{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T15:36:51Z","timestamp":1791560211870,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1145\/3720555.3721989","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T07:20:51Z","timestamp":1746429651000},"page":"10-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["From OpenACC to OpenMP5 GPU Offloading: Performance Evaluation on NAS Parallel Benchmarks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6581-998X","authenticated-orcid":false,"given":"Yehonatan","family":"Fridman","sequence":"first","affiliation":[{"name":"Ben-Gurion University; NRCN, Beer-Sheva, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4654-1757","authenticated-orcid":false,"given":"Yosef","family":"Goren","sequence":"additional","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8831-5423","authenticated-orcid":false,"given":"Gal","family":"Oren","sequence":"additional","affiliation":[{"name":"Stanford University; Technion, Palo Alto, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,5]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. Foundry Cloud Platform. https:\/\/mlfoundry.com. [Online]."},{"key":"e_1_3_3_2_3_2","unstructured":"Hichan Agueny. 2022. Porting OpenACC to OpenMP on heterogeneous systems. arXiv preprint arXiv:2201.11811 (2022)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Gabriell Araujo Dalvan Griebler Dinei\u00a0A Rockenbach Marco Danelutto and Luiz\u00a0G Fernandes. 2023. NAS Parallel Benchmarks with CUDA and beyond. Software: Practice and Experience 53 1 (2023) 53\u201380.","DOI":"10.1002\/spe.3056"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"David\u00a0H Bailey Eric Barszcz John\u00a0T Barton David\u00a0S Browning Robert\u00a0L Carter Leonardo Dagum Rod\u00a0A Fatoohi Paul\u00a0O Frederickson Thomas\u00a0A Lasinski Rob\u00a0S Schreiber et\u00a0al. 1991. The NAS parallel benchmarks. The International Journal of Supercomputing Applications 5 3 (1991) 63\u201373.","DOI":"10.1177\/109434209100500306"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"David\u00a0H Bailey Eric Barszcz Leonardo Dagum and Horst\u00a0D Simon. 1993. NAS parallel benchmark results. IEEE Parallel & Distributed Technology: Systems & Applications 1 1 (1993) 43\u201351.","DOI":"10.1109\/88.219861"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Harshad Bhusare Nandan Sarkar Debajyoti Kumar and Somnath Roy. 2024. Accelerated CFD computations on multi-GPU using OpenMP and OpenACC. S\u0101dhan\u0101 49 1 (2024) 87.","DOI":"10.1007\/s12046-023-02423-6"},{"key":"e_1_3_3_2_8_2","unstructured":"Le Chen Nesreen\u00a0K Ahmed Akash Dutta Arijit Bhattacharjee Sixing Yu Quazi\u00a0Ishtiaque Mahmud Waqwoya Abebe Hung Phan Aishwarya Sarkar Branden Butler et\u00a0al. 2024. The landscape and challenges of HPC research and LLMs. CoRR (2024)."},{"key":"e_1_3_3_2_9_2","first-page":"121","volume-title":"European Conference on Parallel Processing","author":"Chen Le","year":"2024","unstructured":"Le Chen, Arijit Bhattacharjee, Nesreen Ahmed, Niranjan Hasabnis, Gal Oren, Vy Vo, and Ali Jannesari. 2024. OMPGPT: a generative pre-trained transformer model for OpenMP. In European Conference on Parallel Processing. Springer Nature Switzerland Cham, 121\u2013134."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/PDP50117.2020.00009","volume-title":"2020 28th Euromicro international conference on parallel, distributed and network-based processing (PDP)","author":"Araujo Gabriell\u00a0Alves de","year":"2020","unstructured":"Gabriell\u00a0Alves de Araujo, Dalvan Griebler, Marco Danelutto, and Luiz\u00a0Gustavo Fernandes. 2020. Efficient NAS parallel benchmark kernels with CUDA. In 2020 28th Euromicro international conference on parallel, distributed and network-based processing (PDP). IEEE, 9\u201316."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/14866.001.0001","volume-title":"Programming Your GPU with OpenMP: Performance Portability for GPUs","author":"Deakin Tom","year":"2023","unstructured":"Tom Deakin and Timothy\u00a0G Mattson. 2023. Programming Your GPU with OpenMP: Performance Portability for GPUs. MIT Press."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Joel\u00a0E Denny Seyong Lee Pedro Valero-Lara Marc Gonzalez-Tallada Keita Teranishi and Jeffrey\u00a0S Vetter. 