{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T07:22:22Z","timestamp":1779002542529,"version":"3.51.4"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031725661","type":"print"},{"value":"9783031725678","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72567-8_2","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:19:25Z","timestamp":1726762765000},"page":"16-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Performance Porting the\u00a0ExaStar Multi-Physics App Thornado On Heterogeneous Systems - A Fortran-OpenMP Code-Base Evaluation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1240-3475","authenticated-orcid":false,"given":"Mathialakan","family":"Thavappiragasam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-7140","authenticated-orcid":false,"given":"J. Austin","family":"Harris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1251-9507","authenticated-orcid":false,"given":"Eirik","family":"Endeve","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6824-1263","authenticated-orcid":false,"given":"Brice","family":"Videau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,16]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Almgren, A., et al.: CASTRO: a massively parallel compressible astrophysics simulation code. J. Open Source Softw. 5(54), 2513 (2020). https:\/\/doi.org\/10.21105\/joss.02513","DOI":"10.21105\/joss.02513"},{"key":"2_CR2","unstructured":"Argonne Leadership Computing Facility: Aurora (2023). https:\/\/www.alcf.anl.gov\/aurora"},{"key":"2_CR3","unstructured":"Argonne Leadership Computing Facility: JLSE (2023). https:\/\/www.jlse.anl.gov\/hardware-under-development\/"},{"key":"2_CR4","unstructured":"Argonne Leadership Computing Facility: Polaris (2023). https:\/\/docs.alcf.anl.gov\/polaris\/hardware-overview\/machine-overview\/"},{"key":"2_CR5","unstructured":"Argonne Leadership Computing Facility: Sunspot (2023). https:\/\/www.alcf.anl.gov\/support-center\/aurorasunspot\/getting-started-sunspot"},{"key":"2_CR6","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/S0168-9274(97)00056-1","volume":"25","author":"U Ascher","year":"1997","unstructured":"Ascher, U., Ruuth, S., Spiteri, R.: Implicit-explicit Runge-Kutta methods for time-dependent partial differential equations. Appl. Numer. Math. 25, 151\u2013167 (1997)","journal-title":"Appl. Numer. Math."},{"issue":"1","key":"2_CR7","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3847\/1538-4365\/ab7aff","volume":"248","author":"SW Bruenn","year":"2020","unstructured":"Bruenn, S.W., et al.: CHIMERA: a massively parallel code for core-collapse supernova simulations. APJS 248(1), 11 (2020). https:\/\/doi.org\/10.3847\/1538-4365\/ab7aff","journal-title":"APJS"},{"key":"2_CR8","doi-asserted-by":"publisher","first-page":"103004","DOI":"10.1103\/PhysRevD.87.103004","volume":"87","author":"CY Cardall","year":"2013","unstructured":"Cardall, C.Y., Endeve, E., Mezzacappa, A.: Conservative 3+1 general relativistic variable Eddington tensor radiation transport equations. Phys. Rev. D 87, 103004 (2013)","journal-title":"Phys. Rev. D"},{"key":"2_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/978-3-030-85262-7_6","volume-title":"OpenMP: Enabling Massive Node-Level Parallelism","author":"B Chapman","year":"2021","unstructured":"Chapman, B., et al.: Outcomes of OpenMP hackathon: OpenMP application experiences with the offloading model (Part II). In: McIntosh-Smith, S., de Supinski, B.R., Klinkenberg, J. (eds.) IWOMP 2021. LNCS, vol. 12870, pp. 81\u201395. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85262-7_6"},{"key":"2_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10915-020-01359-x","volume":"86","author":"AJ Christlieb","year":"2021","unstructured":"Christlieb, A.J., Guthrey, P.T., Sands, W.A., Thavappiragasm, M.: Parallel algorithms for successive convolution. J. Sci. Comput. 86, 1\u201344 (2021)","journal-title":"J. Sci. Comput."},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.jcp.2019.03.037","volume":"389","author":"R Chu","year":"2019","unstructured":"Chu, R., Endeve, E., Hauck, C., Mezzacappa, A.: Realizability-preserving DG-IMEX method for the two-moment model of fermion transport. J. Comput. Phys. 389, 62\u201393 (2019)","journal-title":"J. Comput. Phys."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Clauss, P., Altintas, E., Kuhn, M.: Automatic collapsing of non-rectangular loops. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 778\u2013787. IEEE (2017)","DOI":"10.1109\/IPDPS.2017.34"},{"key":"2_CR13","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1023\/A:1012873910884","volume":"16","author":"B Cockburn","year":"2001","unstructured":"Cockburn, B., Shu, C.W.: Runge-Kutta discontinuous Galerkin methods for convection-dominated problems. J. Sci. Comput. 16, 173\u2013261 (2001)","journal-title":"J. Sci. Comput."