GMCB:: An industrial benchmark for use in real-time mixed-criticality networks-on-chip

James Robert Harbin; Thomas David Fleming; Leandro Soares Indrusiak; Alan Burns

GMCB: An industrial benchmark for use in real-time mixed-criticality networks-on-chip

James Robert Harbin, Thomas David Fleming, Leandro Soares Indrusiak, Alan Burns

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper specifies and describes GMCB (Generic Mixed-Criticality
Benchmark), a benchmark industrial application model for testing
real-time mixed-criticality multicore systems incorporating a
network-on-chip (NoC). Task execution information such as periods,
latencies and criticality levels is specified. The communication
patterns between the tasks are defined, incorporating message sizes
transmitted between the source and destination nodes. Cycle-accurate
NoC simulation is used to evaluate the performance of the GMCB
model, evaluating the communication latencies encountered under
various task mappings. The behaviour of the application under a recent
mixed-criticality NoC protocol is considered.

Original language	English
Title of host publication	6th International Workshop on Analysis Tools and Methodologies for Embedded and Real-time Systems (WATERS)
Publication status	Published - 7 Jul 2015

MCC: Mixed Criticality Embedded Systems on Many-Core Platforms
Burns, A. (Principal investigator), Bate, I. J. (Co-investigator), Davis, R. I. (Co-investigator), Soares Indrusiak, L. (Co-investigator) & Harbin, J. R. (Researcher)
EPSRC
1/04/13 → 30/09/16
Project: Research project (funded) › Research

Cite this

@inproceedings{78c57239f2214caba9a0bc33067c7330,

title = "GMCB:: An industrial benchmark for use in real-time mixed-criticality networks-on-chip",

abstract = " This paper specifies and describes GMCB (Generic Mixed-Criticality Benchmark), a benchmark industrial application model for testing real-time mixed-criticality multicore systems incorporating a network-on-chip (NoC). Task execution information such as periods, latencies and criticality levels is specified. The communication patterns between the tasks are defined, incorporating message sizes transmitted between the source and destination nodes. Cycle-accurate NoC simulation is used to evaluate the performance of the GMCB model, evaluating the communication latencies encountered under various task mappings. The behaviour of the application under a recent mixed-criticality NoC protocol is considered.",

author = "Harbin, {James Robert} and Fleming, {Thomas David} and {Soares Indrusiak}, Leandro and Alan Burns",

year = "2015",

month = jul,

day = "7",

language = "English",

booktitle = "6th International Workshop on Analysis Tools and Methodologies for Embedded and Real-time Systems (WATERS)",

}

TY - GEN

T1 - GMCB:

T2 - An industrial benchmark for use in real-time mixed-criticality networks-on-chip

AU - Harbin, James Robert

AU - Fleming, Thomas David

AU - Soares Indrusiak, Leandro

AU - Burns, Alan

PY - 2015/7/7

Y1 - 2015/7/7

N2 - This paper specifies and describes GMCB (Generic Mixed-Criticality Benchmark), a benchmark industrial application model for testing real-time mixed-criticality multicore systems incorporating a network-on-chip (NoC). Task execution information such as periods, latencies and criticality levels is specified. The communication patterns between the tasks are defined, incorporating message sizes transmitted between the source and destination nodes. Cycle-accurate NoC simulation is used to evaluate the performance of the GMCB model, evaluating the communication latencies encountered under various task mappings. The behaviour of the application under a recent mixed-criticality NoC protocol is considered.

AB - This paper specifies and describes GMCB (Generic Mixed-Criticality Benchmark), a benchmark industrial application model for testing real-time mixed-criticality multicore systems incorporating a network-on-chip (NoC). Task execution information such as periods, latencies and criticality levels is specified. The communication patterns between the tasks are defined, incorporating message sizes transmitted between the source and destination nodes. Cycle-accurate NoC simulation is used to evaluate the performance of the GMCB model, evaluating the communication latencies encountered under various task mappings. The behaviour of the application under a recent mixed-criticality NoC protocol is considered.

M3 - Conference contribution

BT - 6th International Workshop on Analysis Tools and Methodologies for Embedded and Real-time Systems (WATERS)

ER -

GMCB: An industrial benchmark for use in real-time mixed-criticality networks-on-chip

Abstract

Projects

MCC: Mixed Criticality Embedded Systems on Many-Core Platforms

Cite this