Conf. on Application of Concurrency to System Design (ACSD'06), pages 25-36. IEEE, 2006. Google Scholar
  14. Amir H Hormati, Yoonseo Choi, Manjunath Kudlur, Rodric Rabbah, Trevor Mudge, and Scott Mahlke. Flextream: Adaptive compilation of streaming applications for heterogeneous architectures. In Proceedings of PACT, pages 214-223. IEEE, 2009. Google Scholar
  15. Gilles KAHN. The semantics of a simple language for parallel programming. In Information Processing, 74:471-475, 1974. Google Scholar
  16. Robert Khasanov, Andrés Goens, and Jeronimo Castrillon. Implicit data-parallelism in Kahn process networks: Bridging the MacQueen Gap. In Proceedings of PARMA-DITAM, pages 20-25. ACM, 2018. Google Scholar
  17. Mohaddeseh Nosratighods, Eliathamby Ambikairajah, and Julien Epps. Speaker verification using a novel set of dynamic features. In 18th International Conference on Pattern Recognition (ICPR'06), volume 4, pages 266-269. IEEE, 2006. Google Scholar
  18. Claudius Ptolemaeus. System Design, Modeling, and Simulation using Ptolemy II, 2014. Ptolemy.org, 2014. Google Scholar
  19. John R. Rice et al. The algorithm selection problem. Advances in computers, 15(65-118):5, 1976. Google Scholar
  20. Lars Schor, Iuliana Bacivarov, Hoeseok Yang, and Lothar Thiele. Adapnet: Adapting process networks in response to resource variations. In Proceedings of CASES, page 22. ACM, 2014. Google Scholar
  21. Sander Stuijk, Marc Geilen, Bart Theelen, and Twan Basten. Scenario-aware dataflow: Modeling, analysis and implementation of dynamic applications. In Proceedings of SAMOS, pages 404-411. IEEE, 2011. Google Scholar
  22. Anastasia Stulova, Rainer Leupers, and Gerd Ascheid. Throughput driven transformations of synchronous data flows for mapping to heterogeneous mpsocs. In Proceedings of SAMOS, pages 144-151. IEEE, 2012. Google Scholar
  23. Roberto Togneri and Daniel Pullella. An overview of speaker identification: Accuracy and robustness issues. IEEE Circuits and Systems Magazine, 11(2):23-61, 2011. Google Scholar
  24. OB Tuzun, M Demirekler, and KB Nakiboglu. Comparison of parametric and non-parametric representations of speech for recognition. In Electrotechnical Conference, 1994. Proceedings., 7th Mediterranean, pages 65-68. IEEE, 1994. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact