GPT-Driven Source-to-Source Transformation for Generating Compilable Parallel CUDA Code for Nussinov’s Algorithm

Designing automatic optimizing compilers is an advanced engineering process requiring a great deal of expertise, programming, testing, and experimentation. Maintaining the approach and adapting it to evolving libraries and environments is a time-consuming effort. In recent years, OpenAI has presente...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) Vol. 13; no. 3; p. 488
Main Authors: Palkowski, Marek, Gruzewski, Mateusz
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.02.2024
Subjects:
ISSN:2079-9292, 2079-9292
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Designing automatic optimizing compilers is an advanced engineering process requiring a great deal of expertise, programming, testing, and experimentation. Maintaining the approach and adapting it to evolving libraries and environments is a time-consuming effort. In recent years, OpenAI has presented the GPT model, which is designed for many fields like computer science, image processing, linguistics, and medicine. It also supports automatic programming and translation between programming languages, as well as human languages. This article will verify the usability of the commonly known LLM model, GPT, for the non-trivial NPDP Nussinov’s parallel algorithm code within the OpenMP standard to create a parallel equivalent of CUDA for NVIDIA graphics cards. The goal of this approach is to avoid creating any post-processing scripts and writing any lines of target code. To validate the output code, we compare the resulting arrays with the ones calculated by the optimized code for the CPU generated employing the polyhedral compilers. Finally, the code will be checked for scalability and performance. We will concentrate on assessing the capabilities of GPT, highlighting common challenges that can be refined during future learning processes. This will enhance code generation for various platforms by leveraging the outcomes from polyhedral optimizers.
AbstractList Designing automatic optimizing compilers is an advanced engineering process requiring a great deal of expertise, programming, testing, and experimentation. Maintaining the approach and adapting it to evolving libraries and environments is a time-consuming effort. In recent years, OpenAI has presented the GPT model, which is designed for many fields like computer science, image processing, linguistics, and medicine. It also supports automatic programming and translation between programming languages, as well as human languages. This article will verify the usability of the commonly known LLM model, GPT, for the non-trivial NPDP Nussinov’s parallel algorithm code within the OpenMP standard to create a parallel equivalent of CUDA for NVIDIA graphics cards. The goal of this approach is to avoid creating any post-processing scripts and writing any lines of target code. To validate the output code, we compare the resulting arrays with the ones calculated by the optimized code for the CPU generated employing the polyhedral compilers. Finally, the code will be checked for scalability and performance. We will concentrate on assessing the capabilities of GPT, highlighting common challenges that can be refined during future learning processes. This will enhance code generation for various platforms by leveraging the outcomes from polyhedral optimizers.
Audience Academic
Author Palkowski, Marek
Gruzewski, Mateusz
Author_xml – sequence: 1
  givenname: Marek
  orcidid: 0000-0002-5932-4523
  surname: Palkowski
  fullname: Palkowski, Marek
– sequence: 2
  givenname: Mateusz
  surname: Gruzewski
  fullname: Gruzewski, Mateusz
BookMark eNp9kcFOAyEQhompibX2Cbxs4nkVlm13OTatVpNGm9ieN8AOlYaFCtsm3nwNX88nkbYejDHCYX5gPibzzznqWGcBoUuCryll-AYMyNY7q2UgFFOcl-UJ6ma4YCnLWNb5oc9QP4Q1josRWlLcRX46X6QTr3dgk2e39RLS1qVHlSw8t0E53_BWO5tElUzBgo9Hu0rGrtlow4WBZM49NwZMMl5ORvGhhkPy4zYEbd3u8_0jJCOzcl63L80FOlXcBOh_xx5a3t0uxvfp7Gn6MB7NUkmHpE1rkXOhGK6lrIdC1FAMlZCxE5KzfMCJKGQtgAqsSDkUmZAEEwY0lwCDgjBFe-jq-O_Gu9cthLZax7ZsLFlFK6Jz5T700PUxa8UNVNoq13ou466h0TI6rXS8HxVlhkuWl0UE6BGQ3oXgQVUbrxvu3yqCq_1Aqj8GEin2i5K6Pdgay2nzL_sFQSyZrg
