Off-line mapping of multi-rate dependent task sets to many-core platforms

Wolfgang Puffitsch; Eric Noulard; Claire Pagetti

doi:10.1007/s11241-015-9232-1

Off-line mapping of multi-rate dependent task sets to many-core platforms

Wolfgang Puffitsch, Eric Noulard, Claire Pagetti

Research output: Contribution to journal › Journal article › Research › peer-review

Abstract

This paper presents an approach to execute safety-critical applications on multi- and many-core processors in a predictable manner. We investigate three concrete platforms: the Intel Single-chip Cloud Computer, the Texas Instruments TMS320C6678 and the Tilera TILEmpower-Gx36. We define an execution model to safely execute dependent periodic task sets on these platforms. The four rules of the execution model entail that an off-line mapping of the application to the platform must be computed. The paper details our approach to automatically compute a valid mapping. Furthermore, we evaluate our approach, which is based on constraint programming, by applying it to several task sets that are derived from industrial applications.

Original language	English
Journal	Real-Time Systems
Volume	51
Issue number	5
Pages (from-to)	526-565
ISSN	0922-6443
DOIs	https://doi.org/10.1007/s11241-015-9232-1
Publication status	Published - 2015

Keywords

Real-time systems
Many-core architecture
Off-line scheduling
Constraint programming

Access to Document

10.1007/s11241-015-9232-1

Fingerprint Dive into the research topics of 'Off-line mapping of multi-rate dependent task sets to many-core platforms'. Together they form a unique fingerprint.

Cite this

@article{70873fdc78e44fd6a14bd49b95d91a41,

title = "Off-line mapping of multi-rate dependent task sets to many-core platforms",

abstract = "This paper presents an approach to execute safety-critical applications on multi- and many-core processors in a predictable manner. We investigate three concrete platforms: the Intel Single-chip Cloud Computer, the Texas Instruments TMS320C6678 and the Tilera TILEmpower-Gx36. We define an execution model to safely execute dependent periodic task sets on these platforms. The four rules of the execution model entail that an off-line mapping of the application to the platform must be computed. The paper details our approach to automatically compute a valid mapping. Furthermore, we evaluate our approach, which is based on constraint programming, by applying it to several task sets that are derived from industrial applications.",

keywords = "Real-time systems, Many-core architecture, Off-line scheduling, Constraint programming",

author = "Wolfgang Puffitsch and Eric Noulard and Claire Pagetti",

year = "2015",

doi = "10.1007/s11241-015-9232-1",

language = "English",

volume = "51",

pages = "526--565",

journal = "Real-Time Systems",

issn = "0922-6443",

publisher = "Springer New York",

number = "5",

}

TY - JOUR

T1 - Off-line mapping of multi-rate dependent task sets to many-core platforms

AU - Puffitsch, Wolfgang

AU - Noulard, Eric

AU - Pagetti, Claire

PY - 2015

Y1 - 2015

N2 - This paper presents an approach to execute safety-critical applications on multi- and many-core processors in a predictable manner. We investigate three concrete platforms: the Intel Single-chip Cloud Computer, the Texas Instruments TMS320C6678 and the Tilera TILEmpower-Gx36. We define an execution model to safely execute dependent periodic task sets on these platforms. The four rules of the execution model entail that an off-line mapping of the application to the platform must be computed. The paper details our approach to automatically compute a valid mapping. Furthermore, we evaluate our approach, which is based on constraint programming, by applying it to several task sets that are derived from industrial applications.

AB - This paper presents an approach to execute safety-critical applications on multi- and many-core processors in a predictable manner. We investigate three concrete platforms: the Intel Single-chip Cloud Computer, the Texas Instruments TMS320C6678 and the Tilera TILEmpower-Gx36. We define an execution model to safely execute dependent periodic task sets on these platforms. The four rules of the execution model entail that an off-line mapping of the application to the platform must be computed. The paper details our approach to automatically compute a valid mapping. Furthermore, we evaluate our approach, which is based on constraint programming, by applying it to several task sets that are derived from industrial applications.

KW - Real-time systems

KW - Many-core architecture

KW - Off-line scheduling

KW - Constraint programming

U2 - 10.1007/s11241-015-9232-1

DO - 10.1007/s11241-015-9232-1

M3 - Journal article

VL - 51

SP - 526

EP - 565

JO - Real-Time Systems

JF - Real-Time Systems

SN - 0922-6443

IS - 5

ER -