{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:21:15Z","timestamp":1782854475980,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754668","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"617-626","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Cross-Architecture Performance Analysis Using the RAJA Performance Suite"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1453-5906","authenticated-orcid":false,"given":"Dewi","family":"Yokelson","sequence":"first","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1458-8453","authenticated-orcid":false,"given":"Stephanie","family":"Brink","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3036-0108","authenticated-orcid":false,"given":"Jason","family":"Burmark","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7201-5733","authenticated-orcid":false,"given":"Michael","family":"McKinsey","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1007-9384","authenticated-orcid":false,"given":"Befikir","family":"Bogale","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0009-5487","authenticated-orcid":false,"given":"Ian","family":"Lumsden","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0031-6377","authenticated-orcid":false,"given":"Michela","family":"Taufer","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7234-5743","authenticated-orcid":false,"given":"Tom","family":"Scogland","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1904-9627","authenticated-orcid":false,"given":"Olga","family":"Pearce","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA and Texas A&M University, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. NVIDIA Nsight Compute Profiling Tool. https:\/\/docs.nvidia.com\/ nsight-compute\/NsightCompute\/index.html."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Ayesha Afzal et\u00a0al. 2023. SPEChpc 2021 Benchmarks on Ice Lake and Sapphire Rapids Infiniband Clusters: A Performance and Energy Case Study. Association for Computing Machinery New York NY USA.","DOI":"10.1145\/3624062.3624197"},{"key":"e_1_3_3_1_4_2","unstructured":"AMD. 2024. AMD CDNA3 Architecture. https:\/\/www.amd.com\/content\/dam\/am d\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624177"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"e_1_3_3_1_7_2","series-title":"(SC \u201916)","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Boehme David","year":"2016","unstructured":"David Boehme et\u00a0al. 2016. Caliper: Performance Introspection for HPC Software Stacks. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Salt Lake City, Utah) (SC \u201916). IEEE Press, Article 47, 11\u00a0pages."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3592989"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Leonardo Dagum and Ram Menon. 1998. OpenMP: an industry standard API for shared-memory programming.","DOI":"10.1109\/99.660313"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/PMBS49563.2019.00007","volume-title":"2019 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","author":"Ding Nan","year":"2019","unstructured":"Nan Ding and Samuel Williams. 2019. An Instruction Roofline Model for GPUs. In 2019 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS). 7\u201318."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Nan Ding\u00a0et al.2022. Instruction Roofline: An insightful visual performance model for GPUs. Concurrency & Computation: Practice & Experience 34 20 (2022).","DOI":"10.1002\/cpe.6591"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"David Eberius et\u00a0al. 2022. Understanding Strong Scaling on GPUs Using Empirical Performance Saturation Size. 2022 IEEE\/ACM International Workshop on Performance Portability and Productivity in HPC (P3HPC) (2022) 26\u201335.","DOI":"10.1109\/P3HPC56579.2022.00008"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"H.\u00a0C. Edwards et\u00a0al. 2014. Kokkos: Enabling manycore performance portability through polymorphic memory access patterns. J.Parallel &Distr.Comp. 74 (2014).","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_3_1_14_2","unstructured":"Richard\u00a0D. Hornung and Holger\u00a0E. Jones. [n. d.]. RAJA Performance Suite."},{"key":"e_1_3_3_1_15_2","first-page":"1","volume-title":"2022 IEEE Hot Chips 34 Symposium (HCS)","author":"Jiang Hong","year":"2022","unstructured":"Hong Jiang. 2022. Intel\u2019s Ponte Vecchio GPU : Architecture, Systems and Software. In 2022 IEEE Hot Chips 34 Symposium (HCS). 1\u201329."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"JaeHyuk Kwack et\u00a0al. 2021. Evaluation of Performance Portability of Applications and Mini-Apps across AMD Intel and NVIDIA GPUs. 2021 International Workshop on Performance Portability and Productivity in HPC (P3HPC) (2021) 45\u201356.","DOI":"10.1109\/P3HPC54578.2021.00008"},{"key":"e_1_3_3_1_17_2","unstructured":"NVIDIA. 2023. NVIDIA Grace Hopper Superchip Architecture Whitepaper. https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper."},{"key":"e_1_3_3_1_18_2","unstructured":"Olga Pearce et\u00a0al. 2024. RAJA Performance Suite: Performance Portability Analysis with Caliper and Thicket. 2024 IEEE\/ACM International Workshop on Performance Portability and Productivity in HPC (P3HPC) 1206\u20131218."},{"key":"e_1_3_3_1_19_2","unstructured":"Simon\u00a0John Pennycook et\u00a0al. 2016. A Metric for Performance Portability. ArXiv abs\/1611.07409 (2016)."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Christopher\u00a0M Siefert et\u00a0al. 2023. Latency and Bandwidth Microbenchmarks of US Department of Energy Systems in the June 2023 Top 500 List. Association for Computing Machinery New York NY USA.","DOI":"10.1145\/3624062.3624203"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Christian\u00a0R. Trott et\u00a0al. 2022. Kokkos 3: Programming Model Extensions for the Exascale Era. IEEE Transactions on Parallel and Distributed Systems 33 (2022).","DOI":"10.1109\/TPDS.2021.3097283"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844459"}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:38:49Z","timestamp":1766219929000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":21,"alternative-id":["10.1145\/3754598.3754668","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754668","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}