2024. Clacc: openacc for C\/C++ in clang. The International Journal of High Performance Computing Applications (2024) 10943420241261976.","DOI":"10.1177\/10943420241261976"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/LLVM-HPC.2018.8639349","volume-title":"2018 IEEE\/ACM 5th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC)","author":"Denny Joel\u00a0E","year":"2018","unstructured":"Joel\u00a0E Denny, Seyong Lee, and Jeffrey\u00a0S Vetter. 2018. Clacc: Translating openacc to openmp in clang. In 2018 IEEE\/ACM 5th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC). IEEE, 18\u201329."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/PDP55904.2022.00013","volume-title":"2022 30th Euromicro international conference on parallel, distributed and network-based processing (PDP)","author":"Di\u00a0Domenico Daniel","year":"2022","unstructured":"Daniel Di\u00a0Domenico, Gerson\u00a0GH Cavalheiro, and Jo\u00e3o\u00a0VF Lima. 2022. Nas parallel benchmark kernels with python: A performance and programming effort analysis focusing on gpus. In 2022 30th Euromicro international conference on parallel, distributed and network-based processing (PDP). IEEE, 26\u201333."},{"key":"e_1_3_3_2_15_2","first-page":"93","volume-title":"2019 IEEE International Symposium on Workload Characterization (IISWC)","author":"Do Youngdong","year":"2019","unstructured":"Youngdong Do, Hyungmo Kim, Pyeongseok Oh, Daeyoung Park, and Jaejin Lee. 2019. SNU-NPB 2019: parallelizing and optimizing NPB in OpenCL and CUDA for modern GPUs. In 2019 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 93\u2013105."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1007\/978-3-031-40843-4_28","volume-title":"International Conference on High Performance Computing","author":"Fridman Yehonatan","year":"2023","unstructured":"Yehonatan Fridman, Guy Tamir, and Gal Oren. 2023. Portability and Scalability of OpenMP Offloading on State-of-the-art Accelerators. In International Conference on High Performance Computing. Springer, 378\u2013390."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Marc Gonz\u00e1lez and Enric Morancho. 2020. Multi-GPU parallelization of the NAS multi-zone parallel benchmarks. IEEE Transactions on Parallel and Distributed Systems 32 1 (2020) 229\u2013241.","DOI":"10.1109\/TPDS.2020.3015148"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Marc Gonzalez\u00a0Tallada and Enric Morancho. 2023. Heterogeneous programming using OpenMP and CUDA\/HIP for hybrid CPU-GPU scientific applications. The International Journal of High Performance Computing Applications 37 5 (2023) 626\u2013646.","DOI":"10.1177\/10943420231188079"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Re\u2019em Harel Tal Kadosh Niranjan Hasabnis Timothy Mattson Yuval Pinter and Gal Oren. 2025. PragFormer: Data-Driven Parallel Source Code Classification with Transformers. International Journal of Parallel Programming 53 1 (2025) 1\u201326.","DOI":"10.1007\/s10766-024-00778-9"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Re\u2019em Harel Idan Mosseri Harel Levin Lee-or Alon Matan Rusanovsky and Gal Oren. 2020. Source-to-source parallelization compilers for scientific shared-memory multi-core and accelerated multiprocessing: analysis pitfalls enhancement and potential. International Journal of Parallel Programming 48 (2020) 1\u201331.","DOI":"10.1007\/s10766-019-00640-3"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3582565"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/CGO53902.2022.9741290","volume-title":"2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","author":"Huber Joseph","year":"2022","unstructured":"Joseph Huber, Melanie Cornelius, Giorgis Georgakoudis, Shilei Tian, Jose M\u00a0Monsalve Diaz, Kuter Dinel, Barbara Chapman, and Johannes Doerfert. 2022. Efficient execution of OpenMP on GPUs. In 2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, 41\u201352."},{"key":"e_1_3_3_2_23_2","unstructured":"Intel. [n. d.]. Offload and Optimize OpenMP Applications with Intel Tools. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/training\/offload-optimize-openmp-applications.html. [Online]."},{"key":"e_1_3_3_2_24_2","unstructured":"Intel. 2023. Intel Developer Cloud. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/devcloud\/overview.html. [Online]."},{"key":"e_1_3_3_2_25_2","unstructured":"Hao-Qiang Jin Michael Frumkin and Jerry Yan. 1999. The OpenMP implementation of NAS parallel benchmarks and its performance. (1999)."},{"key":"e_1_3_3_2_26_2","first-page":"1","volume-title":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","author":"Kadosh Tal","year":"2023","unstructured":"Tal Kadosh, Niranjan Hasabnis, Timothy Mattson, Yuval Pinter, and Gal Oren. 2023. Quantifying openmp: Statistical insights into usage and adoption. In 2023 IEEE High Performance Extreme Computing Conference (HPEC). IEEE, 1\u20137."},{"key":"e_1_3_3_2_27_2","volume-title":"Machine Learning for Systems Workshop, NeurIPS","author":"Kadosh Tal","year":"2024","unstructured":"Tal Kadosh, Niranjan Hasabnis, Prema Soundararajan, Vy\u00a0A Vo, Mihai Capota, Nesreen Ahmed, Yuval Pinter, and Gal Oren. 2024. OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation. In Machine Learning for Systems Workshop, NeurIPS."},{"key":"e_1_3_3_2_28_2","unstructured":"Tal Kadosh Niranjan Hasabnis Vy\u00a0A Vo Nadav Schneider Neva Krien Mihai Capota Abdul Wasay Nesreen Ahmed Ted Willke Guy Tamir et\u00a0al. 2023. Domain-Specific Code Language Models: Unraveling the Potential for HPC Codes and Tasks. arXiv preprint arXiv:2312.13322 (2023)."},{"key":"e_1_3_3_2_29_2","unstructured":"Tal Kadosh Niranjan Hasabnis Vy\u00a0A Vo Nadav Schneider Neva Krien Abdul Wasay Nesreen Ahmed Ted Willke Guy Tamir Yuval Pinter et\u00a0al. 2023. Scope is all you need: Transforming LLMs for HPC Code. arXiv preprint arXiv:2308.09440 (2023)."},{"key":"e_1_3_3_2_30_2","first-page":"3","volume-title":"International Workshop on OpenMP","author":"Kadosh Tal","year":"2023","unstructured":"Tal Kadosh, Nadav Schneider, Niranjan Hasabnis, Timothy Mattson, Yuval Pinter, and Gal Oren. 2023. Advising openmp parallelization via a graph-based approach with transformers. In International Workshop on OpenMP. Springer Nature Switzerland Cham, 3\u201317."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Stephen\u00a0W Keckler William\u00a0J Dally Brucek Khailany Michael Garland and David Glasco. 2011. GPUs and the future of parallel computing. IEEE micro 31 5 (2011) 7\u201317.","DOI":"10.1109\/MM.2011.89"},{"key":"e_1_3_3_2_32_2","first-page":"357","volume-title":"Euro-Par 2019: Parallel Processing Workshops: Euro-Par 2019 International Workshops, G\u00f6ttingen, Germany, August 26\u201330, 2019, Revised Selected Papers 25","author":"Lambert Jacob","year":"2019","unstructured":"Jacob Lambert, Seyong Lee, Allen Malony, and Jeffrey\u00a0S Vetter. 2019. Ccamp: Openmp and openacc interoperable framework. In Euro-Par 2019: Parallel Processing Workshops: Euro-Par 2019 International Workshops, G\u00f6ttingen, Germany, August 26\u201330, 2019, Revised Selected Papers 25. Springer, 357\u2013369."},{"key":"e_1_3_3_2_33_2","first-page":"1","volume-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Lambert Jacob","year":"2020","unstructured":"Jacob Lambert, Seyong Lee, Jeffrey\u00a0S Vetter, and Allen\u00a0D Malony. 2020. CCAMP: an integrated translation and optimization framework for OpenACC and OpenMP. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1\u201314."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"J\u00fanior L\u00f6ff Dalvan Griebler Gabriele Mencagli Gabriell Araujo Massimo Torquati Marco Danelutto and Luiz\u00a0Gustavo Fernandes. 2021. The NAS parallel benchmarks for evaluating C++ parallel programming frameworks on shared-memory architectures. Future Generation Computer Systems 125 (2021) 743\u2013757.","DOI":"10.1016\/j.future.2021.07.021"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Kazuaki Matsumura Simon\u00a0Garcia De\u00a0Gonzalo and Antonio\u00a0J Pe\u00f1a. 2023. ACC Saturator: Automatic Kernel Optimization for Directive-Based GPU Code. arXiv preprint arXiv:2306.13002 (2023).","DOI":"10.1109\/SCW63240.2024.00247"},{"key":"e_1_3_3_2_36_2","first-page":"247","volume-title":"OpenMP: Portable Multi-Level Parallelism on Modern Systems: 16th International Workshop on OpenMP, IWOMP 2020, Austin, TX, USA, September 22\u201324, 2020, Proceedings 16","author":"Mosseri Idan","year":"2020","unstructured":"Idan Mosseri, Lee-or Alon, Re\u2019Em Harel, and Gal Oren. 2020. ComPar: optimized multi-compiler for automatic OpenMP S2S parallelization. In OpenMP: Portable Multi-Level Parallelism on Modern Systems: 16th International Workshop on OpenMP, IWOMP 2020, Austin, TX, USA, September 22\u201324, 2020, Proceedings 16. Springer International Publishing, 247\u2013262."