CitedBy_id crossref_primary_10_12688_mep_20815_1
Cites_doi 10.1109/TCBB.2022.3216826
10.1145/3605731.3605886
10.3390/electronics12173579
10.1145/2400682.2400713
10.1016/j.parco.2023.103016
10.1007/978-3-030-86359-3
10.1186/s12859-017-1707-8
10.1186/1471-2105-15-S8-S1
10.1145/2503210.2503289
10.1145/1375581.1375595
10.1109/IPDPSW59300.2023.00068
10.1145/3125632
10.1137/0135006
10.1016/j.jocs.2020.101246
ContentType Journal Article
Copyright COPYRIGHT 2024 MDPI AG
2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: COPYRIGHT 2024 MDPI AG
– notice: 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
7SP
7T9
8FD
8FE
8FG
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L7M
P5Z
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOI 10.3390/electronics13030488
DatabaseName CrossRef
Electronics & Communications Abstracts
Linguistics and Language Behavior Abstracts (LLBA)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Technology collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Publicly Available Content Database
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
Linguistics and Language Behavior Abstracts (LLBA)
ProQuest Technology Collection
ProQuest SciTech Collection
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList CrossRef

Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Medicine
Computer Science
EISSN 2079-9292
ExternalDocumentID A782089487
10_3390_electronics13030488
GeographicLocations Poland
GeographicLocations_xml – name: Poland
GroupedDBID 5VS
8FE
8FG
AAYXX
ADMLS
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BENPR
BGLVJ
CCPQU
CITATION
HCIFZ
IAO
ITC
KQ8
MODMG
M~E
OK1
P62
PHGZM
PHGZT
PIMPY
PQGLB
PROAC
7SP
7T9
8FD
ABUWG
AZQEC
DWQXO
L7M
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c361t-db4abf90dccd6bbde76fbc07914945a1b7cdbe3b0f186b2bc1019e34cee5719f3
IEDL.DBID P5Z
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001159153100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2079-9292
IngestDate Sun Nov 09 03:42:51 EST 2025
Tue Nov 04 18:23:22 EST 2025
Sat Nov 29 07:16:20 EST 2025
Tue Nov 18 21:56:00 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c361t-db4abf90dccd6bbde76fbc07914945a1b7cdbe3b0f186b2bc1019e34cee5719f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-5932-4523
OpenAccessLink https://www.proquest.com/docview/2923908292?pq-origsite=%requestingapplication%
PQID 2923908292
PQPubID 2032404
ParticipantIDs proquest_journals_2923908292
gale_infotracacademiconefile_A782089487
crossref_primary_10_3390_electronics13030488
crossref_citationtrail_10_3390_electronics13030488
PublicationCentury 2000
PublicationDate 2024-02-01
PublicationDateYYYYMMDD 2024-02-01
PublicationDate_xml – month: 02
  year: 2024
  text: 2024-02-01
  day: 01
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Electronics (Basel)
PublicationYear 2024
Publisher MDPI AG
Publisher_xml – name: MDPI AG
References Bielecki (ref_30) 2021; 48
ref_14
ref_36
ref_13
ref_35
ref_12
ref_11
ref_33
ref_10
ref_32
ref_31
Tchendji (ref_34) 2023; 20
ref_19
ref_18
ref_17
ref_39
ref_16
ref_15
ref_37
Verdoolaege (ref_9) 2013; 9
Palkowski (ref_38) 2023; 116
Chowdhury (ref_29) 2017; 4
ref_25
ref_24
ref_23
ref_22
ref_21
ref_20
ref_41
ref_40
ref_1
ref_3
ref_2
ref_28
Nussinov (ref_27) 1978; 35
ref_26
ref_8
ref_5
ref_4
ref_7
ref_6
References_xml – ident: ref_7
– ident: ref_28
– volume: 20
  start-page: 1795
  year: 2023
  ident: ref_34
  article-title: A Parallel Tiled and Sparsified Four-Russians Algorithm for Nussinov’s RNA Folding
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform.
  doi: 10.1109/TCBB.2022.3216826
– ident: ref_24
  doi: 10.1145/3605731.3605886
– ident: ref_39
  doi: 10.3390/electronics12173579
– ident: ref_5
– ident: ref_26
– volume: 9
  start-page: 1
  year: 2013
  ident: ref_9
  article-title: Polyhedral parallel code generation for CUDA
  publication-title: ACM Trans. Archit. Code Optim.
  doi: 10.1145/2400682.2400713
– ident: ref_11
– ident: ref_16
– volume: 116
  start-page: 103016
  year: 2023
  ident: ref_38
  article-title: NPDP benchmark suite for the evaluation of the effectiveness of automatic optimizing compilers
  publication-title: Parallel Comput.
