On Memory Reuse Between Inputs and Outputs of Dataflow Actors

On Memory Reuse Between Inputs and Outputs of Dataflow Actors

This article introduces a new technique to minimize the memory footprints of Digital Signal Processing (DSP) applications specified with Synchronous Dataflow (SDF) graphs and implemented on shared-memory Multiprocessor System-on-Chip (MPSoCs). In addition to the SDF specification, which captures dat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ACM transactions on embedded computing systems 2016-06, Vol.15 (2), p.1-25
Hauptverfasser: Desnos, Karol, Pelcat, Maxime, Nezan, Jean-François, Aridhi, Slaheddine
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science
Embedded Systems
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 25
container_issue 2
container_start_page 1
container_title ACM transactions on embedded computing systems
container_volume 15
creator Desnos, Karol
Pelcat, Maxime
Nezan, Jean-François
Aridhi, Slaheddine
description This article introduces a new technique to minimize the memory footprints of Digital Signal Processing (DSP) applications specified with Synchronous Dataflow (SDF) graphs and implemented on shared-memory Multiprocessor System-on-Chip (MPSoCs). In addition to the SDF specification, which captures data dependencies between coarse-grained tasks called actors, the proposed technique relies on two optional inputs abstracting the internal data dependencies of actors: annotations of the ports of actors, and script-based specifications of merging opportunities between input and output buffers of actors. Experimental results on a set of applications show a reduction of the memory footprint by 48% compared to state-of-the-art minimization techniques.
doi_str_mv 10.1145/2871744
format Article
fullrecord <record><control><sourceid>hal_cross</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_01284333v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>oai_HAL_hal_01284333v1</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-725d80e291e00a3f48b23db3ce20798efdd3d413a261aed715b75bde3ca2031a3</originalsourceid><addsrcrecordid>eNo9kEFLw0AUhBdRsFbxL-xNPET37dvtbg4eYqu2EAmInsMm-4KVNCnZxNJ_r7HF0wzDN3MYxq5B3AEofS-tAaPUCZuA1jZCNdOno8c4ioU15-wihC8hwEilJ-wha_grbdpuz99oCMQfqd8RNXzVbIc-cNd4ng39n28rvnC9q-p2x5Oyb7twyc4qVwe6OuqUfTw_vc-XUZq9rOZJGpUyln1kpPZWkIyBhHBYKVtI9AWWJIWJLVXeo1eATs7AkTegC6MLT1g6KRAcTtntYffT1fm2W29ct89bt86XSZqPmQBpFSJ-wy97c2DLrg2ho-q_ACIfH8qPD-EPZ5VWKQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>On Memory Reuse Between Inputs and Outputs of Dataflow Actors</title><source>ACM Digital Library Complete</source><creator>Desnos, Karol ; Pelcat, Maxime ; Nezan, Jean-François ; Aridhi, Slaheddine</creator><creatorcontrib>Desnos, Karol ; Pelcat, Maxime ; Nezan, Jean-François ; Aridhi, Slaheddine</creatorcontrib><description>This article introduces a new technique to minimize the memory footprints of Digital Signal Processing (DSP) applications specified with Synchronous Dataflow (SDF) graphs and implemented on shared-memory Multiprocessor System-on-Chip (MPSoCs). In addition to the SDF specification, which captures data dependencies between coarse-grained tasks called actors, the proposed technique relies on two optional inputs abstracting the internal data dependencies of actors: annotations of the ports of actors, and script-based specifications of merging opportunities between input and output buffers of actors. Experimental results on a set of applications show a reduction of the memory footprint by 48% compared to state-of-the-art minimization techniques.</description><identifier>ISSN: 1539-9087</identifier><identifier>EISSN: 1558-3465</identifier><identifier>DOI: 10.1145/2871744</identifier><language>eng</language><publisher>ACM</publisher><subject>Computer Science ; Embedded Systems</subject><ispartof>ACM transactions on embedded computing systems, 2016-06, Vol.15 (2), p.1-25</ispartof><rights>Attribution - NonCommercial - NoDerivatives</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-725d80e291e00a3f48b23db3ce20798efdd3d413a261aed715b75bde3ca2031a3</citedby><cites>FETCH-LOGICAL-c292t-725d80e291e00a3f48b23db3ce20798efdd3d413a261aed715b75bde3ca2031a3</cites><orcidid>0000-0003-1527-9668 ; 0000-0002-1158-0915 ; 0000-0002-0609-4592</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,776,780,881,27901,27902</link.rule.ids><backlink>$$Uhttps://hal.science/hal-01284333$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Desnos, Karol</creatorcontrib><creatorcontrib>Pelcat, Maxime</creatorcontrib><creatorcontrib>Nezan, Jean-François</creatorcontrib><creatorcontrib>Aridhi, Slaheddine</creatorcontrib><title>On Memory Reuse Between Inputs and Outputs of Dataflow Actors</title><title>ACM transactions on embedded computing systems</title><description>This article introduces a new technique to minimize the memory footprints of Digital Signal Processing (DSP) applications specified with Synchronous Dataflow (SDF) graphs and implemented on shared-memory Multiprocessor System-on-Chip (MPSoCs). In addition to the SDF specification, which captures data dependencies between coarse-grained tasks called actors, the proposed technique relies on two optional inputs abstracting the internal data dependencies of actors: annotations of the ports of actors, and script-based specifications of merging opportunities between input and output buffers of actors. Experimental results on a set of applications show a reduction of the memory footprint by 48% compared to state-of-the-art minimization techniques.