Exploiting parallelism in geometry processing with general purpose processors and floating-point SIMD instructions
Three-dimensional (3D) graphics applications have become very important workloads running on today's computer systems. A cost-effective graphics solution is to perform geometry processing of 3D graphics on the host CPU and have specialized hardware handle the rendering task. In this paper, we a...
Saved in:
Published in | IEEE transactions on computers Vol. 49; no. 9; pp. 934 - 946 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
New York
IEEE
01.09.2000
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Three-dimensional (3D) graphics applications have become very important workloads running on today's computer systems. A cost-effective graphics solution is to perform geometry processing of 3D graphics on the host CPU and have specialized hardware handle the rendering task. In this paper, we analyze microarchitecture and SIMD instruction set enhancements to a RISC superscalar processor for exploiting parallelism in geometry processing for 3D computer graphics. Our results show that 3D geometry processing has inherent parallelism. Adding SIMD operations improves performance from 8 percent to 28 percent on a 4-issue dynamically scheduled processor that can issue at most two floating-point operations. In comparison, an 8-issue processor, ignoring cycle time effects, can achieve 20 to 60 percent performance improvement over a 4-issue. If processor cycle time scales with the number of ports to the register file, then doubling only the floating-point issue width of a 4-issue processor with SIMD instructions gives the best performance among the architectural configurations that we examine (the most aggressive configuration is an 8-issue processor with SIMD instructions). |
---|---|
AbstractList | Three-dimensional (3D) graphics applications have become very important workloads running on today's computer systems. A cost-effective graphics solution is to perform geometry processing of 3D graphics on the host CPU and have specialized hardware handle the rendering task. In this paper, we analyze microarchitecture and SIMD instruction set enhancements to a RISC superscalar processor for exploiting parallelism in geometry processing for 3D computer graphics. Our results show that 3D geometry processing has inherent parallelism. Adding SIMD operations improves performance from 8 percent to 28 percent on a 4-issue dynamically scheduled processor that can issue at most two floating-point operations. In comparison, an 8-issue processor, ignoring cycle time effects, can achieve 20 to 60 percent performance improvement over a 4-issue. If processor cycle time scales with the number of ports to the register file, then doubling only the floating-point issue width of a 4-issue processor with SIMD instructions gives the best performance among the architectural configurations that we examine (the most aggressive configuration is an 8-issue processor with SIMD instructions) If processor cycle time scales with the number of ports to the register file, then doubling only the floating-point issue width of a 4-issue processor with SIMD instructions gives the best performance among the architectural configurations that we examine (the most aggressive configuration is an 8-issue processor with SIMD instructions) |
Author | Chia-Lin Yang Sano, B. Lebeck, A.R. |
Author_xml | – sequence: 1 surname: Chia-Lin Yang fullname: Chia-Lin Yang organization: Dept. of Comput. Sci., Duke Univ., Durham, NC, USA – sequence: 2 givenname: B. surname: Sano fullname: Sano, B. – sequence: 3 givenname: A.R. surname: Lebeck fullname: Lebeck, A.R. |
BookMark | eNqF0T1PwzAQBmALFYkWGFiZIgYQQ8A-J7E9IigfEogBmCMnuYBRagc7EfTf46rAwACTh_fRq_PdjEyss0jIHqMnjFF1yuBEFopDtkGmLM9FqlReTMiUUiZTxTO6RWYhvFJKC6BqSvz8o--cGYx9TnrtdddhZ8IiMTZ5RrfAwS-T3rsaQ1iRdzO8xMBilEk_-t4F_M6dD4m2TdJ2Tq_60t4ZOyQPN3cXsS4MfqwH42zYIZut7gLufr3b5Oly_nh-nd7eX92cn92mNS_EkGLVQFFpqSslcypBKwEtNlw1rAIKVdYgskoo0fCaApdctlDnjIoKFRdZxbfJ0bo3zvc2YhjKhQk1dp226MZQKpYVHATNojz8U0JcKUBc67-wKIBTxSM8-AVf3eht_G4pZQ6c50xEdLxGtXcheGzL3puF9suS0XJ1zZJBub5mtPtraxDxx32Fn3lxnUM |
CODEN | ITCOB4 |
CitedBy_id | crossref_primary_10_1093_comjnl_bxm099 crossref_primary_10_1016_j_mejo_2007_11_001 crossref_primary_10_1049_el_2011_3923 |