},{"key":"e_1_3_3_2_37_2","volume-title":"OpenMP Application Programming Interface","year":"2024","unstructured":"OpenMP Architecture Review Board 2024. OpenMP Application Programming Interface. OpenMP Architecture Review Board. https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-6-0.pd"},{"key":"e_1_3_3_2_38_2","unstructured":"Rotem\u00a0Industrial Park. [n. d.]. NegevHPC Project. https:\/\/platform.openai.com\/tokenizer. [Online]."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Biagio Peccerillo Mirco Mannino Andrea Mondelli and Sandro Bartolini. 2022. A survey on hardware accelerators: Taxonomy trends challenges and perspectives. Journal of Systems Architecture 129 (2022) 102561.","DOI":"10.1016\/j.sysarc.2022.102561"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC.2018.00007"},{"key":"e_1_3_3_2_41_2","first-page":"1","volume-title":"2017 National Conference on Parallel Computing Technologies (PARCOMPTECH)","author":"Prema S","year":"2017","unstructured":"S Prema, R Jehadeesan, and BK Panigrahi. 2017. Identifying pitfalls in automatic parallelization of NAS parallel benchmarks. In 2017 National Conference on Parallel Computing Technologies (PARCOMPTECH). IEEE, 1\u20136."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"S Prema Rupesh Nasre R Jehadeesan and BK Panigrahi. 2019. A study on popular auto-parallelization frameworks. Concurrency and Computation: Practice and Experience 31 17 (2019) e5168.","DOI":"10.1002\/cpe.5168"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.87"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2011.6114174"},{"key":"e_1_3_3_2_45_2","first-page":"127","volume-title":"International Workshop on OpenMP","author":"Servat Harald","year":"2022","unstructured":"Harald Servat, Giacomo Rossi, Alejandro Duran, and Ravi Narayanaswamy. 2022. On the migration of OpenACC-based applications into OpenMP 5+. In International Workshop on OpenMP. Springer, 127\u2013141."},{"key":"e_1_3_3_2_46_2","first-page":"1","volume-title":"Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale","author":"Sultana Nawrin","year":"2016","unstructured":"Nawrin Sultana, Alexander Calvert, Jeffrey\u00a0L Overbey, and Galen Arnold. 2016. From OpenACC to OpenMP 4: toward automatic translation. In Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale. 1\u20138."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.263"},{"key":"e_1_3_3_2_48_2","first-page":"67","volume-title":"Languages and Compilers for Parallel Computing: 27th International Workshop, LCPC 2014, Hillsboro, OR, USA, September 15-17, 2014, Revised Selected Papers 27","author":"Xu Rengan","year":"2015","unstructured":"Rengan Xu, Xiaonan Tian, Sunita Chandrasekaran, Yonghong Yan, and Barbara Chapman. 2015. Nas parallel benchmarks for gpgpus using a directive-based programming model. In Languages and Compilers for Parallel Computing: 27th International Workshop, LCPC 2014, Hillsboro, OR, USA, September 15-17, 2014, Revised Selected Papers 27. Springer, 67\u201381."}],"event":{"name":"ExHET '25: 4th International Workshop on Extreme Heterogeneity Solutions","location":"Las Vegas NV USA","acronym":"ExHET '25","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 2025 4th International Workshop on Extreme Heterogeneity Solutions"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3720555.3721989","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3720555.3721989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:57:39Z","timestamp":1750283859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3720555.3721989"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":47,"alternative-id":["10.1145\/3720555.3721989","10.1145\/3720555"],"URL":"https:\/\/doi.org\/10.1145\/3720555.3721989","relation":{},"subject":[],"published":{"date-parts":[[2025,3]]},"assertion":[{"value":"2025-05-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}