},{"key":"2_CR14","unstructured":"Corporation, I.: Developer guide: oneAPI GPU optimization guide (2023). https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/optimization-guide-gpu\/2023-0\/overview.html"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"101168","DOI":"10.1016\/j.softx.2022.101168","volume":"19","author":"A Dubey","year":"2022","unstructured":"Dubey, A., Weide, K., O\u2019Neal, J., Dhruv, A., Couch, S., Harris, J.A., Klosterman, T., Jain, R., Rudi, J., Messer, B., et al.: Flash-x: a multiphysics simulation software instrument. SoftwareX 19, 101168 (2022)","journal-title":"SoftwareX"},{"key":"2_CR16","unstructured":"Georgakoudis, G., Parasyris, K., Liao, C., Beckingsale, D., Gamblin, T., de\u00a0Supinski, B.: Machine learning-driven adaptive OpenMP for portable performance on heterogeneous systems. arXiv preprint arXiv:2303.08873 (2023)"},{"key":"2_CR17","unstructured":"Harris, A.: wlInterpolationModule. https:\/\/github.com\/starkiller-astro\/weaklib\/blob\/89c2ff3228c37022e74e3bb98290a1c9a52ba93e\/Distributions\/Library\/wlInterpolationModule.F90"},{"issue":"1","key":"2_CR18","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1177\/10943420211027937","volume":"36","author":"JA Harris","year":"2022","unstructured":"Harris, J.A., et al.: Exascale models of stellar explosions: quintessential multi-physics simulation. Int. J. High Perform. Comput. Appl. 36(1), 59\u201377 (2022)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"2_CR19","unstructured":"Intel-Corporation: Compilation Flow Overview. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/programming-guide\/2023-2\/compilation-flow-overview.html"},{"key":"2_CR20","unstructured":"Intel-Corporation: Intel Data Center GPU Max Series Overview. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-data-center-gpu-max-series-overview.html#gs.25c0bs"},{"key":"2_CR21","unstructured":"Intel-Corporation: oneAPI GPU Optimization Guide. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/optimization-guide-gpu\/2024-0\/ahead-of-time-compilation.html"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"3386","DOI":"10.1093\/mnras\/stv1892","volume":"453","author":"O Just","year":"2015","unstructured":"Just, O., Obergaulinger, M., Janka, H.T.: A new multidimensional, energy-dependent two-moment transport code for neutrino-hydrodynamics. MNRAS 453, 3386\u20133413 (2015)","journal-title":"MNRAS"},{"issue":"2","key":"2_CR23","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3847\/0067-0049\/222\/2\/20","volume":"222","author":"T Kuroda","year":"2016","unstructured":"Kuroda, T., Takiwaki, T., Kotake, K.: A new multi-energy neutrino radiation-hydrodynamics code in full general relativity and its application to the gravitational collapse of massive stars. Astrophys. J. Suppl. Ser. 222(2), 20 (2016). https:\/\/doi.org\/10.3847\/0067-0049\/222\/2\/20","journal-title":"Astrophys. J. Suppl. Ser."},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Laiu, M.P., Endeve, E., Chu, R., Harris, J.A., Messer, O.E.B.: A DG-IMEX method for two-moment neutrino transport: nonlinear solvers for neutrino-matter coupling*. Astrophys. J. Suppl. Ser. 253(2), 52 (2021). https:\/\/doi.org\/10.3847\/1538-4365\/abe2a8","DOI":"10.3847\/1538-4365\/abe2a8"},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Laiu, M.P., Endeve, E., Harris, J.A., Elledge, Z., Mezzacappa, A.: DG-IMEX method for a two-moment model for radiation transport in the $$\\cal{O}(v\/c)$$ Limit. arXiv e-prints arXiv:2309.04429 (2023). https:\/\/doi.org\/10.48550\/arXiv.2309.04429","DOI":"10.48550\/arXiv.2309.04429"},{"issue":"2","key":"2_CR26","doi-asserted-by":"publisher","first-page":"26","DOI":"10.3847\/1538-4365\/ac9966","volume":"263","author":"MTP Liska","year":"2022","unstructured":"Liska, M.T.P., et al.: H-AMR: a new GPU-accelerated GRMHD code for exascale computing with 3D adaptive mesh refinement and local adaptive time stepping. APJS 263(2), 26 (2022). https:\/\/doi.org\/10.3847\/1538-4365\/ac9966","journal-title":"APJS"},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Luebke, D.: CUDA: scalable parallel programming for high-performance scientific computing. In: 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 836\u2013838 (2008). https:\/\/doi.org\/10.1109\/ISBI.2008.4541126","DOI":"10.1109\/ISBI.2008.4541126"},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Martineau, M., McIntosh-Smith, S., Gaudin, W.: Evaluating OpenMP 4.0\u2019s effectiveness as a heterogeneous parallel programming model. In: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 338\u2013347 (2016). https:\/\/doi.org\/10.1109\/IPDPSW.2016.70","DOI":"10.1109\/IPDPSW.2016.70"},{"issue":"1","key":"2_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/TPDS.2016.2549523","volume":"28","author":"X Mei","year":"2016","unstructured":"Mei, X., Chu, X.: Dissecting GPU memory hierarchy through microbenchmarking. IEEE Trans. Parallel Distrib. Syst. 28(1), 72\u201386 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2_CR30","unstructured":"NVIDIA: