IRIS-DMEM: Efficient Memory Management for Heterogeneous Computing
This paper proposes an efficient data memory management approach for the Intelligent RuntIme System (IRIS) heterogeneous computing framework along with new data transfer policies. IRIS provides a task-based programming model for extreme heterogeneous computing (e.g., CPU, GPU, DSP, FPGA) with suppor...
Gespeichert in:
| Veröffentlicht in: | IEEE Conference on High Performance Extreme Computing (Online) S. 1 - 7 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
25.09.2023
|
| Schlagworte: | |
| ISSN: | 2643-1971 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | This paper proposes an efficient data memory management approach for the Intelligent RuntIme System (IRIS) heterogeneous computing framework along with new data transfer policies. IRIS provides a task-based programming model for extreme heterogeneous computing (e.g., CPU, GPU, DSP, FPGA) with support for today's most important programming languages (e.g., OpenMP, OpenCL, CUDA, HIP, OpenACC). However, the IRIS framework either forces the programmer to introduce data transfer commands for each task or relies on suboptimal memory management for automatic and transparent data transfers. The work described here extends IRIS with novel heterogeneous memory handling and introduces novel data transfer policies by employing the Distributed data MEMory handler (DMEM) for efficient and optimal movement of data among the various computing resources. The proposed approach achieves performance gains of up to 7× for tiled LU factorization and tiled DGEMM (i.e., matrix multiplication) benchmarks. Moreover, this approach also reduces data transfers by up to 71% when compared to previous IRIS heterogeneous memory management handlers. This work compares the performance results of the IRIS framework's novel DMEM with the StarPU runtime and MAGMA math library for GPUs. Experiments show a performance gain of up to 1.95× over StarPU and 2.1× over MAGMA. |
|---|---|
| AbstractList | This paper proposes an efficient data memory management approach for the Intelligent RuntIme System (IRIS) heterogeneous computing framework along with new data transfer policies. IRIS provides a task-based programming model for extreme heterogeneous computing (e.g., CPU, GPU, DSP, FPGA) with support for today's most important programming languages (e.g., OpenMP, OpenCL, CUDA, HIP, OpenACC). However, the IRIS framework either forces the programmer to introduce data transfer commands for each task or relies on suboptimal memory management for automatic and transparent data transfers. The work described here extends IRIS with novel heterogeneous memory handling and introduces novel data transfer policies by employing the Distributed data MEMory handler (DMEM) for efficient and optimal movement of data among the various computing resources. The proposed approach achieves performance gains of up to 7× for tiled LU factorization and tiled DGEMM (i.e., matrix multiplication) benchmarks. Moreover, this approach also reduces data transfers by up to 71% when compared to previous IRIS heterogeneous memory management handlers. This work compares the performance results of the IRIS framework's novel DMEM with the StarPU runtime and MAGMA math library for GPUs. Experiments show a performance gain of up to 1.95× over StarPU and 2.1× over MAGMA. |
| Author | Vetter, Jeffrey S. Haque Monil, Mohammad Alaul Liu, Frank Y. Miniskar, Narasinga Rao Valero-Lara, Pedro |
| Author_xml | – sequence: 1 givenname: Narasinga Rao surname: Miniskar fullname: Miniskar, Narasinga Rao email: miniskarnr@ornl.gov organization: Oak Ridge National Laboratory,Computer Science and Mathematics Division,Oak Ridge,TN,USA – sequence: 2 givenname: Mohammad Alaul surname: Haque Monil fullname: Haque Monil, Mohammad Alaul email: monilm@ornl.gov organization: Oak Ridge National Laboratory,Computer Science and Mathematics Division,Oak Ridge,TN,USA – sequence: 3 givenname: Pedro surname: Valero-Lara fullname: Valero-Lara, Pedro email: valerolarap@ornl.gov organization: Oak Ridge National Laboratory,Computer Science and Mathematics Division,Oak Ridge,TN,USA – sequence: 4 givenname: Frank Y. surname: Liu fullname: Liu, Frank Y. email: liufy@ornl.gov organization: Oak Ridge National Laboratory,Computer Science and Mathematics Division,Oak Ridge,TN,USA – sequence: 5 givenname: Jeffrey S. surname: Vetter fullname: Vetter, Jeffrey S. email: vetter@ornl.gov organization: Oak Ridge National Laboratory,Computer Science and Mathematics Division,Oak Ridge,TN,USA |
