{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:15:04Z","timestamp":1777058104250,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100008433","name":"Comunidad de Madrid","doi-asserted-by":"publisher","award":["S2018\/TCS-4423"],"award-info":[{"award-number":["S2018\/TCS-4423"]}],"id":[{"id":"10.13039\/501100008433","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministerio de Econom\u00eda y Competitividad","award":["RTI2018-093684-B-I00"],"award-info":[{"award-number":["RTI2018-093684-B-I00"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,8,17]]},"DOI":"10.1145\/3404397.3404441","type":"proceedings-article","created":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T03:54:26Z","timestamp":1596945266000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Enabling performance portability of data-parallel OpenMP applications on asymmetric multicore processors"],"prefix":"10.1145","author":[{"given":"Juan Carlos","family":"Saez","sequence":"first","affiliation":[{"name":"Complutense University of Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"Castro","sequence":"additional","affiliation":[{"name":"Complutense University of Madrid"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Prieto-Matias","sequence":"additional","affiliation":[{"name":"Complutense University of Madrid"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,8,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SPEC CPU 2017 Overview. What\u2019s New?https:\/\/www.spec.org\/cpu2017\/Docs\/overview.html.","unstructured":"2019. SPEC CPU 2017 Overview. What\u2019s New?https:\/\/www.spec.org\/cpu2017\/Docs\/overview.html. 2019. SPEC CPU 2017 Overview. What\u2019s New?https:\/\/www.spec.org\/cpu2017\/Docs\/overview.html."},{"key":"e_1_3_2_1_2_1","volume-title":"Benefits of the big.LITTLE Architecture","author":"ARM.","unstructured":"ARM. 2012. Benefits of the big.LITTLE Architecture . http:\/\/www.arm.com\/files\/downloads\/Benefits_of_the_big.LITTLE_architecture.pdf. Accessed: 2015-01-10. ARM. 2012. Benefits of the big.LITTLE Architecture. http:\/\/www.arm.com\/files\/downloads\/Benefits_of_the_big.LITTLE_architecture.pdf. Accessed: 2015-01-10."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Eduard Ayguad\u00e9 2003. Is the schedule clause really necessary in OpenMP?. In OpenMP Shared Memory Parallel Programming. WOMPAT (Toronto Canada) (Lecture Notes in Computer Science Vol.\u00a02716). 147\u2013159. Eduard Ayguad\u00e9 2003. Is the schedule clause really necessary in OpenMP?. In OpenMP Shared Memory Parallel Programming. WOMPAT (Toronto Canada) (Lecture Notes in Computer Science Vol.\u00a02716). 147\u2013159.","DOI":"10.1007\/3-540-45009-2_12"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337913"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_2_1_6_1","unstructured":"BSC. 2018. Paraver: a flexible performance analysis tool. https:\/\/tools.bsc.es\/paraver. Accessed: 2019-03-19. BSC. 2018. Paraver: a flexible performance analysis tool. https:\/\/tools.bsc.es\/paraver. Accessed: 2019-03-19."},{"key":"e_1_3_2_1_7_1","unstructured":"Anastasiia Butko 2016. Position Paper: OpenMP scheduling on ARM big.LITTLE architecture. In MULTIPROG: Programmability and Architectures for Heterogeneous Multicores(HAL Id: lirmm-01377630). Anastasiia Butko 2016. Position Paper: OpenMP scheduling on ARM big.LITTLE architecture. In MULTIPROG: Programmability and Architectures for Heterogeneous Multicores(HAL Id: lirmm-01377630)."},{"key":"e_1_3_2_1_8_1","unstructured":"Anastasiia Butko Florent Bruguier Abdoulaye Gamati\u00e9 and Gilles Sassatelli. 2017. Efficient Programming for Multicore Processor Heterogeneity: OpenMP versus OmpS. In OpenSuCo(HAL Id: lirmm-01723762). Anastasiia Butko Florent Bruguier Abdoulaye Gamati\u00e9 and Gilles Sassatelli. 