{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:40:01Z","timestamp":1759066801366,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032063427","type":"print"},{"value":"9783032063434","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06343-4_11","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:24:05Z","timestamp":1759065845000},"page":"165-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating OpenMP on\u00a0Aurora\u2019s Intel GPU Max Series 1550"],"prefix":"10.1007","author":[{"given":"Romain","family":"Pereira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Applencourt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colleen","family":"Bertoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Sala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swann","family":"Perarnau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"11_CR1","unstructured":"Benchmarking scripts for reproducibility for Ponte Vecchio across the Atlantic: Single-node benchmarking of two Intel GPU systems. https:\/\/github.com\/UoB-HPC\/abc-pvc-deepdive, https:\/\/github.com\/UoB-HPC\/abc-pvc-deepdive"},{"key":"11_CR2","unstructured":"Intel (R) Xe GPU Architecture. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/optimization-guide-gpu\/2024-2\/intel-xe-gpu-architecture.html"},{"key":"11_CR3","unstructured":"Intel(R) Data Center GPU Max 1500. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/232873\/intel-data-center-gpu-max-1550\/specifications.html, https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/232873\/intel-data-center-gpu-max-1550\/specifications.html"},{"key":"11_CR4","unstructured":"Intel\u00ae oneAPI GPU Optimization Guide 1. https:\/\/cdrdv2.intel.com\/v1\/dl\/getContent\/771773?fileName=oneapi_optimization-guide-gpu_2023.0-771772-771773.pdf"},{"key":"11_CR5","unstructured":"Intel\u00ae Xeon\u00ae CPU Max 9470 Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/232594\/intel-xeon-cpu-max-9470-processor-105m-cache-2-00-ghz\/specifications.html"},{"key":"11_CR6","unstructured":"IWOMP 2025 Benchmarking scripts for reproducibility. https:\/\/github.com\/colleeneb\/IWOMP_2025, https:\/\/github.com\/colleeneb\/IWOMP_2025"},{"key":"11_CR7","unstructured":"oneAPI: A new era of heterogeneous computing. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/overview.html, https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/overview.html"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Applencourt, T., et al.: Ponte Vecchio across the Atlantic: single-node benchmarking of two Intel GPU systems. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1430\u20131442 (2024). https:\/\/doi.org\/10.1109\/SCW63240.2024.00184","DOI":"10.1109\/SCW63240.2024.00184"},{"key":"11_CR9","doi-asserted-by":"publisher","unstructured":"Asahi, Y., Latu, G., Grandgirard, V., Bigot, J.: Performance portable implementation of a kinetic plasma simulation mini-app. In: Wienke, S., Bhalachandra, S. (eds.) Accelerator Programming Using Directives. WACCPD 2019. LNCS, vol. 12017, pp. 117\u2013139. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-49943-3_6","DOI":"10.1007\/978-3-030-49943-3_6"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Bekele, S., et al.: Thapi: tracing heterogeneous apis (2025). https:\/\/arxiv.org\/abs\/2504.03683","DOI":"10.1007\/978-3-031-99854-6_4"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Bertoni, C., Applencourt, T., Gao, L., Leggett, T.: Millions of matrix-multiplications: GEMM variations on Aurora. In: 2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (2025)","DOI":"10.1109\/IPDPSW66978.2025.00135"},{"issue":"3","key":"11_CR12","first-page":"247","volume":"17","author":"T Deakin","year":"2018","unstructured":"Deakin, T., et al.: Evaluating attainable memory bandwidth of parallel programming models via babelstream. Int. J. Comput. Sci. Eng. 17(3), 247\u2013262 (2018)","journal-title":"Int. J. Comput. Sci. Eng."},{"key":"11_CR13","doi-asserted-by":"publisher","unstructured":"Doerfert, J., et al.: Breaking the vendor lock: Performance portable programming through OpenMP as target independent runtime layer. In: Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, pp. 494\u2013504. PACT \u201922, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3559009.3569687","DOI":"10.1145\/3559009.3569687"},{"key":"11_CR14","doi-asserted-by":"publisher","unstructured":"Ferat, M., Pereira, R., Roussel, A., Carribault, P., Steffenel, L.A., Gautier, T.: Enhancing mpi+openmp task based applications for heterogeneous architectures with gpu support. In: Klemm, M., de Supinski, B.R., Klinkenberg, J., Neth, B. (eds.) OpenMP in a Modern World: From Multi-device Support to Meta Programming. IWOMP 2022. LNCS, vol. 13527, pp. 3\u201316. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15922-0_1","DOI":"10.1007\/978-3-031-15922-0_1"},{"key":"11_CR15","unstructured":"Foundation, L.: The LLVM compiler infrastructure. https:\/\/llvm.org\/, https:\/\/llvm.org\/"},{"key":"11_CR16","doi-asserted-by":"publisher","unstructured":"Gautier, T., Lima, J.V., Maillard, N., Raffin, B.: XKaapi: a runtime system for data-flow task programming on heterogeneous architectures. In: 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, pp. 1299\u20131308 (2013). https:\/\/doi.org\/10.1109\/IPDPS.2013.66","DOI":"10.1109\/IPDPS.2013.66"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"Gomes, W., et al.: Ponte Vecchio: a multi-tile 3D stacked processor for exascale computing. In: 2022 IEEE International Solid-State Circuits Conference (ISSCC), vol.