GPU-S2S: A Compiler for Source-to-Source Translation on GPU

CUDA facilitates the development of General Purpose computing on Graphics Processing Units (GPGPU), however, its complex memory system, thread-level structure, and data transmission control between memories have brought great challenges for programming on GPU. In order to facilitate the development...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2010 3rd International Symposium on Parallel Architectures, Algorithms and Programming s. 144 - 148
Hlavní autori: Dan Li, Haijun Cao, Xiaoshe Dong, Bao Zhang
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.12.2010
Predmet:
Arrays
compiler directive
Data mining
GPU
Graphics processing unit
Instruction sets
Kernel
Libraries
Optimization
source-to-source translation
ISBN:1424494826, 9781424494828
ISSN:2168-3034
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract CUDA facilitates the development of General Purpose computing on Graphics Processing Units (GPGPU), however, its complex memory system, thread-level structure, and data transmission control between memories have brought great challenges for programming on GPU. In order to facilitate the development of parallel programs on GPU and reuse existing sequential codes, in this paper we propose a novel directive based compiler guided approach. Through combining automatic mapping and static compilation, we have implemented a prototype of automatic source-to-source translation tool named GPU-S2S, capable of translating the C sequential code with directives into CUDA code. Experimental results show that CUDA code generated by GPU-S2S can achieve comparable performance with that of CUDA benchmark provided by NVIDIA CUDA SDK, and has significant performance improvements compared with its original C sequential code.
AbstractList CUDA facilitates the development of General Purpose computing on Graphics Processing Units (GPGPU), however, its complex memory system, thread-level structure, and data transmission control between memories have brought great challenges for programming on GPU. In order to facilitate the development of parallel programs on GPU and reuse existing sequential codes, in this paper we propose a novel directive based compiler guided approach. Through combining automatic mapping and static compilation, we have implemented a prototype of automatic source-to-source translation tool named GPU-S2S, capable of translating the C sequential code with directives into CUDA code. Experimental results show that CUDA code generated by GPU-S2S can achieve comparable performance with that of CUDA benchmark provided by NVIDIA CUDA SDK, and has significant performance improvements compared with its original C sequential code.
Author Xiaoshe Dong
Bao Zhang
Dan Li
Haijun Cao
Author_xml – sequence: 1
  surname: Dan Li
  fullname: Dan Li
  email: li.dan@stu.xjtu.edu.cn
  organization: Dept. of Comput. Sci. & Technol., Xi'an Jiaotong Univ., Xi'an, China
– sequence: 2
  surname: Haijun Cao
  fullname: Haijun Cao
  email: caohaijun@mail.xjtu.edu.cn
  organization: Dept. of Comput. Sci. & Technol., Xi'an Jiaotong Univ., Xi'an, China
– sequence: 3
  surname: Xiaoshe Dong
  fullname: Xiaoshe Dong
  email: xsdong@mail.xjtu.edu.cn
  organization: Dept. of Comput. Sci. & Technol., Xi'an Jiaotong Univ., Xi'an, China
– sequence: 4
  surname: Bao Zhang
  fullname: Bao Zhang
  organization: Dept. of Comput. Sci. & Technol., Xi'an Jiaotong Univ., Xi'an, China
BookMark eNotjE1Lw0AYhBdswab25s3L_oGt--736ikErULBQOK5bJI3EEmzJYkH_72RCgMzD8xMQlZDHJCQe-B7AO4f8zTN94IvqOQNSUAJpbxywqzIRoBxTHKp1iT5q3hprde3ZDdNX5xzCc47wzfk-ZB_skIUTzSlWTxfuh5H2saRFvF7rJHNkV0TLccwTH2YuzjQRcvujqzb0E-4-_ctKV9fyuyNHT8O71l6ZJ3nMzPaOKdbqRGwblrRVDIgeKWDbgHBBKx8ZVslgkAVrIXKuKr2CEL7GlQjt-Thetsh4ukyducw_py0Bc2tkb-zZkjO
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PAAP.2010.43
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EndPage 148
ExternalDocumentID 5715076
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i90t-656885f35e1ecdf2db3ae1945a5f1e16aeb9b7f42a2e4a771b68bc9e1259c14d3
IEDL.DBID RIE
ISBN 1424494826
9781424494828
ISSN 2168-3034
IngestDate Wed Aug 27 03:23:11 EDT 2025
IsPeerReviewed false
IsScholarly false
LCCN 2010937795
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-656885f35e1ecdf2db3ae1945a5f1e16aeb9b7f42a2e4a771b68bc9e1259c14d3
PageCount 5
ParticipantIDs ieee_primary_5715076
PublicationCentury 2000
PublicationDate 2010-Dec.
