{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T09:15:51Z","timestamp":1783674951037,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"SPACE Centre of Excellence","award":["101093441"],"award-info":[{"award-number":["101093441"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801488.3806377","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T08:40:14Z","timestamp":1783672814000},"page":"74-81","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Limits of Performance Portability in Directive-Based GPU Programming"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7159-3486","authenticated-orcid":false,"given":"Alessandro","family":"Romeo","sequence":"first","affiliation":[{"name":"SuperComputing Applications and Innovation Department - CINECA, Casalecchio di Reno, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2110-1439","authenticated-orcid":false,"given":"Nitin","family":"Shukla","sequence":"additional","affiliation":[{"name":"SuperComputing Applications and Innovation Department - CINECA, Casalecchio di Reno, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3998-9373","authenticated-orcid":false,"given":"Stefano","family":"Truzzi","sequence":"additional","affiliation":[{"name":"Dipartimento di Fisica, Universit\u00e0 degli studi di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1889-6239","authenticated-orcid":false,"given":"Alessio","family":"Suriano","sequence":"additional","affiliation":[{"name":"Dipartimento di Fisica, Universit\u00e0 degli studi di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8352-6635","authenticated-orcid":false,"given":"Andrea","family":"Mignone","sequence":"additional","affiliation":[{"name":"Dipartimento di Fisica, Universit\u00e0 degli studi di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Advanced Micro Devices Inc.2023. Omniperf: Performance Analysis Tool for AMD GPUs. https:\/\/github.com\/ROCm\/rocm-systems."},{"key":"e_1_3_3_2_3_2","volume-title":"GPU Architecture Hardware Specifications (ROCm Documentation)","author":"Inc. Advanced Micro Devices,","year":"2024","unstructured":"Advanced Micro Devices, Inc.2024. GPU Architecture Hardware Specifications (ROCm Documentation). https:\/\/rocm.docs.amd.com\/en\/docs-6.0.2\/reference\/gpu-arch\/gpu-arch-spec-overview.html"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"M. Aldinucci et\u00a0al. 2021. Practical parallelization of scientific applications with OpenMP OpenACC and MPI. J. Parallel and Distrib. Comput. 157 (2021) 13\u201329. 10.1016\/j.jpdc.2021.05.017","DOI":"10.1016\/j.jpdc.2021.05.017"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/LLVM-HPC.2016.006"},{"key":"e_1_3_3_2_6_2","unstructured":"Argonne Leadership Computing Facility. 2021. Inside the NVIDIA Ampere A100 GPU. Slide deck. https:\/\/www.alcf.anl.gov\/sites\/default\/files\/2021-07\/ALCF_A100_20210728%5B80%5D.pdf"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833161"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"J. Choquette et\u00a0al. 2021. NVIDIA A100 GPU: Performance and Innovation. IEEE Micro 41 2 (2021) 29\u201335. 10.1109\/MM.2021.3061394","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721145.3730423"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00006"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14866.001.0001"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"T. Deakin J. Price M. Martineau and S. McIntosh-Smith. 2018. Evaluating attainable memory bandwidth of parallel programming models via BabelStream. International Journal of Computational Science and Engineering 17 3 (2018) 247\u2013262. 10.1504\/IJCSE.2018.095847","DOI":"10.1504\/IJCSE.2018.095847"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"A. Dubey et\u00a0al. 2021. Performance Portability in the Exascale Computing Project: Exploration Through a Panel Series. Computing in Science & Engineering 23 5 (2021) 46\u201354. 10.1109\/MCSE.2021.3098231","DOI":"10.1109\/MCSE.2021.3098231"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/XSW.2013.7"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40744-4_14"},{"key":"e_1_3_3_2_16_2","unstructured":"ENCCS. 2022. Hierarchical Roofline Performance Analysis on AMD GPUs. https:\/\/enccs.github.io\/amd-rocm-development."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"A. Folch et\u00a0al. 2023. The EU Center of Excellence for Exascale in Solid Earth (ChEESE): Implementation results and roadmap for the second phase. Future Generation Computer Systems 146 (2023) 47\u201361. 10.1016\/j.future.2023.04.006","DOI":"10.1016\/j.future.2023.04.006"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3720555.3721989"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706594.3727577"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"P. Grete F.\u00a0W. Glines and B.\u00a0W. O\u2019Shea. 2021. K-Athena: A Performance Portable Structured Grid Finite Volume Magnetohydrodynamics Code. IEEE Transactions on Parallel and Distributed Systems 32 1 (2021) 85\u201397. 10.1109\/TPDS.2020.3010016","DOI":"10.1109\/TPDS.2020.3010016"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/SECSE.2009.5069157"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00009"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"M. Khalilov and A. Timoveev. 2021. Performance analysis of CUDA OpenACC and OpenMP programming models on TESLA V100 GPU. Journal of Physics: Conference Series 1740 1 (jan 2021) 012056. 10.1088\/1742-6596\/1740\/1\/012056","DOI":"10.1088\/1742-6596\/1740\/1\/012056"},{"key":"e_1_3_3_2_24_2","unstructured":"M. Klemm. 