Automatic workload generation for system-level exploration based on modified GCC compiler

Jari Kreku, Kari Tiensyrjä, Geert Vanmeerbeeck

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

14 Citations (Scopus)

Abstract

Future embedded system products, e.g. smart handheld mobile terminals, will accommodate a large number of applications that will partly run sequentially and independently, partly concurrently and interacting on massively parallel computing platforms. Already for systems of moderate complexity, the design space will be huge and its exploration requires that the system architect is able to quickly evaluate the performances of candidate architectures and application mappings. The mainstream evaluation technique today is the system-level performance simulation of the applications and platforms using abstracted workload and processing capacity models, respectively. These virtual system models allow fast simulation of large systems at an early phase of development with reasonable modeling effort and time. The accuracy of the performance results is dependent on how closely the models used reflect the actual system. This paper presents a compiler based technique for automatic generation of workload models for performance simulation, while exploiting an overall approach and platform performance capacity models developed previously. The resulting workload models are experimented using x264 video and JPEG encoding application examples.
Original languageEnglish
Title of host publicationProceedings of the Conference on Design, Automation and Test in Europe
Subtitle of host publicationDresden, Germany, March 08 - 12, 2010
PublisherAssociation for Computing Machinery ACM
Pages369-374
ISBN (Print)978-3-9810801-6-2
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
EventConference on Design, Automation and Test in Europe, DATE 2010 - Dresden, Germany
Duration: 8 Mar 201012 Mar 2010

Conference

ConferenceConference on Design, Automation and Test in Europe, DATE 2010
Abbreviated titleDATE 2010
CountryGermany
CityDresden
Period8/03/1012/03/10

Fingerprint

Parallel processing systems
Embedded systems
Processing

Keywords

  • embedded software
  • embedded system
  • performance evaluation
  • performance simulation
  • workload modelling
  • workload simulation
  • GCC
  • compilers

Cite this

Kreku, J., Tiensyrjä, K., & Vanmeerbeeck, G. (2010). Automatic workload generation for system-level exploration based on modified GCC compiler. In Proceedings of the Conference on Design, Automation and Test in Europe: Dresden, Germany, March 08 - 12, 2010 (pp. 369-374). [5457175] Association for Computing Machinery ACM.
Kreku, Jari ; Tiensyrjä, Kari ; Vanmeerbeeck, Geert. / Automatic workload generation for system-level exploration based on modified GCC compiler. Proceedings of the Conference on Design, Automation and Test in Europe: Dresden, Germany, March 08 - 12, 2010. Association for Computing Machinery ACM, 2010. pp. 369-374
@inproceedings{616868e74d734b3996ee0d727d6a38bb,
title = "Automatic workload generation for system-level exploration based on modified GCC compiler",
abstract = "Future embedded system products, e.g. smart handheld mobile terminals, will accommodate a large number of applications that will partly run sequentially and independently, partly concurrently and interacting on massively parallel computing platforms. Already for systems of moderate complexity, the design space will be huge and its exploration requires that the system architect is able to quickly evaluate the performances of candidate architectures and application mappings. The mainstream evaluation technique today is the system-level performance simulation of the applications and platforms using abstracted workload and processing capacity models, respectively. These virtual system models allow fast simulation of large systems at an early phase of development with reasonable modeling effort and time. The accuracy of the performance results is dependent on how closely the models used reflect the actual system. This paper presents a compiler based technique for automatic generation of workload models for performance simulation, while exploiting an overall approach and platform performance capacity models developed previously. The resulting workload models are experimented using x264 video and JPEG encoding application examples.",
keywords = "embedded software, embedded system, performance evaluation, performance simulation, workload modelling, workload simulation, GCC, compilers",
author = "Jari Kreku and Kari Tiensyrj{\"a} and Geert Vanmeerbeeck",
year = "2010",
language = "English",
isbn = "978-3-9810801-6-2",
pages = "369--374",
booktitle = "Proceedings of the Conference on Design, Automation and Test in Europe",
publisher = "Association for Computing Machinery ACM",
address = "United States",

}

Kreku, J, Tiensyrjä, K & Vanmeerbeeck, G 2010, Automatic workload generation for system-level exploration based on modified GCC compiler. in Proceedings of the Conference on Design, Automation and Test in Europe: Dresden, Germany, March 08 - 12, 2010., 5457175, Association for Computing Machinery ACM, pp. 369-374, Conference on Design, Automation and Test in Europe, DATE 2010, Dresden, Germany, 8/03/10.

Automatic workload generation for system-level exploration based on modified GCC compiler. / Kreku, Jari; Tiensyrjä, Kari; Vanmeerbeeck, Geert.

Proceedings of the Conference on Design, Automation and Test in Europe: Dresden, Germany, March 08 - 12, 2010. Association for Computing Machinery ACM, 2010. p. 369-374 5457175.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Automatic workload generation for system-level exploration based on modified GCC compiler

AU - Kreku, Jari

AU - Tiensyrjä, Kari

AU - Vanmeerbeeck, Geert

PY - 2010

Y1 - 2010

N2 - Future embedded system products, e.g. smart handheld mobile terminals, will accommodate a large number of applications that will partly run sequentially and independently, partly concurrently and interacting on massively parallel computing platforms. Already for systems of moderate complexity, the design space will be huge and its exploration requires that the system architect is able to quickly evaluate the performances of candidate architectures and application mappings. The mainstream evaluation technique today is the system-level performance simulation of the applications and platforms using abstracted workload and processing capacity models, respectively. These virtual system models allow fast simulation of large systems at an early phase of development with reasonable modeling effort and time. The accuracy of the performance results is dependent on how closely the models used reflect the actual system. This paper presents a compiler based technique for automatic generation of workload models for performance simulation, while exploiting an overall approach and platform performance capacity models developed previously. The resulting workload models are experimented using x264 video and JPEG encoding application examples.

AB - Future embedded system products, e.g. smart handheld mobile terminals, will accommodate a large number of applications that will partly run sequentially and independently, partly concurrently and interacting on massively parallel computing platforms. Already for systems of moderate complexity, the design space will be huge and its exploration requires that the system architect is able to quickly evaluate the performances of candidate architectures and application mappings. The mainstream evaluation technique today is the system-level performance simulation of the applications and platforms using abstracted workload and processing capacity models, respectively. These virtual system models allow fast simulation of large systems at an early phase of development with reasonable modeling effort and time. The accuracy of the performance results is dependent on how closely the models used reflect the actual system. This paper presents a compiler based technique for automatic generation of workload models for performance simulation, while exploiting an overall approach and platform performance capacity models developed previously. The resulting workload models are experimented using x264 video and JPEG encoding application examples.

KW - embedded software

KW - embedded system

KW - performance evaluation

KW - performance simulation

KW - workload modelling

KW - workload simulation

KW - GCC

KW - compilers

M3 - Conference article in proceedings

SN - 978-3-9810801-6-2

SP - 369

EP - 374

BT - Proceedings of the Conference on Design, Automation and Test in Europe

PB - Association for Computing Machinery ACM

ER -

Kreku J, Tiensyrjä K, Vanmeerbeeck G. Automatic workload generation for system-level exploration based on modified GCC compiler. In Proceedings of the Conference on Design, Automation and Test in Europe: Dresden, Germany, March 08 - 12, 2010. Association for Computing Machinery ACM. 2010. p. 369-374. 5457175