2017. Efficient Programming for Multicore Processor Heterogeneity: OpenMP versus OmpS. In OpenSuCo(HAL Id: lirmm-01723762)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243176.3243199"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751235"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.01.007"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Florina\u00a0M. Ciorba Christian Iwainsky and Patrick Buder. 2018. OpenMP Loop Scheduling Revisited: Making a Case for More Schedules. In Evolving OpenMP for Evolving Architectures. 21\u201336. Florina\u00a0M. Ciorba Christian Iwainsky and Patrick Buder. 2018. OpenMP Loop Scheduling Revisited: Making a Case for More Schedules. In Evolving OpenMP for Evolving Architectures. 21\u201336.","DOI":"10.1007\/978-3-319-98521-3_2"},{"key":"e_1_3_2_1_15_1","volume-title":"Accelerator-Rich Architectures: Opportunities and Progresses. In 51st Ann. Design Automation Conf. (DAC 14)","author":"Cong Jason","year":"2014","unstructured":"Jason Cong 2014 . Accelerator-Rich Architectures: Opportunities and Progresses. In 51st Ann. Design Automation Conf. (DAC 14) . Article 180. Jason Cong 2014. Accelerator-Rich Architectures: Opportunities and Progresses. In 51st Ann. Design Automation Conf. (DAC 14). Article 180."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.53"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2836418"},{"key":"e_1_3_2_1_19_1","volume-title":"Odroid XU4 board","unstructured":"Hardkernel. 2016. Odroid XU4 board . http:\/\/odroid.com\/dokuwiki\/doku.php?id=en:odroid-xu4. Accessed: 2016-6-22. Hardkernel. 2016. Odroid XU4 board. http:\/\/odroid.com\/dokuwiki\/doku.php?id=en:odroid-xu4. Accessed: 2016-6-22."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/237502.237576"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485936"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.515.0503"},{"key":"e_1_3_2_1_25_1","first-page":"9","volume":"61","author":"Jouppi P.","year":"2018","unstructured":"Norman\u00a0 P. Jouppi 2018 . A Domain-specific Architecture for Deep Neural Networks. Commun. ACM 61 , 9 (Aug. 2018), 50\u201359. Norman\u00a0P. Jouppi 2018. A Domain-specific Architecture for Deep Neural Networks. Commun. ACM 61, 9 (Aug. 2018), 50\u201359.","journal-title":"A Domain-specific Architecture for Deep Neural Networks. Commun. ACM"},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Supercomputing (SC\u201907)","author":"Kale Vivek","year":"2017","unstructured":"Vivek Kale , Harshitha Menon , and Karthik Senthil . 2017 . Adaptive Loop Scheduling with Charm++ to Improve Performance of Scientific Applications . In International Conference on Supercomputing (SC\u201907) . Poster. Vivek Kale, Harshitha Menon, and Karthik Senthil. 2017. Adaptive Loop Scheduling with Charm++ to Improve Performance of Scientific Applications. In International Conference on Supercomputing (SC\u201907). Poster."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2642769.2642788"},{"key":"e_1_3_2_1_28_1","volume-title":"31st Symposium on High Performance Chips: Hot Chips\u201919","author":"Khushu Sanjeev","year":"2019","unstructured":"Sanjeev Khushu and Wilfred Gomes . 2019 . Lakefield: Hybrid Cores in 3D Package. https:\/\/newsroom.intel.com\/wp-content\/uploads\/sites\/11\/2019\/08\/Intel-Lakefield-HotChips-presentation.pdf . In 31st Symposium on High Performance Chips: Hot Chips\u201919 . Accessed : 2019-11-15. Sanjeev Khushu and Wilfred Gomes. 2019. Lakefield: Hybrid Cores in 3D Package. https:\/\/newsroom.intel.com\/wp-content\/uploads\/sites\/11\/2019\/08\/Intel-Lakefield-HotChips-presentation.pdf. In 31st Symposium on High Performance Chips: Hot Chips\u201919. Accessed: 2019-11-15."},{"key":"e_1_3_2_1_29_1","unstructured":"Michael Klemm Matthijs Van\u00a0Waveren and Jim Cownie. 2018. Twenty years of the OpenMP API. Scientific Computing World(2018). Michael Klemm Matthijs Van\u00a0Waveren and Jim Cownie. 