NVIDIA Ampere Architecture In-Depth. https:\/\/developer.nvidia.com\/blog\/nvidia-ampere-architecture-in-depth"},{"key":"2_CR31","unstructured":"NVIDIA: PTX Compiler APIs. https:\/\/docs.nvidia.com\/cuda\/ptx-compiler-api\/index.html"},{"key":"2_CR32","unstructured":"Oak Ridge Leadership Computing Facility: Frontier user guide (2023). https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html"},{"key":"2_CR33","unstructured":"Oak Ridge Leadership Computing Facility: Summit (2023). https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html"},{"key":"2_CR34","first-page":"129","volume":"25","author":"L Pareschi","year":"2005","unstructured":"Pareschi, L., Russo, G.: Implicit-explicit Runge-Kutta schemes and application to hyperbolic systems with relaxation. J. Sci. Comput. 25, 129\u2013155 (2005)","journal-title":"J. Sci. Comput."},{"key":"2_CR35","unstructured":"Pophale, S., et al.: Outcomes of OpenMP hackathon: OpenMP application experiences with the offloading mode. Technical report, Brookhaven National Lab.(BNL), Upton, NY (United States) (2021)"},{"issue":"20","key":"2_CR36","doi-asserted-by":"publisher","first-page":"205009","DOI":"10.1088\/1361-6382\/acf2d9","volume":"40","author":"S Shankar","year":"2023","unstructured":"Shankar, S., M\u00f6sta, P., Brandt, S.R., Haas, R., Schnetter, E., de Graaf, Y.: GRaM-X: a new GPU-accelerated dynamical spacetime GRMHD code for Exascale computing with the Einstein toolkit. Class. Quantum Gravity 40(20), 205009 (2023). https:\/\/doi.org\/10.1088\/1361-6382\/acf2d9","journal-title":"Class. Quantum Gravity"},{"key":"2_CR37","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1143\/PTP.125.1255","volume":"125","author":"M Shibata","year":"2011","unstructured":"Shibata, M., Kiuchi, K., Sekiguchi, Y., Suwa, Y.: Truncated moment formalism for radiation hydrodynamics in numerical relativity. Progress Theoret. Phys. 125, 1255\u20131287 (2011)","journal-title":"Progress Theoret. Phys."},{"key":"2_CR38","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3847\/1538-4365\/ab007f","volume":"241","author":"MA Skinner","year":"2019","unstructured":"Skinner, M.A., Dolence, J.C., Burrows, A., Radice, D., Vartanyan, D.: FORNAX: a flexible code for Multiphysics astrophysical simulations. ApJS 241, 7 (2019)","journal-title":"ApJS"},{"issue":"20","key":"2_CR39","doi-asserted-by":"publisher","first-page":"e5780","DOI":"10.1002\/cpe.5780","volume":"32","author":"VG Vergara Larrea","year":"2020","unstructured":"Vergara Larrea, V.G., Budiardja, R.D., Gayatri, R., Daley, C., Hernandez, O., Joubert, W.: Experiences in porting mini-applications to OpenACC and OpenMP on heterogeneous systems. Concurrency Comput. Pract. Exper. 32(20), e5780 (2020)","journal-title":"Concurrency Comput. Pract. Exper."},{"issue":"2","key":"2_CR40","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3847\/1538-4357\/acc8cf","volume":"949","author":"CJ White","year":"2023","unstructured":"White, C.J., et al.: An extension of the Athena++ code framework for radiation-magnetohydrodynamics in general relativity using a finite-solid-angle discretization. APJ 949(2), 103 (2023). https:\/\/doi.org\/10.3847\/1538-4357\/acc8cf","journal-title":"APJ"},{"issue":"1","key":"2_CR41","doi-asserted-by":"publisher","first-page":"1430","DOI":"10.1093\/mnras\/stac439","volume":"512","author":"BD Wibking","year":"2022","unstructured":"Wibking, B.D., Krumholz, M.R.: QUOKKA: a code for two-moment AMR radiation hydrodynamics on GPUs. MNRAS 512(1), 1430\u20131449 (2022). https:\/\/doi.org\/10.1093\/mnras\/stac439","journal-title":"MNRAS"},{"key":"2_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1007\/978-3-642-32820-6_85","volume-title":"Euro-Par 2012 Parallel Processing","author":"S Wienke","year":"2012","unstructured":"Wienke, S., Springer, P., Terboven, C., an Mey, D.: OpenACC \u2014 first experiences with real-world applications. In: Kaklamanis, C., Papatheodorou, T., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol. 7484, pp. 859\u2013870. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32820-6_85"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: ytopt: Autotuning scientific applications for energy efficiency at large scales. arXiv preprint arXiv:2303.16245 (2023)","DOI":"10.1002\/cpe.8322"}],"container-title":["Lecture Notes in Computer Science","Advancing OpenMP for Future Accelerators"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72567-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T12:03:43Z","timestamp":1732795423000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72567-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031725661","9783031725678"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72567-8_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 September 2024","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2024","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"}}]}}