Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication

M.H. Wiggers; Marco J.G. Bekooij; Marco Jan Gerrit Bekooij; Gerardus Johannes Maria Smit

doi:10.1109/RTAS.2008.10

Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication

M.H. Wiggers, Marco J.G. Bekooij, Marco Jan Gerrit Bekooij, Gerardus Johannes Maria Smit

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

46 Citations (Scopus)

295 Downloads (Pure)

Abstract

Streaming applications are often implemented as task graphs, in which data is communicated from task to task over buffers. Currently, techniques exist to compute buffer capacities that guarantee satisfaction of the throughput constraint if the amount of data produced and consumed by the tasks is known at design-time. However, applications such as audio and video decoders have tasks that produce and consume an amount of data that depends on the decoded stream. This paper introduces a dataflow model that allows for data-dependent communication, together with an algorithm that computes buffer capacities that guarantee satisfaction of a throughput constraint. The applicability of this algorithm is demonstrated by computing buffer capacities for an H.263 video decoder.

Original language	Undefined
Title of host publication	Proceedings of the 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS'08
Place of Publication	Los Alamitos
Publisher	IEEE
Pages	183-194
Number of pages	12
ISBN (Print)	978-0-7695-3146-5
DOIs	https://doi.org/10.1109/RTAS.2008.10
Publication status	Published - Apr 2008
Event	14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2008 - St. Louis, United States Duration: 22 Apr 2008 → 24 Apr 2008 Conference number: 14

Publication series

Name
Publisher	IEEE Computer Society Press
Number	302
ISSN (Print)	1080-1812

Conference

Conference	14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2008
Abbreviated title	RTAS 2008
Country/Territory	United States
City	St. Louis
Period	22/04/08 → 24/04/08

Keywords

IR-64842
METIS-251042
EWI-12967

Access to Document

10.1109/RTAS.2008.10

Cite this

Wiggers, M. H., Bekooij, M. J. G., Bekooij, M. J. G., & Smit, G. J. M. (2008). Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication. In Proceedings of the 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS'08 (pp. 183-194). Article 10.1109/RTAS.2008.10 IEEE. https://doi.org/10.1109/RTAS.2008.10

@inproceedings{afe235fa50974962a9f4d568031fd314,

title = "Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication",

abstract = "Streaming applications are often implemented as task graphs, in which data is communicated from task to task over buffers. Currently, techniques exist to compute buffer capacities that guarantee satisfaction of the throughput constraint if the amount of data produced and consumed by the tasks is known at design-time. However, applications such as audio and video decoders have tasks that produce and consume an amount of data that depends on the decoded stream. This paper introduces a dataflow model that allows for data-dependent communication, together with an algorithm that computes buffer capacities that guarantee satisfaction of a throughput constraint. The applicability of this algorithm is demonstrated by computing buffer capacities for an H.263 video decoder.",

keywords = "IR-64842, METIS-251042, EWI-12967",

author = "M.H. Wiggers and Bekooij, {Marco J.G.} and Bekooij, {Marco Jan Gerrit} and Smit, {Gerardus Johannes Maria}",

note = "10.1109/RTAS.2008.10 ; 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2008 ; Conference date: 22-04-2008 Through 24-04-2008",

year = "2008",

month = apr,

doi = "10.1109/RTAS.2008.10",

language = "Undefined",

isbn = "978-0-7695-3146-5",

publisher = "IEEE",

number = "302",

pages = "183--194",

booktitle = "Proceedings of the 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS'08",

address = "United States",

}

Wiggers, MH, Bekooij, MJG, Bekooij, MJG & Smit, GJM 2008, Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication. in Proceedings of the 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS'08., 10.1109/RTAS.2008.10, IEEE, Los Alamitos, pp. 183-194, 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2008, St. Louis, Montana, United States, 22/04/08. https://doi.org/10.1109/RTAS.2008.10

Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication. / Wiggers, M.H.; Bekooij, Marco J.G.; Bekooij, Marco Jan Gerrit et al.
Proceedings of the 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS'08. Los Alamitos: IEEE, 2008. p. 183-194 10.1109/RTAS.2008.10.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Buffer Capacity Computation for Throughput Constrained Streaming Applications with Data-Dependent Inter-Task Communication

AU - Wiggers, M.H.

AU - Bekooij, Marco J.G.

AU - Bekooij, Marco Jan Gerrit

AU - Smit, Gerardus Johannes Maria

N1 - Conference code: 14

PY - 2008/4

Y1 - 2008/4

N2 - Streaming applications are often implemented as task graphs, in which data is communicated from task to task over buffers. Currently, techniques exist to compute buffer capacities that guarantee satisfaction of the throughput constraint if the amount of data produced and consumed by the tasks is known at design-time. However, applications such as audio and video decoders have tasks that produce and consume an amount of data that depends on the decoded stream. This paper introduces a dataflow model that allows for data-dependent communication, together with an algorithm that computes buffer capacities that guarantee satisfaction of a throughput constraint. The applicability of this algorithm is demonstrated by computing buffer capacities for an H.263 video decoder.

AB - Streaming applications are often implemented as task graphs, in which data is communicated from task to task over buffers. Currently, techniques exist to compute buffer capacities that guarantee satisfaction of the throughput constraint if the amount of data produced and consumed by the tasks is known at design-time. However, applications such as audio and video decoders have tasks that produce and consume an amount of data that depends on the decoded stream. This paper introduces a dataflow model that allows for data-dependent communication, together with an algorithm that computes buffer capacities that guarantee satisfaction of a throughput constraint. The applicability of this algorithm is demonstrated by computing buffer capacities for an H.263 video decoder.

KW - IR-64842

KW - METIS-251042

KW - EWI-12967

U2 - 10.1109/RTAS.2008.10

DO - 10.1109/RTAS.2008.10

M3 - Conference contribution

SN - 978-0-7695-3146-5

SP - 183

EP - 194

BT - Proceedings of the 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS'08

PB - IEEE

CY - Los Alamitos

T2 - 14th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2008

Y2 - 22 April 2008 through 24 April 2008

ER -