2018. Twenty years of the OpenMP API. Scientific Computing World(2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"David Koufaty Dheeraj Reddy and Scott Hahn. 2010. Bias Scheduling in Heterogeneous Multi-core Architectures. In Eurosys 10. 125\u2013138. David Koufaty Dheeraj Reddy and Scott Hahn. 2010. Bias Scheduling in Heterogeneous Multi-core Architectures. In Eurosys 10. 125\u2013138.","DOI":"10.1145\/1755913.1755928"},{"key":"e_1_3_2_1_31_1","volume-title":"Single-ISA Heterogeneous Multi-Core Architectures for Multithreaded Workload Performance. In 31st Ann. Int\u2019l Symp. Computer Architecture (ISCA 04)","author":"Kumar Rakesh","year":"2004","unstructured":"Rakesh Kumar 2004 . Single-ISA Heterogeneous Multi-Core Architectures for Multithreaded Workload Performance. In 31st Ann. Int\u2019l Symp. Computer Architecture (ISCA 04) . 64\u201375. Rakesh Kumar 2004. Single-ISA Heterogeneous Multi-Core Architectures for Multithreaded Workload Performance. In 31st Ann. Int\u2019l Symp. Computer Architecture (ISCA 04). 64\u201375."},{"key":"e_1_3_2_1_32_1","volume-title":"16th Intl. Symp. High-Performance Computer Architecture (HPCA 10)","author":"Li Tong","year":"2010","unstructured":"Tong Li 2010 . Operating system support for overlapping-ISA heterogeneous multi-core architectures . In 16th Intl. Symp. High-Performance Computer Architecture (HPCA 10) . 1\u201312. Tong Li 2010. Operating system support for overlapping-ISA heterogeneous multi-core architectures. In 16th Intl. Symp. High-Performance Computer Architecture (HPCA 10). 1\u201312."},{"key":"e_1_3_2_1_33_1","volume-title":"Article 45 (Feb.","author":"Mittal Sparsh","year":"2016","unstructured":"Sparsh Mittal . 2016. A Survey of Techniques for Architecting and Managing Asymmetric Multicore Processors. ACM Comput. Surv. 48, 3 , Article 45 (Feb. 2016 ), 38\u00a0pages. Sparsh Mittal. 2016. A Survey of Techniques for Architecting and Managing Asymmetric Multicore Processors. ACM Comput. Surv. 48, 3, Article 45 (Feb. 2016), 38\u00a0pages."},{"key":"e_1_3_2_1_34_1","volume-title":"SPEC OMP2012 \u2013 an Application Benchmark Suite for Parallel Systems Using OpenMP. In Proc. of the 8th International Conference on OpenMP in a Heterogeneous World. 223\u2013236","author":"M\u00fcller S.","year":"2012","unstructured":"Matthias\u00a0 S. M\u00fcller 2012 . SPEC OMP2012 \u2013 an Application Benchmark Suite for Parallel Systems Using OpenMP. In Proc. of the 8th International Conference on OpenMP in a Heterogeneous World. 223\u2013236 . Matthias\u00a0S. M\u00fcller 2012. SPEC OMP2012 \u2013 an Application Benchmark Suite for Parallel Systems Using OpenMP. In Proc. of the 8th International Conference on OpenMP in a Heterogeneous World. 223\u2013236."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373400.3373409"},{"key":"e_1_3_2_1_36_1","unstructured":"OpenMP Architecture Review Board. 2015. OpenMP Application Programming Interface (Version 4.5). https:\/\/www.openmp.org\/wp-content\/uploads\/openmp-4.5.pdf. Accessed: 2020-02-15. OpenMP Architecture Review Board. 2015. OpenMP Application Programming Interface (Version 4.5). https:\/\/www.openmp.org\/wp-content\/uploads\/openmp-4.5.pdf. Accessed: 2020-02-15."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.515.0593"},{"key":"e_1_3_2_1_38_1","unstructured":"Jyothi Krishna\u00a0V. S and Shankar Balachandran. 2018. Compiler Enhanced Scheduling for OpenMP for Heterogeneous Multiprocessors. CoRR abs\/1808.06074(2018). http:\/\/arxiv.org\/abs\/1808.06074 Jyothi Krishna\u00a0V. S and Shankar Balachandran. 2018. Compiler Enhanced Scheduling for OpenMP for Heterogeneous Multiprocessors. CoRR abs\/1808.06074(2018). http:\/\/arxiv.org\/abs\/1808.06074"},{"key":"e_1_3_2_1_39_1","volume-title":"Operating System Support for Mitigating Software Scalability Bottlenecks on Asymmetric Multicore Processors. In 7th Int\u2019l Conf. Computing Frontiers. 31\u201340","author":"Saez Juan\u00a0Carlos","year":"2010","unstructured":"Juan\u00a0Carlos Saez 2010 . Operating System Support for Mitigating Software Scalability Bottlenecks on Asymmetric Multicore Processors. In 7th Int\u2019l Conf. Computing Frontiers. 