\u00a065, pp. 42\u201344 (2022). https:\/\/doi.org\/10.1109\/ISSCC42614.2022.9731673","DOI":"10.1109\/ISSCC42614.2022.9731673"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Guo, Y., et al.: Preparing MPICH for exascale. Int. J. High Perform. Comput. Appl. 39(2), 283\u2013305 (2025). https:\/\/doi.org\/10.1177\/10943420241311608","DOI":"10.1177\/10943420241311608"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Huber, T., et al.: ECP SOLLVE: validation and verification testsuite status update and compiler insight for OpenMP. In: 2022 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), pp. 123\u2013135 (2022). https:\/\/doi.org\/10.1109\/P3HPC56579.2022.00017","DOI":"10.1109\/P3HPC56579.2022.00017"},{"key":"11_CR20","doi-asserted-by":"publisher","unstructured":"Jay, M., Ostapenco, V., Lefevre, L., Trystram, D., Orgerie, A.C., Fichel, B.: An experimental comparison of software-based power meters: focus on CPU and GPU. In: 2023 IEEE\/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pp. 106\u2013118 (2023). https:\/\/doi.org\/10.1109\/CCGrid57682.2023.00020","DOI":"10.1109\/CCGrid57682.2023.00020"},{"key":"11_CR21","unstructured":"Muralidharan, S.: Aurora exascale architecture. Argonne Training Program on Extreme-Scale Computing (ATPESC) (August 2023). https:\/\/extremecomputingtraining.anl.gov\/wp-content\/uploads\/sites\/96\/2023\/08\/ATPESC-2023-Track-1-Talk-3-Servesh-Mulalidharan-Aurora.pdf"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Pereira, R., Roussel, A., Carribault, P., Gautier, T.: Investigating dependency graph discovery impact on task-based MPI+OpenMP applications performances. In: Proceedings of the 52nd International Conference on Parallel Processing, pp. 16\u2013172. ICPP \u201923, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3605573.3605602","DOI":"10.1145\/3605573.3605602"},{"key":"11_CR23","doi-asserted-by":"publisher","unstructured":"Salvadore, F., Rossi, G., Sathyanarayana, S., Bernardini, M.: OpenMP offload at the exascale using Intel\u00ae GPU Max 1550: evaluation of STREAmS compressible solver (April 2024). https:\/\/doi.org\/10.21203\/rs.3.rs-4180620\/v1","DOI":"10.21203\/rs.3.rs-4180620\/v1"},{"key":"11_CR24","unstructured":"TOP500.org: TOP500 List \u2013 November (2024). https:\/\/www.top500.org"},{"key":"11_CR25","doi-asserted-by":"publisher","unstructured":"Tramm, J., et al.: Performance portable Monte Carlo particle transport on Intel, NVIDIA, and AMD GPUs. In: EPJ Web of Conferences, vol. 302 (October 2024). https:\/\/doi.org\/10.1051\/epjconf\/202430204010","DOI":"10.1051\/epjconf\/202430204010"},{"key":"11_CR26","unstructured":"Tramm, J.R., Siegel, A.R., Islam, T., Schulz, M.: XSBench \u2013 the development and verification of a performance abstraction for Monte Carlo reactor analysis. In: PHYSOR 2014 - The Role of Reactor Physics toward a Sustainable Future. Kyoto (2014). https:\/\/www.mcs.anl.gov\/papers\/P5064-0114.pdf"},{"issue":"4","key":"11_CR27","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1109\/TPDS.2021.3097283","volume":"33","author":"CR Trott","year":"2022","unstructured":"Trott, C.R., et al.: Kokkos 3: programming model extensions for the exascale era. IEEE Trans. Parallel Distrib. Syst. 33(4), 805\u2013817 (2022). https:\/\/doi.org\/10.1109\/TPDS.2021.3097283","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"11_CR28","doi-asserted-by":"publisher","unstructured":"Wu, W., Bouteiller, A., Bosilca, G., Faverge, M., Dongarra, J.: Hierarchical DAG scheduling for hybrid distributed systems. In: 2015 IEEE International Parallel and Distributed Processing Symposium, pp. 156\u2013165 (2015). https:\/\/doi.org\/10.1109\/IPDPS.2015.56","DOI":"10.1109\/IPDPS.2015.56"},{"key":"11_CR29","doi-asserted-by":"publisher","unstructured":"Yu, C., Royuela, S., Qui\u00f1ones, E.: Enhancing heterogeneous computing through OpenMP and GPU Graph. In: Proceedings of the 53rd International Conference on Parallel Processing, pp. 534\u2013543. ICPP \u201924, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3673038.3673050","DOI":"10.1145\/3673038.3673050"},{"key":"11_CR30","doi-asserted-by":"publisher","first-page":"51971","DOI":"10.1109\/ACCESS.2023.3269902","volume":"11","author":"D \u00c1lvarez","year":"2023","unstructured":"\u00c1lvarez, D., Beltran, V.: Optimizing iterative data-flow scientific applications using directed cyclic graphs. IEEE Access 11, 51971\u201351984 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3269902","journal-title":"IEEE Access"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Balancing Productivity and Performance Portability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06343-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:24:07Z","timestamp":1759065847000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06343-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032063427","9783032063434"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06343-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Charlotte, NC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iwomp.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}