Loading…

A co-phase matrix to guide simultaneous multithreading simulation

Several commercial processors have architectures that include support for simultaneous multithreading (SMT), yet there is still not a validated methodology for estimating the performance of an SMT machine that does not rely on full program simulation. To create an efficient sampling approach for SMT...

Full description

Saved in:
Bibliographic Details
Main Authors: Van Biesbrouck, M., Sherwood, T., Calder, B.
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 56
container_issue
container_start_page 45
container_title
container_volume
creator Van Biesbrouck, M.
Sherwood, T.
Calder, B.
description Several commercial processors have architectures that include support for simultaneous multithreading (SMT), yet there is still not a validated methodology for estimating the performance of an SMT machine that does not rely on full program simulation. To create an efficient sampling approach for SMT we must determine how far to fast-forward each individual thread between samples. The fast-forwarding distance for each thread will vary according to execution phases, thread interactions and changes to the architectural configuration. We examine using individual program phase information to guide SMT simulation. This is accomplished by creating what we call a co-phase matrix. The co-phase matrix is populated by collecting samples of the programs' phase combinations, and is used to guide fastforwarding between samples. We show for 28 pairs of SPEC programs that using the co-phase matrix provides an average error rate of 4% while requiring that only 1% of the full simulation be performed. The methods are also validated using a variety of architectural configurations and four-threaded workloads.
doi_str_mv 10.1109/ISPASS.2004.1291355
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1291355</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1291355</ieee_id><sourcerecordid>1291355</sourcerecordid><originalsourceid>FETCH-LOGICAL-i218t-b06158b3316625fa3d23dbdb2874ffe758c86523ae9c061be712c2d888df15573</originalsourceid><addsrcrecordid>eNotT9tqwzAUM4zBRpcv6It_IJl9HCcnj6HsUih0kO252PFJ69EkJXZg-_tltEIggYRAjK2lyKQU1fO2-aibJgMh8kxCJZXWdyypShQLFSrU8MCSEL7FglznEuCR1TVvx_RyMoF4b-Lkf3gc-XH2jnjw_XyOZqBxDvzf-niayDg_HK-ZiX4cnth9Z86Bkpuu2Nfry-fmPd3t37abepd6kBhTKwqp0SoliwJ0Z5QD5ayzgGXedVRqbLHQoAxV7VK1VEpowSGi66TWpVqx9XXXE9HhMvneTL-H21H1B7ETSYA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A co-phase matrix to guide simultaneous multithreading simulation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Van Biesbrouck, M. ; Sherwood, T. ; Calder, B.</creator><creatorcontrib>Van Biesbrouck, M. ; Sherwood, T. ; Calder, B.</creatorcontrib><description>Several commercial processors have architectures that include support for simultaneous multithreading (SMT), yet there is still not a validated methodology for estimating the performance of an SMT machine that does not rely on full program simulation. To create an efficient sampling approach for SMT we must determine how far to fast-forward each individual thread between samples. The fast-forwarding distance for each thread will vary according to execution phases, thread interactions and changes to the architectural configuration. We examine using individual program phase information to guide SMT simulation. This is accomplished by creating what we call a co-phase matrix. The co-phase matrix is populated by collecting samples of the programs' phase combinations, and is used to guide fastforwarding between samples. We show for 28 pairs of SPEC programs that using the co-phase matrix provides an average error rate of 4% while requiring that only 1% of the full simulation be performed. The methods are also validated using a variety of architectural configurations and four-threaded workloads.</description><identifier>ISBN: 9780780383852</identifier><identifier>ISBN: 0780383850</identifier><identifier>DOI: 10.1109/ISPASS.2004.1291355</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational modeling ; Computer architecture ; Computer science ; Computer simulation ; Error analysis ; Force measurement ; Modems ; Multithreading ; Surface-mount technology ; Yarn</subject><ispartof>IEEE International Symposium on - ISPASS Performance Analysis of Systems and Software, 2004, 2004, p.45-56</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1291355$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,4048,4049,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1291355$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Van Biesbrouck, M.</creatorcontrib><creatorcontrib>Sherwood, T.</creatorcontrib><creatorcontrib>Calder, B.</creatorcontrib><title>A co-phase matrix to guide simultaneous multithreading simulation</title><title>IEEE International Symposium on - ISPASS Performance Analysis of Systems and Software, 2004</title><addtitle>ISPASS</addtitle><description>Several commercial processors have architectures that include support for simultaneous multithreading (SMT), yet there is still not a validated methodology for estimating the performance of an SMT machine that does not rely on full program simulation. To create an efficient sampling approach for SMT we must determine how far to fast-forward each individual thread between samples. The fast-forwarding distance for each thread will vary according to execution phases, thread interactions and changes to the architectural configuration. We examine using individual program phase information to guide SMT simulation. This is accomplished by creating what we call a co-phase matrix. The co-phase matrix is populated by collecting samples of the programs' phase combinations, and is used to guide fastforwarding between samples. We show for 28 pairs of SPEC programs that using the co-phase matrix provides an average error rate of 4% while requiring that only 1% of the full simulation be performed. The methods are also validated using a variety of architectural configurations and four-threaded workloads.