| BookMark | eNo1j81Og0AURkejibXyBibyAuCducwP7pSikJRo_Fk3w_QOwQg0QBd9e2vU1Um-xcl3LtlZP_TE2A2HmHNIb4uXPJPGKIwFCIw5oELJxQkLUp0alIBgFMApWwiVYMRTzS9YME2fAIAoQCMu2EP5Wr5Fqyqv7sLc-9a11M9hRd0wHsLK9rah7mfxwxgWNNM4NNTTsJ_CbOh2-7ntmyt27u3XRMEfl-zjMX_Pimj9_FRm9-uoFRLnqKYtUrL13HnLNfdcOUMOhdTOameEN-J4ShjpNdegaq9JJqkQTtepomPmkl3_elsi2uzGtrPjYfOfjd8H_U0F |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/HPEC58863.2023.10363512 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) 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 |
| EISBN | 9798350308600 |
| EISSN | 2643-1971 |
| EndPage | 7 |
| ExternalDocumentID | 10363512 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL 6IN ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK OCL RIE RIL |
| ID | FETCH-LOGICAL-i253t-bed3e4df1cfa171f16c8ec3257ca7c82f82320285f71706bf7e54922c7b96e863 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 7 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001156959800038&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 02:24:35 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i253t-bed3e4df1cfa171f16c8ec3257ca7c82f82320285f71706bf7e54922c7b96e863 |
| OpenAccessLink | https://www.osti.gov/biblio/2438976 |
| PageCount | 7 |
| ParticipantIDs | ieee_primary_10363512 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-Sept.-25 |
| PublicationDateYYYYMMDD | 2023-09-25 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-Sept.-25 day: 25 |
| PublicationDecade | 2020 |
| PublicationTitle | IEEE Conference on High Performance Extreme Computing (Online) |
| PublicationTitleAbbrev | HPEC |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003320733 |
| Score | 1.895588 |
| Snippet | This paper proposes an efficient data memory management approach for the Intelligent RuntIme System (IRIS) heterogeneous computing framework along with new... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Data transfer Distributed databases Graphics processing units Heterogeneous computing Iris memory Memory management Performance gain Runtime |
| Title | IRIS-DMEM: Efficient Memory Management for Heterogeneous Computing |
| URI | https://ieeexplore.ieee.org/document/10363512 |
| WOSCitedRecordID | wos001156959800038&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/eLvHCXMwlV1LbwIhECat6aEn-7DpOxx6xRbYBbbH2jV60Jg-Em-GhSHxoo3VJv33ZXDV9NBDb4SECTswGWC_-T5C7vJKVzbLC4Ys1izLssBMYX0MdwEqZhyk7EpiE3o4NONxMaqL1VMtDAAk8Bm0sZn-5fu5W-FTWYxwGfMjagrva63WxVrbBxUpBQoQ1hgu_lDc90ZlJzdGyTZqhLc3o3_pqKQ00m3-cwJHpLUryKOjbao5JnswOyHNjSIDrQP0lDz1X_qv7HlQDh5pmcghoj06QDTtN90hXWg8qdIeAmHmcf9AvPzTta1ovEXeu-Vbp8dqlQQ2Fblcsgq8hMwH7oLlmgeunAEnYyg6q50RwQjUSDd50EiVUwUNyMomnK4KBdE7Z6Qxm8_gnFDrCxDWKW99PCY5bVUFQvP4cZxrlesL0kKfTD7WRBiTjTsu_-i_IofoeYRXiPyaNJaLFdyQA_e1nH4ubtPy_QDJh5nF |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA4yBT3NHxN_m4PXTpM0TerR2dHhOoZO2G2k6SvsssrcBP9787Juw4MHbyGQR_qSx0vS730fIXcyV7kJZRwgi3UQhmEZ6NgULtw5RC7jIGWXF5tQg4Eej-NhXazua2EAwIPPoI1N_y-_qOwSn8pchAuXH1FTeBels9iqXGvzpCIERwnCGsXFHuL7dJh0pNaRaKNKeHs9_peSik8k3eY_p3BIWtuSPDrcJJsjsgOzY9JcazLQOkRPyFPvtfcWPGdJ9kgTTw_h7NEM8bTfdIt1oe6sSlOEwlRuB4G7_tOVLWe8Rd67yaiTBrVOQjDlUiyCHAoBYVEyWxqmWMkiq8EKF4zWKKt5qTmqpGtZKiTLyUsFyMvGrcrjCJx3TkljVs3gjFBTxMCNjQpTuIOSVSbKgSvmPo4xFUl1Tlrok8nHigpjsnbHxR_9t2Q_HWX9Sb83eLkkB7gKCLbg8oo0FvMlXJM9-7WYfs5v_FL-APo5nQw |
| 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=IEEE+Conference+on+High+Performance+Extreme+Computing+%28Online%29&rft.atitle=IRIS-DMEM%3A+Efficient+Memory+Management+for+Heterogeneous+Computing&rft.au=Miniskar%2C+Narasinga+Rao&rft.au=Haque+Monil%2C+Mohammad+Alaul&rft.au=Valero-Lara%2C+Pedro&rft.au=Liu%2C+Frank+Y.&rft.date=2023-09-25&rft.pub=IEEE&rft.eissn=2643-1971&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FHPEC58863.2023.10363512&rft.externalDocID=10363512 |