Fetch-Criticality Reduction through Control Independence

Architectures that exploit control independence (CI) promise to remove in-order fetch bottlenecks, like branch mispredicts, instruction-cache misses and fetch unit stalls, from the critical path of single-threaded execution. By exposing more fetch options, however, CI architectures also expose more...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Agarwal, Mayank, Navale, Nitin, Malik, Kshitiz, Frank, Matthew I.
Format: Tagungsbericht
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 24
container_issue 3
container_start_page 13
container_title
container_volume 36
creator Agarwal, Mayank
Navale, Nitin
Malik, Kshitiz
Frank, Matthew I.
description Architectures that exploit control independence (CI) promise to remove in-order fetch bottlenecks, like branch mispredicts, instruction-cache misses and fetch unit stalls, from the critical path of single-threaded execution. By exposing more fetch options, however, CI architectures also expose more performance tradeoffs. These tradeoffs make it hard to design policies that deliver good performance.This paper presents a criticality-based model for reasoning about CI architectures, and uses that model to describe the tradeoffs between gains from control independence versus increased costs of honoring data dependences. The model is then used to derive the design of a criticality-aware task selection policy that strikes the right balance between fetch-criticality and execute-criticality. Finally, the papervalidates the model by attacking branch-misprediction induced fetch-criticality through the above derived spawnpolicy. This leads to as high as 100% improvements in performance, and in the region of 40% or more improvements for four of the benchmarks where this is the main problem. Criticality analysis shows that this improvement arises due to reduced fetch-criticality.
doi_str_mv 10.1145/1394608.1382170
format Conference Proceeding
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1145_1394608_1382170</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1145_1394608_1382170</sourcerecordid><originalsourceid>FETCH-LOGICAL-c110t-93c060a744b6c1880b4fefc6d2c39cc09787d3f905129b65527e61623fcfe06b3</originalsourceid><addsrcrecordid>eNotz71OwzAUBWAPIFEKM2tewO29tuOfEUUUKlWqhGCOkhubGIWkctyhb08RWc7RWY70MfaEsEFU5RalUxrsBqUVaOCGrQC15KXT6o7dz_M3XLeRsGJ25zP1vEoxR2qGmC_Fu-_OlOM0FrlP0_mrL6ppzGkaiv3Y-ZO_xkj-gd2GZpj949Jr9rl7-aje-OH4uq-eD5wQIXMnCTQ0RqlWE1oLrQo-kO4ESUcEzljTyeCgROFaXZbCeI1ayEDBg27lmm3_fylN85x8qE8p_jTpUiPUf9h6wdYLVv4CZcZIiQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Fetch-Criticality Reduction through Control Independence</title><source>ACM Digital Library</source><creator>Agarwal, Mayank ; Navale, Nitin ; Malik, Kshitiz ; Frank, Matthew I.</creator><creatorcontrib>Agarwal, Mayank ; Navale, Nitin ; Malik, Kshitiz ; Frank, Matthew I.</creatorcontrib><description>Architectures that exploit control independence (CI) promise to remove in-order fetch bottlenecks, like branch mispredicts, instruction-cache misses and fetch unit stalls, from the critical path of single-threaded execution. By exposing more fetch options, however, CI architectures also expose more performance tradeoffs. These tradeoffs make it hard to design policies that deliver good performance.This paper presents a criticality-based model for reasoning about CI architectures, and uses that model to describe the tradeoffs between gains from control independence versus increased costs of honoring data dependences. The model is then used to derive the design of a criticality-aware task selection policy that strikes the right balance between fetch-criticality and execute-criticality. Finally, the papervalidates the model by attacking branch-misprediction induced fetch-criticality through the above derived spawnpolicy. This leads to as high as 100% improvements in performance, and in the region of 40% or more improvements for four of the benchmarks where this is the main problem. Criticality analysis shows that this improvement arises due to reduced fetch-criticality.</description><identifier>ISSN: 0163-5964</identifier><identifier>DOI: 10.1145/1394608.1382170</identifier><language>eng</language><ispartof>Computer architecture news, 2008, Vol.36 (3), p.13-24</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c110t-93c060a744b6c1880b4fefc6d2c39cc09787d3f905129b65527e61623fcfe06b3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Agarwal, Mayank</creatorcontrib><creatorcontrib>Navale, Nitin</creatorcontrib><creatorcontrib>Malik, Kshitiz</creatorcontrib><creatorcontrib>Frank, Matthew I.