Cites_doi | 10.1145/133994.134067 10.1109/CMPCON.1995.512423 10.1109/ISCA.1999.765945 10.1109/4.509850 10.1145/178243.178260 10.1109/HPCA.1996.501172 10.1145/258734.258871 10.1109/ISCA.1997.604689 10.1145/54852.378516 10.1109/MM.1996.526920 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2000 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2000 |
DBID | RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 |
DOI | 10.1109/12.869324 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) - Journals and E-Books CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ANTE: Abstracts in New Technology & Engineering Engineering Research Database |
DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional Engineering Research Database ANTE: Abstracts in New Technology & Engineering |
DatabaseTitleList | Technology Research Database Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Computer Science |
EISSN | 1557-9956 |
EndPage | 946 |
ExternalDocumentID | 2435149221 10_1109_12_869324 869324 |
GroupedDBID | --Z -DZ -~X .55 .DC 0R~ 29I 3EH 3O- 4.4 5GY 5VS 6IK 85S 97E AAJGR AASAJ AAYOK ABFSI ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETEA AETIX AI. AIBXA AKJIK ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F20 HZ~ H~9 IAAWW IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ MVM O9- OCL P2P PQQKQ RIA RIC RIE RIG RNI RNS RXW RZB TAE TN5 TWZ UHB UKR UPT VH1 X7M XFK XJT XOL XZL YXB YYQ YZZ ZCG AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 |
ID | FETCH-LOGICAL-c367t-ebd26ba8ab985082a972fed39d1b202b4dee1b797d3c023838f2c5107be9374b3 |
IEDL.DBID | RIE |
ISSN | 0018-9340 |
IngestDate | Fri Aug 16 04:04:20 EDT 2024 Fri Aug 16 22:12:18 EDT 2024 Sat Aug 17 00:55:55 EDT 2024 Thu Oct 10 18:52:24 EDT 2024 Thu Sep 26 15:44:03 EDT 2024 Wed Jun 26 19:28:26 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 9 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c367t-ebd26ba8ab985082a972fed39d1b202b4dee1b797d3c023838f2c5107be9374b3 |
Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
PQID | 885233517 |
PQPubID | 23500 |
PageCount | 13 |
ParticipantIDs | ieee_primary_869324 crossref_primary_10_1109_12_869324 proquest_miscellaneous_914632704 proquest_journals_885233517 proquest_miscellaneous_28692269 proquest_miscellaneous_26623093 |
PublicationCentury | 2000 |
PublicationDate | 2000-09-01 |
PublicationDateYYYYMMDD | 2000-09-01 |
PublicationDate_xml | – month: 09 year: 2000 text: 2000-09-01 day: 01 |
PublicationDecade | 2000 |
PublicationPlace | New York |
PublicationPlace_xml | – name: New York |
PublicationTitle | IEEE transactions on computers |
PublicationTitleAbbrev | TC |
PublicationYear | 2000 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | (bibT09342) 0 (bibT093413) 0 (bibT093415) 0 yang (bibT093427) 1998 farkas (bibT09344) 1997 foley (bibT09346) 1996 (bibT093416) 1996 bibT093411 bibT093410 (bibT093419) 0 bibT093417 bibT093418 (bibT09343) 0 woo (bibT093426) 1997 bibT09341 (bibT093420) 0 bibT093421 bibT09348 bibT09345 palacharla (bibT093422) 1996 bibT093423 bibT093425 sites (bibT093424) 1992 mcfarling (bibT093412) 1993 (bibT093414) 1997 kane (bibT09349) 1996 (bibT09347) 0 |
References_xml | – year: 0 ident: bibT093419 – ident: bibT093417 doi: 10.1145/133994.134067 – year: 1993 ident: bibT093412 article-title: combing branch predictors contributor: fullname: mcfarling – year: 0 ident: bibT093413 – year: 0 ident: bibT093415 – year: 1997 ident: bibT093414 – ident: bibT093410 doi: 10.1109/CMPCON.1995.512423 – ident: bibT093423 doi: 10.1109/ISCA.1999.765945 – ident: bibT09348 doi: 10.1109/4.509850 – year: 1997 ident: bibT09344 article-title: memory-system design considerations for dynamically-scheduled microprocessors publication-title: ?Memory-System Design Considerations for Dynamically-Scheduled Microprocessors ? contributor: fullname: farkas – year: 1997 ident: bibT093426 publication-title: OpenGL Programming Guide contributor: fullname: woo – year: 0 ident: bibT09342 – year: 1996 ident: bibT093422 article-title: quantifying the complexity of superscalar processors contributor: fullname: palacharla – start-page: 8 year: 0 ident: bibT09343 publication-title: Digital Unix