31\u201340 . Juan\u00a0Carlos Saez 2010. Operating System Support for Mitigating Software Scalability Bottlenecks on Asymmetric Multicore Processors. In 7th Int\u2019l Conf. Computing Frontiers. 31\u201340."},{"key":"e_1_3_2_1_40_1","first-page":"5","article-title":"Run-Time Parallelization and Scheduling of Loops","volume":"40","author":"Salz H.","year":"1991","unstructured":"Joel\u00a0 H. Salz , Ravi Mirchandaney , and Kay Crowley . 1991 . Run-Time Parallelization and Scheduling of Loops . IEEE Trans. Comput. 40 , 5 (May 1991), 603\u2013612. Joel\u00a0H. Salz, Ravi Mirchandaney, and Kay Crowley. 1991. Run-Time Parallelization and Scheduling of Loops. IEEE Trans. Comput. 40, 5 (May 1991), 603\u2013612.","journal-title":"IEEE Trans. Comput."},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. of ASPLOS \u201909","author":"M.","unstructured":"M. \u00a0Aater Suleman 2009. Accelerating Critical Section Execution with Asymmetric Multi-Core Architectures . In Proc. of ASPLOS \u201909 . 253\u2013264. M.\u00a0Aater Suleman 2009. Accelerating Critical Section Execution with Asymmetric Multi-Core Architectures. In Proc. of ASPLOS \u201909. 253\u2013264."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Taichiro Suzuki Akira Nukada and Satoshi Matsuoka. 2015. Efficient Execution of Multiple CUDA Applications Using Transparent Suspend Resume and Migration. In Euro-Par 2015: Parallel Processing. 687\u2013699. Taichiro Suzuki Akira Nukada and Satoshi Matsuoka. 2015. Efficient Execution of Multiple CUDA Applications Using Transparent Suspend Resume and Migration. In Euro-Par 2015: Parallel Processing. 687\u2013699.","DOI":"10.1007\/978-3-662-48096-0_53"},{"key":"e_1_3_2_1_43_1","volume-title":"IEEE International Conference on Parallel Processing.","author":"Tang P.","unstructured":"P. Tang and P.C. Yew . 1986. Processor self-scheduling for multiple-nested parallel loops . In IEEE International Conference on Parallel Processing. P. Tang and P.C. Yew. 1986. Processor self-scheduling for multiple-nested parallel loops. In IEEE International Conference on Parallel Processing."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30961-8_7"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.14"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.205655"},{"key":"e_1_3_2_1_47_1","volume-title":"COLAB: A Collaborative Multi-Factor Scheduler for Asymmetric Multicore Processors. In 18th ACM\/IEEE International Symposium on Code Generation and Optimization(CGO","author":"Yu Teng","year":"2020","unstructured":"Teng Yu 2020 . COLAB: A Collaborative Multi-Factor Scheduler for Asymmetric Multicore Processors. In 18th ACM\/IEEE International Symposium on Code Generation and Optimization(CGO 2020). 268\u2013279. Teng Yu 2020. COLAB: A Collaborative Multi-Factor Scheduler for Asymmetric Multicore Processors. In 18th ACM\/IEEE International Symposium on Code Generation and Optimization(CGO 2020). 268\u2013279."}],"event":{"name":"ICPP '20: 49th International Conference on Parallel Processing","location":"Edmonton AB Canada","acronym":"ICPP '20"},"container-title":["49th International Conference on Parallel Processing - ICPP"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404397.3404441","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404397.3404441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:42Z","timestamp":1750195902000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404397.3404441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,17]]},"references-count":45,"alternative-id":["10.1145\/3404397.3404441","10.1145\/3404397"],"URL":"https:\/\/doi.org\/10.1145\/3404397.3404441","relation":{},"subject":[],"published":{"date-parts":[[2020,8,17]]},"assertion":[{"value":"2020-08-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}