</creatorcontrib><title>Fetch-Criticality Reduction through Control Independence</title><title>Computer architecture news</title><description>Architectures that exploit control independence (CI) promise to remove in-order fetch bottlenecks, like branch mispredicts, instruction-cache misses and fetch unit stalls, from the critical path of single-threaded execution. By exposing more fetch options, however, CI architectures also expose more performance tradeoffs. These tradeoffs make it hard to design policies that deliver good performance.This paper presents a criticality-based model for reasoning about CI architectures, and uses that model to describe the tradeoffs between gains from control independence versus increased costs of honoring data dependences. The model is then used to derive the design of a criticality-aware task selection policy that strikes the right balance between fetch-criticality and execute-criticality. Finally, the papervalidates the model by attacking branch-misprediction induced fetch-criticality through the above derived spawnpolicy. This leads to as high as 100% improvements in performance, and in the region of 40% or more improvements for four of the benchmarks where this is the main problem. Criticality analysis shows that this improvement arises due to reduced fetch-criticality.</description><issn>0163-5964</issn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNotz71OwzAUBWAPIFEKM2tewO29tuOfEUUUKlWqhGCOkhubGIWkctyhb08RWc7RWY70MfaEsEFU5RalUxrsBqUVaOCGrQC15KXT6o7dz_M3XLeRsGJ25zP1vEoxR2qGmC_Fu-_OlOM0FrlP0_mrL6ppzGkaiv3Y-ZO_xkj-gd2GZpj949Jr9rl7-aje-OH4uq-eD5wQIXMnCTQ0RqlWE1oLrQo-kO4ESUcEzljTyeCgROFaXZbCeI1ayEDBg27lmm3_fylN85x8qE8p_jTpUiPUf9h6wdYLVv4CZcZIiQ</recordid><startdate>200806</startdate><enddate>200806</enddate><creator>Agarwal, Mayank</creator><creator>Navale, Nitin</creator><creator>Malik, Kshitiz</creator><creator>Frank, Matthew I.</creator><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>200806</creationdate><title>Fetch-Criticality Reduction through Control Independence</title><author>Agarwal, Mayank ; Navale, Nitin ; Malik, Kshitiz ; Frank, Matthew I.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c110t-93c060a744b6c1880b4fefc6d2c39cc09787d3f905129b65527e61623fcfe06b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Agarwal, Mayank</creatorcontrib><creatorcontrib>Navale, Nitin</creatorcontrib><creatorcontrib>Malik, Kshitiz</creatorcontrib><creatorcontrib>Frank, Matthew I.</creatorcontrib><collection>CrossRef</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Agarwal, Mayank</au><au>Navale, Nitin</au><au>Malik, Kshitiz</au><au>Frank, Matthew I.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Fetch-Criticality Reduction through Control Independence</atitle><btitle>Computer architecture news</btitle><date>2008-06</date><risdate>2008</risdate><volume>36</volume><issue>3</issue><spage>13</spage><epage>24</epage><pages>13-24</pages><issn>0163-5964</issn><abstract>Architectures that exploit control independence (CI) promise to remove in-order fetch bottlenecks, like branch mispredicts, instruction-cache misses and fetch unit stalls, from the critical path of single-threaded execution. By exposing more fetch options, however, CI architectures also expose more performance tradeoffs. These tradeoffs make it hard to design policies that deliver good performance.This paper presents a criticality-based model for reasoning about CI architectures, and uses that model to describe the tradeoffs between gains from control independence versus increased costs of honoring data dependences. The model is then used to derive the design of a criticality-aware task selection policy that strikes the right balance between fetch-criticality and execute-criticality. Finally, the papervalidates the model by attacking branch-misprediction induced fetch-criticality through the above derived spawnpolicy. This leads to as high as 100% improvements in performance, and in the region of 40% or more improvements for four of the benchmarks where this is the main problem. Criticality analysis shows that this improvement arises due to reduced fetch-criticality.</abstract><doi>10.1145/1394608.1382170</doi><tpages>12</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0163-5964
ispartof Computer architecture news, 2008, Vol.36 (3), p.13-24
issn 0163-5964
language eng
recordid cdi_crossref_primary_10_1145_1394608_1382170
source ACM Digital Library
title Fetch-Criticality Reduction through Control Independence
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A49%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Fetch-Criticality%20Reduction%20through%20Control%20Independence&rft.btitle=Computer%20architecture%20news&rft.au=Agarwal,%20Mayank&rft.date=2008-06&rft.volume=36&rft.issue=3&rft.spage=13&rft.epage=24&rft.pages=13-24&rft.issn=0163-5964&rft_id=info:doi/10.1145/1394608.1382170&rft_dat=%3Ccrossref%3E10_1145_1394608_1382170%3C/crossref%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