V4 0 Programmer s Guide – year: 1996 ident: bibT093416 publication-title: Intel Architecture MMX Technology Programmer s Reference Manual – ident: bibT093425 doi: 10.1145/178243.178260 – ident: bibT09345 doi: 10.1109/HPCA.1996.501172 – year: 1996 ident: bibT09349 publication-title: PA-RISC 2 0 Architecture contributor: fullname: kane – ident: bibT093418 doi: 10.1145/258734.258871 – year: 0 ident: bibT093420 – year: 1998 ident: bibT093427 article-title: exploiting instruction level parallelism in geometry processing for three dimensional graphics applications contributor: fullname: yang – ident: bibT093421 doi: 10.1109/ISCA.1997.604689 – year: 1992 ident: bibT093424 publication-title: Alpha Architecture Reference Manual contributor: fullname: sites – year: 1996 ident: bibT09346 publication-title: Computer Graphics?Principles and Practice contributor: fullname: foley – ident: bibT09341 doi: 10.1145/54852.378516 – ident: bibT093411 doi: 10.1109/MM.1996.526920 – year: 0 ident: bibT09347 |
SSID | ssj0006209 |
Score | 1.6808299 |
Snippet | Three-dimensional (3D) graphics applications have become very important workloads running on today's computer systems. A cost-effective graphics solution is to... If processor cycle time scales with the number of ports to the register file, then doubling only the floating-point issue width of a 4-issue processor with... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 934 |
SubjectTerms | 3-D graphics Application software Computational geometry Computer graphics Cycle time Dynamic scheduling Floating point arithmetic Geometry Hardware Microarchitecture Parallel processing Performance enhancement Processor scheduling Processors Reduced instruction set computing Rendering Rendering (computer graphics) Tasks Three dimensional |
Title | Exploiting parallelism in geometry processing with general purpose processors and floating-point SIMD instructions |
URI | https://ieeexplore.ieee.org/document/869324 https://www.proquest.com/docview/885233517 https://search.proquest.com/docview/26623093 https://search.proquest.com/docview/28692269 https://search.proquest.com/docview/914632704 |
Volume | 49 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELbanuBAYQtiW6AW4ppt_NjYPlZA1SK1F6jUW-THBK3YJqtN9tD--o6dZAXlIW5JZmJbtsf-bM98JuSDmys_r6oiQ-jPM8m8zqwRFl99EUzlBXMxOPnyqji_ll9u5jcDz3aKhQGA5HwGs_iYzvJD4zdxq-xEF4g25C7Z1TnvQ7W2g24xenMwtF8h84FEiOXmhPFZ_-MvU0-6S-W3ATjNKmf7fbh2m8gIozPJj9mmczN__4iq8T8L_Jw8G9AlPe27wwuyA_WE7I83N9DBkCfk6U80hAdknRzxFtEBmkYq8OUSlov2li5q-h2aW-jWd3TVBxRElbh1i4JEV01X2FBNC6O8WbfU1oFWy8bG9LJVs6g7-vXi8hMmtyWrbV-S67PP3z6eZ8NdDJkXheoycIEXzmrrjEZMx61RvIIgTGCO59zJAMCcMioIH2GA0BX3aO_KAQIg6cQrslc3Nbwm1OH6XQZjtTcBBcxK65WXhkGRe23zKXk_NlO56ik3yrRUyU3JeNnX6ZRMYnVvFcavR2N7loMttqXWuNgWc6am5HgrRSOKJyO2hmbTlohSeDwS_ocGZoBI1UwJ_YuGwTlHcJXLwz8W7Yg86aP4o3vaG7KHFQ5vEc907l3qyQ_Blvfl |
link.rule.ids | 315,786,790,802,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB5BOQAHCguIpS21ENds48fG8RFRqi10e6GVeov8SrVim6w22UP76xk7yYq3eksyk8TyeOzP9sxngA9mKu20LLMEoT9LBLV5ohXXeGszp0rLqQnJyfPzbHYpvlxNr3qe7ZgL472PwWd-Ei7jXr6r7SYslR3lGaIN8RAe4TCfyi5Za9vtZkM8B0UP5iLtaYRoqo4om3Sv_jL4xNNU_uiC47hystslbDeRjjCEk3yfbFozsXe_kTXes8jP4VmPL8nHrkG8gAe-GsHucHYD6V15BE9_IiJ8CesYircIIdAkkIEvl365aG7IoiLXvr7x7fqWrLqUgqASFm9REAmryQpNVTd-kNfrhujKkXJZ6_C9ZFUvqpZ8O50f4-e2dLXNK7g8-XzxaZb0pzEklmeyTbxxLDM610bliOqYVpKV3nHlqGEpM8J5T41U0nEbgADPS2aDnYxHCCQMfw07VV35N0AMzuCFUzq3yqGAaqGttEJRn6U21-kY3g9mKlYd6UYRJyupKigrujodwyhU91ZheLo32LPovbEp8hyn23xK5RgOt1J0o7A3oitfb5oCcQoLm8L_0cAfIFZVYyD_0FA46nAmU_H2r0U7hMezi_lZcXZ6_nUPnnQ5_SFYbR92sPL9AaKb1ryLrfoH6wT7OQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Exploiting+parallelism+in+geometry+processing+with+general+purpose+processors+and+floating-point+SIMD+instructions&rft.jtitle=IEEE+transactions+on+computers&rft.au=Chia-Lin+Yang&rft.au=Sano%2C+B.&rft.au=Lebeck%2C+A.R.&rft.date=2000-09-01&rft.issn=0018-9340&rft.volume=49&rft.issue=9&rft.spage=934&rft.epage=946&rft_id=info:doi/10.1109%2F12.869324&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_12_869324 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9340&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9340&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9340&client=summon |