</description><subject>Computer Science</subject><subject>Embedded Systems</subject><issn>1539-9087</issn><issn>1558-3465</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNo9kEFLw0AUhBdRsFbxL-xNPET37dvtbg4eYqu2EAmInsMm-4KVNCnZxNJ_r7HF0wzDN3MYxq5B3AEofS-tAaPUCZuA1jZCNdOno8c4ioU15-wihC8hwEilJ-wha_grbdpuz99oCMQfqd8RNXzVbIc-cNd4ng39n28rvnC9q-p2x5Oyb7twyc4qVwe6OuqUfTw_vc-XUZq9rOZJGpUyln1kpPZWkIyBhHBYKVtI9AWWJIWJLVXeo1eATs7AkTegC6MLT1g6KRAcTtntYffT1fm2W29ct89bt86XSZqPmQBpFSJ-wy97c2DLrg2ho-q_ACIfH8qPD-EPZ5VWKQ</recordid><startdate>20160607</startdate><enddate>20160607</enddate><creator>Desnos, Karol</creator><creator>Pelcat, Maxime</creator><creator>Nezan, Jean-François</creator><creator>Aridhi, Slaheddine</creator><general>ACM</general><scope>AAYXX</scope><scope>CITATION</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0003-1527-9668</orcidid><orcidid>https://orcid.org/0000-0002-1158-0915</orcidid><orcidid>https://orcid.org/0000-0002-0609-4592</orcidid></search><sort><creationdate>20160607</creationdate><title>On Memory Reuse Between Inputs and Outputs of Dataflow Actors</title><author>Desnos, Karol ; Pelcat, Maxime ; Nezan, Jean-François ; Aridhi, Slaheddine</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-725d80e291e00a3f48b23db3ce20798efdd3d413a261aed715b75bde3ca2031a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Computer Science</topic><topic>Embedded Systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Desnos, Karol</creatorcontrib><creatorcontrib>Pelcat, Maxime</creatorcontrib><creatorcontrib>Nezan, Jean-François</creatorcontrib><creatorcontrib>Aridhi, Slaheddine</creatorcontrib><collection>CrossRef</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>ACM transactions on embedded computing systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Desnos, Karol</au><au>Pelcat, Maxime</au><au>Nezan, Jean-François</au><au>Aridhi, Slaheddine</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>On Memory Reuse Between Inputs and Outputs of Dataflow Actors</atitle><jtitle>ACM transactions on embedded computing systems</jtitle><date>2016-06-07</date><risdate>2016</risdate><volume>15</volume><issue>2</issue><spage>1</spage><epage>25</epage><pages>1-25</pages><issn>1539-9087</issn><eissn>1558-3465</eissn><abstract>This article introduces a new technique to minimize the memory footprints of Digital Signal Processing (DSP) applications specified with Synchronous Dataflow (SDF) graphs and implemented on shared-memory Multiprocessor System-on-Chip (MPSoCs). In addition to the SDF specification, which captures data dependencies between coarse-grained tasks called actors, the proposed technique relies on two optional inputs abstracting the internal data dependencies of actors: annotations of the ports of actors, and script-based specifications of merging opportunities between input and output buffers of actors. Experimental results on a set of applications show a reduction of the memory footprint by 48% compared to state-of-the-art minimization techniques.</abstract><pub>ACM</pub><doi>10.1145/2871744</doi><tpages>25</tpages><orcidid>https://orcid.org/0000-0003-1527-9668</orcidid><orcidid>https://orcid.org/0000-0002-1158-0915</orcidid><orcidid>https://orcid.org/0000-0002-0609-4592</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1539-9087
ispartof ACM transactions on embedded computing systems, 2016-06, Vol.15 (2), p.1-25
issn 1539-9087
1558-3465
language eng
recordid cdi_hal_primary_oai_HAL_hal_01284333v1
source ACM Digital Library Complete
subjects Computer Science
Embedded Systems
title On Memory Reuse Between Inputs and Outputs of Dataflow Actors
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T02%3A07%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-hal_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=On%20Memory%20Reuse%20Between%20Inputs%20and%20Outputs%20of%20Dataflow%20Actors&rft.jtitle=ACM%20transactions%20on%20embedded%20computing%20systems&rft.au=Desnos,%20Karol&rft.date=2016-06-07&rft.volume=15&rft.issue=2&rft.spage=1&rft.epage=25&rft.pages=1-25&rft.issn=1539-9087&rft.eissn=1558-3465&rft_id=info:doi/10.1145/2871744&rft_dat=%3Chal_cross%3Eoai_HAL_hal_01284333v1%3C/hal_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true