</description><subject>Computational modeling</subject><subject>Computer architecture</subject><subject>Computer science</subject><subject>Computer simulation</subject><subject>Error analysis</subject><subject>Force measurement</subject><subject>Modems</subject><subject>Multithreading</subject><subject>Surface-mount technology</subject><subject>Yarn</subject><isbn>9780780383852</isbn><isbn>0780383850</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2004</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotT9tqwzAUM4zBRpcv6It_IJl9HCcnj6HsUih0kO252PFJ69EkJXZg-_tltEIggYRAjK2lyKQU1fO2-aibJgMh8kxCJZXWdyypShQLFSrU8MCSEL7FglznEuCR1TVvx_RyMoF4b-Lkf3gc-XH2jnjw_XyOZqBxDvzf-niayDg_HK-ZiX4cnth9Z86Bkpuu2Nfry-fmPd3t37abepd6kBhTKwqp0SoliwJ0Z5QD5ayzgGXedVRqbLHQoAxV7VK1VEpowSGi66TWpVqx9XXXE9HhMvneTL-H21H1B7ETSYA</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Van Biesbrouck, M.</creator><creator>Sherwood, T.</creator><creator>Calder, B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2004</creationdate><title>A co-phase matrix to guide simultaneous multithreading simulation</title><author>Van Biesbrouck, M. ; Sherwood, T. ; Calder, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i218t-b06158b3316625fa3d23dbdb2874ffe758c86523ae9c061be712c2d888df15573</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Computational modeling</topic><topic>Computer architecture</topic><topic>Computer science</topic><topic>Computer simulation</topic><topic>Error analysis</topic><topic>Force measurement</topic><topic>Modems</topic><topic>Multithreading</topic><topic>Surface-mount technology</topic><topic>Yarn</topic><toplevel>online_resources</toplevel><creatorcontrib>Van Biesbrouck, M.</creatorcontrib><creatorcontrib>Sherwood, T.</creatorcontrib><creatorcontrib>Calder, B.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEL</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Van Biesbrouck, M.</au><au>Sherwood, T.</au><au>Calder, B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A co-phase matrix to guide simultaneous multithreading simulation</atitle><btitle>IEEE International Symposium on - ISPASS Performance Analysis of Systems and Software, 2004</btitle><stitle>ISPASS</stitle><date>2004</date><risdate>2004</risdate><spage>45</spage><epage>56</epage><pages>45-56</pages><isbn>9780780383852</isbn><isbn>0780383850</isbn><abstract>Several commercial processors have architectures that include support for simultaneous multithreading (SMT), yet there is still not a validated methodology for estimating the performance of an SMT machine that does not rely on full program simulation. To create an efficient sampling approach for SMT we must determine how far to fast-forward each individual thread between samples. The fast-forwarding distance for each thread will vary according to execution phases, thread interactions and changes to the architectural configuration. We examine using individual program phase information to guide SMT simulation. This is accomplished by creating what we call a co-phase matrix. The co-phase matrix is populated by collecting samples of the programs' phase combinations, and is used to guide fastforwarding between samples. We show for 28 pairs of SPEC programs that using the co-phase matrix provides an average error rate of 4% while requiring that only 1% of the full simulation be performed. The methods are also validated using a variety of architectural configurations and four-threaded workloads.</abstract><pub>IEEE</pub><doi>10.1109/ISPASS.2004.1291355</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9780780383852
ispartof IEEE International Symposium on - ISPASS Performance Analysis of Systems and Software, 2004, 2004, p.45-56
issn
language eng
recordid cdi_ieee_primary_1291355
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Computational modeling
Computer architecture
Computer science
Computer simulation
Error analysis
Force measurement
Modems
Multithreading
Surface-mount technology
Yarn
title A co-phase matrix to guide simultaneous multithreading simulation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T12%3A31%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20co-phase%20matrix%20to%20guide%20simultaneous%20multithreading%20simulation&rft.btitle=IEEE%20International%20Symposium%20on%20-%20ISPASS%20Performance%20Analysis%20of%20Systems%20and%20Software,%202004&rft.au=Van%20Biesbrouck,%20M.&rft.date=2004&rft.spage=45&rft.epage=56&rft.pages=45-56&rft.isbn=9780780383852&rft.isbn_list=0780383850&rft_id=info:doi/10.1109/ISPASS.2004.1291355&rft_dat=%3Cieee_6IE%3E1291355%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i218t-b06158b3316625fa3d23dbdb2874ffe758c86523ae9c061be712c2d888df15573%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1291355&rfr_iscdi=true