Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Siteplutao.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP3W/3UGD66G
Repositorysid.inpe.br/plutao/2019/12.03.15.29.56
Last Update2019:12.05.17.54.52 (UTC) lattes
Metadata Repositorysid.inpe.br/plutao/2019/12.03.15.29.57
Metadata Last Update2020:01.06.11.35.26 (UTC) administrator
DOI10.5753/wscad.2019.8657
Labellattes: 6700293516531228 1 FreitasMend:2019:RoAnPe
Citation KeyFreitasMend:2019:RoAnPe
TitleRoofline analysis and performance optimization of the MGB hydrological model
FormatDVD
Year2019
Access Date2024, Apr. 24
Secondary TypePRE CN
Number of Files1
Size425 KiB
2. Context
Author1 Freitas, Henrique Rennó de Azeredo
2 Mendes, Celso Luiz
Group1 CAP-COMP-SESPG-INPE-MCTIC-GOV-BR
2 LABAC-COCTE-INPE-MCTIC-GOV-BR
Affiliation1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 Instituto Nacional de Pesquisas Espaciais (INPE)
Author e-Mail Address1 henrique.renno@inpe.br
2 celso.mendes@inpe.br
Conference NameSimpósio em Sistemas Computacionais de Alto Desempenho, 20
Conference LocationCampo Grande, MS
Date16-18 out.
PublisherSociedade Brasileira de Computação
Pages61-72
Book TitleAnais
Tertiary TypePaper
History (UTC)2019-12-03 15:29:57 :: lattes -> administrator ::
2019-12-04 03:18:01 :: administrator -> lattes :: 2019
2019-12-05 17:54:53 :: lattes -> administrator :: 2019
2020-01-06 11:35:26 :: administrator -> simone :: 2019
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Version Typepublisher
KeywordsPerformance evaluation
Application optimization
Roofline model
CPU/GPU parallelism
AbstractThe Roofline model gives insights about the performance behaviorof applications bounded by either memory or processor limits, providing usefulguidelines for performance improvements. This work uses the Roofline model onthe analysis of the MGB model that simulates hydrological processes in large-scale watersheds. Real-world input data are used to characterize the performanceon two multicore architectures, one with only CPUs and one with CPUs/GPU.The MGB model performance is improved with optimizations for better memoryuse, and also with shared-memory (OpenMP) and GPU (OpenACC) parallelism.CPU performance achieves42:51 %and50:17 %of each systems peak, whereasGPU performance is low due to overheads caused by the MGB model structure.
AreaCOMP
Arrangement 1urlib.net > BDMCI > Fonds > Produção anterior à 2021 > LABAC > Roofline analysis and...
Arrangement 2urlib.net > BDMCI > Fonds > Produção pgr ATUAIS > CAP > Roofline analysis and...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGP3W/3UGD66G
zipped data URLhttp://urlib.net/zip/8JMKD3MGP3W/3UGD66G
Languageen
Target Filefreitas_roofline.pdf
User Grouplattes
Reader Groupadministrator
lattes
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Next Higher Units8JMKD3MGPCW/3ESGTTP
8JMKD3MGPCW/3F2PHGS
Citing Item Listsid.inpe.br/bibdigital/2013/10.12.22.16 4
URL (untrusted data)https://sol.sbc.org.br/index.php/wscad/article/view/8657
Host Collectiondpi.inpe.br/plutao@80/2008/08.19.15.01
6. Notes
Empty Fieldsarchivingpolicy archivist callnumber copyholder copyright creatorhistory descriptionlevel dissemination e-mailaddress edition editor isbn issn lineage mark mirrorrepository nextedition notes numberofvolumes orcid organization parameterlist parentrepositories previousedition previouslowerunit progress project publisheraddress readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark serieseditor session shorttitle sponsor subject tertiarymark type volume
7. Description control
e-Mail (login)simone
update 


Close