Using loop transformations for precision tuning in iterative programs
Many floating-point formats are available, providing all different levels of precision. By mixing several of these formats in the same program, it is possible to achieve good performance while maintaining an acceptable level of output accuracy. Therefore various tools have been designed to adapt the...
Uloženo v:
| Vydáno v: | Proceedings - Symposium on Computer Arithmetic s. 159 - 166 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
04.09.2023
|
| Témata: | |
| ISSN: | 2576-2265 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Many floating-point formats are available, providing all different levels of precision. By mixing several of these formats in the same program, it is possible to achieve good performance while maintaining an acceptable level of output accuracy. Therefore various tools have been designed to adapt the precision of computations in floating-point programs for performance and accuracy purposes. However most of them do not consider the iterative nature of these programs. This article presents a tool that enables to adapt the precision of floating-point computations in iterative routines, at the iteration level. This tool is based on multiple-precision computations to evaluate the impact of some format adaptations on the output accuracy, and it uses the delta-debugging to isolate the most relevant instruction set to be tuned. The originality of our approach is that it relies on static loop transformations to duplicate loop body instructions, and thus to increase the number of possible instructions that can be targeted. These transformations include especially the loop splitting and unrolling, which enable to allocate different precisions for different iterations, and thus to improve the tuning process. We show the advantages of this approach on a representative set of iterative programs. |
|---|---|
| AbstractList | Many floating-point formats are available, providing all different levels of precision. By mixing several of these formats in the same program, it is possible to achieve good performance while maintaining an acceptable level of output accuracy. Therefore various tools have been designed to adapt the precision of computations in floating-point programs for performance and accuracy purposes. However most of them do not consider the iterative nature of these programs. This article presents a tool that enables to adapt the precision of floating-point computations in iterative routines, at the iteration level. This tool is based on multiple-precision computations to evaluate the impact of some format adaptations on the output accuracy, and it uses the delta-debugging to isolate the most relevant instruction set to be tuned. The originality of our approach is that it relies on static loop transformations to duplicate loop body instructions, and thus to increase the number of possible instructions that can be targeted. These transformations include especially the loop splitting and unrolling, which enable to allocate different precisions for different iterations, and thus to improve the tuning process. We show the advantages of this approach on a representative set of iterative programs. |
| Author | Revy, Guillaume Fakhreddine, Youssef |
| Author_xml | – sequence: 1 givenname: Youssef surname: Fakhreddine fullname: Fakhreddine, Youssef organization: Univ Perpignan Via Domitia,DALI,Perpignan,France – sequence: 2 givenname: Guillaume surname: Revy fullname: Revy, Guillaume organization: Univ Perpignan Via Domitia,DALI,Perpignan,France |