  doi: 10.1016/j.parco.2023.103016
– ident: ref_37
– ident: ref_14
– ident: ref_1
– ident: ref_18
– ident: ref_23
– ident: ref_3
  doi: 10.1007/978-3-030-86359-3
– ident: ref_21
– ident: ref_32
  doi: 10.1186/s12859-017-1707-8
– ident: ref_35
  doi: 10.1186/1471-2105-15-S8-S1
– ident: ref_6
– ident: ref_33
  doi: 10.1145/2503210.2503289
– ident: ref_8
– ident: ref_25
– ident: ref_31
– ident: ref_2
– ident: ref_12
– ident: ref_10
– ident: ref_4
  doi: 10.1145/1375581.1375595
– ident: ref_41
– ident: ref_15
– ident: ref_40
  doi: 10.1109/IPDPSW59300.2023.00068
– ident: ref_13
– ident: ref_17
– volume: 4
  start-page: 1
  year: 2017
  ident: ref_29
  article-title: Autogen: Automatic Discovery of Efficient Recursive Divide-8-Conquer Algorithms for Solving Dynamic Programming Problems
  publication-title: ACM Trans. Parallel Comput.
  doi: 10.1145/3125632
– ident: ref_36
– ident: ref_19
– ident: ref_22
– ident: ref_20
– volume: 35
  start-page: 68
  year: 1978
  ident: ref_27
  article-title: Algorithms for loop matchings
  publication-title: SIAM J. Appl. Math.
  doi: 10.1137/0135006
– volume: 48
  start-page: 101246
  year: 2021
  ident: ref_30
  article-title: 3D parallel tiled code implementing a modified Knuth’s optimal binary search tree algorithm
  publication-title: J. Comput. Sci.
  doi: 10.1016/j.jocs.2020.101246
SSID ssj0000913830
Score 2.3008432
Snippet Designing automatic optimizing compilers is an advanced engineering process requiring a great deal of expertise, programming, testing, and experimentation....
SourceID proquest
gale
crossref
SourceType Aggregation Database
Enrichment Source
Index Database
StartPage 488
SubjectTerms Algorithms
Artificial intelligence
Chatbots
Codes
Compilers
Compiling (Electronic computers)
Computer graphics
Computer programming
Computer science
Coroutines
Dependence
Dynamic programming
Experiments
High performance computing
Image processing
Language
Languages
Learning processes
Libraries
Linguistics
Machine translation
Mathematical optimization
Medicine
Methods
Optimization
Programming languages
Python
Scripts
Transformation
Title GPT-Driven Source-to-Source Transformation for Generating Compilable Parallel CUDA Code for Nussinov’s Algorithm
URI https://www.proquest.com/docview/2923908292
Volume 13
WOSCitedRecordID wos001159153100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2079-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913830
  issn: 2079-9292
  databaseCode: M~E
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest advanced technologies & aerospace journals
  customDbUrl:
  eissn: 2079-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913830
  issn: 2079-9292
  databaseCode: P5Z
  dateStart: 20120301
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2079-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913830
  issn: 2079-9292
  databaseCode: BENPR
  dateStart: 20120301
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2079-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913830