2025. OpenMP\u00ae Target Offloading for AMD Instinct GPUs and APUs. https:\/\/tu-dresden.de\/zih\/das-department\/ressourcen\/dateien\/kolloquium\/2025_03_27-MichaelKlemm.pdf. Tutorial on OpenMP offloading and GPU performance Accessed 2025."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"E. Krishnasamy et\u00a0al. 2026. Performance and Programmability of MPI+X Integration with CUDA HIP SYCL OpenACC and OpenMP Offloading for Supercomputing: A Case Study on Dense Matrix-Vector Multiplication. 10.1145\/3784828.3786264","DOI":"10.1145\/3784828.3786264"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"A. Marowka. 2025. Portability efficiency approach for calculating performance portability. Future Generation Computer Systems 170 (2025) 107826. 10.1016\/j.future.2025.107826","DOI":"10.1016\/j.future.2025.107826"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-74224-9_1"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3110355.3110356"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"A. Myers et\u00a0al. 2021. Porting WarpX to GPU-accelerated platforms. Parallel Comput. 108 (2021) 102833. 10.1016\/j.parco.2021.102833","DOI":"10.1016\/j.parco.2021.102833"},{"key":"e_1_3_3_2_30_2","unstructured":"NVIDIA. 2026. NVIDIA Ampere GPU Architecture Tuning Guide. https:\/\/docs.nvidia.com\/cuda\/ampere-tuning-guide\/index.html"},{"key":"e_1_3_3_2_31_2","unstructured":"NVIDIA Corporation. 2023. Nsight Compute Documentation: Memory Workload Analysis. https:\/\/docs.nvidia.com\/nsight-compute\/NsightCompute\/index.html."},{"key":"e_1_3_3_2_32_2","volume-title":"The OpenACC Application Programming Interface, Version 3.3","year":"2023","unstructured":"OpenACC-Standard.org. 2023. The OpenACC Application Programming Interface, Version 3.3. Technical Report. OpenACC Organization. https:\/\/www.openacc.org\/specification"},{"key":"e_1_3_3_2_33_2","volume-title":"OpenMP Application Programming Interface, Version 5.2","author":"Board OpenMP Architecture Review","year":"2021","unstructured":"OpenMP Architecture Review Board. 2021. OpenMP Application Programming Interface, Version 5.2. Technical Report. OpenMP ARB. https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-5-2.pdf"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"J. Owens et\u00a0al. 2008. GPU computing. Proc. IEEE 96 (05 2008) 879\u2013899. 10.1109\/JPROC.2008.917757","DOI":"10.1109\/JPROC.2008.917757"},{"key":"e_1_3_3_2_35_2","unstructured":"S.\u00a0J. Pennycook J.\u00a0D. Sewall and V.\u00a0W. Lee. 2016. A Metric for Performance Portability. arxiv:https:\/\/arXiv.org\/abs\/1611.07409\u00a0[cs.PF] https:\/\/arxiv.org\/abs\/1611.07409"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"M. Rossazza et\u00a0al. 2026. The PLUTO code on GPUs: A first look at Eulerian MHD methods. Astronomy and Computing (2026) 101076. 10.1016\/j.ascom.2026.101076","DOI":"10.1016\/j.ascom.2026.101076"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00079"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC51967.2020.00007"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"N. Shukla et\u00a0al. 2025. Towards Exascale Computing for Astrophysical Simulation Leveraging the Leonardo EuroHPC System. Procedia Computer Science 267 (2025) 112\u2013123. 10.1016\/j.procs.2025.08.238Proceedings of the Third EuroHPC user day.","DOI":"10.1016\/j.procs.2025.08.238"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"N. Shukla et\u00a0al. 2026. Exascale computing to accelerate discoveries in astrophysics and space plasma physics. Nature Astronomy 10 (2026) 330\u2013334. 10.1038\/s41550-026-02807-8","DOI":"10.1038\/s41550-026-02807-8"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22750-0_58"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895477"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"J.\u00a0M. Stone K. Tomida C.\u00a0J. White and K.\u00a0G. Felker. 2020. The Athena++ Adaptive Mesh Refinement Framework: Design and Magnetohydrodynamic Solvers. The Astrophysical Journal Supplement Series 249 1 (June 2020) 4. 10.3847\/1538-4365\/ab929b","DOI":"10.3847\/1538-4365\/ab929b"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"A. Suriano et\u00a0al. 2026. The PLUTO code on GPUs: Offloading Lagrangian Particle methods. Astronomy and Computing 55 (2026) 101088. 10.1016\/j.ascom.2026.101088","DOI":"10.1016\/j.ascom.2026.101088"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528925"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_85"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09873-9_68"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63749-0_22"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"S. Williams A. Waterman and D. Patterson. 2009. Roofline: An Insightful Visual Performance Model for Multicore Architectures. Commun. ACM 52 4 (2009) 65\u201376. 10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-06343-4"}],"event":{"name":"CF '26 Companion: 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26 Companion","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers: Workshops and Special Sessions"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801488.3806377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T08:40:39Z","timestamp":1783672839000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801488.3806377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":49,"alternative-id":["10.1145\/3801488.3806377","10.1145\/3801488"],"URL":"https:\/\/doi.org\/10.1145\/3801488.3806377","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}