| BookMark | eNotjN1KAzEUhKMo2Na-gUJeYNeTk83PXpZSbaEgSHtdkm1SI91sSVbBtzeiMDAzzMdMyU0coiPkkUHNGLRPi7fNbi20RFkjIK8BgLMrMm9Vq7kouUVsrskEhZIVohR3ZJrzBwBrW6kmZLXPIZ7oeRgudEwmZj-k3oxhiJmWSC_JdSGXSsfP-EuGSMPoUkG-XFmHUzJ9vie33pyzm__7jOyfV7vlutq-vmyWi231jlqNldTcad3BkXvToUOrwHjg1hvbSW8l50dlpJC28ygEeq4BFSvqLBrtJZ-Rh7_f4Jw7XFLoTfo-MGgkazTjP6jfT7U |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/ARITH58626.2023.00031 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISBN | 9798350319224 |
| EISSN | 2576-2265 |
| EndPage | 166 |
| ExternalDocumentID | 10461481 |
| Genre | orig-research |
| GroupedDBID | 29F 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-h287t-683e88c0d3fac2e2b70af03bfabc6fb633d7a656bcf2552f380271271cb2a8f63 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001191294100027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:17:05 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-h287t-683e88c0d3fac2e2b70af03bfabc6fb633d7a656bcf2552f380271271cb2a8f63 |
| OpenAccessLink | https://hal-lirmm.ccsd.cnrs.fr/lirmm-04939356 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_10461481 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-Sept.-4 |
| PublicationDateYYYYMMDD | 2023-09-04 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-Sept.-4 day: 04 |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings - Symposium on Computer Arithmetic |
| PublicationTitleAbbrev | ARITH |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0019967 |
| Score | 2.2379882 |
| Snippet | Many floating-point formats are available, providing all different levels of precision. By mixing several of these formats in the same program, it is possible... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 159 |
| SubjectTerms | delta-debugging algorithm Digital arithmetic dynamic precision tuning tool floating-point arithmetic Instruction sets Iterative methods loop splitting and unrolling mixed-precision multiple-precision Runtime Tuning |
| Title | Using loop transformations for precision tuning in iterative programs |
| URI | https://ieeexplore.ieee.org/document/10461481 |
| WOSCitedRecordID | wos001191294100027&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 | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09a8MwEBVt6NAp_XDpNxq6KpEt25LHUhJSKCGUtGQL-jjRQLFN4uT3V1KcNEuHggfhwYKTbb2nu3cPoSfNKQWpMhILbUkKhhKV2IxomRor0pTqYPf2-cbHYzGbFZNWrB60MAAQis-g54chl28qvfZHZX2fj3Tw3ZGdY875Vqy1Txk44M5biU5Mi_7z--t0lHm83vMO4b5PoTeSO7BQCTvIsPvPuc9Q9KvFw5P9LnOOjqC8QN2dGQNuv81LNAjJf_xdVTVuDtCoe6uwG-J62brp4Gbtz0LwosTblsruf4fbMq1VhD6Gg-nLiLQeCeTLcZ2G5IKBEJoaZqVOIFGcSkuZslLp3KqcMcOlw2xKW0ceEsuE46Gxu7RKpLA5u0KdsirhGmERc0kzMCCgSLmgBXNEOyvcM6TRSsQ3KPJhmdfbNhjzXURu_7h_h0595ENBVnqPOs1yDQ_oRG-axWr5GBbvB3FmnTI |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA4yBT3Nj4nf5uC1W9qkTXoU2dhwjiFTdhv5eIMDacfW-ftNsjp38SD0EHpoIEmT58n7Pu-D0IPmhIBUaRQLbSMGhkQqsWmkJTNWMEZ0sHt7H_LRSEyn-bgWqwctDACE5DNo-2aI5ZtSr_1VWcfHIx18d2RnP2UsiTdyrW3QwEF3Xot0YpJ3Hl8Hk37qEXvbe4T7SoXeSm7HRCWcIb3mP3s_Rq1fNR4eb8-ZE7QHxSlq_tgx4PrvPEPdEP7Hn2W5wNUOHnXrCrsmXixrPx1crf1tCJ4XeFNU2e14uE7UWrXQW687eepHtUtC9OHYThVlgoIQmhhqpU4gUZxIS6iyUunMqoxSw6VDbUpbRx8SS4VjorF7tEqksBk9R42iLOACYRFzSVIwICBnXJCcOqqd5u4b0mgl4kvU8sMyW2wKYcx-RuTqj_f36LA_eRnOhoPR8zU68rMQ0rPYDWpUyzXcogP9Vc1Xy7swkd_NG6B5 |
| 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=Proceedings+-+Symposium+on+Computer+Arithmetic&rft.atitle=Using+loop+transformations+for+precision+tuning+in+iterative+programs&rft.au=Fakhreddine%2C+Youssef&rft.au=Revy%2C+Guillaume&rft.date=2023-09-04&rft.pub=IEEE&rft.eissn=2576-2265&rft.spage=159&rft.epage=166&rft_id=info:doi/10.1109%2FARITH58626.2023.00031&rft.externalDocID=10461481 |