  issn: 2079-9292
  databaseCode: PIMPY
  dateStart: 20120301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTtwwEB7xU1X0UNptEVvoygekXhqRH28cn9ACC-1hVxFdJNpLFDtOQVoSSALHitfo6_VJOpN4gUqIS29WbCeOxjOeGdvfB7CDa7jwXZ07tAmDAQp3Uec87eggFZEUqdZKt2QTYjqNzs5kbBNutT1WubCJraHOSk058l0fPRGi55b-3tW1Q6xRtLtqKTSWYZVQEoi6IR7-uM-xEOZlFLgd2FCA3XcfuGVqMt40ff9ZkJ42y-1ac7T-v6N8A6-tl8lG3bR4C0um6MH6gsGBWYXuwatHcIQ9eDmxG-3voDqOZ85hRaaQfWvz-05TOl2JzR45u2XBsMQ69Go6Qs3oKxdzupHF4rQiqpY5Ozg9HGFFZtrG0xtUxKK8_XP3u2aj-U_8geb88j2cHo1nB18cS8-Aggy9xskUT1Uu3UzrLFQqMyLMlXaFxKCLD1NPCZ0pEyg396JQ-Uqj9ksTcFyWh8KTebABK0VZmE1gIc9DIzKeGpNyDHiUQbdDeUMhXW5CrvrgL2SUaItdThQa8wRjGBJs8oRg-_D5vtNVB93xfPNPJPyEFBvfrVN7PwFHSBBZyYiQBSOJAV4fthfCT6zG18mD5D88X70Faz46Rt3J721Yaaob8xFe6Nvmoq4GsLo_nsYnA1ie_BoP2umMz-Kvk_j7X_jWA1k
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3NbtQwEB6VLaLlQGEp6kIBH0BciJofbxwfEFp1KV21u4rEViqnEDtOW2lJSpIWceM1eAkeiidhJj9tkareeuBmyY5tOZ_nxx7PB_AKdbhwbZ1adAmDDgq3cc852tJeLAIpYq2VrskmxGwWHB7KcAl-d29hKKyyk4m1oE5yTWfkWy5aIkTPLd33p98sYo2i29WOQqOBxZ758R1dtvLdZIz_97Xr7nyYb-9aLasAju87lZUoHqtU2onWia9UYoSfKm0Lib4CH8aOEjpRxlN26gS-cpVG0ErjcdQmQ-HI1MN-78AyJ7D3YDmcTMPPF6c6lGUz8OwmvZGHE966ZLMpSV3QhvlHBV6vCGrttrP2v63LQ3jQ2tFs1AD_ESyZrA9rHUcFa0VWH-5fSbjYh3vTNpTgMRQfw7k1LkjYs0_1DYZV5VZTYvMr5nyeMSyxJj83BYkzGuVkQW_OWBgXREazYNsH4xFWJKZuPDtDUZPl539-_irZaHGEC1Ydf12Hg1tZkifQy_LMbADzeeobkfDYmJijS6cMGlbKGQppc-NzNQC3w0Sk2-zsRBKyiNBLIyBF1wBpAG8vPjptkpPc3PwNgS0i0YV967h9gYEzpCRg0YhyJwYSXdgBbHZgi1qZVkaXSHt6c_VLWNmdT_ej_cls7xmsumgGNnHum9CrijPzHO7q8-qkLF6024fBl9tG5l87a2E5
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3dTtRAFD5BNEQuQFeJC4hzofHGZvsz2-lcELNhWSXopolLQrypnekUSdYW2gLxztfgVXwcn8Rz-gOYEO648K7JTKeT6Xf-Zs6cD-A12nDh2jq16BAGAxRuo8w52tJeLAIpYq2VrskmxHQaHB7KcAF-d3dhKK2y04m1ok5yTXvkAxc9EaLnlu4gbdMiwvHk_cmpRQxSdNLa0Wk0ENk3Py8wfCu398b4r9-47mR3tvPRahkGcC6-U1mJ4rFKpZ1onfhKJUb4qdK2kBg38GHsKKETZTxlp07gK1dpBLA0HkfLMhSOTD0c9wE8FBhjUjphOPx6tb9D9TYDz24KHXk49cE1r01JhoNE5x9jeLtJqO3cZPV_XqEnsNJ612zUiMNTWDBZD1Y75grWKrIeLN8ow9iDpc9tgsEzKD6EM2tckAlgX-pzDavKreaJzW44-XnG8Ik1VbspdZzRV47ndBONhXFBFDVztnMwHmFDYurO0zNUQFl-_ufXZclG8yNcsOr7j-dwcC9LsgaLWZ6ZF8B8nvpGJDw2JuYY6CmD7pZyhkLa3Phc9cHt8BHptmY7UYfMI4zdCFTRLaDqw7url06akiV3d39LwItIoeHYOm7vZeAMqTRYNKKKioHEwLYPmx3wolbTldE16tbvbn4FSwjH6NPedH8DHrvoGzbJ75uwWBVn5iU80ufVcVls1XLE4Nt9w_Iv9TFonA
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=GPT-Driven+Source-to-Source+Transformation+for+Generating+Compilable+Parallel+CUDA+Code+for+Nussinov%E2%80%99s+Algorithm&rft.jtitle=Electronics+%28Basel%29&rft.au=Palkowski%2C+Marek&rft.au=Gruzewski%2C+Mateusz&rft.date=2024-02-01&rft.issn=2079-9292&rft.eissn=2079-9292&rft.volume=13&rft.issue=3&rft.spage=488&rft_id=info:doi/10.3390%2Felectronics13030488&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_electronics13030488
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2079-9292&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2079-9292&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2079-9292&client=summon