PublicationDateYYYYMMDD 2010-12-01
PublicationDate_xml – month: 12
  year: 2010
  text: 2010-Dec.
PublicationDecade 2010
PublicationTitle 2010 3rd International Symposium on Parallel Architectures, Algorithms and Programming
PublicationTitleAbbrev paap
PublicationYear 2010
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003189860
ssj0000527807
Score 1.4636338
Snippet CUDA facilitates the development of General Purpose computing on Graphics Processing Units (GPGPU), however, its complex memory system, thread-level structure,...
SourceID ieee
SourceType Publisher
StartPage 144
SubjectTerms Arrays
compiler directive
Data mining
GPU
Graphics processing unit
Instruction sets
Kernel
Libraries
Optimization
source-to-source translation
Title GPU-S2S: A Compiler for Source-to-Source Translation on GPU
URI https://ieeexplore.ieee.org/document/5715076
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELbaioGpQIt4ywMjhtjxE6YKUZiqSC1St8p2bKlLi0rK78d2HjCwIGWwE0WKHNv33fn77gC4Fbz0NmfBTWUiQ9QzgTRmEpWE-pjyDkvuU7EJMZvJ5VIVPXDXaWGcc4l85u5jM53ll1u7j6Gy4LxH-ML7oC8Er7VaXTwlY0TIxpWJ_TBXlUwiYYK5RGGnpq2uS9GAqdt0T01fdqR49VBMJkVN-opanl9FV5LNmQ7_97VHYPwj3oNFZ5aOQc9tTsCwrd4Am8U8Ak-vxTuak_kjnMD4NGwPOxggLJyneD6qtqhuwWTPas4cDFd4bwwW05fF8xtqSimgtcoqFECblMznzGFnS09Kk2uHFWWaeeww184oIzwlmjiqhcCGS2OVC-hHWUzL_BQMNtuNOwPQZ9IrpY3lJpatloZr6ktObe4wxQafg1EcitVHnSxj1YzCxd-3L8Eh6fghV2BQ7fbuGhzYr2r9ubtJf_gbN_-dVg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5zCnqauom_zcGj0SXNTz0NcU6co7AJu42kTWCXTWbn32-SdtWDF6GHpKVQ0iTvey_vex8A14LnLkuYd1OZ6CLqmEAaM4lyQl0oeYcld1FsQoxGcjpVaQPc1FwYa21MPrO3oRnP8vNltg6hMu-8B_jCt8B2UM6q2Fp1RKXLiJCVMxP6frYqGWnCBHOJ_F5NN8wuRT2q3hR8qvqyTotXd2mvl5ZpX4HN80t2JVqdfut_37sPOj_0PZjWhukANOziELQ2-g2wWs5t8PCcvqMxGd_DHgxP_Qaxgh7EwnGM6KNiicoWjBatzJqD_vLvdcCk_zR5HKBKTAHNVbdAHrZJyVzCLLZZ7khuEm2xokwzhy3m2hplhKNEE0u1ENhwaTJlPf5RGaZ5cgSai-XCHgPoutIppU3GTRCuloZr6nJOs8Riig0-Ae0wFLOPslzGrBqF079vX4HdweRtOBu-jF7PwB6ps0XOQbNYre0F2Mm-ivnn6jL-7W-klKCf
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%3Abook&rft.genre=proceeding&rft.title=2010+3rd+International+Symposium+on+Parallel+Architectures%2C+Algorithms+and+Programming&rft.atitle=GPU-S2S%3A+A+Compiler+for+Source-to-Source+Translation+on+GPU&rft.au=Dan+Li&rft.au=Haijun+Cao&rft.au=Xiaoshe+Dong&rft.au=Bao+Zhang&rft.date=2010-12-01&rft.pub=IEEE&rft.isbn=9781424494828&rft.issn=2168-3034&rft.spage=144&rft.epage=148&rft_id=info:doi/10.1109%2FPAAP.2010.43&rft.externalDocID=5715076
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-3034&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-3034&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-3034&client=summon