Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Methods to explore design space for MPEG RVC codec specifications

Mattavelli, Marco ; Brunet, Simone Casale ; Elguindy, Abdallah A. A. ; Bezati, Endri ; Thavot, Richard ; Roquier, Ghislain and Janneck, Jörn LU (2013) In Signal Processing. Image Communication 28(10). p.1278-1294
Abstract
Abstract in Undetermined
The recent MPEG Reconfigurable Media Coding (RMC) standard aims at defining media processing specifications (e.g. video codecs) in a form that abstracts from the implementation platform, but at the same time is an appropriate starting point for implementation on specific targets. To this end, the RMC framework has standardized both an asynchronous dataflow model of computation and an associated specification language. Either are providing the formalism and the theoretical foundation for multimedia specifications. Even though these specifications are abstract and platform-independent the new approach of developing implementations from such initial specifications presents obvious advantages over the approaches... (More)
Abstract in Undetermined
The recent MPEG Reconfigurable Media Coding (RMC) standard aims at defining media processing specifications (e.g. video codecs) in a form that abstracts from the implementation platform, but at the same time is an appropriate starting point for implementation on specific targets. To this end, the RMC framework has standardized both an asynchronous dataflow model of computation and an associated specification language. Either are providing the formalism and the theoretical foundation for multimedia specifications. Even though these specifications are abstract and platform-independent the new approach of developing implementations from such initial specifications presents obvious advantages over the approaches based on classical sequential specifications. The advantages appear particularly appealing when targeting the current and emerging homogeneous and heterogeneous manycore or multicore processing platforms. These highly parallel computing machines are gradually replacing single-core processors, particularly when the system design aims at reducing power dissipation or at increasing throughput However, a straightforward mapping of an abstract dataflow specification onto a concurrent and heterogeneous platform does often not produce an efficient result Before an abstract specification can be translated into an efficient implementation in software and hardware, the dataflow networks need to be partitioned and then mapped to individual processing elements. Moreover, system performance requirements need to be accounted for in the design optimization process. This paper discusses the state of the art of the combinatorial problems that need to be faced at this design space exploration step. Some recent developments and experimental results for image and video coding applications are illustrated. Both well-known and novel heuristics for problems such as mapping, scheduling and buffer minimization are investigated in the specific context of exploring the design space of dataflow program implementations. (C) 2013 Elsevier B.V. All rights reserved. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
computing, Parallel, Reconfigurable Media Coding, Design space exploration, Dataflow programming, Parallel Analysis and Optimization
in
Signal Processing. Image Communication
volume
28
issue
10
pages
1278 - 1294
publisher
EURASIP
external identifiers
  • wos:000328233200006
  • scopus:84888201791
ISSN
0923-5965
DOI
10.1016/j.image.2013.08.012
language
English
LU publication?
yes
id
b0afa1b7-f51a-47c5-9665-eaaa68c0e9ce (old id 3731820)
date added to LUP
2016-04-01 12:58:33
date last changed
2022-05-15 01:55:16
@article{b0afa1b7-f51a-47c5-9665-eaaa68c0e9ce,
  abstract     = {{Abstract in Undetermined<br/>The recent MPEG Reconfigurable Media Coding (RMC) standard aims at defining media processing specifications (e.g. video codecs) in a form that abstracts from the implementation platform, but at the same time is an appropriate starting point for implementation on specific targets. To this end, the RMC framework has standardized both an asynchronous dataflow model of computation and an associated specification language. Either are providing the formalism and the theoretical foundation for multimedia specifications. Even though these specifications are abstract and platform-independent the new approach of developing implementations from such initial specifications presents obvious advantages over the approaches based on classical sequential specifications. The advantages appear particularly appealing when targeting the current and emerging homogeneous and heterogeneous manycore or multicore processing platforms. These highly parallel computing machines are gradually replacing single-core processors, particularly when the system design aims at reducing power dissipation or at increasing throughput However, a straightforward mapping of an abstract dataflow specification onto a concurrent and heterogeneous platform does often not produce an efficient result Before an abstract specification can be translated into an efficient implementation in software and hardware, the dataflow networks need to be partitioned and then mapped to individual processing elements. Moreover, system performance requirements need to be accounted for in the design optimization process. This paper discusses the state of the art of the combinatorial problems that need to be faced at this design space exploration step. Some recent developments and experimental results for image and video coding applications are illustrated. Both well-known and novel heuristics for problems such as mapping, scheduling and buffer minimization are investigated in the specific context of exploring the design space of dataflow program implementations. (C) 2013 Elsevier B.V. All rights reserved.}},
  author       = {{Mattavelli, Marco and Brunet, Simone Casale and Elguindy, Abdallah A. A. and Bezati, Endri and Thavot, Richard and Roquier, Ghislain and Janneck, Jörn}},
  issn         = {{0923-5965}},
  keywords     = {{computing; Parallel; Reconfigurable Media Coding; Design space exploration; Dataflow programming; Parallel Analysis and Optimization}},
  language     = {{eng}},
  number       = {{10}},
  pages        = {{1278--1294}},
  publisher    = {{EURASIP}},
  series       = {{Signal Processing. Image Communication}},
  title        = {{Methods to explore design space for MPEG RVC codec specifications}},
  url          = {{https://lup.lub.lu.se/search/files/3081647/3731821.pdf}},
  doi          = {{10.1016/j.image.2013.08.012}},
  volume       = {{28}},
  year         = {{2013}},
}